Quant for 4.25

README.md

@@ -58,68 +58,255 @@ datasets:
 - WizardLM/WizardLM_evol_instruct_70k
 - abacusai/SystemChat-1.1
 - H-D-T/Buzz-V1.2
-quantized_by: bartowski
-pipeline_tag: text-generation
 ---
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/KLQP1jK-DIzpwHzYRIH-Q.png)
 
-## Exllama v2 Quantizations of Einstein-v7-Qwen2-7B
+# 🔬 Einstein-v7-Qwen2-7B
 
-Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.1.6">turboderp's ExLlamaV2 v0.1.6</a> for quantization.
+This model is a full fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on diverse datasets.
 
-<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
+This model is finetuned using `8xMI300X` using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl).
 
-Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
+<details><summary>See axolotl config</summary>
 
-Original model: https://huggingface.co/Weyaxi/Einstein-v7-Qwen2-7B
+axolotl version: `0.4.0`
+```yaml
+base_model: Qwen/Qwen2-7B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+chat_template: chatml
+datasets:
+  - path: data/airoboros_3.2_without_contextual_slimorca_orca_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+
+  - path: data/allenai_wild_chat_gpt4_english_toxic_random_half_4k_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    strict: false
+    conversation: chatml
+
+  - path: data/buzz_unstacked_chosen_math_removed_filtered.json
+    ds_type: json
+    type: alpaca
+    conversation: chatml
+
+  - path: data/capybara_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+
+  - path: data/cot_alpaca_gpt4_extracted_openhermes_2.5_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+
+  - path: data/everythinglm-data-v3_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    strict: false
+    conversation: chatml
+
+  - path: data/gpt4_data_lmys_1m_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+
+  - path: data/gpteacher-instruct-special-alpaca.json
+    ds_type: json
+    type: gpteacher
+    conversation: chatml
+
+  - path: data/merged_all.json
+    ds_type: json
+    type: alpaca
+    conversation: chatml
+
+  - path: data/no_robots_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    strict: false
+    conversation: chatml
+
+  - path: data/oasst_top1_from_fusechatmixture_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    strict: false
+    conversation: chatml
+
+  - path: data/pippa_bagel_repo_3k_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+
+  - path: data/rpguild_quarter_alignment_lab_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+
+  - path: data/sharegpt_gpt4_english.json
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+
+  - path: data/slimorca_dedup_filtered_95k_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+
+  - path: data/soda_diaolog_longest_tenth_buzz_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+
+  - path: data/synthia-v1.3_sharegpt_12500.json
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+
+  - path: data/system_conversations_dolphin_sharegpt.json
+    ds_type: json
+    type: sharegpt
+    conversation: chatml
+  
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.002
+
+output_dir: ./Einstein-v7-Qwen2-7B-model
+
+sequence_len: 8192
+sample_packing: true
+pad_to_sequence_len: true
+eval_sample_packing: false
+
+wandb_project: Einstein
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+hub_model_id: Weyaxi/Einstein-v7-Qwen2-7B
+
+gradient_accumulation_steps: 4
+micro_batch_size: 6
+num_epochs: 2
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.00001 # look
 
-## Prompt format
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: unsloth
+gradient_checkpointing_kwargs:
+   use_reentrant: true # look
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 2
+eval_table_size:
+eval_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+
+deepspeed: deepspeed_configs/zero3_bf16.json
+weight_decay: 0.05
+fsdp:
+fsdp_config:
+special_tokens:
+  eos_token: "<|im_end|>"
+  pad_token: "<|end_of_text|>"
+tokens:
+  - "<|im_start|>"
+  - "<|im_end|>"
+```
+
+</details><br>
+
+# 💬 Prompt Template
+
+You can use ChatML prompt template while using the model:
+
+### ChatML
 
 ```
 <|im_start|>system
-{system_prompt}<|im_end|>
+{system}<|im_end|>
 <|im_start|>user
-{prompt}<|im_end|>
+{user}<|im_end|>
 <|im_start|>assistant
+{asistant}<|im_end|>
+```
 
+This prompt template is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
+`tokenizer.apply_chat_template()` method:
+
+```python
+messages = [
+    {"role": "system", "content": "You are helpful AI asistant."},
+    {"role": "user", "content": "Hello!"}
+]
+gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
+model.generate(**gen_input)
 ```
 
-## Available sizes
+# 📊 Datasets used in this model
 
+The datasets used to train this model are listed in the metadata section of the model card.
 
-| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
-| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
-| [8_0](https://huggingface.co/bartowski/Einstein-v7-Qwen2-7B-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
-| [6_5](https://huggingface.co/bartowski/Einstein-v7-Qwen2-7B-exl2/tree/6_5) | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
-| [5_0](https://huggingface.co/bartowski/Einstein-v7-Qwen2-7B-exl2/tree/5_0) | 5.0 | 6.0 | 6.0 GB | 7.4 GB |  9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
-| [4_25](https://huggingface.co/bartowski/Einstein-v7-Qwen2-7B-exl2/tree/4_25) | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
-| [3_5](https://huggingface.co/bartowski/Einstein-v7-Qwen2-7B-exl2/tree/3_5) | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. |
+Please note that certain datasets mentioned in the metadata may have undergone filtering based on various criteria.
 
-## Download instructions
+The results of this filtering process and its outcomes are in a diffrent repository:
 
-With git:
+[Weyaxi/sci-datasets/main](https://huggingface.co/datasets/Weyaxi/sci-datasets/tree/main)
 
-```shell
-git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Einstein-v7-Qwen2-7B-exl2 Einstein-v7-Qwen2-7B-exl2-6_5
-```
+# 🔄 Quantizationed versions
 
-With huggingface hub (credit to TheBloke for instructions):
+## GGUF [@bartowski](https://huggingface.co/bartowski)
 
-```shell
-pip3 install huggingface-hub
-```
+- https://huggingface.co/bartowski/Einstein-v7-Qwen2-7B-GGUF
 
-To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:
+## ExLlamaV2 [@bartowski](https://huggingface.co/bartowski)
 
-Linux:
+- https://huggingface.co/bartowski/Einstein-v7-Qwen2-7B-exl2
 
-```shell
-huggingface-cli download bartowski/Einstein-v7-Qwen2-7B-exl2 --revision 6_5 --local-dir Einstein-v7-Qwen2-7B-exl2-6_5
-```
+# 🎯 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
 
-Windows (which apparently doesn't like _ in folders sometimes?):
+# 🤖 Additional information about training
 
-```shell
-huggingface-cli download bartowski/Einstein-v7-Qwen2-7B-exl2 --revision 6_5 --local-dir Einstein-v7-Qwen2-7B-exl2-6.5
-```
+This model is full fine-tuned for 2 epoch. 
+
+Total number of steps was 500.
+
+<details><summary>Loss graph</summary>
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/bkJGgh_JUfKeRlTLo_ZcB.png)
+
+</details><br>
+
+# 🤝 Acknowledgments
+
+Thanks to all the dataset authors mentioned in the datasets section.
+
+Thanks to [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) for making the repository I used to make this model.
+
+Thanks to all open source AI community.
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+
+If you would like to support me:
 
-Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
+[☕ Buy Me a Coffee](https://www.buymeacoffee.com/weyaxi)

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|end_of_text|>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,38 @@
+{
+    "_name_or_path": "Qwen/Qwen2-7B",
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "max_position_embeddings": 131072,
+    "max_window_layers": 28,
+    "model_type": "qwen2",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sliding_window": 131072,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.40.0.dev0",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 152064,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.6",
+        "bits": 4.25,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.40.0.dev0"
+}

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77343eb75b57104c31af5503e1bdd3704677e3dfe8fc01afbfbc9e8bcf92f94d
+size 4988716004

