Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-7b-sft-full
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# zephyr-7b-sft-full
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9393
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9355        | 1.0   | 1090 | 0.9393          |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9795057065989993,
+    "train_runtime": 15753.4108,
+    "train_samples": 207864,
+    "train_samples_per_second": 8.85,
+    "train_steps_per_second": 0.069
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e7abb1f70ebee78adb05c3af4ad264d0b8df4ee1e5b238d450618723fa1afa
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08e0fa94fcb88585837521d2f9a8b0cb1bece89826e11485b4513c7366ccde7
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:420037a0066d706f55699aea4934e015a680afd12975fc76f16c4b48b2105cb7
+size 4540516344

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9795057065989993,
+    "train_runtime": 15753.4108,
+    "train_samples": 207864,
+    "train_samples_per_second": 8.85,
+    "train_steps_per_second": 0.069
+}

trainer_state.json

@@ -0,0 +1,1571 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1090,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 9.77339219775282,
+      "learning_rate": 1.8348623853211012e-07,
+      "loss": 1.1557,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 7.7326824203360625,
+      "learning_rate": 9.174311926605506e-07,
+      "loss": 1.1259,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.217943082141626,
+      "learning_rate": 1.8348623853211011e-06,
+      "loss": 1.0814,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.1553293441150627,
+      "learning_rate": 2.7522935779816517e-06,
+      "loss": 1.0173,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.624974536136745,
+      "learning_rate": 3.6697247706422022e-06,
+      "loss": 1.01,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.9346693086685613,
+      "learning_rate": 4.587155963302753e-06,
+      "loss": 0.9699,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.0023694879238265,
+      "learning_rate": 5.504587155963303e-06,
+      "loss": 0.9871,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.9243231029659136,
+      "learning_rate": 6.422018348623854e-06,
+      "loss": 0.9731,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.3079689233656158,
+      "learning_rate": 7.3394495412844045e-06,
+      "loss": 0.9786,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.9848142793089458,
+      "learning_rate": 8.256880733944956e-06,
+      "loss": 0.9683,
+      "step": 45
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.1601847540175347,
+      "learning_rate": 9.174311926605506e-06,
+      "loss": 0.9655,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.995827350954353,
+      "learning_rate": 1.0091743119266055e-05,
+      "loss": 0.9763,
+      "step": 55
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.8778202478820005,
+      "learning_rate": 1.1009174311926607e-05,
+      "loss": 0.9828,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.6097761971016706,
+      "learning_rate": 1.1926605504587156e-05,
+      "loss": 0.9917,
+      "step": 65
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.9438707878045542,
+      "learning_rate": 1.2844036697247708e-05,
+      "loss": 0.9781,
+      "step": 70
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.5283537508840412,
+      "learning_rate": 1.3761467889908258e-05,
+      "loss": 0.9766,
+      "step": 75
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.4698926435303807,
+      "learning_rate": 1.4678899082568809e-05,
+      "loss": 0.9744,
+      "step": 80
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.7950947398875594,
+      "learning_rate": 1.559633027522936e-05,
+      "loss": 0.9925,
+      "step": 85
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.849659361988556,
+      "learning_rate": 1.6513761467889912e-05,
+      "loss": 0.9951,
+      "step": 90
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.091607616206256,
+      "learning_rate": 1.743119266055046e-05,
+      "loss": 1.0061,
+      "step": 95
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.066221029636183,
+      "learning_rate": 1.834862385321101e-05,
+      "loss": 0.9985,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.869454578032626,
+      "learning_rate": 1.9266055045871563e-05,
+      "loss": 0.9907,
+      "step": 105
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.2432123776551944,
+      "learning_rate": 1.999994872196626e-05,
+      "loss": 1.0027,
+      "step": 110
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.328668819896044,
+      "learning_rate": 1.9998154046002822e-05,
+      "loss": 0.9926,
+      "step": 115
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.9876127666903096,
+      "learning_rate": 1.999379599421534e-05,
+      "loss": 1.0011,
+      "step": 120
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.8724555785709804,
+      "learning_rate": 1.9986875683942535e-05,
+      "loss": 1.0242,
+      "step": 125
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.1894981771490443,
+      "learning_rate": 1.9977394889447526e-05,
