Upload folder using huggingface_hub

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+base_model: teknium/OpenHermes-2.5-Mistral-7B
+tags:
+- generated_from_trainer
+model-index:
+- name: out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/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)
+# out
+
+This model is a fine-tuned version of [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1923
+
+## 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: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.1498        | 0.0   | 1    | 1.1953          |
+| 0.321         | 0.1   | 31   | 0.3176          |
+| 0.2693        | 0.2   | 62   | 0.2712          |
+| 0.2701        | 0.31  | 93   | 0.2523          |
+| 0.27          | 0.41  | 124  | 0.2362          |
+| 0.2244        | 0.51  | 155  | 0.2284          |
+| 0.2227        | 0.61  | 186  | 0.2260          |
+| 0.2167        | 0.71  | 217  | 0.2171          |
+| 0.2098        | 0.81  | 248  | 0.2082          |
+| 0.1842        | 0.92  | 279  | 0.2047          |
+| 0.1917        | 1.02  | 310  | 0.2013          |
+| 0.1639        | 1.12  | 341  | 0.1982          |
+| 0.1835        | 1.22  | 372  | 0.1968          |
+| 0.1666        | 1.32  | 403  | 0.1953          |
+| 0.1694        | 1.43  | 434  | 0.1932          |
+| 0.1461        | 1.53  | 465  | 0.1929          |
+| 0.1535        | 1.63  | 496  | 0.1927          |
+| 0.1419        | 1.73  | 527  | 0.1925          |
+| 0.1612        | 1.83  | 558  | 0.1923          |
+| 0.1857        | 1.93  | 589  | 0.1923          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

checkpoint-304/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32002
+}

checkpoint-304/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "transformers_version": "4.34.1"
+}

checkpoint-304/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e6187564e0cb423c502ad7c4c471b40e3a3948b33291e75fe96e5eee8fa136
+size 14512135879

checkpoint-304/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0460f2ef47ab8ffe104b355e94d643362c5a2d30e7c88ff25309ea8d3dbf6c5a
+size 9886765428

checkpoint-304/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:769dc4ff85335c5680fca0fc804c81420600c1b9d287a32bb36611c418168385
+size 5121688491

checkpoint-304/pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 15008350208
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

checkpoint-304/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b79fdab1d04d2fef64e6cc48d12f3c84ce5b8c1a21bebdb7dbe2a42d800421e
+size 15607

checkpoint-304/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31694b994f0607cfe91452414877c57b870598c9a4bd9bae0760f822c13a1461
+size 15607

checkpoint-304/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7547983ff9227d6a5b68c9efde9fe1bc3541fcc13d36c1688a739942d845584c
+size 627