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "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": false
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|end_of_text|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,3561 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9740777666999003,
+  "eval_steps": 125,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.8329473944625845,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.9189,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 0.8840048313140869,
+      "eval_runtime": 99.9262,
+      "eval_samples_per_second": 17.693,
+      "eval_steps_per_second": 0.37,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.7916344264608899,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.8962,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.8909931480365287,
+      "learning_rate": 3e-06,
+      "loss": 0.8805,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.6318273112027453,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.913,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.2463401136319747,
+      "learning_rate": 5e-06,
+      "loss": 0.908,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.1463980681106876,
+      "learning_rate": 6e-06,
+      "loss": 0.8729,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.9477573494094379,
+      "learning_rate": 7e-06,
+      "loss": 0.8411,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.0165120162042935,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.0541,
+      "step": 8
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.0713771331971476,
+      "learning_rate": 9e-06,
+      "loss": 0.8495,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8667235558943894,
+      "learning_rate": 1e-05,
+      "loss": 0.8199,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.7411429457268661,
+      "learning_rate": 9.999897234791831e-06,
+      "loss": 0.7964,
+      "step": 11
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5729968036750446,
+      "learning_rate": 9.999588943391597e-06,
+      "loss": 0.8039,
+      "step": 12
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5402964207486183,
+      "learning_rate": 9.99907513847195e-06,
+      "loss": 0.8287,
+      "step": 13
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.5633328266442124,
+      "learning_rate": 9.9983558411534e-06,
+      "loss": 0.7842,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.5412290905686791,
+      "learning_rate": 9.99743108100344e-06,
+      "loss": 0.8345,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4895379189634968,
+      "learning_rate": 9.99630089603534e-06,
+      "loss": 0.7922,
+      "step": 16
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.5088260537094976,
+      "learning_rate": 9.994965332706574e-06,
+      "loss": 0.7969,
+      "step": 17
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.47075507205524136,
+      "learning_rate": 9.993424445916923e-06,
+      "loss": 0.7931,
+      "step": 18
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3878407143429931,
+      "learning_rate": 9.991678299006206e-06,
+      "loss": 0.8041,
+      "step": 19
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3873731682942636,
+      "learning_rate": 9.989726963751683e-06,
+      "loss": 0.8107,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.42417629604043083,
+      "learning_rate": 9.987570520365105e-06,
+      "loss": 0.7874,
+      "step": 21
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.4324680733617199,
+      "learning_rate": 9.98520905748941e-06,
+      "loss": 0.8025,
+      "step": 22
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.34546199757993784,
+      "learning_rate": 9.982642672195093e-06,
+      "loss": 0.8048,
+      "step": 23
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.35958771648273496,
+      "learning_rate": 9.979871469976197e-06,
+      "loss": 0.831,
+      "step": 24
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.3940074197908444,
+      "learning_rate": 9.976895564745993e-06,
+      "loss": 0.7944,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.3818406187889153,
+      "learning_rate": 9.973715078832288e-06,
+      "loss": 0.7936,
+      "step": 26
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 10.237346743255186,
+      "learning_rate": 9.970330142972403e-06,
+      "loss": 1.0017,
+      "step": 27
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 6.504690612414681,
+      "learning_rate": 9.966740896307791e-06,
+      "loss": 1.0329,
+      "step": 28
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.4028775109425473,
+      "learning_rate": 9.962947486378325e-06,
+      "loss": 0.7702,
+      "step": 29
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.39810277536967076,
+      "learning_rate": 9.95895006911623e-06,
+      "loss": 0.771,
+      "step": 30
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.29862663396811506,
+      "learning_rate": 9.954748808839675e-06,
+      "loss": 0.7767,
+      "step": 31
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.3106188272362696,
+      "learning_rate": 9.950343878246011e-06,
+      "loss": 0.7943,
+      "step": 32
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.34702364911134964,
+      "learning_rate": 9.945735458404681e-06,
+      "loss": 0.7972,
+      "step": 33
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3216448960978253,
+      "learning_rate": 9.94092373874978e-06,
+      "loss": 0.7847,
+      "step": 34
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.31232207978504006,
+      "learning_rate": 9.935908917072253e-06,
+      "loss": 0.7738,
+      "step": 35
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3004886604892709,
+      "learning_rate": 9.930691199511775e-06,
+      "loss": 0.7877,
+      "step": 36
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.2870013960815822,
+      "learning_rate": 9.925270800548285e-06,
+      "loss": 0.754,
+      "step": 37
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.28322113595593756,
+      "learning_rate": 9.91964794299315e-06,
+      "loss": 0.7445,
+      "step": 38
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.3065117198934518,
+      "learning_rate": 9.91382285798002e-06,
+      "loss": 0.787,
+      "step": 39
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.2727693466806482,
+      "learning_rate": 9.907795784955327e-06,
+      "loss": 0.7865,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.2746198009076503,
+      "learning_rate": 9.901566971668437e-06,
+      "loss": 0.7755,
+      "step": 41
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.2888207750688948,
+      "learning_rate": 9.895136674161466e-06,
+      "loss": 0.7789,
+      "step": 42
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.26218141394209254,
+      "learning_rate": 9.888505156758758e-06,
+      "loss": 0.7781,
+      "step": 43
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.27028128323788914,
+      "learning_rate": 9.881672692056022e-06,
+      "loss": 0.7596,
+      "step": 44
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.301432889634355,
+      "learning_rate": 9.874639560909118e-06,
+      "loss": 0.7746,
+      "step": 45
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.27768870163187315,
+      "learning_rate": 9.867406052422525e-06,
+      "loss": 0.7751,
+      "step": 46
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.2638230079020965,
+      "learning_rate": 9.85997246393744e-06,
+      "loss": 0.8085,
+      "step": 47
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.2826098837962784,
+      "learning_rate": 9.852339101019574e-06,
+      "loss": 0.7878,
+      "step": 48
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2673052298412088,
+      "learning_rate": 9.844506277446577e-06,
+      "loss": 0.7747,
+      "step": 49
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2589820555015507,
+      "learning_rate": 9.836474315195148e-06,
+      "loss": 0.7491,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.27744141325372174,
+      "learning_rate": 9.828243544427795e-06,
+      "loss": 0.771,
+      "step": 51
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.25617202776049003,
+      "learning_rate": 9.819814303479268e-06,
+      "loss": 0.789,
+      "step": 52
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.25777796417187593,
+      "learning_rate": 9.811186938842645e-06,
+      "loss": 0.7498,
+      "step": 53
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.26356120702424557,
+      "learning_rate": 9.802361805155097e-06,
+      "loss": 0.7618,
+      "step": 54
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.24594116238284844,
+      "learning_rate": 9.793339265183303e-06,
+      "loss": 0.7647,
+      "step": 55
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.2766331605712476,
+      "learning_rate": 9.784119689808545e-06,
+      "loss": 0.7757,
+      "step": 56
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.2674205732918615,
+      "learning_rate": 9.774703458011453e-06,
+      "loss": 0.7479,
+      "step": 57
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.25100414008068433,
+      "learning_rate": 9.765090956856437e-06,
+      "loss": 0.7629,
+      "step": 58
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2558976905977626,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.7368,
+      "step": 59
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2816597522453804,
+      "learning_rate": 9.745278735053345e-06,
+      "loss": 0.7675,
+      "step": 60
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.27864046582364604,
+      "learning_rate": 9.735079828808107e-06,
+      "loss": 0.7693,
+      "step": 61
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2537495381298166,
+      "learning_rate": 9.724686281977146e-06,
+      "loss": 0.7612,
+      "step": 62
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.27161360619636454,
+      "learning_rate": 9.714098521798466e-06,
+      "loss": 0.7659,
+      "step": 63
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.257282261183055,
+      "learning_rate": 9.703316983493414e-06,
+      "loss": 0.77,
+      "step": 64
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.2598148868150837,
+      "learning_rate": 9.692342110248802e-06,
+      "loss": 0.7637,
+      "step": 65
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.25319486577746536,
+      "learning_rate": 9.681174353198687e-06,
+      "loss": 0.7529,
+      "step": 66
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2616187230129625,
+      "learning_rate": 9.669814171405818e-06,
+      "loss": 0.7482,
+      "step": 67
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2531735015293101,
+      "learning_rate": 9.658262031842772e-06,
+      "loss": 0.7507,
+      "step": 68
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.2540031125746497,
+      "learning_rate": 9.64651840937276e-06,
+      "loss": 0.7573,
+      "step": 69
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.26251145119756225,
+      "learning_rate": 9.63458378673011e-06,
+      "loss": 0.7617,
+      "step": 70
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 11.659656865913,
+      "learning_rate": 9.622458654500408e-06,
+      "loss": 0.9807,
+      "step": 71
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 43.33218979251603,
+      "learning_rate": 9.610143511100354e-06,
+      "loss": 1.0213,
+      "step": 72
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.29661440448786996,
