Upload folder using huggingface_hub

3b-mb_base/README.md

@@ -0,0 +1,164 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-3B-Instruct
+tags:
+- generated_from_trainer
+datasets:
+- mb_base.jsonl
+model-index:
+- name: outputs/out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.6.0`
+```yaml
+base_model: Qwen/Qwen2.5-3B-Instruct
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+trust_remote_code: false
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+output_dir: ./outputs/out
+chat_template: qwen_25
+datasets:
+  - path: mb_base.jsonl
+    type: chat_template
+    field_messages: messages
+    message_field_role: role
+    message_field_content: content
+    roles:
+      system:
+        - system
+      user:
+        - user
+      assistant:
+        - assistant
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.005
+output_dir: ./outputs/out
+eval_sample_packing: False
+
+sequence_len: 8192
+sample_packing: False
+pad_to_sequence_len: False
+
+wandb_project: mergedbench
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_swiglu: true
+liger_fused_linear_cross_entropy: true
+
+gradient_accumulation_steps: 4
+micro_batch_size: 8
+eval_batch_size: 4
+num_epochs: 3
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 2e-5
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 30
+evals_per_epoch: 3
+eval_max_new_tokens: 128
+eval_table_size:
+saves_per_epoch: 1
+debug:
+deepspeed: deepspeed_configs/zero1.json
+weight_decay: 0.01
+fsdp:
+fsdp_config:
+special_tokens:
+```
+
+</details><br>
+
+# outputs/out
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the mb_base.jsonl dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3531
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 30
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.062         | 0.0059 | 1    | 1.0835          |
+| 0.3584        | 0.3368 | 57   | 0.3954          |
+| 0.3372        | 0.6736 | 114  | 0.3638          |
+| 0.2579        | 1.0059 | 171  | 0.3497          |
+| 0.2359        | 1.3427 | 228  | 0.3520          |
+| 0.2258        | 1.6795 | 285  | 0.3461          |
+| 0.1673        | 2.0118 | 342  | 0.3411          |
+| 0.1567        | 2.3486 | 399  | 0.3547          |
+| 0.1571        | 2.6854 | 456  | 0.3531          |
+
+
+### Framework versions
+
+- Transformers 4.48.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

3b-mb_base/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

3b-mb_base/checkpoint-169/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

3b-mb_base/checkpoint-169/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

3b-mb_base/checkpoint-169/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.1"
+}

3b-mb_base/checkpoint-169/latest

@@ -0,0 +1 @@
+global_step169

3b-mb_base/checkpoint-169/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bbb82b5eaddd2218ee91401271bd0a8f1feb8a88645a5a6a5d4f463a4db80e
+size 4956450288

3b-mb_base/checkpoint-169/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34e9667355221493ef25c9b481baef41b9d892ed7f471f8e96dd2b8087a2ffd
+size 1835586736

3b-mb_base/checkpoint-169/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 6791987200
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

3b-mb_base/checkpoint-169/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9affc1541e7e94c18354d5173bc55400c5f07faf3d080c6d453d48e7a8d6ac3
+size 14512

3b-mb_base/checkpoint-169/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4748c3ebf0e4c051c58b92e4a8c5b87cdb39d55cfdc2aec81a1baef0f02fc113
+size 14512

3b-mb_base/checkpoint-169/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579fc25e0fa1981bf31c24488d0d7572584313555af920879f011e878787fee4
+size 1064