checkpoint-304/trainer_state.json

@@ -0,0 +1,1923 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9983579638752053,
+  "eval_steps": 31,
+  "global_step": 304,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.1498,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.1952733993530273,
+      "eval_runtime": 15.2597,
+      "eval_samples_per_second": 6.226,
+      "eval_steps_per_second": 1.573,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.176,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5e-06,
+      "loss": 1.1287,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.0172,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.5e-06,
+      "loss": 0.8997,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3e-06,
+      "loss": 0.8616,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.5e-06,
+      "loss": 0.7128,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6826,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.5e-06,
+      "loss": 0.5946,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-06,
+      "loss": 0.5616,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.999965501009142e-06,
+      "loss": 0.4778,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.999862004988709e-06,
+      "loss": 0.5264,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.999689514795112e-06,
+      "loss": 0.4518,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9994480351889364e-06,
+      "loss": 0.46,
+      "step": 14
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.999137572834828e-06,
+      "loss": 0.4111,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.998758136301295e-06,
+      "loss": 0.3646,
+      "step": 16
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.99830973606048e-06,
+      "loss": 0.4024,
+      "step": 17
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.997792384487867e-06,
+      "loss": 0.4042,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.997206095861944e-06,
+      "loss": 0.3659,
+      "step": 19
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.996550886363801e-06,
+      "loss": 0.3527,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.995826774076693e-06,
+      "loss": 0.3726,
+      "step": 21
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.995033778985534e-06,
+      "loss": 0.3551,
+      "step": 22
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.994171922976349e-06,
+      "loss": 0.382,
+      "step": 23
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.993241229835666e-06,
+      "loss": 0.3694,
+      "step": 24
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.992241725249866e-06,
+      "loss": 0.3603,
+      "step": 25
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.991173436804468e-06,
+      "loss": 0.3383,
+      "step": 26
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.990036393983372e-06,
+      "loss": 0.3455,
+      "step": 27
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9888306281680405e-06,
+      "loss": 0.3428,
+      "step": 28
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.987556172636637e-06,
+      "loss": 0.3001,
+      "step": 29
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.986213062563104e-06,
+      "loss": 0.307,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.984801335016198e-06,
+      "loss": 0.321,
+      "step": 31
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.3176000714302063,
+      "eval_runtime": 15.512,
+      "eval_samples_per_second": 6.124,
+      "eval_steps_per_second": 1.547,
+      "step": 31
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.9833210289584574e-06,
+      "loss": 0.2925,
+      "step": 32
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.981772185245135e-06,
+      "loss": 0.311,
+      "step": 33
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.980154846623067e-06,
+      "loss": 0.3066,
+      "step": 34
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.978469057729493e-06,
+      "loss": 0.2879,
+      "step": 35
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.976714865090827e-06,
+      "loss": 0.3001,
+      "step": 36
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.974892317121368e-06,
+      "loss": 0.3111,
+      "step": 37
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.97300146412197e-06,
+      "loss": 0.3067,
+      "step": 38
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.9710423582786485e-06,
+      "loss": 0.3091,
+      "step": 39
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.969015053661142e-06,
+      "loss": 0.302,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.966919606221423e-06,
+      "loss": 0.2991,
+      "step": 41
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.964756073792148e-06,
+      "loss": 0.3034,
+      "step": 42
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.9625245160850674e-06,
+      "loss": 0.2877,
+      "step": 43
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.960224994689371e-06,
+      "loss": 0.283,
+      "step": 44
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.957857573069992e-06,
+      "loss": 0.2993,
+      "step": 45
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.955422316565856e-06,
+      "loss": 0.2738,
+      "step": 46
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.952919292388079e-06,
+      "loss": 0.293,
+      "step": 47
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.950348569618105e-06,
+      "loss": 0.3053,
+      "step": 48
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.947710219205808e-06,
+      "loss": 0.2875,
+      "step": 49
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.9450043139675284e-06,
+      "loss": 0.2798,
+      "step": 50
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.9422309285840684e-06,
+      "loss": 0.3172,
+      "step": 51