+      "learning_rate": 9.597638862757255e-06,
+      "loss": 0.7597,
+      "step": 73
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2674359864711363,
+      "learning_rate": 9.584945223488227e-06,
+      "loss": 0.7716,
+      "step": 74
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2587397735578842,
+      "learning_rate": 9.572063115079063e-06,
+      "loss": 0.7654,
+      "step": 75
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.27326638279450294,
+      "learning_rate": 9.558993067062785e-06,
+      "loss": 0.7832,
+      "step": 76
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.26424783232216553,
+      "learning_rate": 9.545735616697875e-06,
+      "loss": 0.7509,
+      "step": 77
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.26894661215694415,
+      "learning_rate": 9.532291308946191e-06,
+      "loss": 0.7638,
+      "step": 78
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 12.381149099110814,
+      "learning_rate": 9.518660696450567e-06,
+      "loss": 0.9726,
+      "step": 79
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 63.276974873593076,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 0.961,
+      "step": 80
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.34404347007223207,
+      "learning_rate": 9.490842806067095e-06,
+      "loss": 0.7366,
+      "step": 81
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.2761892805994169,
+      "learning_rate": 9.476656671663766e-06,
+      "loss": 0.7565,
+      "step": 82
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.2938700568825168,
+      "learning_rate": 9.462286519438531e-06,
+      "loss": 0.7586,
+      "step": 83
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.30998708104141814,
+      "learning_rate": 9.44773294009206e-06,
+      "loss": 0.747,
+      "step": 84
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.2789622879446074,
+      "learning_rate": 9.432996531865001e-06,
+      "loss": 0.7381,
+      "step": 85
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.3043211841621936,
+      "learning_rate": 9.418077900513377e-06,
+      "loss": 0.7648,
+      "step": 86
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.27269347275749684,
+      "learning_rate": 9.40297765928369e-06,
+      "loss": 0.7287,
+      "step": 87
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.29165683068711035,
+      "learning_rate": 9.387696428887715e-06,
+      "loss": 0.7714,
+      "step": 88
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.29093659611546846,
+      "learning_rate": 9.372234837476979e-06,
+      "loss": 0.754,
+      "step": 89
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.2622000520062877,
+      "learning_rate": 9.356593520616948e-06,
+      "loss": 0.7604,
+      "step": 90
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.29648676556314774,
+      "learning_rate": 9.340773121260893e-06,
+      "loss": 0.7677,
+      "step": 91
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.2971691719126809,
+      "learning_rate": 9.324774289723469e-06,
+      "loss": 0.7826,
+      "step": 92
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.2695147958164756,
+      "learning_rate": 9.308597683653976e-06,
+      "loss": 0.7675,
+      "step": 93
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.2947547264550856,
+      "learning_rate": 9.292243968009332e-06,
+      "loss": 0.7611,
+      "step": 94
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.2698951119585888,
+      "learning_rate": 9.275713815026732e-06,
+      "loss": 0.7437,
+      "step": 95
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.2922871464880811,
+      "learning_rate": 9.259007904196023e-06,
+      "loss": 0.7716,
+      "step": 96
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 13.342043215041077,
+      "learning_rate": 9.242126922231763e-06,
+      "loss": 1.0262,
+      "step": 97
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 3.3348436860369577,
+      "learning_rate": 9.225071563045007e-06,
+      "loss": 0.9733,
+      "step": 98
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.30515152013617763,
+      "learning_rate": 9.207842527714767e-06,
+      "loss": 0.7491,
+      "step": 99
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2797372956926758,
+      "learning_rate": 9.190440524459203e-06,
+      "loss": 0.7658,
+      "step": 100
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.295442681103485,
+      "learning_rate": 9.172866268606514e-06,
+      "loss": 0.7359,
+      "step": 101
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.2890934213055238,
+      "learning_rate": 9.15512048256552e-06,
+      "loss": 0.7783,
+      "step": 102
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.2698602196909741,
+      "learning_rate": 9.137203895795983e-06,
+      "loss": 0.7476,
+      "step": 103
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.30586672847809404,
+      "learning_rate": 9.119117244778609e-06,
+      "loss": 0.7494,
+      "step": 104
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.28256137853789653,
+      "learning_rate": 9.10086127298478e-06,
+      "loss": 0.7347,
+      "step": 105
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.2654565204147507,
+      "learning_rate": 9.082436730845993e-06,
+      "loss": 0.7282,
+      "step": 106
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.3110313172517606,
+      "learning_rate": 9.063844375723014e-06,
+      "loss": 0.7442,
+      "step": 107
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.30406144580285027,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.7365,
+      "step": 108
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.2578097986689305,
+      "learning_rate": 9.026159290426782e-06,
+      "loss": 0.7644,
+      "step": 109
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.2875228334986064,
+      "learning_rate": 9.007068109339783e-06,
+      "loss": 0.7359,
+      "step": 110
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.3007292657335934,
+      "learning_rate": 8.987812213377423e-06,
+      "loss": 0.7571,
+      "step": 111
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.2705781647990633,
+      "learning_rate": 8.968392394074164e-06,
+      "loss": 0.7321,
+      "step": 112
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 7.709717121399015,
+      "learning_rate": 8.948809449702712e-06,
+      "loss": 1.0663,
+      "step": 113
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.3159530858994423,
+      "learning_rate": 8.929064185241214e-06,
+      "loss": 0.7594,
+      "step": 114
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.3001925080979955,
+      "learning_rate": 8.90915741234015e-06,
+      "loss": 0.7486,
+      "step": 115
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.7719217922453914,
+      "learning_rate": 8.889089949288986e-06,
+      "loss": 1.0014,
+      "step": 116
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.2980097580186808,
+      "learning_rate": 8.868862620982534e-06,
+      "loss": 0.7302,
+      "step": 117
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.2674175783919389,
+      "learning_rate": 8.84847625888703e-06,
+      "loss": 0.7515,
+      "step": 118
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.33089914745986465,
+      "learning_rate": 8.827931701005974e-06,
+      "loss": 0.7452,
+      "step": 119
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.2657873873108844,
+      "learning_rate": 8.807229791845673e-06,
+      "loss": 0.7565,
+      "step": 120
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.26891569095038903,
+      "learning_rate": 8.786371382380527e-06,
+      "loss": 0.7525,
+      "step": 121
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.30828049821760906,
+      "learning_rate": 8.765357330018056e-06,
+      "loss": 0.7395,
+      "step": 122
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.2703956947723179,
+      "learning_rate": 8.74418849856364e-06,
+      "loss": 0.7762,
+      "step": 123
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.27665743831770573,
+      "learning_rate": 8.722865758185036e-06,
+      "loss": 0.7499,
+      "step": 124
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.31328445024397394,
+      "learning_rate": 8.701389985376578e-06,
+      "loss": 0.7368,
+      "step": 125
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.7192811369895935,
+      "eval_runtime": 97.0775,
+      "eval_samples_per_second": 18.212,
+      "eval_steps_per_second": 0.381,
+      "step": 125
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.26565830658390915,
+      "learning_rate": 8.679762062923176e-06,
+      "loss": 0.7727,
+      "step": 126
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.2768705145101062,
+      "learning_rate": 8.657982879864007e-06,
+      "loss": 0.7178,
+      "step": 127
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.27658899618203814,
+      "learning_rate": 8.636053331455986e-06,
+      "loss": 0.7521,
+      "step": 128
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.2687326456666238,
+      "learning_rate": 8.613974319136959e-06,
+      "loss": 0.7411,
+      "step": 129
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2618083386724651,
+      "learning_rate": 8.591746750488639e-06,
+      "loss": 0.7306,
+      "step": 130
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.25666246646393165,
+      "learning_rate": 8.569371539199316e-06,
+      "loss": 0.7505,
+      "step": 131
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.3203048983481449,
+      "learning_rate": 8.54684960502629e-06,
+      "loss": 0.7515,
+      "step": 132
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.2521993776332652,
+      "learning_rate": 8.52418187375806e-06,
+      "loss": 0.7505,
+      "step": 133
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.26591933789428035,
+      "learning_rate": 8.501369277176275e-06,
+      "loss": 0.7353,
+      "step": 134
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.27603393300812845,
+      "learning_rate": 8.478412753017433e-06,
+      "loss": 0.7609,
+      "step": 135
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.2668194745887302,
+      "learning_rate": 8.455313244934324e-06,
+      "loss": 0.7141,
+      "step": 136
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.2707242484249978,
+      "learning_rate": 8.432071702457253e-06,
+      "loss": 0.7223,
+      "step": 137
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.25511126409448154,
+      "learning_rate": 8.408689080954997e-06,
+      "loss": 0.7153,
+      "step": 138
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 15.420395873510664,
+      "learning_rate": 8.38516634159555e-06,
+      "loss": 1.0042,
+      "step": 139
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.3012234081880187,
+      "learning_rate": 8.361504451306585e-06,
+      "loss": 0.7713,
+      "step": 140
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2598491249346932,
+      "learning_rate": 8.337704382735741e-06,
+      "loss": 0.7288,
+      "step": 141
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.26256298238822373,
+      "learning_rate": 8.313767114210615e-06,
+      "loss": 0.7379,
+      "step": 142
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.2945113973208366,
+      "learning_rate": 8.289693629698564e-06,
+      "loss": 0.7401,
+      "step": 143
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.24981458420819586,