3b-mb_base/checkpoint-169/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

3b-mb_base/checkpoint-169/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

3b-mb_base/checkpoint-169/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

3b-mb_base/checkpoint-169/trainer_state.json

@@ -0,0 +1,1240 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9985228951255539,
+  "eval_steps": 57,
+  "global_step": 169,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005908419497784343,
+      "grad_norm": 4.501461029052734,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 1.062,
+      "step": 1
+    },
+    {
+      "epoch": 0.005908419497784343,
+      "eval_loss": 1.0835397243499756,
+      "eval_runtime": 4.3539,
+      "eval_samples_per_second": 12.632,
+      "eval_steps_per_second": 1.608,
+      "step": 1
+    },
+    {
+      "epoch": 0.011816838995568686,
+      "grad_norm": 4.469114303588867,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 1.0268,
+      "step": 2
+    },
+    {
+      "epoch": 0.01772525849335303,
+      "grad_norm": 4.554893970489502,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.0401,
+      "step": 3
+    },
+    {
+      "epoch": 0.023633677991137372,
+      "grad_norm": 4.374792575836182,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 1.0423,
+      "step": 4
+    },
+    {
+      "epoch": 0.029542097488921712,
+      "grad_norm": 3.4377498626708984,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.9965,
+      "step": 5
+    },
+    {
+      "epoch": 0.03545051698670606,
+      "grad_norm": 3.1242499351501465,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.9479,
+      "step": 6
+    },
+    {
+      "epoch": 0.0413589364844904,
+      "grad_norm": 1.8368685245513916,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.8296,
+      "step": 7
+    },
+    {
+      "epoch": 0.047267355982274745,
+      "grad_norm": 1.7457680702209473,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.8159,
+      "step": 8
+    },
+    {
+      "epoch": 0.053175775480059084,
+      "grad_norm": 1.2953853607177734,
+      "learning_rate": 6e-06,
+      "loss": 0.664,
+      "step": 9
+    },
+    {
+      "epoch": 0.059084194977843424,
+      "grad_norm": 1.1054794788360596,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6486,
+      "step": 10
+    },
+    {
+      "epoch": 0.06499261447562776,
+      "grad_norm": 0.8712942004203796,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.6415,
+      "step": 11
+    },
+    {
+      "epoch": 0.07090103397341212,
+      "grad_norm": 1.4441039562225342,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.6255,
+      "step": 12
+    },
+    {
+      "epoch": 0.07680945347119646,
+      "grad_norm": 1.4984484910964966,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.5561,
+      "step": 13
+    },
+    {
+      "epoch": 0.0827178729689808,
+      "grad_norm": 0.8376960754394531,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.5534,
+      "step": 14
+    },
+    {
+      "epoch": 0.08862629246676514,
+      "grad_norm": 0.7184750437736511,
+      "learning_rate": 1e-05,
+      "loss": 0.5062,
+      "step": 15
+    },
+    {
+      "epoch": 0.09453471196454949,
+      "grad_norm": 0.8381787538528442,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.5531,
+      "step": 16
+    },
+    {
+      "epoch": 0.10044313146233383,
+      "grad_norm": 0.7621350288391113,
+      "learning_rate": 1.1333333333333334e-05,
+      "loss": 0.4876,
+      "step": 17
+    },
+    {
+      "epoch": 0.10635155096011817,
+      "grad_norm": 0.6955872178077698,
+      "learning_rate": 1.2e-05,
+      "loss": 0.5019,
+      "step": 18
+    },
+    {
+      "epoch": 0.11225997045790251,
+      "grad_norm": 0.5844917297363281,
+      "learning_rate": 1.2666666666666667e-05,
+      "loss": 0.4368,
+      "step": 19
+    },
+    {
+      "epoch": 0.11816838995568685,
+      "grad_norm": 0.5807573795318604,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.4965,
+      "step": 20
+    },
+    {
+      "epoch": 0.1240768094534712,
+      "grad_norm": 0.5376399755477905,
+      "learning_rate": 1.4e-05,
+      "loss": 0.4841,
+      "step": 21
+    },
+    {
+      "epoch": 0.12998522895125553,
+      "grad_norm": 0.5053263902664185,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.4573,
+      "step": 22
+    },
+    {
+      "epoch": 0.1358936484490399,
+      "grad_norm": 0.5155225396156311,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 0.451,
+      "step": 23
+    },
+    {
+      "epoch": 0.14180206794682423,
+      "grad_norm": 0.52030348777771,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.4199,
+      "step": 24
+    },
+    {
+      "epoch": 0.14771048744460857,
+      "grad_norm": 0.5321907997131348,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.4532,
+      "step": 25
+    },
+    {
+      "epoch": 0.1536189069423929,
+      "grad_norm": 0.5318155288696289,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 0.4813,
+      "step": 26
+    },
+    {
+      "epoch": 0.15952732644017725,
+      "grad_norm": 0.5176340937614441,
+      "learning_rate": 1.8e-05,
+      "loss": 0.4288,
+      "step": 27
+    },
+    {
+      "epoch": 0.1654357459379616,
+      "grad_norm": 0.43893975019454956,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.3766,
+      "step": 28
+    },
+    {
+      "epoch": 0.17134416543574593,
+      "grad_norm": 0.43830162286758423,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 0.4159,
+      "step": 29
+    },
+    {
+      "epoch": 0.17725258493353027,
+      "grad_norm": 0.45950719714164734,
+      "learning_rate": 2e-05,
+      "loss": 0.4505,
+      "step": 30
+    },
+    {
+      "epoch": 0.1831610044313146,
+      "grad_norm": 0.40500667691230774,
+      "learning_rate": 1.9999783114048658e-05,
+      "loss": 0.3726,
+      "step": 31
+    },
+    {
+      "epoch": 0.18906942392909898,
+      "grad_norm": 0.43435147404670715,
+      "learning_rate": 1.9999132465602526e-05,
+      "loss": 0.442,
+      "step": 32
+    },
+    {
+      "epoch": 0.19497784342688332,
+      "grad_norm": 0.44813328981399536,
+      "learning_rate": 1.999804808288491e-05,
+      "loss": 0.437,
+      "step": 33
+    },
+    {
+      "epoch": 0.20088626292466766,
+      "grad_norm": 0.48166996240615845,
+      "learning_rate": 1.9996530012933285e-05,
+      "loss": 0.4107,
+      "step": 34
+    },
+    {
+      "epoch": 0.206794682422452,
+      "grad_norm": 0.398764044046402,
+      "learning_rate": 1.9994578321597258e-05,
+      "loss": 0.3882,
+      "step": 35
+    },
+    {
+      "epoch": 0.21270310192023634,
+      "grad_norm": 0.44229164719581604,
+      "learning_rate": 1.999219309353572e-05,
+      "loss": 0.4154,
+      "step": 36
+    },
+    {
+      "epoch": 0.21861152141802068,
+      "grad_norm": 0.44369620084762573,
+      "learning_rate": 1.998937443221316e-05,
+      "loss": 0.3863,
+      "step": 37
+    },
+    {
+      "epoch": 0.22451994091580502,
+      "grad_norm": 0.44270017743110657,
+      "learning_rate": 1.9986122459895182e-05,
+      "loss": 0.3945,
+      "step": 38
+    },
+    {
+      "epoch": 0.23042836041358936,
+      "grad_norm": 0.42152372002601624,
+      "learning_rate": 1.9982437317643218e-05,
+      "loss": 0.4094,
+      "step": 39
+    },
+    {
+      "epoch": 0.2363367799113737,
+      "grad_norm": 0.4120837450027466,
+      "learning_rate": 1.9978319165308373e-05,
+      "loss": 0.4411,
+      "step": 40
+    },
+    {
+      "epoch": 0.24224519940915806,
+      "grad_norm": 0.4064903259277344,
+      "learning_rate": 1.997376818152453e-05,
+      "loss": 0.3818,
+      "step": 41
+    },
+    {
+      "epoch": 0.2481536189069424,
+      "grad_norm": 0.3692624270915985,
+      "learning_rate": 1.9968784563700586e-05,
+      "loss": 0.3874,
+      "step": 42
+    },
+    {
+      "epoch": 0.25406203840472674,
+      "grad_norm": 0.4399218261241913,
+      "learning_rate": 1.9963368528011867e-05,
+      "loss": 0.3749,
+      "step": 43
+    },
+    {
+      "epoch": 0.25997045790251105,
+      "grad_norm": 0.3779003620147705,
+      "learning_rate": 1.9957520309390786e-05,
+      "loss": 0.3656,
+      "step": 44
+    },
+    {
+      "epoch": 0.2658788774002954,
+      "grad_norm": 0.3946981132030487,
+      "learning_rate": 1.9951240161516643e-05,
+      "loss": 0.3612,
+      "step": 45
+    },
+    {
+      "epoch": 0.2717872968980798,
+      "grad_norm": 0.3969726264476776,
+      "learning_rate": 1.99445283568046e-05,
+      "loss": 0.3932,
+      "step": 46
+    },
+    {
+      "epoch": 0.2776957163958641,
+      "grad_norm": 0.4239075183868408,
+      "learning_rate": 1.9937385186393888e-05,
+      "loss": 0.387,
+      "step": 47
+    },
+    {
+      "epoch": 0.28360413589364847,
+      "grad_norm": 0.3688453733921051,
+      "learning_rate": 1.992981096013517e-05,
+      "loss": 0.3524,
+      "step": 48
+    },
+    {
+      "epoch": 0.2895125553914328,
+      "grad_norm": 0.4294806718826294,
+      "learning_rate": 1.9921806006577102e-05,
+      "loss": 0.3787,
+      "step": 49
+    },
+    {
+      "epoch": 0.29542097488921715,
+      "grad_norm": 0.3867166042327881,
+      "learning_rate": 1.9913370672952074e-05,
+      "loss": 0.3756,
+      "step": 50
+    },
+    {
+      "epoch": 0.30132939438700146,
+      "grad_norm": 0.43365901708602905,
+      "learning_rate": 1.990450532516116e-05,
+      "loss": 0.3896,
+      "step": 51
+    },
+    {
+      "epoch": 0.3072378138847858,
+      "grad_norm": 0.38658151030540466,
+      "learning_rate": 1.9895210347758233e-05,
+      "loss": 0.3703,
+      "step": 52
+    },
+    {
+      "epoch": 0.31314623338257014,
+      "grad_norm": 0.37093815207481384,
+      "learning_rate": 1.98854861439333e-05,
+      "loss": 0.3763,
+      "step": 53
+    },
+    {
+      "epoch": 0.3190546528803545,
+      "grad_norm": 0.40044137835502625,
+      "learning_rate": 1.9875333135495e-05,
+      "loss": 0.3752,
+      "step": 54
+    },
+    {
+      "epoch": 0.3249630723781389,
+      "grad_norm": 0.39133360981941223,
+      "learning_rate": 1.986475176285232e-05,
+      "loss": 0.3589,
+      "step": 55
+    },
+    {
+      "epoch": 0.3308714918759232,
+      "grad_norm": 0.38397374749183655,
+      "learning_rate": 1.985374248499546e-05,
+      "loss": 0.3701,
+      "step": 56
+    },
+    {
+      "epoch": 0.33677991137370755,
+      "grad_norm": 0.3795414865016937,
+      "learning_rate": 1.984230577947597e-05,
+      "loss": 0.3584,
+      "step": 57
+    },
+    {
+      "epoch": 0.33677991137370755,
+      "eval_loss": 0.3953791558742523,
+      "eval_runtime": 4.6385,
+      "eval_samples_per_second": 11.857,
+      "eval_steps_per_second": 1.509,
+      "step": 57
+    },
+    {
+      "epoch": 0.34268833087149186,
+      "grad_norm": 0.3709493577480316,
+      "learning_rate": 1.9830442142386e-05,
+      "loss": 0.3647,
+      "step": 58
+    },
+    {
+      "epoch": 0.34859675036927623,
+      "grad_norm": 0.35005033016204834,
+      "learning_rate": 1.9818152088336786e-05,
+      "loss": 0.3317,
+      "step": 59
+    },
+    {
+      "epoch": 0.35450516986706054,
+      "grad_norm": 0.3652004599571228,
+      "learning_rate": 1.9805436150436352e-05,
+      "loss": 0.3394,
+      "step": 60
+    },
+    {
+      "epoch": 0.3604135893648449,
+      "grad_norm": 0.3940984904766083,
+      "learning_rate": 1.9792294880266346e-05,
+      "loss": 0.3711,
+      "step": 61
+    },
+    {
+      "epoch": 0.3663220088626292,
+      "grad_norm": 0.35634928941726685,
+      "learning_rate": 1.977872884785815e-05,
+      "loss": 0.3455,
+      "step": 62
+    },
+    {
+      "epoch": 0.3722304283604136,
+      "grad_norm": 0.3972924053668976,
+      "learning_rate": 1.9764738641668137e-05,
+      "loss": 0.3652,
+      "step": 63
+    },
+    {
+      "epoch": 0.37813884785819796,
+      "grad_norm": 0.40372708439826965,
+      "learning_rate": 1.9750324868552133e-05,
+      "loss": 0.3662,
+      "step": 64
+    },
+    {
+      "epoch": 0.38404726735598227,
+      "grad_norm": 0.396133691072464,
+      "learning_rate": 1.9735488153739128e-05,
+      "loss": 0.3726,
+      "step": 65
+    },
+    {
+      "epoch": 0.38995568685376664,
+      "grad_norm": 0.398989737033844,
+      "learning_rate": 1.972022914080411e-05,
+      "loss": 0.3595,
+      "step": 66
+    },
+    {
+      "epoch": 0.39586410635155095,
+      "grad_norm": 0.4102807939052582,
+      "learning_rate": 1.9704548491640195e-05,
+      "loss": 0.3308,
+      "step": 67
+    },
+    {
+      "epoch": 0.4017725258493353,
+      "grad_norm": 0.344397634267807,
+      "learning_rate": 1.9688446886429885e-05,
+      "loss": 0.3653,
+      "step": 68
+    },
+    {
+      "epoch": 0.4076809453471196,
+      "grad_norm": 0.3550814390182495,
+      "learning_rate": 1.9671925023615572e-05,
+      "loss": 0.3412,
+      "step": 69
+    },
+    {
+      "epoch": 0.413589364844904,
+      "grad_norm": 0.4047009348869324,
+      "learning_rate": 1.9654983619869242e-05,
+      "loss": 0.3578,
+      "step": 70
+    },
+    {
+      "epoch": 0.4194977843426883,
+      "grad_norm": 0.41112563014030457,
+      "learning_rate": 1.9637623410061392e-05,
+      "loss": 0.3694,
+      "step": 71
+    },
+    {
+      "epoch": 0.4254062038404727,
+      "grad_norm": 0.3775319755077362,
+      "learning_rate": 1.961984514722914e-05,
+      "loss": 0.3571,
+      "step": 72
+    },
+    {
+      "epoch": 0.43131462333825704,
+      "grad_norm": 0.3610381782054901,
+      "learning_rate": 1.960164960254358e-05,
+      "loss": 0.3713,
+      "step": 73
+    },
+    {
+      "epoch": 0.43722304283604135,
+      "grad_norm": 0.38662371039390564,
+      "learning_rate": 1.9583037565276314e-05,
+      "loss": 0.311,
+      "step": 74
+    },
+    {
+      "epoch": 0.4431314623338257,
+      "grad_norm": 0.3574771285057068,
+      "learning_rate": 1.9564009842765225e-05,
+      "loss": 0.3353,
+      "step": 75
+    },
+    {
+      "epoch": 0.44903988183161003,
+      "grad_norm": 0.3932562470436096,
+      "learning_rate": 1.9544567260379455e-05,
+      "loss": 0.3536,
+      "step": 76
+    },
+    {
+      "epoch": 0.4549483013293944,
+      "grad_norm": 0.3974682092666626,
+      "learning_rate": 1.9524710661483594e-05,
+      "loss": 0.3556,
+      "step": 77
+    },
+    {
+      "epoch": 0.4608567208271787,
+      "grad_norm": 0.37172290682792664,
+      "learning_rate": 1.9504440907401113e-05,
+      "loss": 0.3568,
+      "step": 78
+    },
+    {
+      "epoch": 0.4667651403249631,
+      "grad_norm": 0.37170422077178955,
+      "learning_rate": 1.948375887737699e-05,
+      "loss": 0.3556,
+      "step": 79
+    },
+    {
+      "epoch": 0.4726735598227474,
+      "grad_norm": 0.3596966862678528,
+      "learning_rate": 1.9462665468539582e-05,
+      "loss": 0.332,
+      "step": 80
+    },
+    {
+      "epoch": 0.47858197932053176,
+      "grad_norm": 0.35934680700302124,
+      "learning_rate": 1.944116159586169e-05,
+      "loss": 0.3276,
+      "step": 81
+    },
+    {
+      "epoch": 0.4844903988183161,
+      "grad_norm": 0.40984946489334106,
+      "learning_rate": 1.94192481921209e-05,
+      "loss": 0.3685,
+      "step": 82
+    },
+    {
+      "epoch": 0.49039881831610044,
+      "grad_norm": 0.3622114658355713,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.3336,
+      "step": 83
+    },
+    {
+      "epoch": 0.4963072378138848,
+      "grad_norm": 0.34888842701911926,
+      "learning_rate": 1.9374196611341212e-05,
+      "loss": 0.3625,
+      "step": 84
+    },
+    {
+      "epoch": 0.5022156573116692,
+      "grad_norm": 0.37125518918037415,
+      "learning_rate": 1.9351060388513304e-05,
+      "loss": 0.3304,
+      "step": 85
+    },
+    {
+      "epoch": 0.5081240768094535,
+      "grad_norm": 0.4107120931148529,
+      "learning_rate": 1.9327518542959717e-05,
+      "loss": 0.3755,
+      "step": 86
+    },
+    {
+      "epoch": 0.5140324963072378,
+      "grad_norm": 0.3420109748840332,
+      "learning_rate": 1.9303572095859545e-05,
+      "loss": 0.3457,
+      "step": 87
+    },
+    {
+      "epoch": 0.5199409158050221,
+      "grad_norm": 0.35079535841941833,
+      "learning_rate": 1.9279222085942396e-05,
+      "loss": 0.3454,
+      "step": 88
+    },
+    {
+      "epoch": 0.5258493353028065,
+      "grad_norm": 0.3775666058063507,
+      "learning_rate": 1.9254469569443274e-05,
+      "loss": 0.3501,
+      "step": 89
+    },
+    {
+      "epoch": 0.5317577548005908,
+      "grad_norm": 0.3327409625053406,
+      "learning_rate": 1.9229315620056805e-05,
+      "loss": 0.3507,
+      "step": 90
+    },
+    {
+      "epoch": 0.5376661742983752,
+      "grad_norm": 0.37142789363861084,
+      "learning_rate": 1.9203761328890626e-05,
+      "loss": 0.3453,
+      "step": 91
+    },
+    {
+      "epoch": 0.5435745937961596,
+      "grad_norm": 0.36256077885627747,
+      "learning_rate": 1.91778078044181e-05,
+      "loss": 0.3588,
+      "step": 92
+    },
+    {
+      "epoch": 0.5494830132939439,
+      "grad_norm": 0.3861102759838104,
+      "learning_rate": 1.9151456172430186e-05,
+      "loss": 0.3479,
+      "step": 93
+    },
+    {
+      "epoch": 0.5553914327917282,
+      "grad_norm": 0.3359353542327881,
+      "learning_rate": 1.9124707575986642e-05,
+      "loss": 0.318,
+      "step": 94
+    },
+    {
+      "epoch": 0.5612998522895125,
+      "grad_norm": 0.33662593364715576,
+      "learning_rate": 1.909756317536643e-05,
+      "loss": 0.3421,
+      "step": 95
+    },
+    {
+      "epoch": 0.5672082717872969,
+      "grad_norm": 0.35831600427627563,
+      "learning_rate": 1.9070024148017375e-05,
+      "loss": 0.3409,
+      "step": 96
+    },
+    {
+      "epoch": 0.5731166912850812,
+      "grad_norm": 0.39858701825141907,
+      "learning_rate": 1.9042091688505104e-05,
+      "loss": 0.3319,
+      "step": 97
+    },
+    {
+      "epoch": 0.5790251107828656,
+      "grad_norm": 0.3343643546104431,
+      "learning_rate": 1.9013767008461236e-05,
+      "loss": 0.3352,
+      "step": 98
+    },
+    {
+      "epoch": 0.5849335302806499,
+      "grad_norm": 0.3519919216632843,
+      "learning_rate": 1.89850513365308e-05,
+      "loss": 0.3634,
+      "step": 99
+    },
+    {
+      "epoch": 0.5908419497784343,
+      "grad_norm": 0.32900717854499817,
+      "learning_rate": 1.895594591831896e-05,
+      "loss": 0.3415,
+      "step": 100
+    },
+    {
+      "epoch": 0.5967503692762186,
+      "grad_norm": 0.34432175755500793,
+      "learning_rate": 1.8926452016336987e-05,
+      "loss": 0.3169,
+      "step": 101
+    },
+    {
+      "epoch": 0.6026587887740029,
+      "grad_norm": 0.33144107460975647,
+      "learning_rate": 1.8896570909947477e-05,
+      "loss": 0.3431,
+      "step": 102
+    },
+    {
+      "epoch": 0.6085672082717873,
+      "grad_norm": 0.3299802839756012,
+      "learning_rate": 1.8866303895308856e-05,
+      "loss": 0.3411,
+      "step": 103
+    },
+    {
+      "epoch": 0.6144756277695717,
+      "grad_norm": 0.30740225315093994,
+      "learning_rate": 1.883565228531919e-05,
+      "loss": 0.3355,
+      "step": 104
+    },
+    {
+      "epoch": 0.620384047267356,
+      "grad_norm": 0.34325993061065674,
+      "learning_rate": 1.88046174095592e-05,
+      "loss": 0.3188,
+      "step": 105
+    },
+    {
+      "epoch": 0.6262924667651403,
+      "grad_norm": 0.3394065797328949,
+      "learning_rate": 1.8773200614234587e-05,
+      "loss": 0.3153,
+      "step": 106
+    },
+    {
+      "epoch": 0.6322008862629247,
+      "grad_norm": 0.35468512773513794,
+      "learning_rate": 1.874140326211766e-05,
+      "loss": 0.3387,
+      "step": 107
+    },
+    {
+      "epoch": 0.638109305760709,
+      "grad_norm": 0.36726799607276917,
+      "learning_rate": 1.8709226732488216e-05,
+      "loss": 0.3457,
+      "step": 108
+    },
+    {
+      "epoch": 0.6440177252584933,
+      "grad_norm": 0.3223711848258972,
+      "learning_rate": 1.86766724210737e-05,
+      "loss": 0.3588,
+      "step": 109
+    },
+    {
+      "epoch": 0.6499261447562777,
+      "grad_norm": 0.3537541925907135,
+      "learning_rate": 1.8643741739988672e-05,
+      "loss": 0.3506,
+      "step": 110
+    },
+    {
+      "epoch": 0.6558345642540621,
+      "grad_norm": 0.3755073845386505,
+      "learning_rate": 1.8610436117673557e-05,
+      "loss": 0.3221,
+      "step": 111
+    },
+    {
+      "epoch": 0.6617429837518464,
+      "grad_norm": 0.31778833270072937,
+      "learning_rate": 1.8576756998832667e-05,
+      "loss": 0.3161,
+      "step": 112
+    },
+    {
+      "epoch": 0.6676514032496307,
+      "grad_norm": 0.3517738878726959,
+      "learning_rate": 1.8542705844371544e-05,
+      "loss": 0.3442,
+      "step": 113
+    },
+    {
+      "epoch": 0.6735598227474151,
+      "grad_norm": 0.3254755139350891,
+      "learning_rate": 1.8508284131333604e-05,
+      "loss": 0.3372,
+      "step": 114
+    },
+    {
+      "epoch": 0.6735598227474151,
+      "eval_loss": 0.363791823387146,
+      "eval_runtime": 4.0908,
+      "eval_samples_per_second": 13.445,
+      "eval_steps_per_second": 1.711,
+      "step": 114
+    },
+    {
+      "epoch": 0.6794682422451994,
+      "grad_norm": 0.3458060622215271,
+      "learning_rate": 1.8473493352836032e-05,
+      "loss": 0.3329,
+      "step": 115
+    },
+    {
+      "epoch": 0.6853766617429837,
+      "grad_norm": 0.33962881565093994,
+      "learning_rate": 1.8438335018005052e-05,
+      "loss": 0.3478,
+      "step": 116
+    },
+    {
+      "epoch": 0.691285081240768,
+      "grad_norm": 0.33980926871299744,
+      "learning_rate": 1.8402810651910444e-05,
+      "loss": 0.3484,
+      "step": 117
+    },
+    {
+      "epoch": 0.6971935007385525,
+      "grad_norm": 0.355694979429245,
+      "learning_rate": 1.8366921795499394e-05,
+      "loss": 0.3686,
+      "step": 118
+    },
+    {
+      "epoch": 0.7031019202363368,
+      "grad_norm": 0.3415476083755493,
+      "learning_rate": 1.8330670005529657e-05,
+      "loss": 0.3204,
+      "step": 119
+    },
+    {
+      "epoch": 0.7090103397341211,
+      "grad_norm": 0.3336890935897827,
+      "learning_rate": 1.829405685450202e-05,
+      "loss": 0.3323,
+      "step": 120
+    },
+    {
+      "epoch": 0.7149187592319055,
+      "grad_norm": 0.34337785840034485,
+      "learning_rate": 1.8257083930592102e-05,
+      "loss": 0.3283,
+      "step": 121
+    },
+    {
+      "epoch": 0.7208271787296898,
+      "grad_norm": 0.3578524887561798,
+      "learning_rate": 1.8219752837581466e-05,
+      "loss": 0.3326,
+      "step": 122
+    },
+    {
+      "epoch": 0.7267355982274741,
+      "grad_norm": 0.32392922043800354,
+      "learning_rate": 1.8182065194788024e-05,
+      "loss": 0.3141,
+      "step": 123
+    },
+    {
+      "epoch": 0.7326440177252584,
+      "grad_norm": 0.36127492785453796,
+      "learning_rate": 1.814402263699584e-05,
+      "loss": 0.3461,
+      "step": 124
+    },
+    {
+      "epoch": 0.7385524372230429,
+      "grad_norm": 0.33812931180000305,
+      "learning_rate": 1.8105626814384173e-05,
+      "loss": 0.3404,
+      "step": 125
+    },
+    {
+      "epoch": 0.7444608567208272,
+      "grad_norm": 0.3138431906700134,
+      "learning_rate": 1.8066879392455932e-05,
+      "loss": 0.3237,
+      "step": 126
+    },
+    {
+      "epoch": 0.7503692762186115,
+      "grad_norm": 0.33033978939056396,
+      "learning_rate": 1.8027782051965408e-05,
+      "loss": 0.3416,
+      "step": 127
+    },
+    {
+      "epoch": 0.7562776957163959,
+      "grad_norm": 0.3907163143157959,
+      "learning_rate": 1.7988336488845374e-05,
+      "loss": 0.3352,
+      "step": 128
+    },
+    {
+      "epoch": 0.7621861152141802,
+      "grad_norm": 0.315248042345047,
+      "learning_rate": 1.7948544414133534e-05,
+      "loss": 0.3225,
+      "step": 129
+    },
+    {
+      "epoch": 0.7680945347119645,
+      "grad_norm": 0.3284492790699005,
+      "learning_rate": 1.7908407553898282e-05,
+      "loss": 0.3217,
+      "step": 130
+    },
+    {
+      "epoch": 0.7740029542097489,
+      "grad_norm": 0.3439176082611084,
+      "learning_rate": 1.7867927649163838e-05,
+      "loss": 0.3367,
+      "step": 131
+    },
+    {
+      "epoch": 0.7799113737075333,
+      "grad_norm": 0.31954073905944824,
+      "learning_rate": 1.782710645583473e-05,
+      "loss": 0.3133,
+      "step": 132
+    },
+    {
+      "epoch": 0.7858197932053176,
+      "grad_norm": 0.38416293263435364,
+      "learning_rate": 1.7785945744619642e-05,
+      "loss": 0.3484,
+      "step": 133
+    },
+    {
+      "epoch": 0.7917282127031019,
+      "grad_norm": 0.34139737486839294,
+      "learning_rate": 1.774444730095456e-05,
+      "loss": 0.3042,
+      "step": 134
+    },
+    {
+      "epoch": 0.7976366322008862,
+      "grad_norm": 0.3623535931110382,
+      "learning_rate": 1.7702612924925377e-05,
+      "loss": 0.3318,
+      "step": 135
+    },
+    {
+      "epoch": 0.8035450516986706,
+      "grad_norm": 0.32973209023475647,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.3092,
+      "step": 136
+    },
+    {
+      "epoch": 0.8094534711964549,
+      "grad_norm": 0.30704402923583984,
+      "learning_rate": 1.761794364889855e-05,
+      "loss": 0.321,
+      "step": 137
+    },
+    {
+      "epoch": 0.8153618906942393,
+      "grad_norm": 0.34877485036849976,
+      "learning_rate": 1.7575112421616203e-05,
+      "loss": 0.3266,
+      "step": 138
+    },
+    {
+      "epoch": 0.8212703101920237,
+      "grad_norm": 0.3538282811641693,
+      "learning_rate": 1.7531952607241033e-05,
+      "loss": 0.3703,
+      "step": 139
+    },
+    {
+      "epoch": 0.827178729689808,
+      "grad_norm": 0.35590365529060364,
+      "learning_rate": 1.7488466077924525e-05,
+      "loss": 0.3506,
+      "step": 140
+    },
+    {
+      "epoch": 0.8330871491875923,
+      "grad_norm": 0.33215418457984924,
+      "learning_rate": 1.7444654719990128e-05,
+      "loss": 0.3207,
+      "step": 141
+    },
+    {
+      "epoch": 0.8389955686853766,
+      "grad_norm": 0.3381923735141754,
+      "learning_rate": 1.7400520433851457e-05,
+      "loss": 0.3237,
+      "step": 142
+    },
+    {
+      "epoch": 0.844903988183161,
+      "grad_norm": 0.3371356129646301,
+      "learning_rate": 1.735606513392984e-05,
+      "loss": 0.3394,
+      "step": 143
+    },
+    {
+      "epoch": 0.8508124076809453,
+      "grad_norm": 0.344291627407074,
+      "learning_rate": 1.7311290748571273e-05,
+      "loss": 0.3604,
+      "step": 144
+    },
+    {
+      "epoch": 0.8567208271787297,
+      "grad_norm": 0.3567575216293335,
+      "learning_rate": 1.72661992199628e-05,
+      "loss": 0.3518,
+      "step": 145
+    },
+    {
+      "epoch": 0.8626292466765141,
+      "grad_norm": 0.33762165904045105,
+      "learning_rate": 1.7220792504048227e-05,
+      "loss": 0.3146,
+      "step": 146
+    },
+    {
+      "epoch": 0.8685376661742984,
+      "grad_norm": 0.3404117822647095,
+      "learning_rate": 1.717507257044331e-05,
+      "loss": 0.3192,
+      "step": 147
+    },
+    {
+      "epoch": 0.8744460856720827,
+      "grad_norm": 0.3535095751285553,
+      "learning_rate": 1.7129041402350317e-05,
+      "loss": 0.3364,
+      "step": 148
+    },
+    {
+      "epoch": 0.880354505169867,
+      "grad_norm": 0.3418992757797241,
+      "learning_rate": 1.708270099647198e-05,
+      "loss": 0.3327,
+      "step": 149
+    },
+    {
+      "epoch": 0.8862629246676514,
+      "grad_norm": 0.3172495663166046,
+      "learning_rate": 1.7036053362924896e-05,
+      "loss": 0.3404,
+      "step": 150
+    },
+    {
+      "epoch": 0.8921713441654358,
+      "grad_norm": 0.3307952284812927,
+      "learning_rate": 1.6989100525152346e-05,
+      "loss": 0.3279,
+      "step": 151
+    },
+    {
+      "epoch": 0.8980797636632201,
+      "grad_norm": 0.29014381766319275,
+      "learning_rate": 1.694184451983651e-05,
+      "loss": 0.3027,
+      "step": 152
+    },
+    {
+      "epoch": 0.9039881831610044,
+      "grad_norm": 0.3290538191795349,
+      "learning_rate": 1.689428739681012e-05,
+      "loss": 0.3297,
+      "step": 153
+    },
+    {
+      "epoch": 0.9098966026587888,
+      "grad_norm": 0.3165034353733063,
+      "learning_rate": 1.684643121896755e-05,
+      "loss": 0.3225,
+      "step": 154
+    },
+    {
+      "epoch": 0.9158050221565731,
+      "grad_norm": 0.3677435517311096,
+      "learning_rate": 1.679827806217533e-05,
+      "loss": 0.328,
+      "step": 155
+    },
+    {
+      "epoch": 0.9217134416543574,
+      "grad_norm": 0.3617594242095947,
+      "learning_rate": 1.6749830015182106e-05,
+      "loss": 0.3299,
+      "step": 156
+    },
+    {
+      "epoch": 0.9276218611521418,
+      "grad_norm": 0.31069889664649963,
+      "learning_rate": 1.6701089179528032e-05,
+      "loss": 0.3146,
+      "step": 157
+    },
+    {
+      "epoch": 0.9335302806499262,
+      "grad_norm": 0.3610530197620392,
+      "learning_rate": 1.6652057669453606e-05,
+      "loss": 0.3223,
+      "step": 158
+    },
+    {
+      "epoch": 0.9394387001477105,
+      "grad_norm": 0.3169001638889313,
+      "learning_rate": 1.6602737611807975e-05,
+      "loss": 0.3194,
+      "step": 159
+    },
+    {
+      "epoch": 0.9453471196454948,
+      "grad_norm": 0.33033737540245056,
+      "learning_rate": 1.655313114595666e-05,
+      "loss": 0.3317,
+      "step": 160
+    },
+    {
+      "epoch": 0.9512555391432792,
+      "grad_norm": 0.35510334372520447,
+      "learning_rate": 1.6503240423688768e-05,
+      "loss": 0.3249,
+      "step": 161
+    },
+    {
+      "epoch": 0.9571639586410635,
+      "grad_norm": 0.356079638004303,
+      "learning_rate": 1.6453067609123656e-05,
+      "loss": 0.3274,
+      "step": 162
+    },
+    {
+      "epoch": 0.9630723781388478,
+      "grad_norm": 0.36350899934768677,
+      "learning_rate": 1.6402614878617037e-05,
+      "loss": 0.3553,
+      "step": 163
+    },
+    {
+      "epoch": 0.9689807976366323,
+      "grad_norm": 0.3371831476688385,
+      "learning_rate": 1.6351884420666616e-05,
+      "loss": 0.3245,
+      "step": 164
+    },
+    {
+      "epoch": 0.9748892171344166,
+      "grad_norm": 0.3398657739162445,
+      "learning_rate": 1.6300878435817115e-05,
+      "loss": 0.3043,
+      "step": 165
+    },
+    {
+      "epoch": 0.9807976366322009,
+      "grad_norm": 0.34537115693092346,
+      "learning_rate": 1.6249599136564837e-05,
+      "loss": 0.349,
+      "step": 166
+    },
+    {
+      "epoch": 0.9867060561299852,
+      "grad_norm": 0.31506776809692383,
+      "learning_rate": 1.619804874726171e-05,
+      "loss": 0.315,
+      "step": 167
+    },
+    {
+      "epoch": 0.9926144756277696,
+      "grad_norm": 0.32844215631484985,
+      "learning_rate": 1.6146229504018777e-05,
+      "loss": 0.3247,
+      "step": 168
+    },
+    {
+      "epoch": 0.9985228951255539,
+      "grad_norm": 0.3447742760181427,
+      "learning_rate": 1.609414365460921e-05,
+      "loss": 0.3193,
+      "step": 169
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 507,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 169,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.892740285085778e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