+      "loss": 1.0032,
+      "step": 130
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.5051450231269605,
+      "learning_rate": 1.9965356041462954e-05,
+      "loss": 1.0154,
+      "step": 135
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.01438038230488,
+      "learning_rate": 1.9950762226567783e-05,
+      "loss": 1.0023,
+      "step": 140
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.974662211540992,
+      "learning_rate": 1.9933617186395917e-05,
+      "loss": 0.9996,
+      "step": 145
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.7299662712917598,
+      "learning_rate": 1.9913925316676946e-05,
+      "loss": 1.0024,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.675351804082685,
+      "learning_rate": 1.9891691666109112e-05,
+      "loss": 0.9807,
+      "step": 155
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.7568442047779815,
+      "learning_rate": 1.9866921935064907e-05,
+      "loss": 1.0026,
+      "step": 160
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.8020826944560722,
+      "learning_rate": 1.9839622474129595e-05,
+      "loss": 0.9945,
+      "step": 165
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.880978608228776,
+      "learning_rate": 1.9809800282473014e-05,
+      "loss": 1.0131,
+      "step": 170
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.9533970099597644,
+      "learning_rate": 1.977746300605507e-05,
+      "loss": 1.0154,
+      "step": 175
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.8000655097775127,
+      "learning_rate": 1.9742618935665478e-05,
+      "loss": 0.9994,
+      "step": 180
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.6150313589958014,
+      "learning_rate": 1.9705277004798072e-05,
+      "loss": 1.0017,
+      "step": 185
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.6236825548036045,
+      "learning_rate": 1.9665446787360444e-05,
+      "loss": 1.0084,
+      "step": 190
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.681320814042372,
+      "learning_rate": 1.9623138495219292e-05,
+      "loss": 1.0185,
+      "step": 195
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.909108842556375,
+      "learning_rate": 1.957836297558229e-05,
+      "loss": 1.0128,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.6634688766473966,
+      "learning_rate": 1.9531131708217005e-05,
+      "loss": 1.0145,
+      "step": 205
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.556894984467879,
+      "learning_rate": 1.948145680250766e-05,
+      "loss": 0.9924,
+      "step": 210
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.620552922782101,
+      "learning_rate": 1.9429350994350483e-05,
+      "loss": 1.0044,
+      "step": 215
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.635093025466642,
+      "learning_rate": 1.93748276428884e-05,
+      "loss": 0.9856,
+      "step": 220
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.674299362647312,
+      "learning_rate": 1.931790072708596e-05,
+      "loss": 0.9934,
+      "step": 225
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.6887591497181855,
+      "learning_rate": 1.9258584842145342e-05,
+      "loss": 1.0112,
+      "step": 230
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.645113774478941,
+      "learning_rate": 1.9196895195764363e-05,
+      "loss": 1.0066,
+      "step": 235
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.6845020042548609,
+      "learning_rate": 1.913284760423745e-05,
+      "loss": 1.0158,
+      "step": 240
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.647832284848899,
+      "learning_rate": 1.9066458488400586e-05,
+      "loss": 1.0086,
+      "step": 245
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.697080815625411,
+      "learning_rate": 1.8997744869421248e-05,
+      "loss": 1.0155,
+      "step": 250
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.7170796898803107,
+      "learning_rate": 1.8926724364434447e-05,
+      "loss": 1.0041,
+      "step": 255
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.706074031599582,
+      "learning_rate": 1.8853415182025953e-05,
+      "loss": 0.9922,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.8989841472640996,
+      "learning_rate": 1.8777836117563894e-05,
+      "loss": 0.9941,
+      "step": 265
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.7121367648810273,
+      "learning_rate": 1.8700006548379898e-05,
+      "loss": 1.0023,
+      "step": 270
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.9417882651127933,
+      "learning_rate": 1.861994642880105e-05,
+      "loss": 1.0081,
+      "step": 275
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.7496252675391932,
+      "learning_rate": 1.8537676285033886e-05,
+      "loss": 1.0012,
+      "step": 280
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.5992757261270931,
+      "learning_rate": 1.845321720990181e-05,
+      "loss": 0.9882,
+      "step": 285
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.5982026868074015,
+      "learning_rate": 1.8366590857437182e-05,
+      "loss": 0.9935,
+      "step": 290
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 2.0122073912291203,
+      "learning_rate": 1.8277819437329577e-05,