+      "learning_rate": 8.265484918766243e-06,
+      "loss": 0.7512,
+      "step": 144
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.2678413297548206,
+      "learning_rate": 8.241141976538944e-06,
+      "loss": 0.7449,
+      "step": 145
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.2623417103083203,
+      "learning_rate": 8.216665803659671e-06,
+      "loss": 0.7647,
+      "step": 146
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.263785777979794,
+      "learning_rate": 8.192057406248028e-06,
+      "loss": 0.7725,
+      "step": 147
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.2519540317965661,
+      "learning_rate": 8.16731779585885e-06,
+      "loss": 0.715,
+      "step": 148
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.27015785362121375,
+      "learning_rate": 8.142447989440618e-06,
+      "loss": 0.7532,
+      "step": 149
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.25863328277564784,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.7335,
+      "step": 150
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2550714525590909,
+      "learning_rate": 8.092321883028157e-06,
+      "loss": 0.7182,
+      "step": 151
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2752483825047847,
+      "learning_rate": 8.067067643521834e-06,
+      "loss": 0.772,
+      "step": 152
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2582002365542859,
+      "learning_rate": 8.041687328877566e-06,
+      "loss": 0.7284,
+      "step": 153
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.24823845365447103,
+      "learning_rate": 8.016181982380682e-06,
+      "loss": 0.7467,
+      "step": 154
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.25644169647568194,
+      "learning_rate": 7.99055265245608e-06,
+      "loss": 0.7191,
+      "step": 155
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.27463144458405375,
+      "learning_rate": 7.96480039262513e-06,
+      "loss": 0.7375,
+      "step": 156
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.2642553744129046,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.7587,
+      "step": 157
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.25679436337027056,
+      "learning_rate": 7.912931322551981e-06,
+      "loss": 0.7312,
+      "step": 158
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.2784563408983632,
+      "learning_rate": 7.886816644444099e-06,
+      "loss": 0.7213,
+      "step": 159
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2638439438037005,
+      "learning_rate": 7.860583300610849e-06,
+      "loss": 0.7286,
+      "step": 160
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2599487424469649,
+      "learning_rate": 7.83423236940225e-06,
+      "loss": 0.7211,
+      "step": 161
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.2620169279227201,
+      "learning_rate": 7.807764934001875e-06,
+      "loss": 0.7243,
+      "step": 162
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.3455142385888707,
+      "learning_rate": 7.781182082382325e-06,
+      "loss": 0.7709,
+      "step": 163
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.25797958121628417,
+      "learning_rate": 7.754484907260513e-06,
+      "loss": 0.7371,
+      "step": 164
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.26245124486082283,
+      "learning_rate": 7.727674506052744e-06,
+      "loss": 0.7625,
+      "step": 165
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.259525851556208,
+      "learning_rate": 7.700751980829601e-06,
+      "loss": 0.7785,
+      "step": 166
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.25578616887441574,
+      "learning_rate": 7.673718438270649e-06,
+      "loss": 0.7349,
+      "step": 167
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.26880908011952676,
+      "learning_rate": 7.646574989618938e-06,
+      "loss": 0.7423,
+      "step": 168
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.28268284846763475,
+      "learning_rate": 7.619322750635327e-06,
+      "loss": 0.8089,
+      "step": 169
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.2565025440158926,
+      "learning_rate": 7.591962841552627e-06,
+      "loss": 0.708,
+      "step": 170
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.2589330645555015,
+      "learning_rate": 7.564496387029532e-06,
+      "loss": 0.7276,
+      "step": 171
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 4.072287518324262,
+      "learning_rate": 7.536924516104411e-06,
+      "loss": 0.963,
+      "step": 172
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 5.236195816930884,
+      "learning_rate": 7.509248362148889e-06,
+      "loss": 0.9786,
+      "step": 173
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.3208811366448085,
+      "learning_rate": 7.481469062821252e-06,
+      "loss": 0.7417,
+      "step": 174
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.280850125752099,
+      "learning_rate": 7.453587760019691e-06,
+      "loss": 0.7249,
+      "step": 175
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.26692675004354643,
+      "learning_rate": 7.42560559983536e-06,
+      "loss": 0.727,
+      "step": 176
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.27369623001787907,
+      "learning_rate": 7.39752373250527e-06,
+      "loss": 0.7617,
+      "step": 177
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.2784142807735342,
+      "learning_rate": 7.369343312364994e-06,
+      "loss": 0.7466,
+      "step": 178
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 37.27250895412763,
+      "learning_rate": 7.34106549780123e-06,
+      "loss": 1.0667,
+      "step": 179
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.2760061039631398,
+      "learning_rate": 7.312691451204178e-06,
+      "loss": 0.7244,
+      "step": 180
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.25459829854169064,
+      "learning_rate": 7.284222338919758e-06,
+      "loss": 0.7364,
+      "step": 181
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.26179305555253735,
+      "learning_rate": 7.255659331201673e-06,
+      "loss": 0.733,
+      "step": 182
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.2604418741829541,
+      "learning_rate": 7.227003602163296e-06,
+      "loss": 0.7209,
+      "step": 183
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.26185681215109163,
+      "learning_rate": 7.198256329729412e-06,
+      "loss": 0.7164,
+      "step": 184
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 16.152387103951856,
+      "learning_rate": 7.169418695587791e-06,
+      "loss": 1.0372,
+      "step": 185
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 21.228735850953576,
+      "learning_rate": 7.140491885140629e-06,
+      "loss": 1.0402,
+      "step": 186
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.28404810159037286,
+      "learning_rate": 7.1114770874558e-06,
+      "loss": 0.7006,
+      "step": 187
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.26609034714435736,
+      "learning_rate": 7.082375495217996e-06,
+      "loss": 0.7537,
+      "step": 188
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.25765084929276133,
+      "learning_rate": 7.053188304679691e-06,
+      "loss": 0.7302,
+      "step": 189
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.26384158886834463,
+      "learning_rate": 7.023916715611969e-06,
+      "loss": 0.712,
+      "step": 190
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.27151931787506317,
+      "learning_rate": 6.994561931255209e-06,
+      "loss": 0.7502,
+      "step": 191
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.27031492068457535,
+      "learning_rate": 6.965125158269619e-06,
+      "loss": 0.7179,
+      "step": 192
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.26995073084719196,
+      "learning_rate": 6.935607606685642e-06,
+      "loss": 0.7624,
+      "step": 193
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.25666755324587454,
+      "learning_rate": 6.906010489854209e-06,
+      "loss": 0.7426,
+      "step": 194
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.2764461509009301,
+      "learning_rate": 6.876335024396872e-06,
+      "loss": 0.723,
+      "step": 195
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.2597906002555833,
+      "learning_rate": 6.846582430155783e-06,
+      "loss": 0.7407,
+      "step": 196
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.26409742487438864,
+      "learning_rate": 6.816753930143558e-06,
+      "loss": 0.7206,
+      "step": 197
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.25320169233675405,
+      "learning_rate": 6.786850750493006e-06,
+      "loss": 0.7437,
+      "step": 198
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.2708696048462205,
+      "learning_rate": 6.7568741204067145e-06,
+      "loss": 0.7422,
+      "step": 199
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.26542323915181154,
+      "learning_rate": 6.726825272106539e-06,
+      "loss": 0.7514,
+      "step": 200
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.26307166597433396,
+      "learning_rate": 6.696705440782939e-06,
+      "loss": 0.7509,
+      "step": 201
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.26671446872754456,
+      "learning_rate": 6.66651586454421e-06,
+      "loss": 0.7465,
+      "step": 202
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.2720083369272757,
+      "learning_rate": 6.636257784365585e-06,
+      "loss": 0.7349,
+      "step": 203
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.2652218770116059,
+      "learning_rate": 6.605932444038229e-06,
+      "loss": 0.7348,
+      "step": 204
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.26402314109149694,
+      "learning_rate": 6.575541090118105e-06,
+      "loss": 0.7495,
+      "step": 205
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.2639803511821082,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.7138,
+      "step": 206
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.2673567043268493,
+      "learning_rate": 6.514565341239861e-06,
+      "loss": 0.7341,
+      "step": 207
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 74.0236556664021,
+      "learning_rate": 6.483983452755953e-06,
+      "loss": 1.084,
+      "step": 208
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.2694930198888902,
+      "learning_rate": 6.4533405635246696e-06,
+      "loss": 0.7422,
+      "step": 209
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.2808089325365656,
+      "learning_rate": 6.4226379331551625e-06,
+      "loss": 0.7543,
+      "step": 210
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.24629087243802783,
+      "learning_rate": 6.3918768237123175e-06,
+      "loss": 0.7088,
+      "step": 211
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.2605148206784209,
+      "learning_rate": 6.361058499664856e-06,
+      "loss": 0.7434,
+      "step": 212
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.26199687024127344,
+      "learning_rate": 6.330184227833376e-06,
+      "loss": 0.7369,
+      "step": 213
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.2693080928270376,
+      "learning_rate": 6.299255277338265e-06,
+      "loss": 0.7337,
+      "step": 214
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.2573571779304293,
+      "learning_rate": 6.268272919547537e-06,
+      "loss": 0.7366,
+      "step": 215
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.25347655388671,
+      "learning_rate": 6.237238428024573e-06,