3b-mb_base/checkpoint-169/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d657c9786dc6c8c08c64e914a96a01397e0a80c1d965337767408bc8f80e5cf
+size 10744

3b-mb_base/checkpoint-169/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

3b-mb_base/checkpoint-338/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

3b-mb_base/checkpoint-338/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

3b-mb_base/checkpoint-338/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.1"
+}

3b-mb_base/checkpoint-338/latest

@@ -0,0 +1 @@
+global_step337

3b-mb_base/checkpoint-338/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1dcaf6f5430f06caba435ab343745ffde124cf70490a36f66d78187bf075e4
+size 4956450288

3b-mb_base/checkpoint-338/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3981a3a9d6b4e220344b35a25a971d7825c700fbd96ff52859b234be31da7df
+size 1835586736

3b-mb_base/checkpoint-338/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 6791987200
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

3b-mb_base/checkpoint-338/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dcb161b22b2558dbf7e3f8c871050cec383d11a40423fab11f18d5e630639bf
+size 14512

3b-mb_base/checkpoint-338/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d50af6aef769414a6f28fa1b1bc51ce707dc8ecd15474e03f99a2f10fde086be
+size 14512

3b-mb_base/checkpoint-338/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0ff87d03adec7a7483b66c31fc3a08e9184f59f52667e0a62a335c052ee5c8
+size 1064