+      "loss": 1.0075,
+      "step": 295
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 21.05626958615313,
+      "learning_rate": 1.8186925709231534e-05,
+      "loss": 1.0239,
+      "step": 300
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.626174907352815,
+      "learning_rate": 1.809393297692334e-05,
+      "loss": 1.1336,
+      "step": 305
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.5588583574219355,
+      "learning_rate": 1.799886508233829e-05,
+      "loss": 1.0703,
+      "step": 310
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 52.257959922882186,
+      "learning_rate": 1.790174639944997e-05,
+      "loss": 1.2478,
+      "step": 315
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 8.296874056632827,
+      "learning_rate": 1.780260182802314e-05,
+      "loss": 1.4918,
+      "step": 320
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 17.554936318206273,
+      "learning_rate": 1.7701456787229805e-05,
+      "loss": 1.2285,
+      "step": 325
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 8.45205253267018,
+      "learning_rate": 1.7598337209132142e-05,
+      "loss": 1.1503,
+      "step": 330
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 6.266748541585308,
+      "learning_rate": 1.7493269532033882e-05,
+      "loss": 1.1033,
+      "step": 335
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 111.52289151968921,
+      "learning_rate": 1.738628069370195e-05,
+      "loss": 1.1048,
+      "step": 340
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 7.688414643609198,
+      "learning_rate": 1.7277398124460022e-05,
+      "loss": 1.1117,
+      "step": 345
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.031319921903212,
+      "learning_rate": 1.71666497401558e-05,
+      "loss": 1.0816,
+      "step": 350
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 11.431111354306312,
+      "learning_rate": 1.7054063935003813e-05,
+      "loss": 1.0609,
+      "step": 355
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.2441387172030134,
+      "learning_rate": 1.6939669574305565e-05,
+      "loss": 1.0462,
+      "step": 360
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.0523696752811604,
+      "learning_rate": 1.6823495987048922e-05,
+      "loss": 1.0476,
+      "step": 365
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.8895154393147975,
+      "learning_rate": 1.6705572958388576e-05,
+      "loss": 1.0311,
+      "step": 370
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.8139444627013965,
+      "learning_rate": 1.6585930722009602e-05,
+      "loss": 1.0371,
+      "step": 375
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.7032921177242157,
+      "learning_rate": 1.6464599952375998e-05,
+      "loss": 1.0436,
+      "step": 380
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.7285341229493167,
+      "learning_rate": 1.63416117568662e-05,
+      "loss": 1.0119,
+      "step": 385
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.722890751549469,
+      "learning_rate": 1.621699766779763e-05,
+      "loss": 1.0317,
+      "step": 390
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.599051242781322,
+      "learning_rate": 1.6090789634342278e-05,
+      "loss": 1.0147,
+      "step": 395
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 2.011875168952266,
+      "learning_rate": 1.5963020014335437e-05,
+      "loss": 1.0109,
+      "step": 400
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.7745695288261167,
+      "learning_rate": 1.583372156597961e-05,
+      "loss": 1.0226,
+      "step": 405
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.7032574663832216,
+      "learning_rate": 1.570292743944583e-05,
+      "loss": 0.9938,
+      "step": 410
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.710578272048905,
+      "learning_rate": 1.557067116837444e-05,
+      "loss": 0.9883,
+      "step": 415
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.6957880003939496,
+      "learning_rate": 1.5436986661277578e-05,
+      "loss": 0.9908,
+      "step": 420
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.6008040760391928,
+      "learning_rate": 1.530190819284555e-05,
+      "loss": 1.0016,
+      "step": 425
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.7382539416393734,
+      "learning_rate": 1.5165470395159314e-05,
+      "loss": 0.9929,
+      "step": 430
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.8011281382514583,
+      "learning_rate": 1.5027708248811331e-05,
+      "loss": 0.9953,
+      "step": 435
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.6996850685052767,
+      "learning_rate": 1.4888657073937077e-05,
+      "loss": 0.9906,
+      "step": 440
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.618144358393542,
+      "learning_rate": 1.4748352521159492e-05,
+      "loss": 1.0065,
+      "step": 445
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.52251331168285,
+      "learning_rate": 1.4606830562448692e-05,
+      "loss": 0.9944,
+      "step": 450
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.9393071866897407,
+      "learning_rate": 1.4464127481899312e-05,
+      "loss": 0.9765,
+      "step": 455