+      "loss": 0.7392,
+      "step": 216
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.254807709796356,
+      "learning_rate": 6.2061530784757625e-06,
+      "loss": 0.7709,
+      "step": 217
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.25435065962054804,
+      "learning_rate": 6.175018148698077e-06,
+      "loss": 0.7472,
+      "step": 218
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.25856868944475736,
+      "learning_rate": 6.143834918526528e-06,
+      "loss": 0.7442,
+      "step": 219
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.24960062893507637,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 0.7163,
+      "step": 220
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.2544024553733407,
+      "learning_rate": 6.0813286862164175e-06,
+      "loss": 0.7236,
+      "step": 221
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.2532920039697931,
+      "learning_rate": 6.050008253464247e-06,
+      "loss": 0.7427,
+      "step": 222
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.25372808971698796,
+      "learning_rate": 6.018644658985378e-06,
+      "loss": 0.7286,
+      "step": 223
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.2570514856547558,
+      "learning_rate": 5.987239192014336e-06,
+      "loss": 0.7349,
+      "step": 224
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2578576277551542,
+      "learning_rate": 5.955793143506863e-06,
+      "loss": 0.7266,
+      "step": 225
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.26312215832145636,
+      "learning_rate": 5.9243078060868445e-06,
+      "loss": 0.7389,
+      "step": 226
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.26518617358808877,
+      "learning_rate": 5.892784473993184e-06,
+      "loss": 0.7108,
+      "step": 227
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.25620517627113376,
+      "learning_rate": 5.861224443026595e-06,
+      "loss": 0.7232,
+      "step": 228
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 28.36402580586963,
+      "learning_rate": 5.82962901049634e-06,
+      "loss": 0.9734,
+      "step": 229
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.2807037939514787,
+      "learning_rate": 5.797999475166897e-06,
+      "loss": 0.7341,
+      "step": 230
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 8.208344028346868,
+      "learning_rate": 5.766337137204579e-06,
+      "loss": 0.938,
+      "step": 231
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.26445130385050997,
+      "learning_rate": 5.734643298124091e-06,
+      "loss": 0.7316,
+      "step": 232
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.251567451954335,
+      "learning_rate": 5.702919260735015e-06,
+      "loss": 0.6966,
+      "step": 233
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.26329080787916564,
+      "learning_rate": 5.671166329088278e-06,
+      "loss": 0.7319,
+      "step": 234
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.2566777339661679,
+      "learning_rate": 5.6393858084225305e-06,
+      "loss": 0.7529,
+      "step": 235
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.2710815554700812,
+      "learning_rate": 5.6075790051105025e-06,
+      "loss": 0.7515,
+      "step": 236
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.27096961550302734,
+      "learning_rate": 5.575747226605298e-06,
+      "loss": 0.7073,
+      "step": 237
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.2509131795738037,
+      "learning_rate": 5.543891781386655e-06,
+      "loss": 0.7513,
+      "step": 238
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.26210506205941153,
+      "learning_rate": 5.512013978907157e-06,
+      "loss": 0.7569,
+      "step": 239
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.25123130642497177,
+      "learning_rate": 5.480115129538409e-06,
+      "loss": 0.7239,
+      "step": 240
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2596821607229612,
+      "learning_rate": 5.448196544517168e-06,
+      "loss": 0.7256,
+      "step": 241
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2714818563550966,
+      "learning_rate": 5.4162595358914475e-06,
+      "loss": 0.7329,
+      "step": 242
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.260503064108439,
+      "learning_rate": 5.384305416466584e-06,
+      "loss": 0.7112,
+      "step": 243
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2661267608396215,
+      "learning_rate": 5.35233549975127e-06,
+      "loss": 0.7534,
+      "step": 244
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.27502743208671454,
+      "learning_rate": 5.320351099903565e-06,
+      "loss": 0.7355,
+      "step": 245
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.2598641343680277,
+      "learning_rate": 5.288353531676873e-06,
+      "loss": 0.7476,
+      "step": 246
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2629788348419056,
+      "learning_rate": 5.256344110365896e-06,
+      "loss": 0.7523,
+      "step": 247
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.256123432185156,
+      "learning_rate": 5.224324151752575e-06,
+      "loss": 0.7479,
+      "step": 248
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2592695095071067,
+      "learning_rate": 5.192294972051992e-06,
+      "loss": 0.7586,
+      "step": 249
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.26264999139615697,
+      "learning_rate": 5.160257887858278e-06,
+      "loss": 0.7406,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7036678791046143,
+      "eval_runtime": 96.3087,
+      "eval_samples_per_second": 18.358,
+      "eval_steps_per_second": 0.384,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2614921961545108,
+      "learning_rate": 5.128214216090478e-06,
+      "loss": 0.7488,
+      "step": 251
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2605743808221771,
+      "learning_rate": 5.0961652739384356e-06,
+      "loss": 0.7338,
+      "step": 252
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 2.904417203670962,
+      "learning_rate": 5.064112378808636e-06,
+      "loss": 0.9738,
+      "step": 253
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.2581985759494367,
+      "learning_rate": 5.032056848270056e-06,
+      "loss": 0.7693,
+      "step": 254
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.25102446332314765,
+      "learning_rate": 5e-06,
+      "loss": 0.7213,
+      "step": 255
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4216598983588058,
+      "learning_rate": 4.967943151729945e-06,
+      "loss": 0.9193,
+      "step": 256
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.32982276331099014,
+      "learning_rate": 4.935887621191364e-06,
+      "loss": 0.6842,
+      "step": 257
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.29043411467478625,
+      "learning_rate": 4.903834726061565e-06,
+      "loss": 0.7087,
+      "step": 258
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.25986254756592664,
+      "learning_rate": 4.871785783909523e-06,
+      "loss": 0.6741,
+      "step": 259
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.30049816553828484,
+      "learning_rate": 4.839742112141725e-06,
+      "loss": 0.7063,
+      "step": 260
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.2895999616622155,
+      "learning_rate": 4.807705027948008e-06,
+      "loss": 0.7146,
+      "step": 261
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.30041272052643164,
+      "learning_rate": 4.775675848247427e-06,
+      "loss": 0.7134,
+      "step": 262
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.27518299819790887,
+      "learning_rate": 4.743655889634105e-06,
+      "loss": 0.692,
+      "step": 263
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.26955160521446175,
+      "learning_rate": 4.711646468323129e-06,
+      "loss": 0.658,
+      "step": 264
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.27535739664976405,
+      "learning_rate": 4.679648900096436e-06,
+      "loss": 0.6908,
+      "step": 265
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.26763089124769246,
+      "learning_rate": 4.64766450024873e-06,
+      "loss": 0.6861,
+      "step": 266
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 74.38254133611925,
+      "learning_rate": 4.615694583533418e-06,
+      "loss": 0.9994,
+      "step": 267
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.2986551656205794,
+      "learning_rate": 4.583740464108554e-06,
+      "loss": 0.7075,
+      "step": 268
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.27619714658975547,
+      "learning_rate": 4.551803455482833e-06,
+      "loss": 0.6596,
+      "step": 269
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.25242413092583954,
+      "learning_rate": 4.5198848704615915e-06,
+      "loss": 0.6628,
+      "step": 270
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.26017582720690735,
+      "learning_rate": 4.487986021092844e-06,
+      "loss": 0.6916,
+      "step": 271
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.2719334401383232,
+      "learning_rate": 4.456108218613346e-06,
+      "loss": 0.6935,
+      "step": 272
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.2874168693732095,
+      "learning_rate": 4.424252773394704e-06,
+      "loss": 0.7013,
+      "step": 273
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.27088215577908004,
+      "learning_rate": 4.392420994889498e-06,
+      "loss": 0.693,
+      "step": 274
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.2532812233498042,
+      "learning_rate": 4.3606141915774695e-06,
+      "loss": 0.6762,
+      "step": 275
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.263089719520046,
+      "learning_rate": 4.3288336709117246e-06,
+      "loss": 0.6677,
+      "step": 276
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.2544227492529696,
+      "learning_rate": 4.297080739264987e-06,
+      "loss": 0.6744,
+      "step": 277
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.2645751047762965,
+      "learning_rate": 4.265356701875911e-06,
+      "loss": 0.7047,
+      "step": 278
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.2602397068309733,
+      "learning_rate": 4.23366286279542e-06,
+      "loss": 0.6792,
+      "step": 279
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.27012218470061766,
+      "learning_rate": 4.2020005248331056e-06,
+      "loss": 0.6914,
+      "step": 280
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.2645729945558582,
+      "learning_rate": 4.170370989503662e-06,
+      "loss": 0.6812,
+      "step": 281
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.26158176244234604,
+      "learning_rate": 4.138775556973406e-06,
+      "loss": 0.6545,
+      "step": 282
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.2609966416888788,
+      "learning_rate": 4.107215526006818e-06,
+      "loss": 0.6534,
+      "step": 283
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.2633177456953443,
+      "learning_rate": 4.075692193913156e-06,
+      "loss": 0.6617,
+      "step": 284
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.2711366514748812,
+      "learning_rate": 4.04420685649314e-06,
+      "loss": 0.7026,
+      "step": 285
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.26016920693531187,
+      "learning_rate": 4.012760807985665e-06,
+      "loss": 0.685,
+      "step": 286
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.2634077734164485,
+      "learning_rate": 3.9813553410146225e-06,
+      "loss": 0.6732,
+      "step": 287