3b-mb_base/checkpoint-338/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

3b-mb_base/checkpoint-338/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

3b-mb_base/checkpoint-338/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

3b-mb_base/checkpoint-338/trainer_state.json

@@ -0,0 +1,2447 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9926144756277697,
+  "eval_steps": 57,
+  "global_step": 338,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005908419497784343,
+      "grad_norm": 4.501461029052734,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 1.062,
+      "step": 1
+    },
+    {
+      "epoch": 0.005908419497784343,
+      "eval_loss": 1.0835397243499756,
+      "eval_runtime": 4.3539,
+      "eval_samples_per_second": 12.632,
+      "eval_steps_per_second": 1.608,
+      "step": 1
+    },
+    {
+      "epoch": 0.011816838995568686,
+      "grad_norm": 4.469114303588867,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 1.0268,
+      "step": 2
+    },
+    {
+      "epoch": 0.01772525849335303,
+      "grad_norm": 4.554893970489502,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.0401,
+      "step": 3
+    },
+    {
+      "epoch": 0.023633677991137372,
+      "grad_norm": 4.374792575836182,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 1.0423,
+      "step": 4
+    },
+    {
+      "epoch": 0.029542097488921712,
+      "grad_norm": 3.4377498626708984,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.9965,
+      "step": 5
+    },
+    {
+      "epoch": 0.03545051698670606,
+      "grad_norm": 3.1242499351501465,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.9479,
+      "step": 6
+    },
+    {
+      "epoch": 0.0413589364844904,
+      "grad_norm": 1.8368685245513916,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.8296,
+      "step": 7
+    },
+    {
+      "epoch": 0.047267355982274745,
+      "grad_norm": 1.7457680702209473,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.8159,
+      "step": 8
+    },
+    {
+      "epoch": 0.053175775480059084,
+      "grad_norm": 1.2953853607177734,
+      "learning_rate": 6e-06,
+      "loss": 0.664,
+      "step": 9
+    },
+    {
+      "epoch": 0.059084194977843424,
+      "grad_norm": 1.1054794788360596,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6486,
+      "step": 10
+    },
+    {
+      "epoch": 0.06499261447562776,
+      "grad_norm": 0.8712942004203796,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.6415,
+      "step": 11
+    },
+    {
+      "epoch": 0.07090103397341212,
+      "grad_norm": 1.4441039562225342,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.6255,
+      "step": 12
+    },
+    {
+      "epoch": 0.07680945347119646,
+      "grad_norm": 1.4984484910964966,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.5561,
+      "step": 13
+    },
+    {
+      "epoch": 0.0827178729689808,
+      "grad_norm": 0.8376960754394531,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.5534,
+      "step": 14
+    },
+    {
+      "epoch": 0.08862629246676514,
+      "grad_norm": 0.7184750437736511,
+      "learning_rate": 1e-05,
+      "loss": 0.5062,
+      "step": 15
+    },
+    {
+      "epoch": 0.09453471196454949,
+      "grad_norm": 0.8381787538528442,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.5531,
+      "step": 16
+    },
+    {
+      "epoch": 0.10044313146233383,
+      "grad_norm": 0.7621350288391113,
+      "learning_rate": 1.1333333333333334e-05,
+      "loss": 0.4876,
+      "step": 17
+    },
+    {
+      "epoch": 0.10635155096011817,
+      "grad_norm": 0.6955872178077698,
+      "learning_rate": 1.2e-05,
+      "loss": 0.5019,
+      "step": 18
+    },
+    {
+      "epoch": 0.11225997045790251,
+      "grad_norm": 0.5844917297363281,
+      "learning_rate": 1.2666666666666667e-05,
+      "loss": 0.4368,
+      "step": 19
+    },
+    {
+      "epoch": 0.11816838995568685,
+      "grad_norm": 0.5807573795318604,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.4965,
+      "step": 20
+    },
+    {
+      "epoch": 0.1240768094534712,
+      "grad_norm": 0.5376399755477905,
+      "learning_rate": 1.4e-05,
+      "loss": 0.4841,
+      "step": 21
+    },
+    {
+      "epoch": 0.12998522895125553,
+      "grad_norm": 0.5053263902664185,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.4573,
+      "step": 22
+    },
+    {
+      "epoch": 0.1358936484490399,
+      "grad_norm": 0.5155225396156311,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 0.451,
+      "step": 23
+    },
+    {
+      "epoch": 0.14180206794682423,
+      "grad_norm": 0.52030348777771,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.4199,
+      "step": 24
+    },
+    {
+      "epoch": 0.14771048744460857,
+      "grad_norm": 0.5321907997131348,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.4532,
+      "step": 25
+    },
+    {
+      "epoch": 0.1536189069423929,
+      "grad_norm": 0.5318155288696289,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 0.4813,
+      "step": 26
+    },
+    {
+      "epoch": 0.15952732644017725,
+      "grad_norm": 0.5176340937614441,
+      "learning_rate": 1.8e-05,
+      "loss": 0.4288,
+      "step": 27
+    },
+    {
+      "epoch": 0.1654357459379616,
+      "grad_norm": 0.43893975019454956,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.3766,
+      "step": 28
+    },
+    {
+      "epoch": 0.17134416543574593,
+      "grad_norm": 0.43830162286758423,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 0.4159,
+      "step": 29
+    },
+    {
+      "epoch": 0.17725258493353027,
+      "grad_norm": 0.45950719714164734,
+      "learning_rate": 2e-05,
+      "loss": 0.4505,
+      "step": 30
+    },
+    {
+      "epoch": 0.1831610044313146,
+      "grad_norm": 0.40500667691230774,
+      "learning_rate": 1.9999783114048658e-05,
+      "loss": 0.3726,
+      "step": 31
+    },
+    {
+      "epoch": 0.18906942392909898,
+      "grad_norm": 0.43435147404670715,
+      "learning_rate": 1.9999132465602526e-05,
+      "loss": 0.442,
+      "step": 32
+    },
+    {
+      "epoch": 0.19497784342688332,
+      "grad_norm": 0.44813328981399536,
+      "learning_rate": 1.999804808288491e-05,
+      "loss": 0.437,
+      "step": 33
+    },
+    {
+      "epoch": 0.20088626292466766,
+      "grad_norm": 0.48166996240615845,
+      "learning_rate": 1.9996530012933285e-05,
+      "loss": 0.4107,
+      "step": 34
+    },
+    {
+      "epoch": 0.206794682422452,
+      "grad_norm": 0.398764044046402,
+      "learning_rate": 1.9994578321597258e-05,
+      "loss": 0.3882,
+      "step": 35
+    },
+    {
+      "epoch": 0.21270310192023634,
+      "grad_norm": 0.44229164719581604,
+      "learning_rate": 1.999219309353572e-05,
+      "loss": 0.4154,
+      "step": 36
+    },
+    {
+      "epoch": 0.21861152141802068,
+      "grad_norm": 0.44369620084762573,
+      "learning_rate": 1.998937443221316e-05,
+      "loss": 0.3863,
+      "step": 37
+    },
+    {
+      "epoch": 0.22451994091580502,
+      "grad_norm": 0.44270017743110657,
+      "learning_rate": 1.9986122459895182e-05,
+      "loss": 0.3945,
+      "step": 38
+    },
+    {
+      "epoch": 0.23042836041358936,
+      "grad_norm": 0.42152372002601624,
+      "learning_rate": 1.9982437317643218e-05,
+      "loss": 0.4094,
+      "step": 39
+    },
+    {
+      "epoch": 0.2363367799113737,
+      "grad_norm": 0.4120837450027466,
+      "learning_rate": 1.9978319165308373e-05,
+      "loss": 0.4411,
+      "step": 40
+    },
+    {
+      "epoch": 0.24224519940915806,
+      "grad_norm": 0.4064903259277344,
+      "learning_rate": 1.997376818152453e-05,
+      "loss": 0.3818,
+      "step": 41
+    },
+    {
+      "epoch": 0.2481536189069424,
+      "grad_norm": 0.3692624270915985,
+      "learning_rate": 1.9968784563700586e-05,
+      "loss": 0.3874,
+      "step": 42
+    },
+    {
+      "epoch": 0.25406203840472674,
+      "grad_norm": 0.4399218261241913,
+      "learning_rate": 1.9963368528011867e-05,
+      "loss": 0.3749,
+      "step": 43
+    },
+    {
+      "epoch": 0.25997045790251105,
+      "grad_norm": 0.3779003620147705,
+      "learning_rate": 1.9957520309390786e-05,
+      "loss": 0.3656,
+      "step": 44
+    },
+    {
+      "epoch": 0.2658788774002954,
+      "grad_norm": 0.3946981132030487,
+      "learning_rate": 1.9951240161516643e-05,
+      "loss": 0.3612,
+      "step": 45
+    },
+    {
+      "epoch": 0.2717872968980798,
+      "grad_norm": 0.3969726264476776,
+      "learning_rate": 1.99445283568046e-05,
+      "loss": 0.3932,
+      "step": 46
+    },
+    {
+      "epoch": 0.2776957163958641,
+      "grad_norm": 0.4239075183868408,
+      "learning_rate": 1.9937385186393888e-05,
+      "loss": 0.387,
+      "step": 47
+    },
+    {
+      "epoch": 0.28360413589364847,
+      "grad_norm": 0.3688453733921051,
+      "learning_rate": 1.992981096013517e-05,
+      "loss": 0.3524,
+      "step": 48
+    },
+    {
+      "epoch": 0.2895125553914328,
+      "grad_norm": 0.4294806718826294,
+      "learning_rate": 1.9921806006577102e-05,
+      "loss": 0.3787,
+      "step": 49
+    },
+    {
+      "epoch": 0.29542097488921715,
+      "grad_norm": 0.3867166042327881,
+      "learning_rate": 1.9913370672952074e-05,
+      "loss": 0.3756,
+      "step": 50
+    },
+    {
+      "epoch": 0.30132939438700146,
+      "grad_norm": 0.43365901708602905,
+      "learning_rate": 1.990450532516116e-05,
+      "loss": 0.3896,
+      "step": 51
+    },
+    {
+      "epoch": 0.3072378138847858,
+      "grad_norm": 0.38658151030540466,
+      "learning_rate": 1.9895210347758233e-05,
+      "loss": 0.3703,
+      "step": 52
+    },
+    {
+      "epoch": 0.31314623338257014,
+      "grad_norm": 0.37093815207481384,
+      "learning_rate": 1.98854861439333e-05,
+      "loss": 0.3763,
+      "step": 53
+    },
+    {
+      "epoch": 0.3190546528803545,
+      "grad_norm": 0.40044137835502625,
+      "learning_rate": 1.9875333135495e-05,
+      "loss": 0.3752,
+      "step": 54
+    },
+    {
+      "epoch": 0.3249630723781389,
+      "grad_norm": 0.39133360981941223,
+      "learning_rate": 1.986475176285232e-05,
+      "loss": 0.3589,
+      "step": 55
+    },
+    {
+      "epoch": 0.3308714918759232,
+      "grad_norm": 0.38397374749183655,
+      "learning_rate": 1.985374248499546e-05,
+      "loss": 0.3701,
+      "step": 56
+    },
+    {
+      "epoch": 0.33677991137370755,
+      "grad_norm": 0.3795414865016937,
+      "learning_rate": 1.984230577947597e-05,
+      "loss": 0.3584,
+      "step": 57
+    },
+    {
+      "epoch": 0.33677991137370755,
+      "eval_loss": 0.3953791558742523,
+      "eval_runtime": 4.6385,
+      "eval_samples_per_second": 11.857,
+      "eval_steps_per_second": 1.509,
+      "step": 57
+    },
+    {
+      "epoch": 0.34268833087149186,
+      "grad_norm": 0.3709493577480316,
+      "learning_rate": 1.9830442142386e-05,
+      "loss": 0.3647,
+      "step": 58
+    },
+    {
+      "epoch": 0.34859675036927623,
+      "grad_norm": 0.35005033016204834,
+      "learning_rate": 1.9818152088336786e-05,
+      "loss": 0.3317,
+      "step": 59
+    },
+    {
+      "epoch": 0.35450516986706054,
+      "grad_norm": 0.3652004599571228,
+      "learning_rate": 1.9805436150436352e-05,
+      "loss": 0.3394,
+      "step": 60
+    },
+    {
+      "epoch": 0.3604135893648449,
+      "grad_norm": 0.3940984904766083,
+      "learning_rate": 1.9792294880266346e-05,
+      "loss": 0.3711,
+      "step": 61
+    },
+    {
+      "epoch": 0.3663220088626292,
+      "grad_norm": 0.35634928941726685,
+      "learning_rate": 1.977872884785815e-05,
+      "loss": 0.3455,
+      "step": 62
+    },
+    {
+      "epoch": 0.3722304283604136,
+      "grad_norm": 0.3972924053668976,
+      "learning_rate": 1.9764738641668137e-05,
+      "loss": 0.3652,
+      "step": 63
+    },
+    {
+      "epoch": 0.37813884785819796,
+      "grad_norm": 0.40372708439826965,
+      "learning_rate": 1.9750324868552133e-05,
+      "loss": 0.3662,
+      "step": 64
+    },
+    {
+      "epoch": 0.38404726735598227,
+      "grad_norm": 0.396133691072464,
+      "learning_rate": 1.9735488153739128e-05,
+      "loss": 0.3726,
+      "step": 65
+    },
+    {
+      "epoch": 0.38995568685376664,
+      "grad_norm": 0.398989737033844,
+      "learning_rate": 1.972022914080411e-05,
+      "loss": 0.3595,
+      "step": 66
+    },
+    {
+      "epoch": 0.39586410635155095,
+      "grad_norm": 0.4102807939052582,
+      "learning_rate": 1.9704548491640195e-05,
+      "loss": 0.3308,
+      "step": 67
+    },
+    {
+      "epoch": 0.4017725258493353,
+      "grad_norm": 0.344397634267807,
+      "learning_rate": 1.9688446886429885e-05,
+      "loss": 0.3653,
+      "step": 68
+    },
+    {
+      "epoch": 0.4076809453471196,
+      "grad_norm": 0.3550814390182495,
+      "learning_rate": 1.9671925023615572e-05,
+      "loss": 0.3412,
+      "step": 69
+    },
+    {
+      "epoch": 0.413589364844904,
+      "grad_norm": 0.4047009348869324,
+      "learning_rate": 1.9654983619869242e-05,
+      "loss": 0.3578,
+      "step": 70
+    },
+    {
+      "epoch": 0.4194977843426883,
+      "grad_norm": 0.41112563014030457,
+      "learning_rate": 1.9637623410061392e-05,
+      "loss": 0.3694,
+      "step": 71
+    },
+    {
+      "epoch": 0.4254062038404727,
+      "grad_norm": 0.3775319755077362,
+      "learning_rate": 1.961984514722914e-05,
+      "loss": 0.3571,
+      "step": 72
+    },
+    {
+      "epoch": 0.43131462333825704,
+      "grad_norm": 0.3610381782054901,
+      "learning_rate": 1.960164960254358e-05,
+      "loss": 0.3713,
+      "step": 73
+    },
+    {
+      "epoch": 0.43722304283604135,
+      "grad_norm": 0.38662371039390564,
+      "learning_rate": 1.9583037565276314e-05,
+      "loss": 0.311,
+      "step": 74
+    },
+    {
+      "epoch": 0.4431314623338257,
+      "grad_norm": 0.3574771285057068,
+      "learning_rate": 1.9564009842765225e-05,
+      "loss": 0.3353,
+      "step": 75
+    },
+    {
+      "epoch": 0.44903988183161003,
+      "grad_norm": 0.3932562470436096,
+      "learning_rate": 1.9544567260379455e-05,
+      "loss": 0.3536,
+      "step": 76
+    },
+    {
+      "epoch": 0.4549483013293944,
+      "grad_norm": 0.3974682092666626,
+      "learning_rate": 1.9524710661483594e-05,
+      "loss": 0.3556,
+      "step": 77
+    },
+    {
+      "epoch": 0.4608567208271787,
+      "grad_norm": 0.37172290682792664,
+      "learning_rate": 1.9504440907401113e-05,
+      "loss": 0.3568,
+      "step": 78
+    },
+    {
+      "epoch": 0.4667651403249631,
+      "grad_norm": 0.37170422077178955,
+      "learning_rate": 1.948375887737699e-05,
+      "loss": 0.3556,
+      "step": 79
+    },
+    {
+      "epoch": 0.4726735598227474,
+      "grad_norm": 0.3596966862678528,
+      "learning_rate": 1.9462665468539582e-05,
+      "loss": 0.332,
+      "step": 80
+    },
+    {
+      "epoch": 0.47858197932053176,
+      "grad_norm": 0.35934680700302124,
+      "learning_rate": 1.944116159586169e-05,
+      "loss": 0.3276,
+      "step": 81
+    },
+    {
+      "epoch": 0.4844903988183161,
+      "grad_norm": 0.40984946489334106,
+      "learning_rate": 1.94192481921209e-05,
+      "loss": 0.3685,
+      "step": 82
+    },
+    {
+      "epoch": 0.49039881831610044,
+      "grad_norm": 0.3622114658355713,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.3336,
+      "step": 83
+    },
+    {
+      "epoch": 0.4963072378138848,
+      "grad_norm": 0.34888842701911926,
+      "learning_rate": 1.9374196611341212e-05,
+      "loss": 0.3625,