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.6893250353047762,
+      "learning_rate": 1.4320279866427798e-05,
+      "loss": 1.0034,
+      "step": 460
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.5907871510849094,
+      "learning_rate": 1.4175324596392075e-05,
+      "loss": 0.9839,
+      "step": 465
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.6419259125990346,
+      "learning_rate": 1.402929883613599e-05,
+      "loss": 1.004,
+      "step": 470
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.5792169432621945,
+      "learning_rate": 1.3882240024460928e-05,
+      "loss": 0.9583,
+      "step": 475
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.5453338942420716,
+      "learning_rate": 1.3734185865027061e-05,
+      "loss": 0.9818,
+      "step": 480
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.6532156284337152,
+      "learning_rate": 1.358517431668672e-05,
+      "loss": 0.9812,
+      "step": 485
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.8030804926474087,
+      "learning_rate": 1.3435243583752294e-05,
+      "loss": 0.9799,
+      "step": 490
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.6418123185067888,
+      "learning_rate": 1.3284432106201233e-05,
+      "loss": 0.9916,
+      "step": 495
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.6258591855391478,
+      "learning_rate": 1.313277854982062e-05,
+      "loss": 0.9917,
+      "step": 500
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.02063585594681,
+      "learning_rate": 1.2980321796293838e-05,
+      "loss": 0.9821,
+      "step": 505
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.4641044058112402,
+      "learning_rate": 1.2827100933231904e-05,
+      "loss": 0.9669,
+      "step": 510
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.4734009074897523,
+      "learning_rate": 1.2673155244151985e-05,
+      "loss": 0.9887,
+      "step": 515
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.504049205573269,
+      "learning_rate": 1.2518524198405699e-05,
+      "loss": 0.9752,
+      "step": 520
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.5871801520121447,
+      "learning_rate": 1.2363247441059775e-05,
+      "loss": 0.986,
+      "step": 525
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.5031034877601523,
+      "learning_rate": 1.2207364782731657e-05,
+      "loss": 0.9827,
+      "step": 530
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.680552260004968,
+      "learning_rate": 1.2050916189382646e-05,
+      "loss": 0.977,
+      "step": 535
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.5439369139377679,
+      "learning_rate": 1.189394177207125e-05,
+      "loss": 0.9746,
+      "step": 540
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.4901425478827495,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.9653,
+      "step": 545
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.468475262540055,
+      "learning_rate": 1.1578576573543541e-05,
+      "loss": 0.9887,
+      "step": 550
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.4398608054707567,
+      "learning_rate": 1.1420266647205232e-05,
+      "loss": 0.9761,
+      "step": 555
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.5422374491434532,
+      "learning_rate": 1.1261592585930576e-05,
+      "loss": 0.9582,
+      "step": 560
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.5286775911829815,
+      "learning_rate": 1.1102595071354471e-05,
+      "loss": 0.9738,
+      "step": 565
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.4817522889069266,
+      "learning_rate": 1.0943314868040365e-05,
+      "loss": 0.9813,
+      "step": 570
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.4293384597101042,
+      "learning_rate": 1.0783792813028828e-05,
+      "loss": 0.9674,
+      "step": 575
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.5261318491484366,
+      "learning_rate": 1.0624069805367558e-05,
+      "loss": 0.985,
+      "step": 580
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.5097693128941394,
+      "learning_rate": 1.0464186795625481e-05,
+      "loss": 0.9639,
+      "step": 585
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.5846698306417735,
+      "learning_rate": 1.0304184775393642e-05,
+      "loss": 0.9701,
+      "step": 590
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.4231247673906455,
+      "learning_rate": 1.0144104766775574e-05,
+      "loss": 0.9684,
+      "step": 595
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.4645243353450357,
+      "learning_rate": 9.983987811869863e-06,
+      "loss": 0.9726,
+      "step": 600
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.6188671105629062,
+      "learning_rate": 9.823874962247565e-06,
+      "loss": 0.9562,
+      "step": 605
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.4748824240542495,
+      "learning_rate": 9.663807268427197e-06,
+      "loss": 0.9677,
+      "step": 610
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.427861703011802,
+      "learning_rate": 9.503825769350016e-06,
+      "loss": 0.9645,
+      "step": 615
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.4151510701857246,
+      "learning_rate": 9.343971481858246e-06,