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.939390139598623e-06,
+      "loss": 0.2713,
+      "step": 52
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.936482025414677e-06,
+      "loss": 0.2372,
+      "step": 53
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.933506666293834e-06,
+      "loss": 0.3125,
+      "step": 54
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.9304641443536015e-06,
+      "loss": 0.2687,
+      "step": 55
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.927354543565131e-06,
+      "loss": 0.2701,
+      "step": 56
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.924177949750893e-06,
+      "loss": 0.2681,
+      "step": 57
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.920934450582311e-06,
+      "loss": 0.2751,
+      "step": 58
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.917624135577346e-06,
+      "loss": 0.2902,
+      "step": 59
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.914247096098019e-06,
+      "loss": 0.2618,
+      "step": 60
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.910803425347892e-06,
+      "loss": 0.2569,
+      "step": 61
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.907293218369499e-06,
+      "loss": 0.2693,
+      "step": 62
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.27119407057762146,
+      "eval_runtime": 15.5684,
+      "eval_samples_per_second": 6.102,
+      "eval_steps_per_second": 1.542,
+      "step": 62
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.903716572041718e-06,
+      "loss": 0.2475,
+      "step": 63
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.9000735850771e-06,
+      "loss": 0.2492,
+      "step": 64
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.8963643580191446e-06,
+      "loss": 0.273,
+      "step": 65
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.8925889932395246e-06,
+      "loss": 0.2193,
+      "step": 66
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.888747594935259e-06,
+      "loss": 0.2637,
+      "step": 67
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.88484026912584e-06,
+      "loss": 0.3141,
+      "step": 68
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.880867123650306e-06,
+      "loss": 0.254,
+      "step": 69
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.876828268164264e-06,
+      "loss": 0.2778,
+      "step": 70
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.872723814136866e-06,
+      "loss": 0.2809,
+      "step": 71
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.868553874847728e-06,
+      "loss": 0.266,
+      "step": 72
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.864318565383809e-06,
+      "loss": 0.2174,
+      "step": 73
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.86001800263623e-06,
+      "loss": 0.2732,
+      "step": 74
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.855652305297052e-06,
+      "loss": 0.2507,
+      "step": 75
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.8512215938559955e-06,
+      "loss": 0.2514,
+      "step": 76
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.846725990597122e-06,
+      "loss": 0.268,
+      "step": 77
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.84216561959545e-06,
+      "loss": 0.228,
+      "step": 78
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.837540606713538e-06,
+      "loss": 0.2606,
+      "step": 79
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.832851079598007e-06,
+      "loss": 0.2554,
+      "step": 80
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.82809716767602e-06,
+      "loss": 0.257,
+      "step": 81
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.8232790021517094e-06,
+      "loss": 0.2475,
+      "step": 82
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.818396716002553e-06,
+      "loss": 0.2636,
+      "step": 83
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.813450443975705e-06,
+      "loss": 0.2076,
+      "step": 84
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.808440322584283e-06,
+      "loss": 0.2336,
+      "step": 85
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.803366490103593e-06,
+      "loss": 0.2664,
+      "step": 86
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.798229086567312e-06,
+      "loss": 0.2559,
+      "step": 87
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.793028253763633e-06,
+      "loss": 0.2687,
+      "step": 88
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.787764135231342e-06,
+      "loss": 0.2263,
+      "step": 89
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.7824368762558595e-06,
+      "loss": 0.2058,
+      "step": 90
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.7770466238652336e-06,
+      "loss": 0.246,
+      "step": 91
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.771593526826078e-06,
+      "loss": 0.2592,
+      "step": 92
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.76607773563947e-06,
+      "loss": 0.2701,
+      "step": 93
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.25227251648902893,
+      "eval_runtime": 15.5184,
+      "eval_samples_per_second": 6.122,
+      "eval_steps_per_second": 1.547,
+      "step": 93
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.760499402536792e-06,
+      "loss": 0.2154,
+      "step": 94
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.754858681475534e-06,
+      "loss": 0.2748,
+      "step": 95
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.7491557281350455e-06,
+      "loss": 0.2461,
+      "step": 96
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.743390699912232e-06,
+      "loss": 0.2245,
+      "step": 97
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.737563755917219e-06,
+      "loss": 0.2446,
+      "step": 98