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.2630739058989318,
+      "learning_rate": 3.949991746535753e-06,
+      "loss": 0.6898,
+      "step": 288
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.26810735877032293,
+      "learning_rate": 3.918671313783583e-06,
+      "loss": 0.6739,
+      "step": 289
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.2667138269733132,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.6649,
+      "step": 290
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.2563222658817468,
+      "learning_rate": 3.856165081473474e-06,
+      "loss": 0.708,
+      "step": 291
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.26451201369218524,
+      "learning_rate": 3.824981851301924e-06,
+      "loss": 0.6715,
+      "step": 292
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.2598494927634439,
+      "learning_rate": 3.7938469215242374e-06,
+      "loss": 0.6955,
+      "step": 293
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.25396403307478727,
+      "learning_rate": 3.7627615719754294e-06,
+      "loss": 0.6676,
+      "step": 294
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.2532765659210287,
+      "learning_rate": 3.731727080452464e-06,
+      "loss": 0.6748,
+      "step": 295
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.26061271523616963,
+      "learning_rate": 3.7007447226617367e-06,
+      "loss": 0.7058,
+      "step": 296
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.25801226716086006,
+      "learning_rate": 3.669815772166625e-06,
+      "loss": 0.6717,
+      "step": 297
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.2678578983084559,
+      "learning_rate": 3.638941500335145e-06,
+      "loss": 0.6785,
+      "step": 298
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.2629273311111566,
+      "learning_rate": 3.608123176287685e-06,
+      "loss": 0.6846,
+      "step": 299
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.26372287416738016,
+      "learning_rate": 3.5773620668448384e-06,
+      "loss": 0.7155,
+      "step": 300
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.2705437923133382,
+      "learning_rate": 3.5466594364753325e-06,
+      "loss": 0.6723,
+      "step": 301
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.2839291053250124,
+      "learning_rate": 3.516016547244047e-06,
+      "loss": 0.7035,
+      "step": 302
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.2760313377640414,
+      "learning_rate": 3.48543465876014e-06,
+      "loss": 0.6751,
+      "step": 303
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.25394626546919435,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.6795,
+      "step": 304
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.2591221216055477,
+      "learning_rate": 3.424458909881897e-06,
+      "loss": 0.6766,
+      "step": 305
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.2691782924782941,
+      "learning_rate": 3.3940675559617724e-06,
+      "loss": 0.6895,
+      "step": 306
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.26815145183562566,
+      "learning_rate": 3.363742215634416e-06,
+      "loss": 0.6671,
+      "step": 307
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.26601253229287064,
+      "learning_rate": 3.3334841354557923e-06,
+      "loss": 0.6902,
+      "step": 308
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.2759140499002526,
+      "learning_rate": 3.303294559217063e-06,
+      "loss": 0.7011,
+      "step": 309
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.2532152571509874,
+      "learning_rate": 3.273174727893463e-06,
+      "loss": 0.6631,
+      "step": 310
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.2587732106097895,
+      "learning_rate": 3.2431258795932863e-06,
+      "loss": 0.6964,
+      "step": 311
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.26154429819114283,
+      "learning_rate": 3.213149249506997e-06,
+      "loss": 0.7018,
+      "step": 312
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.2640699829932556,
+      "learning_rate": 3.183246069856443e-06,
+      "loss": 0.6809,
+      "step": 313
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.26350081604751235,
+      "learning_rate": 3.1534175698442194e-06,
+      "loss": 0.655,
+      "step": 314
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.2620810766791341,
+      "learning_rate": 3.12366497560313e-06,
+      "loss": 0.7034,
+      "step": 315
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.26759545817238656,
+      "learning_rate": 3.093989510145792e-06,
+      "loss": 0.7238,
+      "step": 316
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.26779990918516644,
+      "learning_rate": 3.0643923933143603e-06,
+      "loss": 0.6733,
+      "step": 317
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.266460909749917,
+      "learning_rate": 3.0348748417303826e-06,
+      "loss": 0.6708,
+      "step": 318
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.26133722668937404,
+      "learning_rate": 3.005438068744792e-06,
+      "loss": 0.6838,
+      "step": 319
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.26893527319559857,
+      "learning_rate": 2.976083284388031e-06,
+      "loss": 0.662,
+      "step": 320
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.2699706439018165,
+      "learning_rate": 2.9468116953203107e-06,
+      "loss": 0.6867,
+      "step": 321
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.2660357193246072,
+      "learning_rate": 2.9176245047820064e-06,
+      "loss": 0.6802,
+      "step": 322
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.2676372441332764,
+      "learning_rate": 2.8885229125442022e-06,
+      "loss": 0.7143,
+      "step": 323
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.26172654998349437,
+      "learning_rate": 2.859508114859374e-06,
+      "loss": 0.6688,
+      "step": 324
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.26622148926216194,
+      "learning_rate": 2.83058130441221e-06,
+      "loss": 0.671,
+      "step": 325
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.28436198488003145,
+      "learning_rate": 2.80174367027059e-06,
+      "loss": 0.7157,
+      "step": 326
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.2637348527869296,
+      "learning_rate": 2.772996397836704e-06,
+      "loss": 0.6893,
+      "step": 327
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.27094660677035604,
+      "learning_rate": 2.7443406687983267e-06,
+      "loss": 0.7149,
+      "step": 328
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.26943858696681655,
+      "learning_rate": 2.7157776610802416e-06,
+      "loss": 0.6756,
+      "step": 329
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.2637431948145577,
+      "learning_rate": 2.687308548795825e-06,
+      "loss": 0.6731,
+      "step": 330
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.2605764257900338,
+      "learning_rate": 2.6589345021987725e-06,
+      "loss": 0.6601,
+      "step": 331
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.2691370320929689,
+      "learning_rate": 2.6306566876350072e-06,
+      "loss": 0.6747,
+      "step": 332
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.26505353096492007,
+      "learning_rate": 2.6024762674947313e-06,
+      "loss": 0.6355,
+      "step": 333
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.2771254154185314,
+      "learning_rate": 2.5743944001646394e-06,
+      "loss": 0.6679,
+      "step": 334
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.2734747453519109,
+      "learning_rate": 2.5464122399803126e-06,
+      "loss": 0.6842,
+      "step": 335
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.26644275829657593,
+      "learning_rate": 2.5185309371787515e-06,
+      "loss": 0.6986,
+      "step": 336
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 2.921169787601039,
+      "learning_rate": 2.4907516378511137e-06,
+      "loss": 0.9339,
+      "step": 337
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.25960894123414624,
+      "learning_rate": 2.46307548389559e-06,
+      "loss": 0.6743,
+      "step": 338
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.2637156946948773,
+      "learning_rate": 2.43550361297047e-06,
+      "loss": 0.682,
+      "step": 339
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.26481304373722364,
+      "learning_rate": 2.408037158447375e-06,
+      "loss": 0.6838,
+      "step": 340
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.3098032445823631,
+      "learning_rate": 2.3806772493646725e-06,
+      "loss": 0.6569,
+      "step": 341
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.26219269959571206,
+      "learning_rate": 2.353425010381063e-06,
+      "loss": 0.6761,
+      "step": 342
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.2595963563694489,
+      "learning_rate": 2.3262815617293517e-06,
+      "loss": 0.6705,
+      "step": 343
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 6.834107729255299,
+      "learning_rate": 2.2992480191704003e-06,
+      "loss": 0.9304,
+      "step": 344
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.27845487671808766,
+      "learning_rate": 2.272325493947257e-06,
+      "loss": 0.7032,
+      "step": 345
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.27640918477115356,
+      "learning_rate": 2.245515092739488e-06,
+      "loss": 0.6782,
+      "step": 346
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.2807587758407648,
+      "learning_rate": 2.2188179176176767e-06,
+      "loss": 0.6932,
+      "step": 347
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.27767259525555504,
+      "learning_rate": 2.1922350659981262e-06,
+      "loss": 0.6466,
+      "step": 348
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.267658673895331,
+      "learning_rate": 2.165767630597752e-06,
+      "loss": 0.7089,
+      "step": 349
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.2745228363539692,
+      "learning_rate": 2.139416699389153e-06,
+      "loss": 0.6778,
+      "step": 350
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.26408657536920843,
+      "learning_rate": 2.1131833555559037e-06,
+      "loss": 0.693,
+      "step": 351
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.27582062474841573,
+      "learning_rate": 2.08706867744802e-06,
+      "loss": 0.6896,
+      "step": 352
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.26826511006390147,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.6796,
+      "step": 353
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.26630216372896987,
+      "learning_rate": 2.0351996073748713e-06,
+      "loss": 0.664,
+      "step": 354
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.2809694093215496,
+      "learning_rate": 2.00944734754392e-06,
+      "loss": 0.7044,
+      "step": 355
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.2984772108139377,
+      "learning_rate": 1.983818017619318e-06,
+      "loss": 0.9348,
+      "step": 356
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.2721943586746493,
+      "learning_rate": 1.9583126711224342e-06,
+      "loss": 0.6918,
+      "step": 357
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.27480703238103743,
+      "learning_rate": 1.932932356478168e-06,
+      "loss": 0.6854,
+      "step": 358
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.27867368393846137,
+      "learning_rate": 1.9076781169718426e-06,
+      "loss": 0.6892,
+      "step": 359