+      "loss": 0.9423,
+      "step": 620
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.4516242963328596,
+      "learning_rate": 9.184285390178978e-06,
+      "loss": 0.9656,
+      "step": 625
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.7062684460068769,
+      "learning_rate": 9.024808435416435e-06,
+      "loss": 0.9637,
+      "step": 630
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.4522675784960328,
+      "learning_rate": 8.865581505055292e-06,
+      "loss": 0.9786,
+      "step": 635
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.4328537035514395,
+      "learning_rate": 8.706645422477739e-06,
+      "loss": 0.948,
+      "step": 640
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.5567683964703176,
+      "learning_rate": 8.548040936496989e-06,
+      "loss": 0.9613,
+      "step": 645
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.5074863131808958,
+      "learning_rate": 8.389808710909881e-06,
+      "loss": 0.9514,
+      "step": 650
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.4273894196530337,
+      "learning_rate": 8.231989314071318e-06,
+      "loss": 0.9656,
+      "step": 655
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.471995206720774,
+      "learning_rate": 8.07462320849313e-06,
+      "loss": 0.9475,
+      "step": 660
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.568608987104535,
+      "learning_rate": 7.917750740470116e-06,
+      "loss": 0.9769,
+      "step": 665
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.3745365175696858,
+      "learning_rate": 7.761412129735853e-06,
+      "loss": 0.9603,
+      "step": 670
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.466522406606583,
+      "learning_rate": 7.605647459150961e-06,
+      "loss": 0.9332,
+      "step": 675
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.3463238948259868,
+      "learning_rate": 7.4504966644264775e-06,
+      "loss": 0.9436,
+      "step": 680
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.4997500356384885,
+      "learning_rate": 7.295999523884921e-06,
+      "loss": 0.9363,
+      "step": 685
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.4849900349578966,
+      "learning_rate": 7.142195648261747e-06,
+      "loss": 0.9699,
+      "step": 690
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.4732303903444304,
+      "learning_rate": 6.989124470549746e-06,
+      "loss": 0.9582,
+      "step": 695
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.3881607197451564,
+      "learning_rate": 6.83682523588902e-06,
+      "loss": 0.9457,
+      "step": 700
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.441527770787461,
+      "learning_rate": 6.685336991505122e-06,
+      "loss": 0.961,
+      "step": 705
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.5093653951413892,
+      "learning_rate": 6.5346985766979384e-06,
+      "loss": 0.9557,
+      "step": 710
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.3906632586548848,
+      "learning_rate": 6.384948612883872e-06,
+      "loss": 0.9274,
+      "step": 715
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.4296014203069103,
+      "learning_rate": 6.2361254936939e-06,
+      "loss": 0.9333,
+      "step": 720
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.4300856178576173,
+      "learning_rate": 6.0882673751300235e-06,
+      "loss": 0.9462,
+      "step": 725
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.3936601183930903,
+      "learning_rate": 5.941412165782645e-06,
+      "loss": 0.9479,
+      "step": 730
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.6621722765974563,
+      "learning_rate": 5.79559751711138e-06,
+      "loss": 0.9459,
+      "step": 735
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.4433022742228918,
+      "learning_rate": 5.650860813791786e-06,
+      "loss": 0.9308,
+      "step": 740
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.3734643883063014,
+      "learning_rate": 5.507239164130501e-06,
+      "loss": 0.9487,
+      "step": 745
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.387981074803405,
+      "learning_rate": 5.364769390551225e-06,
+      "loss": 0.9545,
+      "step": 750
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.391011395848312,
+      "learning_rate": 5.223488020154028e-06,
+      "loss": 0.9419,
+      "step": 755
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4792090950991559,
+      "learning_rate": 5.083431275350312e-06,
+      "loss": 0.9426,
+      "step": 760
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.3955718332534048,
+      "learning_rate": 4.9446350645759885e-06,
+      "loss": 0.9303,
+      "step": 765
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.4552341272988114,
+      "learning_rate": 4.807134973085036e-06,
+      "loss": 0.9551,
+      "step": 770
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.4197472248094545,
+      "learning_rate": 4.670966253826027e-06,
+      "loss": 0.948,
+      "step": 775
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.3903141656921318,
+      "learning_rate": 4.53616381840377e-06,
+      "loss": 0.9404,
+      "step": 780
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.4683373587462776,