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.731675056968958e-06,
+      "loss": 0.2563,
+      "step": 99
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.7257247655907854e-06,
+      "loss": 0.2512,
+      "step": 100
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.7197130460059385e-06,
+      "loss": 0.2613,
+      "step": 101
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.7136400641330245e-06,
+      "loss": 0.2294,
+      "step": 102
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.7075059875814424e-06,
+      "loss": 0.2162,
+      "step": 103
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.70131098564675e-06,
+      "loss": 0.251,
+      "step": 104
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.695055229306001e-06,
+      "loss": 0.2468,
+      "step": 105
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.6887388912130206e-06,
+      "loss": 0.2467,
+      "step": 106
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.68236214569364e-06,
+      "loss": 0.2588,
+      "step": 107
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.675925168740887e-06,
+      "loss": 0.2592,
+      "step": 108
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.6694281380101304e-06,
+      "loss": 0.2225,
+      "step": 109
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.662871232814171e-06,
+      "loss": 0.2411,
+      "step": 110
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.656254634118301e-06,
+      "loss": 0.2512,
+      "step": 111
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.649578524535302e-06,
+      "loss": 0.2252,
+      "step": 112
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.642843088320408e-06,
+      "loss": 0.2288,
+      "step": 113
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.636048511366222e-06,
+      "loss": 0.2339,
+      "step": 114
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.6291949811975814e-06,
+      "loss": 0.2252,
+      "step": 115
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.622282686966387e-06,
+      "loss": 0.2497,
+      "step": 116
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.615311819446379e-06,
+      "loss": 0.2339,
+      "step": 117
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.6082825710278724e-06,
+      "loss": 0.2946,
+      "step": 118
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.60119513571245e-06,
+      "loss": 0.2797,
+      "step": 119
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.594049709107604e-06,
+      "loss": 0.272,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.58684648842134e-06,
+      "loss": 0.2437,
+      "step": 121
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.5795856724567344e-06,
+      "loss": 0.2328,
+      "step": 122
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.572267461606446e-06,
+      "loss": 0.2333,
+      "step": 123
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.564892057847184e-06,
+      "loss": 0.27,
+      "step": 124
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.2362014800310135,
+      "eval_runtime": 15.5362,
+      "eval_samples_per_second": 6.115,
+      "eval_steps_per_second": 1.545,
+      "step": 124
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.5574596647341414e-06,
+      "loss": 0.2202,
+      "step": 125
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.549970487395365e-06,
+      "loss": 0.2129,
+      "step": 126
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.542424732526105e-06,
+      "loss": 0.2343,
+      "step": 127
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.534822608383104e-06,
+      "loss": 0.2527,
+      "step": 128
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.5271643247788496e-06,
+      "loss": 0.2622,
+      "step": 129
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.519450093075787e-06,
+      "loss": 0.247,
+      "step": 130
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.5116801261804846e-06,
+      "loss": 0.2612,
+      "step": 131
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.503854638537756e-06,
+      "loss": 0.2515,
+      "step": 132
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.49597384612474e-06,
+      "loss": 0.2164,
+      "step": 133
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.488037966444948e-06,
+      "loss": 0.2545,
+      "step": 134
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.48004721852225e-06,
+      "loss": 0.2547,
+      "step": 135
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.472001822894839e-06,
+      "loss": 0.1869,
+      "step": 136
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.463902001609139e-06,
+      "loss": 0.2383,
+      "step": 137
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.455747978213679e-06,
+      "loss": 0.2234,
+      "step": 138
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.44753997775292e-06,
+      "loss": 0.2356,
+      "step": 139
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.43927822676105e-06,
+      "loss": 0.232,
+      "step": 140
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.430962953255725e-06,
+      "loss": 0.2352,
+      "step": 141
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.4225943867317835e-06,
+      "loss": 0.2199,
+      "step": 142
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.4141727581549025e-06,
+      "loss": 0.2175,
+      "step": 143
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.405698299955234e-06,
+      "loss": 0.221,
+      "step": 144
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.39717124602098e-06,
+      "loss": 0.2522,
+      "step": 145
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.388591831691948e-06,
+      "loss": 0.2412,
+      "step": 146
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.3799602937530464e-06,
+      "loss": 0.2176,