+      "step": 84
+    },
+    {
+      "epoch": 0.5022156573116692,
+      "grad_norm": 0.37125518918037415,
+      "learning_rate": 1.9351060388513304e-05,
+      "loss": 0.3304,
+      "step": 85
+    },
+    {
+      "epoch": 0.5081240768094535,
+      "grad_norm": 0.4107120931148529,
+      "learning_rate": 1.9327518542959717e-05,
+      "loss": 0.3755,
+      "step": 86
+    },
+    {
+      "epoch": 0.5140324963072378,
+      "grad_norm": 0.3420109748840332,
+      "learning_rate": 1.9303572095859545e-05,
+      "loss": 0.3457,
+      "step": 87
+    },
+    {
+      "epoch": 0.5199409158050221,
+      "grad_norm": 0.35079535841941833,
+      "learning_rate": 1.9279222085942396e-05,
+      "loss": 0.3454,
+      "step": 88
+    },
+    {
+      "epoch": 0.5258493353028065,
+      "grad_norm": 0.3775666058063507,
+      "learning_rate": 1.9254469569443274e-05,
+      "loss": 0.3501,
+      "step": 89
+    },
+    {
+      "epoch": 0.5317577548005908,
+      "grad_norm": 0.3327409625053406,
+      "learning_rate": 1.9229315620056805e-05,
+      "loss": 0.3507,
+      "step": 90
+    },
+    {
+      "epoch": 0.5376661742983752,
+      "grad_norm": 0.37142789363861084,
+      "learning_rate": 1.9203761328890626e-05,
+      "loss": 0.3453,
+      "step": 91
+    },
+    {
+      "epoch": 0.5435745937961596,
+      "grad_norm": 0.36256077885627747,
+      "learning_rate": 1.91778078044181e-05,
+      "loss": 0.3588,
+      "step": 92
+    },
+    {
+      "epoch": 0.5494830132939439,
+      "grad_norm": 0.3861102759838104,
+      "learning_rate": 1.9151456172430186e-05,
+      "loss": 0.3479,
+      "step": 93
+    },
+    {
+      "epoch": 0.5553914327917282,
+      "grad_norm": 0.3359353542327881,
+      "learning_rate": 1.9124707575986642e-05,
+      "loss": 0.318,
+      "step": 94
+    },
+    {
+      "epoch": 0.5612998522895125,
+      "grad_norm": 0.33662593364715576,
+      "learning_rate": 1.909756317536643e-05,
+      "loss": 0.3421,
+      "step": 95
+    },
+    {
+      "epoch": 0.5672082717872969,
+      "grad_norm": 0.35831600427627563,
+      "learning_rate": 1.9070024148017375e-05,
+      "loss": 0.3409,
+      "step": 96
+    },
+    {
+      "epoch": 0.5731166912850812,
+      "grad_norm": 0.39858701825141907,
+      "learning_rate": 1.9042091688505104e-05,
+      "loss": 0.3319,
+      "step": 97
+    },
+    {
+      "epoch": 0.5790251107828656,
+      "grad_norm": 0.3343643546104431,
+      "learning_rate": 1.9013767008461236e-05,
+      "loss": 0.3352,
+      "step": 98
+    },
+    {
+      "epoch": 0.5849335302806499,
+      "grad_norm": 0.3519919216632843,
+      "learning_rate": 1.89850513365308e-05,
+      "loss": 0.3634,
+      "step": 99
+    },
+    {
+      "epoch": 0.5908419497784343,
+      "grad_norm": 0.32900717854499817,
+      "learning_rate": 1.895594591831896e-05,
+      "loss": 0.3415,
+      "step": 100
+    },
+    {
+      "epoch": 0.5967503692762186,
+      "grad_norm": 0.34432175755500793,
+      "learning_rate": 1.8926452016336987e-05,
+      "loss": 0.3169,
+      "step": 101
+    },
+    {
+      "epoch": 0.6026587887740029,
+      "grad_norm": 0.33144107460975647,
+      "learning_rate": 1.8896570909947477e-05,
+      "loss": 0.3431,
+      "step": 102
+    },
+    {
+      "epoch": 0.6085672082717873,
+      "grad_norm": 0.3299802839756012,
+      "learning_rate": 1.8866303895308856e-05,
+      "loss": 0.3411,
+      "step": 103
+    },
+    {
+      "epoch": 0.6144756277695717,
+      "grad_norm": 0.30740225315093994,
+      "learning_rate": 1.883565228531919e-05,
+      "loss": 0.3355,
+      "step": 104
+    },
+    {
+      "epoch": 0.620384047267356,
+      "grad_norm": 0.34325993061065674,
+      "learning_rate": 1.88046174095592e-05,
+      "loss": 0.3188,
+      "step": 105
+    },
+    {
+      "epoch": 0.6262924667651403,
+      "grad_norm": 0.3394065797328949,
+      "learning_rate": 1.8773200614234587e-05,
+      "loss": 0.3153,
+      "step": 106
+    },
+    {
+      "epoch": 0.6322008862629247,
+      "grad_norm": 0.35468512773513794,
+      "learning_rate": 1.874140326211766e-05,
+      "loss": 0.3387,
+      "step": 107
+    },
+    {
+      "epoch": 0.638109305760709,
+      "grad_norm": 0.36726799607276917,
+      "learning_rate": 1.8709226732488216e-05,
+      "loss": 0.3457,
+      "step": 108
+    },
+    {
+      "epoch": 0.6440177252584933,
+      "grad_norm": 0.3223711848258972,
+      "learning_rate": 1.86766724210737e-05,
+      "loss": 0.3588,
+      "step": 109
+    },
+    {
+      "epoch": 0.6499261447562777,
+      "grad_norm": 0.3537541925907135,
+      "learning_rate": 1.8643741739988672e-05,
+      "loss": 0.3506,
+      "step": 110
+    },
+    {
+      "epoch": 0.6558345642540621,
+      "grad_norm": 0.3755073845386505,
+      "learning_rate": 1.8610436117673557e-05,
+      "loss": 0.3221,
+      "step": 111
+    },
+    {
+      "epoch": 0.6617429837518464,
+      "grad_norm": 0.31778833270072937,
+      "learning_rate": 1.8576756998832667e-05,
+      "loss": 0.3161,
+      "step": 112
+    },
+    {
+      "epoch": 0.6676514032496307,
+      "grad_norm": 0.3517738878726959,
+      "learning_rate": 1.8542705844371544e-05,
+      "loss": 0.3442,
+      "step": 113
+    },
+    {
+      "epoch": 0.6735598227474151,
+      "grad_norm": 0.3254755139350891,
+      "learning_rate": 1.8508284131333604e-05,
+      "loss": 0.3372,
+      "step": 114
+    },
+    {
+      "epoch": 0.6735598227474151,
+      "eval_loss": 0.363791823387146,
+      "eval_runtime": 4.0908,
+      "eval_samples_per_second": 13.445,
+      "eval_steps_per_second": 1.711,
+      "step": 114
+    },
+    {
+      "epoch": 0.6794682422451994,
+      "grad_norm": 0.3458060622215271,
+      "learning_rate": 1.8473493352836032e-05,
+      "loss": 0.3329,
+      "step": 115
+    },
+    {
+      "epoch": 0.6853766617429837,
+      "grad_norm": 0.33962881565093994,
+      "learning_rate": 1.8438335018005052e-05,
+      "loss": 0.3478,
+      "step": 116
+    },
+    {
+      "epoch": 0.691285081240768,
+      "grad_norm": 0.33980926871299744,
+      "learning_rate": 1.8402810651910444e-05,
+      "loss": 0.3484,
+      "step": 117
+    },
+    {
+      "epoch": 0.6971935007385525,
+      "grad_norm": 0.355694979429245,
+      "learning_rate": 1.8366921795499394e-05,
+      "loss": 0.3686,
+      "step": 118
+    },
+    {
+      "epoch": 0.7031019202363368,
+      "grad_norm": 0.3415476083755493,
+      "learning_rate": 1.8330670005529657e-05,
+      "loss": 0.3204,
+      "step": 119
+    },
+    {
+      "epoch": 0.7090103397341211,
+      "grad_norm": 0.3336890935897827,
+      "learning_rate": 1.829405685450202e-05,
+      "loss": 0.3323,
+      "step": 120
+    },
+    {
+      "epoch": 0.7149187592319055,
+      "grad_norm": 0.34337785840034485,
+      "learning_rate": 1.8257083930592102e-05,
+      "loss": 0.3283,
+      "step": 121
+    },
+    {
+      "epoch": 0.7208271787296898,
+      "grad_norm": 0.3578524887561798,
+      "learning_rate": 1.8219752837581466e-05,
+      "loss": 0.3326,
+      "step": 122
+    },
+    {
+      "epoch": 0.7267355982274741,
+      "grad_norm": 0.32392922043800354,
+      "learning_rate": 1.8182065194788024e-05,
+      "loss": 0.3141,
+      "step": 123
+    },
+    {
+      "epoch": 0.7326440177252584,
+      "grad_norm": 0.36127492785453796,
+      "learning_rate": 1.814402263699584e-05,
+      "loss": 0.3461,
+      "step": 124
+    },
+    {
+      "epoch": 0.7385524372230429,
+      "grad_norm": 0.33812931180000305,
+      "learning_rate": 1.8105626814384173e-05,
+      "loss": 0.3404,
+      "step": 125
+    },
+    {
+      "epoch": 0.7444608567208272,
+      "grad_norm": 0.3138431906700134,
+      "learning_rate": 1.8066879392455932e-05,
+      "loss": 0.3237,
+      "step": 126
+    },
+    {
+      "epoch": 0.7503692762186115,
+      "grad_norm": 0.33033978939056396,
+      "learning_rate": 1.8027782051965408e-05,
+      "loss": 0.3416,
+      "step": 127
+    },
+    {
+      "epoch": 0.7562776957163959,
+      "grad_norm": 0.3907163143157959,
+      "learning_rate": 1.7988336488845374e-05,
+      "loss": 0.3352,
+      "step": 128
+    },
+    {
+      "epoch": 0.7621861152141802,
+      "grad_norm": 0.315248042345047,
+      "learning_rate": 1.7948544414133534e-05,
+      "loss": 0.3225,
+      "step": 129
+    },
+    {
+      "epoch": 0.7680945347119645,
+      "grad_norm": 0.3284492790699005,
+      "learning_rate": 1.7908407553898282e-05,
+      "loss": 0.3217,
+      "step": 130
+    },
+    {
+      "epoch": 0.7740029542097489,
+      "grad_norm": 0.3439176082611084,
+      "learning_rate": 1.7867927649163838e-05,
+      "loss": 0.3367,
+      "step": 131
+    },
+    {
+      "epoch": 0.7799113737075333,
+      "grad_norm": 0.31954073905944824,
+      "learning_rate": 1.782710645583473e-05,
+      "loss": 0.3133,
+      "step": 132
+    },
+    {
+      "epoch": 0.7858197932053176,
+      "grad_norm": 0.38416293263435364,
+      "learning_rate": 1.7785945744619642e-05,
+      "loss": 0.3484,
+      "step": 133
+    },
+    {
+      "epoch": 0.7917282127031019,
+      "grad_norm": 0.34139737486839294,
+      "learning_rate": 1.774444730095456e-05,
+      "loss": 0.3042,
+      "step": 134
+    },
+    {
+      "epoch": 0.7976366322008862,
+      "grad_norm": 0.3623535931110382,
+      "learning_rate": 1.7702612924925377e-05,
+      "loss": 0.3318,
+      "step": 135
+    },
+    {
+      "epoch": 0.8035450516986706,
+      "grad_norm": 0.32973209023475647,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.3092,
+      "step": 136
+    },
+    {
+      "epoch": 0.8094534711964549,
+      "grad_norm": 0.30704402923583984,
+      "learning_rate": 1.761794364889855e-05,
+      "loss": 0.321,
+      "step": 137
+    },
+    {
+      "epoch": 0.8153618906942393,
+      "grad_norm": 0.34877485036849976,
+      "learning_rate": 1.7575112421616203e-05,
+      "loss": 0.3266,
+      "step": 138
+    },
+    {
+      "epoch": 0.8212703101920237,
+      "grad_norm": 0.3538282811641693,
+      "learning_rate": 1.7531952607241033e-05,
+      "loss": 0.3703,
+      "step": 139
+    },
+    {
+      "epoch": 0.827178729689808,
+      "grad_norm": 0.35590365529060364,
+      "learning_rate": 1.7488466077924525e-05,
+      "loss": 0.3506,
+      "step": 140
+    },
+    {
+      "epoch": 0.8330871491875923,
+      "grad_norm": 0.33215418457984924,
+      "learning_rate": 1.7444654719990128e-05,
+      "loss": 0.3207,
+      "step": 141
+    },
+    {
+      "epoch": 0.8389955686853766,
+      "grad_norm": 0.3381923735141754,
+      "learning_rate": 1.7400520433851457e-05,
+      "loss": 0.3237,
+      "step": 142
+    },
+    {
+      "epoch": 0.844903988183161,
+      "grad_norm": 0.3371356129646301,
+      "learning_rate": 1.735606513392984e-05,
+      "loss": 0.3394,
+      "step": 143
+    },
+    {
+      "epoch": 0.8508124076809453,
+      "grad_norm": 0.344291627407074,
+      "learning_rate": 1.7311290748571273e-05,
+      "loss": 0.3604,
+      "step": 144
+    },
+    {
+      "epoch": 0.8567208271787297,
+      "grad_norm": 0.3567575216293335,
+      "learning_rate": 1.72661992199628e-05,
+      "loss": 0.3518,
+      "step": 145
+    },
+    {
+      "epoch": 0.8626292466765141,
+      "grad_norm": 0.33762165904045105,
+      "learning_rate": 1.7220792504048227e-05,
+      "loss": 0.3146,
+      "step": 146
+    },
+    {
+      "epoch": 0.8685376661742984,
+      "grad_norm": 0.3404117822647095,
+      "learning_rate": 1.717507257044331e-05,
+      "loss": 0.3192,
+      "step": 147
+    },
+    {
+      "epoch": 0.8744460856720827,
+      "grad_norm": 0.3535095751285553,
+      "learning_rate": 1.7129041402350317e-05,
+      "loss": 0.3364,
+      "step": 148
+    },
+    {
+      "epoch": 0.880354505169867,
+      "grad_norm": 0.3418992757797241,
+      "learning_rate": 1.708270099647198e-05,
+      "loss": 0.3327,
+      "step": 149
+    },
+    {
+      "epoch": 0.8862629246676514,
+      "grad_norm": 0.3172495663166046,
+      "learning_rate": 1.7036053362924896e-05,
+      "loss": 0.3404,
+      "step": 150
+    },
+    {
+      "epoch": 0.8921713441654358,
+      "grad_norm": 0.3307952284812927,
+      "learning_rate": 1.6989100525152346e-05,
+      "loss": 0.3279,
+      "step": 151
+    },
+    {
+      "epoch": 0.8980797636632201,
+      "grad_norm": 0.29014381766319275,
+      "learning_rate": 1.694184451983651e-05,
+      "loss": 0.3027,
+      "step": 152
+    },
+    {
+      "epoch": 0.9039881831610044,
+      "grad_norm": 0.3290538191795349,
+      "learning_rate": 1.689428739681012e-05,
+      "loss": 0.3297,
+      "step": 153
+    },
+    {
+      "epoch": 0.9098966026587888,
+      "grad_norm": 0.3165034353733063,
+      "learning_rate": 1.684643121896755e-05,
+      "loss": 0.3225,
+      "step": 154
+    },
+    {
+      "epoch": 0.9158050221565731,
+      "grad_norm": 0.3677435517311096,
+      "learning_rate": 1.679827806217533e-05,
+      "loss": 0.328,
+      "step": 155
+    },
+    {
+      "epoch": 0.9217134416543574,
+      "grad_norm": 0.3617594242095947,
+      "learning_rate": 1.6749830015182106e-05,
+      "loss": 0.3299,
+      "step": 156
+    },
+    {
+      "epoch": 0.9276218611521418,
+      "grad_norm": 0.31069889664649963,
+      "learning_rate": 1.6701089179528032e-05,
+      "loss": 0.3146,
+      "step": 157
+    },
+    {
+      "epoch": 0.9335302806499262,
+      "grad_norm": 0.3610530197620392,
+      "learning_rate": 1.6652057669453606e-05,
+      "loss": 0.3223,
+      "step": 158
+    },
+    {
+      "epoch": 0.9394387001477105,
+      "grad_norm": 0.3169001638889313,
+      "learning_rate": 1.6602737611807975e-05,
+      "loss": 0.3194,
+      "step": 159
+    },
+    {
+      "epoch": 0.9453471196454948,
+      "grad_norm": 0.33033737540245056,
+      "learning_rate": 1.655313114595666e-05,
+      "loss": 0.3317,
+      "step": 160
+    },
+    {
+      "epoch": 0.9512555391432792,
+      "grad_norm": 0.35510334372520447,
+      "learning_rate": 1.6503240423688768e-05,
+      "loss": 0.3249,
+      "step": 161
+    },
+    {
+      "epoch": 0.9571639586410635,
+      "grad_norm": 0.356079638004303,
+      "learning_rate": 1.6453067609123656e-05,
+      "loss": 0.3274,
+      "step": 162
+    },
+    {
+      "epoch": 0.9630723781388478,
+      "grad_norm": 0.36350899934768677,
+      "learning_rate": 1.6402614878617037e-05,
+      "loss": 0.3553,
+      "step": 163
+    },
+    {
+      "epoch": 0.9689807976366323,
+      "grad_norm": 0.3371831476688385,
+      "learning_rate": 1.6351884420666616e-05,
+      "loss": 0.3245,
+      "step": 164
+    },
+    {
+      "epoch": 0.9748892171344166,
+      "grad_norm": 0.3398657739162445,
+      "learning_rate": 1.6300878435817115e-05,
+      "loss": 0.3043,
+      "step": 165
+    },
+    {
+      "epoch": 0.9807976366322009,
+      "grad_norm": 0.34537115693092346,
+      "learning_rate": 1.6249599136564837e-05,
+      "loss": 0.349,
+      "step": 166
+    },
+    {
+      "epoch": 0.9867060561299852,
+      "grad_norm": 0.31506776809692383,
+      "learning_rate": 1.619804874726171e-05,
+      "loss": 0.315,
+      "step": 167
+    },
+    {
+      "epoch": 0.9926144756277696,
+      "grad_norm": 0.32844215631484985,
+      "learning_rate": 1.6146229504018777e-05,
+      "loss": 0.3247,
+      "step": 168
+    },
+    {
+      "epoch": 0.9985228951255539,
+      "grad_norm": 0.3447742760181427,
+      "learning_rate": 1.609414365460921e-05,
+      "loss": 0.3193,
+      "step": 169
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3447742760181427,