+      "learning_rate": 4.402762228128531e-06,
+      "loss": 0.9393,
+      "step": 785
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.3895342562056905,
+      "learning_rate": 4.270795685155001e-06,
+      "loss": 0.9295,
+      "step": 790
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.3645654190042658,
+      "learning_rate": 4.140298023713416e-06,
+      "loss": 0.9322,
+      "step": 795
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.3831028295258314,
+      "learning_rate": 4.0113027014349374e-06,
+      "loss": 0.9393,
+      "step": 800
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.402507806165818,
+      "learning_rate": 3.883842790773647e-06,
+      "loss": 0.9407,
+      "step": 805
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.3477220628229905,
+      "learning_rate": 3.757950970527249e-06,
+      "loss": 0.9399,
+      "step": 810
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.4105862702544307,
+      "learning_rate": 3.633659517458736e-06,
+      "loss": 0.9429,
+      "step": 815
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.4134155318530202,
+      "learning_rate": 3.511000298021098e-06,
+      "loss": 0.9267,
+      "step": 820
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.671468704931624,
+      "learning_rate": 3.39000476018726e-06,
+      "loss": 0.9405,
+      "step": 825
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.518363690298914,
+      "learning_rate": 3.2707039253872796e-06,
+      "loss": 0.9499,
+      "step": 830
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.391445796072115,
+      "learning_rate": 3.153128380554941e-06,
+      "loss": 0.9397,
+      "step": 835
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.4199198449516006,
+      "learning_rate": 3.037308270285709e-06,
+      "loss": 0.9374,
+      "step": 840
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.3725059360040226,
+      "learning_rate": 2.923273289108115e-06,
+      "loss": 0.9289,
+      "step": 845
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.402432038179815,
+      "learning_rate": 2.8110526738705345e-06,
+      "loss": 0.9399,
+      "step": 850
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.3538150837811775,
+      "learning_rate": 2.700675196245288e-06,
+      "loss": 0.9235,
+      "step": 855
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.3719901639969891,
+      "learning_rate": 2.592169155352031e-06,
+      "loss": 0.9305,
+      "step": 860
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.3417159608633782,
+      "learning_rate": 2.485562370502279e-06,
+      "loss": 0.93,
+      "step": 865
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.447083155674768,
+      "learning_rate": 2.3808821740669608e-06,
+      "loss": 0.9444,
+      "step": 870
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.457818919394179,
+      "learning_rate": 2.2781554044688015e-06,
+      "loss": 0.944,
+      "step": 875
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.3423569321240763,
+      "learning_rate": 2.1774083993013715e-06,
+      "loss": 0.9284,
+      "step": 880
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.4022698745517062,
+      "learning_rate": 2.0786669885765044e-06,
+      "loss": 0.943,
+      "step": 885
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.3695761420314987,
+      "learning_rate": 1.981956488101898e-06,
+      "loss": 0.9419,
+      "step": 890
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.351231324123156,
+      "learning_rate": 1.8873016929904942e-06,
+      "loss": 0.9315,
+      "step": 895
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.4420470493119792,
+      "learning_rate": 1.7947268713034128e-06,
+      "loss": 0.9247,
+      "step": 900
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.376296944069193,
+      "learning_rate": 1.704255757827963e-06,
+      "loss": 0.9443,
+      "step": 905
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.3432275033995362,
+      "learning_rate": 1.6159115479924259e-06,
+      "loss": 0.9453,
+      "step": 910
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.408037299795807,
+      "learning_rate": 1.529716891919074e-06,
+      "loss": 0.9168,
+      "step": 915
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.3321909436006458,
+      "learning_rate": 1.4456938886170413e-06,
+      "loss": 0.9284,
+      "step": 920
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.4347603275075604,
+      "learning_rate": 1.3638640803164516e-06,
+      "loss": 0.928,
+      "step": 925
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.414525145641175,
+      "learning_rate": 1.2842484469453365e-06,
+      "loss": 0.9247,
+      "step": 930
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.3556935778322545,
+      "learning_rate": 1.2068674007506787e-06,
+      "loss": 0.9212,
+      "step": 935
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.4388764825242009,
+      "learning_rate": 1.1317407810650372e-06,
+      "loss": 0.9168,
+      "step": 940
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.3989979018945433,
+      "learning_rate": 1.0588878492200261e-06,
+      "loss": 0.9288,
+      "step": 945