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.2747868621778029,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.6947,
+      "step": 360
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.2819831023326237,
+      "learning_rate": 1.857552010559382e-06,
+      "loss": 0.7059,
+      "step": 361
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.27392909848006375,
+      "learning_rate": 1.8326822041411524e-06,
+      "loss": 0.6909,
+      "step": 362
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.2743865258535757,
+      "learning_rate": 1.8079425937519729e-06,
+      "loss": 0.679,
+      "step": 363
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 2.5387012983068686,
+      "learning_rate": 1.7833341963403312e-06,
+      "loss": 0.8855,
+      "step": 364
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.265533513891752,
+      "learning_rate": 1.7588580234610592e-06,
+      "loss": 0.6915,
+      "step": 365
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.27359948413194535,
+      "learning_rate": 1.7345150812337564e-06,
+      "loss": 0.6983,
+      "step": 366
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.2742529435490673,
+      "learning_rate": 1.7103063703014372e-06,
+      "loss": 0.6712,
+      "step": 367
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.27199602044830407,
+      "learning_rate": 1.6862328857893856e-06,
+      "loss": 0.6929,
+      "step": 368
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.26752081718353027,
+      "learning_rate": 1.6622956172642601e-06,
+      "loss": 0.6693,
+      "step": 369
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.2729904749450422,
+      "learning_rate": 1.6384955486934157e-06,
+      "loss": 0.6545,
+      "step": 370
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.27686659493721505,
+      "learning_rate": 1.6148336584044539e-06,
+      "loss": 0.6957,
+      "step": 371
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.27203211099316454,
+      "learning_rate": 1.5913109190450033e-06,
+      "loss": 0.6709,
+      "step": 372
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.2748872025880921,
+      "learning_rate": 1.567928297542749e-06,
+      "loss": 0.6648,
+      "step": 373
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.28544562477258,
+      "learning_rate": 1.544686755065677e-06,
+      "loss": 0.6937,
+      "step": 374
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.27110159404128226,
+      "learning_rate": 1.5215872469825682e-06,
+      "loss": 0.6593,
+      "step": 375
+    },
+    {
+      "epoch": 1.48,
+      "eval_loss": 0.6996302008628845,
+      "eval_runtime": 96.9399,
+      "eval_samples_per_second": 18.238,
+      "eval_steps_per_second": 0.382,
+      "step": 375
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.28648432605335455,
+      "learning_rate": 1.4986307228237268e-06,
+      "loss": 0.6883,
+      "step": 376
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.2695264027977092,
+      "learning_rate": 1.4758181262419425e-06,
+      "loss": 0.6696,
+      "step": 377
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.2786040566891135,
+      "learning_rate": 1.4531503949737107e-06,
+      "loss": 0.6768,
+      "step": 378
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.2730138945863401,
+      "learning_rate": 1.4306284608006837e-06,
+      "loss": 0.699,
+      "step": 379
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.28711818986138005,
+      "learning_rate": 1.4082532495113627e-06,
+      "loss": 0.6961,
+      "step": 380
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.27838100192134935,
+      "learning_rate": 1.3860256808630429e-06,
+      "loss": 0.6589,
+      "step": 381
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.2798399005913698,
+      "learning_rate": 1.3639466685440133e-06,
+      "loss": 0.6924,
+      "step": 382
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.2801056534585314,
+      "learning_rate": 1.3420171201359933e-06,
+      "loss": 0.7047,
+      "step": 383
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.28576658015544487,
+      "learning_rate": 1.3202379370768254e-06,
+      "loss": 0.6617,
+      "step": 384
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.3100321738765892,
+      "learning_rate": 1.298610014623423e-06,
+      "loss": 0.9236,
+      "step": 385
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.303191205875695,
+      "learning_rate": 1.2771342418149658e-06,
+      "loss": 0.6896,
+      "step": 386
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.29469211064765755,
+      "learning_rate": 1.2558115014363592e-06,
+      "loss": 0.6804,
+      "step": 387
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.2772656639598833,
+      "learning_rate": 1.234642669981946e-06,
+      "loss": 0.7043,
+      "step": 388
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.28874341170670975,
+      "learning_rate": 1.2136286176194744e-06,
+      "loss": 0.6839,
+      "step": 389
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.29443238526351323,
+      "learning_rate": 1.1927702081543279e-06,
+      "loss": 0.6852,
+      "step": 390
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.28011985365824127,
+      "learning_rate": 1.1720682989940264e-06,
+      "loss": 0.7019,
+      "step": 391
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.2987249208096274,
+      "learning_rate": 1.1515237411129698e-06,
+      "loss": 0.6625,
+      "step": 392
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.30150125882304396,
+      "learning_rate": 1.1311373790174656e-06,
+      "loss": 0.7102,
+      "step": 393
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.28396138619493894,
+      "learning_rate": 1.1109100507110133e-06,
+      "loss": 0.6538,
+      "step": 394
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.28445333602874173,
+      "learning_rate": 1.0908425876598512e-06,
+      "loss": 0.6719,
+      "step": 395
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.2914051878027514,
+      "learning_rate": 1.0709358147587883e-06,
+      "loss": 0.6803,
+      "step": 396
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.2969873740157493,
+      "learning_rate": 1.0511905502972885e-06,
+      "loss": 0.6845,
+      "step": 397
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.27955221055069657,
+      "learning_rate": 1.031607605925839e-06,
+      "loss": 0.6819,
+      "step": 398
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.2840904640426781,
+      "learning_rate": 1.0121877866225783e-06,
+      "loss": 0.6685,
+      "step": 399
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.2866769315662431,
+      "learning_rate": 9.929318906602176e-07,
+      "loss": 0.7126,
+      "step": 400
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.28635331619928306,
+      "learning_rate": 9.738407095732195e-07,
+      "loss": 0.6825,
+      "step": 401
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.29612030431665504,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.6889,
+      "step": 402
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.2800350134356635,
+      "learning_rate": 9.361556242769871e-07,
+      "loss": 0.6902,
+      "step": 403
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.303825841465723,
+      "learning_rate": 9.175632691540065e-07,
+      "loss": 0.6949,
+      "step": 404
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.2869303466691903,
+      "learning_rate": 8.991387270152202e-07,
+      "loss": 0.6953,
+      "step": 405
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.2822567891211309,
+      "learning_rate": 8.808827552213917e-07,
+      "loss": 0.6733,
+      "step": 406
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.29613652418881947,
+      "learning_rate": 8.627961042040183e-07,
+      "loss": 0.6721,
+      "step": 407
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.2904383828418472,
+      "learning_rate": 8.448795174344803e-07,
+      "loss": 0.6849,
+      "step": 408
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.28422518396116003,
+      "learning_rate": 8.271337313934869e-07,
+      "loss": 0.676,
+      "step": 409
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.2998884374161429,
+      "learning_rate": 8.095594755407971e-07,
+      "loss": 0.72,
+      "step": 410
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.2877123964038153,
+      "learning_rate": 7.921574722852343e-07,
+      "loss": 0.686,
+      "step": 411
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.2848351263069502,
+      "learning_rate": 7.749284369549954e-07,
+      "loss": 0.6755,
+      "step": 412
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 3.762805837262192,
+      "learning_rate": 7.578730777682386e-07,
+      "loss": 0.9037,
+      "step": 413
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.2782769592021476,
+      "learning_rate": 7.409920958039795e-07,
+      "loss": 0.6686,
+      "step": 414
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.28369386272785363,
+      "learning_rate": 7.242861849732696e-07,
+      "loss": 0.6772,
+      "step": 415
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.28870985589458403,
+      "learning_rate": 7.077560319906696e-07,
+      "loss": 0.6665,
+      "step": 416
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.2880267458624612,
+      "learning_rate": 6.914023163460248e-07,
+      "loss": 0.6767,
+      "step": 417
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.2879073116640725,
+      "learning_rate": 6.752257102765325e-07,
+      "loss": 0.6733,
+      "step": 418
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.2978223401759706,
+      "learning_rate": 6.592268787391077e-07,
+      "loss": 0.707,
+      "step": 419
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.2781074725093229,
+      "learning_rate": 6.43406479383053e-07,
+      "loss": 0.6962,
+      "step": 420
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.29577562012306474,
+      "learning_rate": 6.277651625230219e-07,
+      "loss": 0.6772,
+      "step": 421
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.2848699679509908,
+      "learning_rate": 6.12303571112286e-07,
+      "loss": 0.7008,
+      "step": 422
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.2728708533046375,
+      "learning_rate": 5.9702234071631e-07,
+      "loss": 0.6994,
+      "step": 423
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.2971147397482144,
+      "learning_rate": 5.819220994866237e-07,
+      "loss": 0.6784,
+      "step": 424
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.2918077307247773,
+      "learning_rate": 5.670034681349995e-07,
+      "loss": 0.6798,
+      "step": 425
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.2766527969263755,
+      "learning_rate": 5.522670599079416e-07,
+      "loss": 0.692,
+      "step": 426
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.2896023594106076,
+      "learning_rate": 5.377134805614714e-07,
+      "loss": 0.6885,
+      "step": 427
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.29226174571780184,
+      "learning_rate": 5.233433283362349e-07,
+      "loss": 0.6609,
+      "step": 428
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.30313380575685006,
+      "learning_rate": 5.091571939329049e-07,
+      "loss": 0.6559,
+      "step": 429
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.2851579977806079,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.6862,
+      "step": 430