+      "learning_rate": 1.6041793458370812e-05,
+      "loss": 0.3359,
+      "step": 170
+    },
+    {
+      "epoch": 1.0059084194977843,
+      "grad_norm": 0.27635836601257324,
+      "learning_rate": 1.5989181186108003e-05,
+      "loss": 0.2579,
+      "step": 171
+    },
+    {
+      "epoch": 1.0059084194977843,
+      "eval_loss": 0.3496532440185547,
+      "eval_runtime": 4.0258,
+      "eval_samples_per_second": 13.662,
+      "eval_steps_per_second": 1.739,
+      "step": 171
+    },
+    {
+      "epoch": 1.0118168389955686,
+      "grad_norm": 0.27547529339790344,
+      "learning_rate": 1.5936309119993333e-05,
+      "loss": 0.2532,
+      "step": 172
+    },
+    {
+      "epoch": 1.017725258493353,
+      "grad_norm": 0.2674752473831177,
+      "learning_rate": 1.5883179553468465e-05,
+      "loss": 0.2413,
+      "step": 173
+    },
+    {
+      "epoch": 1.0236336779911375,
+      "grad_norm": 0.3056715428829193,
+      "learning_rate": 1.5829794791144723e-05,
+      "loss": 0.2418,
+      "step": 174
+    },
+    {
+      "epoch": 1.0295420974889218,
+      "grad_norm": 0.27895164489746094,
+      "learning_rate": 1.5776157148703094e-05,
+      "loss": 0.2516,
+      "step": 175
+    },
+    {
+      "epoch": 1.035450516986706,
+      "grad_norm": 0.2935872972011566,
+      "learning_rate": 1.5722268952793806e-05,
+      "loss": 0.254,
+      "step": 176
+    },
+    {
+      "epoch": 1.0413589364844904,
+      "grad_norm": 0.28329288959503174,
+      "learning_rate": 1.566813254093538e-05,
+      "loss": 0.2356,
+      "step": 177
+    },
+    {
+      "epoch": 1.0472673559822747,
+      "grad_norm": 0.29026728868484497,
+      "learning_rate": 1.5613750261413256e-05,
+      "loss": 0.2404,
+      "step": 178
+    },
+    {
+      "epoch": 1.053175775480059,
+      "grad_norm": 0.3126751780509949,
+      "learning_rate": 1.555912447317792e-05,
+      "loss": 0.2303,
+      "step": 179
+    },
+    {
+      "epoch": 1.0590841949778433,
+      "grad_norm": 0.26517724990844727,
+      "learning_rate": 1.5504257545742585e-05,
+      "loss": 0.2175,
+      "step": 180
+    },
+    {
+      "epoch": 1.0649926144756279,
+      "grad_norm": 0.26433265209198,
+      "learning_rate": 1.5449151859080395e-05,
+      "loss": 0.2169,
+      "step": 181
+    },
+    {
+      "epoch": 1.0709010339734122,
+      "grad_norm": 0.2908313274383545,
+      "learning_rate": 1.5393809803521213e-05,
+      "loss": 0.2236,
+      "step": 182
+    },
+    {
+      "epoch": 1.0768094534711965,
+      "grad_norm": 0.2951337397098541,
+      "learning_rate": 1.533823377964791e-05,
+      "loss": 0.2305,
+      "step": 183
+    },
+    {
+      "epoch": 1.0827178729689808,
+      "grad_norm": 0.29755067825317383,
+      "learning_rate": 1.528242619819224e-05,
+      "loss": 0.2385,
+      "step": 184
+    },
+    {
+      "epoch": 1.0886262924667651,
+      "grad_norm": 0.2879098355770111,
+      "learning_rate": 1.5226389479930296e-05,
+      "loss": 0.2377,
+      "step": 185
+    },
+    {
+      "epoch": 1.0945347119645494,
+      "grad_norm": 0.2590835392475128,
+      "learning_rate": 1.517012605557746e-05,
+      "loss": 0.2312,
+      "step": 186
+    },
+    {
+      "epoch": 1.1004431314623337,
+      "grad_norm": 0.2694130837917328,
+      "learning_rate": 1.5113638365682996e-05,
+      "loss": 0.2347,
+      "step": 187
+    },
+    {
+      "epoch": 1.106351550960118,
+      "grad_norm": 0.29442402720451355,
+      "learning_rate": 1.5056928860524181e-05,
+      "loss": 0.2428,
+      "step": 188
+    },
+    {
+      "epoch": 1.1122599704579026,
+      "grad_norm": 0.29042768478393555,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.2501,
+      "step": 189
+    },
+    {
+      "epoch": 1.118168389955687,
+      "grad_norm": 0.2620311975479126,
+      "learning_rate": 1.4942854253524479e-05,
+      "loss": 0.2395,
+      "step": 190
+    },
+    {
+      "epoch": 1.1240768094534712,
+      "grad_norm": 0.26113441586494446,
+      "learning_rate": 1.488549409991953e-05,
+      "loss": 0.2532,
+      "step": 191
+    },
+    {
+      "epoch": 1.1299852289512555,
+      "grad_norm": 0.2995262145996094,
+      "learning_rate": 1.482792202730745e-05,
+      "loss": 0.2319,
+      "step": 192
+    },
+    {
+      "epoch": 1.1358936484490398,
+      "grad_norm": 0.27327674627304077,
+      "learning_rate": 1.477014053300299e-05,
+      "loss": 0.2348,
+      "step": 193
+    },
+    {
+      "epoch": 1.1418020679468242,
+      "grad_norm": 0.26245003938674927,
+      "learning_rate": 1.4712152123405018e-05,
+      "loss": 0.228,
+      "step": 194
+    },
+    {
+      "epoch": 1.1477104874446087,
+      "grad_norm": 0.28888335824012756,
+      "learning_rate": 1.4653959313887813e-05,
+      "loss": 0.2436,
+      "step": 195
+    },
+    {
+      "epoch": 1.153618906942393,
+      "grad_norm": 0.2724781632423401,
+      "learning_rate": 1.4595564628691944e-05,
+      "loss": 0.2442,
+      "step": 196
+    },
+    {
+      "epoch": 1.1595273264401773,
+      "grad_norm": 0.2921780049800873,
+      "learning_rate": 1.4536970600814789e-05,
+      "loss": 0.2412,
+      "step": 197
+    },
+    {
+      "epoch": 1.1654357459379616,
+      "grad_norm": 0.27938568592071533,
+      "learning_rate": 1.4478179771900634e-05,
+      "loss": 0.2465,
+      "step": 198
+    },
+    {
+      "epoch": 1.171344165435746,
+      "grad_norm": 0.29516273736953735,
+      "learning_rate": 1.4419194692130453e-05,
+      "loss": 0.2415,
+      "step": 199
+    },
+    {
+      "epoch": 1.1772525849335302,
+      "grad_norm": 0.27947136759757996,
+      "learning_rate": 1.436001792011128e-05,
+      "loss": 0.2295,
+      "step": 200
+    },
+    {
+      "epoch": 1.1831610044313146,
+      "grad_norm": 0.26482367515563965,
+      "learning_rate": 1.4300652022765207e-05,
+      "loss": 0.2273,
+      "step": 201
+    },
+    {
+      "epoch": 1.1890694239290989,
+      "grad_norm": 0.2728091776371002,
+      "learning_rate": 1.424109957521806e-05,
+      "loss": 0.2227,
+      "step": 202
+    },
+    {
+      "epoch": 1.1949778434268834,
+      "grad_norm": 0.28748828172683716,
+      "learning_rate": 1.4181363160687693e-05,
+      "loss": 0.2402,
+      "step": 203
+    },
+    {
+      "epoch": 1.2008862629246677,
+      "grad_norm": 0.2891993820667267,
+      "learning_rate": 1.4121445370371922e-05,
+      "loss": 0.224,
+      "step": 204
+    },
+    {
+      "epoch": 1.206794682422452,
+      "grad_norm": 0.24767152965068817,
+      "learning_rate": 1.4061348803336135e-05,
+      "loss": 0.221,
+      "step": 205
+    },
+    {
+      "epoch": 1.2127031019202363,
+      "grad_norm": 0.2819165885448456,
+      "learning_rate": 1.400107606640056e-05,
+      "loss": 0.2231,
+      "step": 206
+    },
+    {
+      "epoch": 1.2186115214180206,
+      "grad_norm": 0.27328819036483765,
+      "learning_rate": 1.394062977402717e-05,
+      "loss": 0.229,
+      "step": 207
+    },
+    {
+      "epoch": 1.224519940915805,
+      "grad_norm": 0.2674582302570343,
+      "learning_rate": 1.3880012548206292e-05,
+      "loss": 0.2155,
+      "step": 208
+    },
+    {
+      "epoch": 1.2304283604135893,
+      "grad_norm": 0.2989075481891632,
+      "learning_rate": 1.3819227018342865e-05,
+      "loss": 0.2184,
+      "step": 209
+    },
+    {
+      "epoch": 1.2363367799113738,
+      "grad_norm": 0.30796098709106445,
+      "learning_rate": 1.3758275821142382e-05,
+      "loss": 0.2288,
+      "step": 210
+    },
+    {
+      "epoch": 1.2422451994091581,
+      "grad_norm": 0.29833805561065674,
+      "learning_rate": 1.3697161600496525e-05,
+      "loss": 0.2368,
+      "step": 211
+    },
+    {
+      "epoch": 1.2481536189069424,
+      "grad_norm": 0.26458829641342163,
+      "learning_rate": 1.3635887007368467e-05,
+      "loss": 0.2376,
+      "step": 212
+    },
+    {
+      "epoch": 1.2540620384047267,
+      "grad_norm": 0.2781698703765869,
+      "learning_rate": 1.3574454699677893e-05,
+      "loss": 0.2167,
+      "step": 213
+    },
+    {
+      "epoch": 1.259970457902511,
+      "grad_norm": 0.268433153629303,
+      "learning_rate": 1.3512867342185705e-05,
+      "loss": 0.2229,
+      "step": 214
+    },
+    {
+      "epoch": 1.2658788774002954,
+      "grad_norm": 0.2726047933101654,
+      "learning_rate": 1.3451127606378425e-05,
+      "loss": 0.223,
+      "step": 215
+    },
+    {
+      "epoch": 1.2717872968980797,
+      "grad_norm": 0.29567429423332214,
+      "learning_rate": 1.3389238170352318e-05,
+      "loss": 0.2105,
+      "step": 216
+    },
+    {
+      "epoch": 1.277695716395864,
+      "grad_norm": 0.30303359031677246,
+      "learning_rate": 1.3327201718697232e-05,
+      "loss": 0.2602,
+      "step": 217
+    },
+    {
+      "epoch": 1.2836041358936485,
+      "grad_norm": 0.27332380414009094,
+      "learning_rate": 1.326502094238013e-05,
+      "loss": 0.2288,
+      "step": 218
+    },
+    {
+      "epoch": 1.2895125553914328,
+      "grad_norm": 0.2703614830970764,
+      "learning_rate": 1.3202698538628376e-05,
+      "loss": 0.2308,
+      "step": 219
+    },
+    {
+      "epoch": 1.2954209748892171,
+      "grad_norm": 0.2788908779621124,
+      "learning_rate": 1.3140237210812741e-05,
+      "loss": 0.2254,
+      "step": 220
+    },
+    {
+      "epoch": 1.3013293943870015,
+      "grad_norm": 0.27442580461502075,
+      "learning_rate": 1.3077639668330124e-05,
+      "loss": 0.2158,
+      "step": 221
+    },
+    {
+      "epoch": 1.3072378138847858,
+      "grad_norm": 0.28895896673202515,
+      "learning_rate": 1.3014908626486032e-05,
+      "loss": 0.2404,
+      "step": 222
+    },
+    {
+      "epoch": 1.31314623338257,
+      "grad_norm": 0.24982582032680511,
+      "learning_rate": 1.2952046806376806e-05,
+      "loss": 0.2201,
+      "step": 223
+    },
+    {
+      "epoch": 1.3190546528803546,
+      "grad_norm": 0.28909650444984436,
+      "learning_rate": 1.2889056934771577e-05,
+      "loss": 0.2384,
+      "step": 224
+    },
+    {
+      "epoch": 1.324963072378139,
+      "grad_norm": 0.28018954396247864,
+      "learning_rate": 1.282594174399399e-05,
+      "loss": 0.2324,
+      "step": 225
+    },
+    {
+      "epoch": 1.3308714918759232,
+      "grad_norm": 0.29922735691070557,
+      "learning_rate": 1.2762703971803684e-05,
+      "loss": 0.2457,
+      "step": 226
+    },
+    {
+      "epoch": 1.3367799113737076,
+      "grad_norm": 0.289288729429245,
+      "learning_rate": 1.2699346361277538e-05,
+      "loss": 0.2366,
+      "step": 227
+    },
+    {
+      "epoch": 1.3426883308714919,
+      "grad_norm": 0.2790012061595917,
+      "learning_rate": 1.2635871660690677e-05,
+      "loss": 0.2359,
+      "step": 228
+    },
+    {
+      "epoch": 1.3426883308714919,
+      "eval_loss": 0.35204342007637024,
+      "eval_runtime": 4.4578,
+      "eval_samples_per_second": 12.338,
+      "eval_steps_per_second": 1.57,
+      "step": 228
+    },
+    {
+      "epoch": 1.3485967503692762,
+      "grad_norm": 0.36030444502830505,
+      "learning_rate": 1.2572282623397268e-05,
+      "loss": 0.2405,
+      "step": 229
+    },
+    {
+      "epoch": 1.3545051698670605,
+      "grad_norm": 0.24079382419586182,
+      "learning_rate": 1.2508582007711074e-05,
+      "loss": 0.2148,
+      "step": 230
+    },
+    {
+      "epoch": 1.3604135893648448,
+      "grad_norm": 0.26674559712409973,
+      "learning_rate": 1.2444772576785828e-05,
+      "loss": 0.2457,
+      "step": 231
+    },
+    {
+      "epoch": 1.3663220088626291,
+      "grad_norm": 0.25345727801322937,
+      "learning_rate": 1.2380857098495355e-05,
+      "loss": 0.2229,
+      "step": 232
+    },
+    {
+      "epoch": 1.3722304283604136,
+      "grad_norm": 0.2623337507247925,
+      "learning_rate": 1.2316838345313517e-05,
+      "loss": 0.231,
+      "step": 233
+    },
+    {
+      "epoch": 1.378138847858198,
+      "grad_norm": 0.27783095836639404,
+      "learning_rate": 1.225271909419395e-05,
+      "loss": 0.2251,
+      "step": 234
+    },
+    {
+      "epoch": 1.3840472673559823,
+      "grad_norm": 0.25021976232528687,
+      "learning_rate": 1.2188502126449616e-05,
+      "loss": 0.226,
+      "step": 235
+    },
+    {
+      "epoch": 1.3899556868537666,
+      "grad_norm": 0.2695038318634033,
+      "learning_rate": 1.2124190227632138e-05,
+      "loss": 0.2438,
+      "step": 236
+    },
+    {
+      "epoch": 1.395864106351551,
+      "grad_norm": 0.24312005937099457,
+      "learning_rate": 1.2059786187410984e-05,
+      "loss": 0.2138,
+      "step": 237
+    },
+    {
+      "epoch": 1.4017725258493354,
+      "grad_norm": 0.2761548161506653,
+      "learning_rate": 1.1995292799452472e-05,
+      "loss": 0.244,
+      "step": 238
+    },
+    {
+      "epoch": 1.4076809453471197,
+      "grad_norm": 0.2740529477596283,
+      "learning_rate": 1.1930712861298553e-05,
+      "loss": 0.2416,
+      "step": 239
+    },
+    {
+      "epoch": 1.413589364844904,
+      "grad_norm": 0.2605426013469696,
+      "learning_rate": 1.186604917424549e-05,
+      "loss": 0.2515,
+      "step": 240
+    },
+    {
+      "epoch": 1.4194977843426884,
+      "grad_norm": 0.27557292580604553,
+      "learning_rate": 1.1801304543222349e-05,
+      "loss": 0.232,
+      "step": 241
+    },
+    {
+      "epoch": 1.4254062038404727,
+      "grad_norm": 0.2512328624725342,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.2311,
+      "step": 242
+    },
+    {
+      "epoch": 1.431314623338257,
+      "grad_norm": 0.2634104788303375,
+      "learning_rate": 1.1671583686415833e-05,
+      "loss": 0.2207,
+      "step": 243
+    },
+    {
+      "epoch": 1.4372230428360413,
+      "grad_norm": 0.2541881203651428,
+      "learning_rate": 1.1606613087558748e-05,
+      "loss": 0.2207,
+      "step": 244
+    },
+    {
+      "epoch": 1.4431314623338256,
+      "grad_norm": 0.24408863484859467,
+      "learning_rate": 1.1541572798340076e-05,
+      "loss": 0.2155,
+      "step": 245
+    },
+    {
+      "epoch": 1.44903988183161,
+      "grad_norm": 0.25305289030075073,
+      "learning_rate": 1.1476465640024814e-05,
+      "loss": 0.2245,
+      "step": 246
+    },
+    {
+      "epoch": 1.4549483013293945,
+      "grad_norm": 0.26579606533050537,
+      "learning_rate": 1.1411294436778562e-05,
+      "loss": 0.2295,
+      "step": 247
+    },
+    {
+      "epoch": 1.4608567208271788,
+      "grad_norm": 0.26332345604896545,
+      "learning_rate": 1.1346062015544997e-05,
+      "loss": 0.2363,
+      "step": 248
+    },
+    {
+      "epoch": 1.466765140324963,
+      "grad_norm": 0.2519514262676239,
+      "learning_rate": 1.1280771205923269e-05,
+      "loss": 0.2215,
+      "step": 249
+    },
+    {
+      "epoch": 1.4726735598227474,
+      "grad_norm": 0.2569345533847809,
+      "learning_rate": 1.1215424840045254e-05,
+      "loss": 0.223,
+      "step": 250
+    },
+    {
+      "epoch": 1.4785819793205317,
+      "grad_norm": 0.25557035207748413,
+      "learning_rate": 1.1150025752452693e-05,
+      "loss": 0.2511,
+      "step": 251
+    },
+    {
+      "epoch": 1.4844903988183162,
+      "grad_norm": 0.26646342873573303,
+      "learning_rate": 1.1084576779974257e-05,
+      "loss": 0.2476,
+      "step": 252
+    },
+    {
+      "epoch": 1.4903988183161005,
+      "grad_norm": 0.27917614579200745,
+      "learning_rate": 1.1019080761602473e-05,
+      "loss": 0.2284,
+      "step": 253
+    },
+    {
+      "epoch": 1.4963072378138849,
+      "grad_norm": 0.2594425082206726,
+      "learning_rate": 1.0953540538370591e-05,