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.3566434474333582,
+      "learning_rate": 9.883272836080116e-07,
+      "loss": 0.926,
+      "step": 950
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.4319194447938426,
+      "learning_rate": 9.200771748932513e-07,
+      "loss": 0.9455,
+      "step": 955
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.3526304536258829,
+      "learning_rate": 8.541550213737171e-07,
+      "loss": 0.9261,
+      "step": 960
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.399241882005225,
+      "learning_rate": 7.905777244947954e-07,
+      "loss": 0.9316,
+      "step": 965
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.4094250992512831,
+      "learning_rate": 7.293615845160196e-07,
+      "loss": 0.9275,
+      "step": 970
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.3526180756349577,
+      "learning_rate": 6.705222963319191e-07,
+      "loss": 0.9363,
+      "step": 975
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.416809797785314,
+      "learning_rate": 6.140749454480932e-07,
+      "loss": 0.9297,
+      "step": 980
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.351887149750103,
+      "learning_rate": 5.600340041135133e-07,
+      "loss": 0.9393,
+      "step": 985
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.3895523431306795,
+      "learning_rate": 5.0841332761005e-07,
+      "loss": 0.9383,
+      "step": 990
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.3424090925296945,
+      "learning_rate": 4.592261507001994e-07,
+      "loss": 0.9215,
+      "step": 995
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.3838142145295658,
+      "learning_rate": 4.124850842338779e-07,
+      "loss": 0.9369,
+      "step": 1000
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.4019675844003927,
+      "learning_rate": 3.6820211191520127e-07,
+      "loss": 0.9269,
+      "step": 1005
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.4513095530474966,
+      "learning_rate": 3.263885872300343e-07,
+      "loss": 0.9507,
+      "step": 1010
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.361924533980129,
+      "learning_rate": 2.870552305351382e-07,
+      "loss": 0.9196,
+      "step": 1015
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.3927244960089797,
+      "learning_rate": 2.5021212630962246e-07,
+      "loss": 0.9328,
+      "step": 1020
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.3290530166960066,
+      "learning_rate": 2.158687205694443e-07,
+      "loss": 0.9405,
+      "step": 1025
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.3680987060349954,
+      "learning_rate": 1.840338184455881e-07,
+      "loss": 0.9276,
+      "step": 1030
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.3438546650666667,
+      "learning_rate": 1.5471558192656776e-07,
+      "loss": 0.9221,
+      "step": 1035
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.4512371380173261,
+      "learning_rate": 1.279215277658097e-07,
+      "loss": 0.9336,
+      "step": 1040
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.362018016831518,
+      "learning_rate": 1.0365852555447642e-07,
+      "loss": 0.9175,
+      "step": 1045
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.359560038203717,
+      "learning_rate": 8.19327959602012e-08,
+      "loss": 0.91,
+      "step": 1050
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.3944491658597338,
+      "learning_rate": 6.274990913221035e-08,
+      "loss": 0.946,
+      "step": 1055
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.3012436329306727,
+      "learning_rate": 4.6114783273213395e-08,
+      "loss": 0.9316,
+      "step": 1060
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.4375328358464377,
+      "learning_rate": 3.203168337845508e-08,
+      "loss": 0.9098,
+      "step": 1065
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.321439340704291,
+      "learning_rate": 2.05042201422323e-08,
+      "loss": 0.9084,
+      "step": 1070
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.4259870829955092,
+      "learning_rate": 1.1535349032167908e-08,
+      "loss": 0.9399,
+      "step": 1075
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.4012106970656215,
+      "learning_rate": 5.127369531473525e-09,
+      "loss": 0.9261,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3831302460073325,
+      "learning_rate": 1.2819245493955746e-09,
+      "loss": 0.9336,
+      "step": 1085
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3587054894081556,
+      "learning_rate": 0.0,
+      "loss": 0.9355,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9393356442451477,
+      "eval_runtime": 322.3924,
+      "eval_samples_per_second": 47.864,
+      "eval_steps_per_second": 0.751,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0,
+      "step": 1090,
+      "total_flos": 456447649382400.0,
+      "train_loss": 0.9795057065989993,
+      "train_runtime": 15753.4108,
+      "train_samples_per_second": 8.85,
+      "train_steps_per_second": 0.069
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1090,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 456447649382400.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}