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.28828722620682673,
+      "learning_rate": 4.813393035494329e-07,
+      "loss": 0.673,
+      "step": 431
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.283083619090625,
+      "learning_rate": 4.677086910538092e-07,
+      "loss": 0.6477,
+      "step": 432
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.29809618255032516,
+      "learning_rate": 4.542643833021254e-07,
+      "loss": 0.7054,
+      "step": 433
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.3086409841744957,
+      "learning_rate": 4.410069329372152e-07,
+      "loss": 0.6763,
+      "step": 434
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.3016981542599131,
+      "learning_rate": 4.279368849209381e-07,
+      "loss": 0.6843,
+      "step": 435
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.27698126686942587,
+      "learning_rate": 4.150547765117746e-07,
+      "loss": 0.6891,
+      "step": 436
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.2793586730481018,
+      "learning_rate": 4.0236113724274716e-07,
+      "loss": 0.6796,
+      "step": 437
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.28666974827878056,
+      "learning_rate": 3.8985648889964755e-07,
+      "loss": 0.6648,
+      "step": 438
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.28527293041641727,
+      "learning_rate": 3.77541345499593e-07,
+      "loss": 0.7071,
+      "step": 439
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.29843069047155474,
+      "learning_rate": 3.6541621326989183e-07,
+      "loss": 0.6803,
+      "step": 440
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.3001228333782996,
+      "learning_rate": 3.534815906272404e-07,
+      "loss": 0.7176,
+      "step": 441
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.2928174202718284,
+      "learning_rate": 3.417379681572297e-07,
+      "loss": 0.6747,
+      "step": 442
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.2951128501223636,
+      "learning_rate": 3.301858285941845e-07,
+      "loss": 0.7046,
+      "step": 443
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.2931876464433515,
+      "learning_rate": 3.18825646801314e-07,
+      "loss": 0.6734,
+      "step": 444
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.29349560436630445,
+      "learning_rate": 3.076578897511978e-07,
+      "loss": 0.6852,
+      "step": 445
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.7457047514934827,
+      "learning_rate": 2.966830165065876e-07,
+      "loss": 0.9017,
+      "step": 446
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.2813462622367945,
+      "learning_rate": 2.8590147820153513e-07,
+      "loss": 0.6969,
+      "step": 447
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.30904433658187347,
+      "learning_rate": 2.7531371802285436e-07,
+      "loss": 0.6829,
+      "step": 448
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.28837856935691286,
+      "learning_rate": 2.6492017119189415e-07,
+      "loss": 0.6527,
+      "step": 449
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.2940858357017207,
+      "learning_rate": 2.547212649466568e-07,
+      "loss": 0.6696,
+      "step": 450
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.27956534271888384,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.7048,
+      "step": 451
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.28259810422391984,
+      "learning_rate": 2.3490904314356412e-07,
+      "loss": 0.6772,
+      "step": 452
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.2846763408984384,
+      "learning_rate": 2.2529654198854834e-07,
+      "loss": 0.7507,
+      "step": 453
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.2784656918785677,
+      "learning_rate": 2.1588031019145638e-07,
+      "loss": 0.7072,
+      "step": 454
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.28593045031546543,
+      "learning_rate": 2.0666073481669714e-07,
+      "loss": 0.6944,
+      "step": 455
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.296176705173677,
+      "learning_rate": 1.9763819484490353e-07,
+      "loss": 0.6691,
+      "step": 456
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.2923471158891105,
+      "learning_rate": 1.8881306115735632e-07,
+      "loss": 0.705,
+      "step": 457
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.2769134760770555,
+      "learning_rate": 1.801856965207338e-07,
+      "loss": 0.6845,
+      "step": 458
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.30153347516541434,
+      "learning_rate": 1.7175645557220567e-07,
+      "loss": 0.6935,
+      "step": 459
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.29938078931561396,
+      "learning_rate": 1.6352568480485277e-07,
+      "loss": 0.6822,
+      "step": 460
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.2909845977727433,
+      "learning_rate": 1.5549372255342367e-07,
+      "loss": 0.6959,
+      "step": 461
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.2851155920589762,
+      "learning_rate": 1.4766089898042678e-07,
+      "loss": 0.6909,
+      "step": 462
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.590844633307425,
+      "learning_rate": 1.4002753606256082e-07,
+      "loss": 0.9279,
+      "step": 463
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.289769942223222,
+      "learning_rate": 1.3259394757747678e-07,
+      "loss": 0.6664,
+      "step": 464
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 1.4756345980091514,
+      "learning_rate": 1.253604390908819e-07,
+      "loss": 0.9066,
+      "step": 465
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.2905542054012534,
+      "learning_rate": 1.1832730794397951e-07,
+      "loss": 0.6989,
+      "step": 466
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.3056790622208962,
+      "learning_rate": 1.1149484324124326e-07,
+      "loss": 0.64,
+      "step": 467
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.2915224050071343,
+      "learning_rate": 1.0486332583853565e-07,
+      "loss": 0.6411,
+      "step": 468
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.2947477867782055,
+      "learning_rate": 9.843302833156377e-08,
+      "loss": 0.6901,
+      "step": 469
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.6968434274277037,
+      "learning_rate": 9.22042150446728e-08,
+      "loss": 0.9234,
+      "step": 470
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.28365980605268926,
+      "learning_rate": 8.617714201998084e-08,
+      "loss": 0.6871,
+      "step": 471
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.29456041125148436,
+      "learning_rate": 8.035205700685167e-08,
+      "loss": 0.6841,
+      "step": 472
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.3143240746562965,
+      "learning_rate": 7.47291994517163e-08,
+      "loss": 0.6793,
+      "step": 473
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.3002190997085016,
+      "learning_rate": 6.930880048822531e-08,
+      "loss": 0.6909,
+      "step": 474
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.28198233683666907,
+      "learning_rate": 6.409108292774912e-08,
+      "loss": 0.6677,
+      "step": 475
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.2974351663902672,
+      "learning_rate": 5.907626125022159e-08,
+      "loss": 0.6863,
+      "step": 476
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.3167342201027022,
+      "learning_rate": 5.426454159531913e-08,
+      "loss": 0.6728,
+      "step": 477
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.2838121481556639,
+      "learning_rate": 4.9656121753990924e-08,
+      "loss": 0.6765,
+      "step": 478
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.28117138518414553,
+      "learning_rate": 4.52511911603265e-08,
+      "loss": 0.6827,
+      "step": 479
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.29399576903346636,
+      "learning_rate": 4.104993088376974e-08,
+      "loss": 0.6933,
+      "step": 480
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.29636385882946953,
+      "learning_rate": 3.705251362167484e-08,
+      "loss": 0.6641,
+      "step": 481
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.2913085312105263,
+      "learning_rate": 3.325910369220975e-08,
+      "loss": 0.6973,
+      "step": 482
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.29080057862930364,
+      "learning_rate": 2.966985702759828e-08,
+      "loss": 0.6678,
+      "step": 483
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.2952306166117519,
+      "learning_rate": 2.6284921167712975e-08,
+      "loss": 0.7017,
+      "step": 484
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.2959396595629797,
+      "learning_rate": 2.3104435254008852e-08,
+      "loss": 0.6569,
+      "step": 485
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.28791733733513286,
+      "learning_rate": 2.012853002380466e-08,
+      "loss": 0.6573,
+      "step": 486
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.2923526176448832,
+      "learning_rate": 1.735732780490884e-08,
+      "loss": 0.6903,
+      "step": 487
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.2908268098513957,
+      "learning_rate": 1.4790942510590767e-08,
+      "loss": 0.6756,
+      "step": 488
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.29069043095745606,
+      "learning_rate": 1.2429479634897268e-08,
+      "loss": 0.6722,
+      "step": 489
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.28912174671892155,
+      "learning_rate": 1.0273036248318325e-08,
+      "loss": 0.6927,
+      "step": 490
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.29773909318477504,
+      "learning_rate": 8.321700993795812e-09,
+      "loss": 0.6703,
+      "step": 491
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.2846360921300275,
+      "learning_rate": 6.575554083078084e-09,
+      "loss": 0.6915,
+      "step": 492
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.3040183654289367,
+      "learning_rate": 5.034667293427053e-09,
+      "loss": 0.6836,
+      "step": 493
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.29012455377167307,
+      "learning_rate": 3.6991039646616657e-09,
+      "loss": 0.6844,
+      "step": 494
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.2778518633390048,
+      "learning_rate": 2.568918996560532e-09,
+      "loss": 0.6779,
+      "step": 495
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.29541155663074187,
+      "learning_rate": 1.6441588466009627e-09,
+      "loss": 0.6979,
+      "step": 496
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.28364315270086676,
+      "learning_rate": 9.248615280499362e-10,
+      "loss": 0.6792,
+      "step": 497
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.2865142006406564,
+      "learning_rate": 4.1105660840368154e-10,
+      "loss": 0.7034,
+      "step": 498
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.2854424675916699,
+      "learning_rate": 1.0276520816976388e-10,
+      "loss": 0.6747,
+      "step": 499
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.29666466368391803,
+      "learning_rate": 0.0,
+      "loss": 0.6754,
+      "step": 500
+    },
+    {
+      "epoch": 1.97,
+      "eval_loss": 0.6983408331871033,
+      "eval_runtime": 93.907,
+      "eval_samples_per_second": 18.827,
+      "eval_steps_per_second": 0.394,
+      "step": 500
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 1571976955035648.0,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}