+      "loss": 0.2319,
+      "step": 254
+    },
+    {
+      "epoch": 1.5022156573116692,
+      "grad_norm": 0.23648317158222198,
+      "learning_rate": 1.0887958953229349e-05,
+      "loss": 0.225,
+      "step": 255
+    },
+    {
+      "epoch": 1.5081240768094535,
+      "grad_norm": 0.24810343980789185,
+      "learning_rate": 1.0822338850923644e-05,
+      "loss": 0.2222,
+      "step": 256
+    },
+    {
+      "epoch": 1.5140324963072378,
+      "grad_norm": 0.25305667519569397,
+      "learning_rate": 1.0756683077869133e-05,
+      "loss": 0.2178,
+      "step": 257
+    },
+    {
+      "epoch": 1.519940915805022,
+      "grad_norm": 0.23994190990924835,
+      "learning_rate": 1.069099448202878e-05,
+      "loss": 0.2274,
+      "step": 258
+    },
+    {
+      "epoch": 1.5258493353028064,
+      "grad_norm": 0.28112536668777466,
+      "learning_rate": 1.0625275912789307e-05,
+      "loss": 0.2157,
+      "step": 259
+    },
+    {
+      "epoch": 1.5317577548005907,
+      "grad_norm": 0.2910768687725067,
+      "learning_rate": 1.0559530220837593e-05,
+      "loss": 0.2337,
+      "step": 260
+    },
+    {
+      "epoch": 1.537666174298375,
+      "grad_norm": 0.26320862770080566,
+      "learning_rate": 1.049376025803703e-05,
+      "loss": 0.2156,
+      "step": 261
+    },
+    {
+      "epoch": 1.5435745937961596,
+      "grad_norm": 0.2653874456882477,
+      "learning_rate": 1.0427968877303809e-05,
+      "loss": 0.2269,
+      "step": 262
+    },
+    {
+      "epoch": 1.549483013293944,
+      "grad_norm": 0.24998469650745392,
+      "learning_rate": 1.0362158932483165e-05,
+      "loss": 0.2252,
+      "step": 263
+    },
+    {
+      "epoch": 1.5553914327917282,
+      "grad_norm": 0.25920990109443665,
+      "learning_rate": 1.0296333278225599e-05,
+      "loss": 0.2274,
+      "step": 264
+    },
+    {
+      "epoch": 1.5612998522895125,
+      "grad_norm": 0.2827723026275635,
+      "learning_rate": 1.023049476986304e-05,
+      "loss": 0.248,
+      "step": 265
+    },
+    {
+      "epoch": 1.567208271787297,
+      "grad_norm": 0.27848076820373535,
+      "learning_rate": 1.0164646263284993e-05,
+      "loss": 0.2372,
+      "step": 266
+    },
+    {
+      "epoch": 1.5731166912850814,
+      "grad_norm": 0.2601296305656433,
+      "learning_rate": 1.0098790614814658e-05,
+      "loss": 0.212,
+      "step": 267
+    },
+    {
+      "epoch": 1.5790251107828657,
+      "grad_norm": 0.24360589683055878,
+      "learning_rate": 1.0032930681085028e-05,
+      "loss": 0.2152,
+      "step": 268
+    },
+    {
+      "epoch": 1.58493353028065,
+      "grad_norm": 0.3080978989601135,
+      "learning_rate": 9.967069318914977e-06,
+      "loss": 0.2218,
+      "step": 269
+    },
+    {
+      "epoch": 1.5908419497784343,
+      "grad_norm": 0.26208099722862244,
+      "learning_rate": 9.901209385185345e-06,
+      "loss": 0.2184,
+      "step": 270
+    },
+    {
+      "epoch": 1.5967503692762186,
+      "grad_norm": 0.2984671890735626,
+      "learning_rate": 9.835353736715007e-06,
+      "loss": 0.2432,
+      "step": 271
+    },
+    {
+      "epoch": 1.602658788774003,
+      "grad_norm": 0.26782581210136414,
+      "learning_rate": 9.769505230136962e-06,
+      "loss": 0.2126,
+      "step": 272
+    },
+    {
+      "epoch": 1.6085672082717872,
+      "grad_norm": 0.28440967202186584,
+      "learning_rate": 9.703666721774403e-06,
+      "loss": 0.2214,
+      "step": 273
+    },
+    {
+      "epoch": 1.6144756277695715,
+      "grad_norm": 0.2926226854324341,
+      "learning_rate": 9.637841067516837e-06,
+      "loss": 0.2256,
+      "step": 274
+    },
+    {
+      "epoch": 1.6203840472673559,
+      "grad_norm": 0.25548121333122253,
+      "learning_rate": 9.572031122696196e-06,
+      "loss": 0.2304,
+      "step": 275
+    },
+    {
+      "epoch": 1.6262924667651402,
+      "grad_norm": 0.28455373644828796,
+      "learning_rate": 9.506239741962971e-06,
+      "loss": 0.2299,
+      "step": 276
+    },
+    {
+      "epoch": 1.6322008862629247,
+      "grad_norm": 0.262614369392395,
+      "learning_rate": 9.440469779162407e-06,
+      "loss": 0.2251,
+      "step": 277
+    },
+    {
+      "epoch": 1.638109305760709,
+      "grad_norm": 0.27394819259643555,
+      "learning_rate": 9.374724087210698e-06,
+      "loss": 0.2117,
+      "step": 278
+    },
+    {
+      "epoch": 1.6440177252584933,
+      "grad_norm": 0.2843812108039856,
+      "learning_rate": 9.309005517971222e-06,
+      "loss": 0.2268,
+      "step": 279
+    },
+    {
+      "epoch": 1.6499261447562779,
+      "grad_norm": 0.25647154450416565,
+      "learning_rate": 9.24331692213087e-06,
+      "loss": 0.2187,
+      "step": 280
+    },
+    {
+      "epoch": 1.6558345642540622,
+      "grad_norm": 0.27861371636390686,
+      "learning_rate": 9.17766114907636e-06,
+      "loss": 0.2311,
+      "step": 281
+    },
+    {
+      "epoch": 1.6617429837518465,
+      "grad_norm": 0.270049512386322,
+      "learning_rate": 9.112041046770653e-06,
+      "loss": 0.2265,
+      "step": 282
+    },
+    {
+      "epoch": 1.6676514032496308,
+      "grad_norm": 0.2750328779220581,
+      "learning_rate": 9.04645946162941e-06,
+      "loss": 0.2253,
+      "step": 283
+    },
+    {
+      "epoch": 1.673559822747415,
+      "grad_norm": 0.2412230521440506,
+      "learning_rate": 8.980919238397532e-06,
+      "loss": 0.2394,
+      "step": 284
+    },
+    {
+      "epoch": 1.6794682422451994,
+      "grad_norm": 0.2524693012237549,
+      "learning_rate": 8.915423220025747e-06,
+      "loss": 0.2258,
+      "step": 285
+    },
+    {
+      "epoch": 1.6794682422451994,
+      "eval_loss": 0.3460842967033386,
+      "eval_runtime": 4.0784,
+      "eval_samples_per_second": 13.486,
+      "eval_steps_per_second": 1.716,
+      "step": 285
+    },
+    {
+      "epoch": 1.6853766617429837,
+      "grad_norm": 0.25439098477363586,
+      "learning_rate": 8.849974247547307e-06,
+      "loss": 0.2266,
+      "step": 286
+    },
+    {
+      "epoch": 1.691285081240768,
+      "grad_norm": 0.257929265499115,
+      "learning_rate": 8.784575159954748e-06,
+      "loss": 0.2133,
+      "step": 287
+    },
+    {
+      "epoch": 1.6971935007385524,
+      "grad_norm": 0.24912972748279572,
+      "learning_rate": 8.719228794076733e-06,
+      "loss": 0.2129,
+      "step": 288
+    },
+    {
+      "epoch": 1.7031019202363367,
+      "grad_norm": 0.27103564143180847,
+      "learning_rate": 8.653937984455007e-06,
+      "loss": 0.2276,
+      "step": 289
+    },
+    {
+      "epoch": 1.709010339734121,
+      "grad_norm": 0.2718878984451294,
+      "learning_rate": 8.588705563221444e-06,
+      "loss": 0.2276,
+      "step": 290
+    },
+    {
+      "epoch": 1.7149187592319055,
+      "grad_norm": 0.26431816816329956,
+      "learning_rate": 8.52353435997519e-06,
+      "loss": 0.2328,
+      "step": 291
+    },
+    {
+      "epoch": 1.7208271787296898,
+      "grad_norm": 0.2725984752178192,
+      "learning_rate": 8.458427201659926e-06,
+      "loss": 0.2292,
+      "step": 292
+    },
+    {
+      "epoch": 1.7267355982274741,
+      "grad_norm": 0.2515108585357666,
+      "learning_rate": 8.393386912441257e-06,
+      "loss": 0.226,
+      "step": 293
+    },
+    {
+      "epoch": 1.7326440177252584,
+      "grad_norm": 0.2476361244916916,
+      "learning_rate": 8.328416313584169e-06,
+      "loss": 0.2277,
+      "step": 294
+    },
+    {
+      "epoch": 1.738552437223043,
+      "grad_norm": 0.25414201617240906,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.2268,
+      "step": 295
+    },
+    {
+      "epoch": 1.7444608567208273,
+      "grad_norm": 0.26264503598213196,
+      "learning_rate": 8.198695456777653e-06,
+      "loss": 0.2193,
+      "step": 296
+    },
+    {
+      "epoch": 1.7503692762186116,
+      "grad_norm": 0.26917147636413574,
+      "learning_rate": 8.133950825754511e-06,
+      "loss": 0.2251,
+      "step": 297
+    },
+    {
+      "epoch": 1.756277695716396,
+      "grad_norm": 0.2692192792892456,
+      "learning_rate": 8.069287138701452e-06,
+      "loss": 0.232,
+      "step": 298
+    },
+    {
+      "epoch": 1.7621861152141802,
+      "grad_norm": 0.27494263648986816,
+      "learning_rate": 8.004707200547534e-06,
+      "loss": 0.2461,
+      "step": 299
+    },
+    {
+      "epoch": 1.7680945347119645,
+      "grad_norm": 0.28247448801994324,
+      "learning_rate": 7.940213812589018e-06,
+      "loss": 0.2226,
+      "step": 300
+    },
+    {
+      "epoch": 1.7740029542097489,
+      "grad_norm": 0.2632560133934021,
+      "learning_rate": 7.875809772367867e-06,
+      "loss": 0.216,
+      "step": 301
+    },
+    {
+      "epoch": 1.7799113737075332,
+      "grad_norm": 0.26561063528060913,
+      "learning_rate": 7.81149787355039e-06,
+      "loss": 0.2286,
+      "step": 302
+    },
+    {
+      "epoch": 1.7858197932053175,
+      "grad_norm": 0.24065916240215302,
+      "learning_rate": 7.747280905806051e-06,
+      "loss": 0.2201,
+      "step": 303
+    },
+    {
+      "epoch": 1.7917282127031018,
+      "grad_norm": 0.288473904132843,
+      "learning_rate": 7.683161654686486e-06,
+      "loss": 0.2179,
+      "step": 304
+    },
+    {
+      "epoch": 1.797636632200886,
+      "grad_norm": 0.27798035740852356,
+      "learning_rate": 7.619142901504649e-06,
+      "loss": 0.2341,
+      "step": 305
+    },
+    {
+      "epoch": 1.8035450516986706,
+      "grad_norm": 0.28387168049812317,
+      "learning_rate": 7.555227423214174e-06,
+      "loss": 0.226,
+      "step": 306
+    },
+    {
+      "epoch": 1.809453471196455,
+      "grad_norm": 0.28974682092666626,
+      "learning_rate": 7.491417992288927e-06,
+      "loss": 0.2296,
+      "step": 307
+    },
+    {
+      "epoch": 1.8153618906942393,
+      "grad_norm": 0.26052042841911316,
+      "learning_rate": 7.427717376602739e-06,
+      "loss": 0.2002,
+      "step": 308
+    },
+    {
+      "epoch": 1.8212703101920238,
+      "grad_norm": 0.29558730125427246,
+      "learning_rate": 7.364128339309326e-06,
+      "loss": 0.263,
+      "step": 309
+    },
+    {
+      "epoch": 1.827178729689808,
+      "grad_norm": 0.24457122385501862,
+      "learning_rate": 7.300653638722463e-06,
+      "loss": 0.224,
+      "step": 310
+    },
+    {
+      "epoch": 1.8330871491875924,
+      "grad_norm": 0.2517196834087372,
+      "learning_rate": 7.2372960281963165e-06,
+      "loss": 0.2134,
+      "step": 311
+    },
+    {
+      "epoch": 1.8389955686853767,
+      "grad_norm": 0.27632561326026917,
+      "learning_rate": 7.174058256006012e-06,
+      "loss": 0.2229,
+      "step": 312
+    },
+    {
+      "epoch": 1.844903988183161,
+      "grad_norm": 0.2603515684604645,
+      "learning_rate": 7.110943065228425e-06,
+      "loss": 0.2299,
+      "step": 313
+    },
+    {
+      "epoch": 1.8508124076809453,
+      "grad_norm": 0.24517123401165009,
+      "learning_rate": 7.047953193623195e-06,
+      "loss": 0.2096,
+      "step": 314
+    },
+    {
+      "epoch": 1.8567208271787297,
+      "grad_norm": 0.24135427176952362,
+      "learning_rate": 6.985091373513972e-06,
+      "loss": 0.2072,
+      "step": 315
+    },
+    {
+      "epoch": 1.862629246676514,
+      "grad_norm": 0.2676647901535034,
+      "learning_rate": 6.92236033166988e-06,
+      "loss": 0.2173,
+      "step": 316
+    },
+    {
+      "epoch": 1.8685376661742983,
+      "grad_norm": 0.2504200041294098,
+      "learning_rate": 6.859762789187259e-06,
+      "loss": 0.2192,
+      "step": 317
+    },
+    {
+      "epoch": 1.8744460856720826,
+      "grad_norm": 0.26364269852638245,
+      "learning_rate": 6.797301461371626e-06,
+      "loss": 0.2193,
+      "step": 318
+    },
+    {
+      "epoch": 1.880354505169867,
+      "grad_norm": 0.24448218941688538,
+      "learning_rate": 6.734979057619873e-06,
+      "loss": 0.2208,
+      "step": 319
+    },
+    {
+      "epoch": 1.8862629246676514,
+      "grad_norm": 0.24706940352916718,
+      "learning_rate": 6.67279828130277e-06,
+      "loss": 0.2211,
+      "step": 320
+    },
+    {
+      "epoch": 1.8921713441654358,
+      "grad_norm": 0.24761930108070374,
+      "learning_rate": 6.610761829647685e-06,
+      "loss": 0.2222,
+      "step": 321
+    },
+    {
+      "epoch": 1.89807976366322,
+      "grad_norm": 0.2566414475440979,
+      "learning_rate": 6.548872393621578e-06,
+      "loss": 0.2136,
+      "step": 322
+    },
+    {
+      "epoch": 1.9039881831610044,
+      "grad_norm": 0.2611066401004791,
+      "learning_rate": 6.487132657814297e-06,
+      "loss": 0.2146,
+      "step": 323
+    },
+    {
+      "epoch": 1.909896602658789,
+      "grad_norm": 0.27130842208862305,
+      "learning_rate": 6.4255453003221115e-06,
+      "loss": 0.2184,
+      "step": 324
+    },
+    {
+      "epoch": 1.9158050221565732,
+      "grad_norm": 0.2548243999481201,
+      "learning_rate": 6.364112992631537e-06,
+      "loss": 0.2299,
+      "step": 325
+    },
+    {
+      "epoch": 1.9217134416543575,
+      "grad_norm": 0.2533697187900543,
+      "learning_rate": 6.302838399503477e-06,
+      "loss": 0.2043,
+      "step": 326
+    },
+    {
+      "epoch": 1.9276218611521418,
+      "grad_norm": 0.2540424168109894,
+      "learning_rate": 6.241724178857621e-06,
+      "loss": 0.2039,
+      "step": 327
+    },
+    {
+      "epoch": 1.9335302806499262,
+      "grad_norm": 0.2535569965839386,
+      "learning_rate": 6.180772981657139e-06,
+      "loss": 0.2019,
+      "step": 328
+    },
+    {
+      "epoch": 1.9394387001477105,
+      "grad_norm": 0.29982754588127136,
+      "learning_rate": 6.119987451793711e-06,
+      "loss": 0.2228,
+      "step": 329
+    },
+    {
+      "epoch": 1.9453471196454948,
+      "grad_norm": 0.23110415041446686,
+      "learning_rate": 6.059370225972834e-06,
+      "loss": 0.2188,
+      "step": 330
+    },
+    {
+      "epoch": 1.951255539143279,
+      "grad_norm": 0.2608148753643036,
+      "learning_rate": 5.998923933599443e-06,
+      "loss": 0.2236,
+      "step": 331
+    },
+    {
+      "epoch": 1.9571639586410634,
+      "grad_norm": 0.26010897755622864,
+      "learning_rate": 5.938651196663865e-06,
+      "loss": 0.2032,
+      "step": 332
+    },
+    {
+      "epoch": 1.9630723781388477,
+      "grad_norm": 0.26297712326049805,
+      "learning_rate": 5.878554629628081e-06,
+      "loss": 0.2224,
+      "step": 333
+    },
+    {
+      "epoch": 1.9689807976366323,
+      "grad_norm": 0.2658803164958954,
+      "learning_rate": 5.818636839312309e-06,
+      "loss": 0.2153,
+      "step": 334
+    },
+    {
+      "epoch": 1.9748892171344166,
+      "grad_norm": 0.23885361850261688,
+      "learning_rate": 5.758900424781939e-06,
+      "loss": 0.2029,
+      "step": 335
+    },
+    {
+      "epoch": 1.9807976366322009,
+      "grad_norm": 0.2604767978191376,
+      "learning_rate": 5.699347977234799e-06,
+      "loss": 0.2059,
+      "step": 336
+    },
+    {
+      "epoch": 1.9867060561299852,
+      "grad_norm": 0.2535778284072876,
+      "learning_rate": 5.6399820798887266e-06,
+      "loss": 0.2204,
+      "step": 337
+    },
+    {
+      "epoch": 1.9926144756277697,
+      "grad_norm": 0.2699243128299713,
+      "learning_rate": 5.580805307869549e-06,
+      "loss": 0.2158,
+      "step": 338
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 507,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 169,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.797158580880671e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

3b-mb_base/checkpoint-338/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d657c9786dc6c8c08c64e914a96a01397e0a80c1d965337767408bc8f80e5cf
+size 10744

3b-mb_base/checkpoint-338/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

3b-mb_base/checkpoint-507/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

3b-mb_base/checkpoint-507/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

3b-mb_base/checkpoint-507/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.1"
+}

3b-mb_base/checkpoint-507/latest

@@ -0,0 +1 @@
+global_step505

3b-mb_base/checkpoint-507/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63c90852fa3fa4280db2cd535d3288d97103797c36bc01f6b86838774637395
+size 4956450288

3b-mb_base/checkpoint-507/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5abba5a27427c5628dcedab5d617b319036407f2fc964f81ba71cfb4a973b178
+size 1835586736

3b-mb_base/checkpoint-507/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 6791987200
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

3b-mb_base/checkpoint-507/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f3803bff3f596c03b55881de967a825b5734e4a581739164f9cb9e7fd1aee89
+size 14512

3b-mb_base/checkpoint-507/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d768a04b798e2ca42effbe096b8e4481f32a402a9125a2ced390586dab8eb29e
+size 14512

3b-mb_base/checkpoint-507/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7cc083c6282a60be998cf859b1a6c559bc7ea7e1edebd39819cd91f2b32e45e
+size 1064

3b-mb_base/checkpoint-507/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}