+      "step": 147
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.3712768704277535e-06,
+      "loss": 0.2242,
+      "step": 148
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.362541801371542e-06,
+      "loss": 0.2156,
+      "step": 149
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.353755327665268e-06,
+      "loss": 0.2077,
+      "step": 150
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.344917691808511e-06,
+      "loss": 0.2285,
+      "step": 151
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.3360291377128864e-06,
+      "loss": 0.2364,
+      "step": 152
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.32708991069531e-06,
+      "loss": 0.2577,
+      "step": 153
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.318100257471233e-06,
+      "loss": 0.2347,
+      "step": 154
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.309060426147826e-06,
+      "loss": 0.2244,
+      "step": 155
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.22840476036071777,
+      "eval_runtime": 15.5442,
+      "eval_samples_per_second": 6.112,
+      "eval_steps_per_second": 1.544,
+      "step": 155
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.299970666217135e-06,
+      "loss": 0.2197,
+      "step": 156
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.290831228549196e-06,
+      "loss": 0.2618,
+      "step": 157
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.281642365385111e-06,
+      "loss": 0.2498,
+      "step": 158
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.272404330330084e-06,
+      "loss": 0.2309,
+      "step": 159
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.263117378346425e-06,
+      "loss": 0.2163,
+      "step": 160
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.253781765746511e-06,
+      "loss": 0.1968,
+      "step": 161
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.244397750185714e-06,
+      "loss": 0.2127,
+      "step": 162
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.234965590655287e-06,
+      "loss": 0.2088,
+      "step": 163
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.225485547475217e-06,
+      "loss": 0.2082,
+      "step": 164
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.215957882287044e-06,
+      "loss": 0.2549,
+      "step": 165
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.206382858046636e-06,
+      "loss": 0.2131,
+      "step": 166
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.19676073901693e-06,
+      "loss": 0.2048,
+      "step": 167
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.187091790760644e-06,
+      "loss": 0.2451,
+      "step": 168
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.177376280132946e-06,
+      "loss": 0.1896,
+      "step": 169
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.167614475274082e-06,
+      "loss": 0.2253,
+      "step": 170
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.1578066456019885e-06,
+      "loss": 0.2167,
+      "step": 171
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.147953061804845e-06,
+      "loss": 0.2262,
+      "step": 172
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.1380539958336095e-06,
+      "loss": 0.2483,
+      "step": 173
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.128109720894512e-06,
+      "loss": 0.2824,
+      "step": 174
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.118120511441512e-06,
+      "loss": 0.2273,
+      "step": 175
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.108086643168724e-06,
+      "loss": 0.2177,
+      "step": 176
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.098008393002816e-06,
+      "loss": 0.2147,
+      "step": 177
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.087886039095353e-06,
+      "loss": 0.1915,
+      "step": 178
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.077719860815132e-06,
+      "loss": 0.2123,
+      "step": 179
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.067510138740467e-06,
+      "loss": 0.2418,
+      "step": 180
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.057257154651444e-06,
+      "loss": 0.2055,
+      "step": 181
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.046961191522147e-06,
+      "loss": 0.2098,
+      "step": 182
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.036622533512845e-06,
+      "loss": 0.2304,
+      "step": 183
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.026241465962154e-06,
+      "loss": 0.2018,
+      "step": 184
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.0158182753791566e-06,
+      "loss": 0.2009,
+      "step": 185
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.0053532494354985e-06,
+      "loss": 0.2227,
+      "step": 186
+    },
+    {
+      "epoch": 0.61,
+      "eval_loss": 0.2260431945323944,
+      "eval_runtime": 15.5286,
+      "eval_samples_per_second": 6.118,
+      "eval_steps_per_second": 1.546,
+      "step": 186
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.994846676957448e-06,
+      "loss": 0.1973,
+      "step": 187
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.984298847917923e-06,
+      "loss": 0.2192,
+      "step": 188
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.973710053428487e-06,
+      "loss": 0.2016,
+      "step": 189
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.963080585731324e-06,
+      "loss": 0.2118,
+      "step": 190
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.952410738191158e-06,
+      "loss": 0.2361,
+      "step": 191
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.941700805287169e-06,
+      "loss": 0.2132,
+      "step": 192
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.9309510826048556e-06,
+      "loss": 0.2117,
+      "step": 193
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.92016186682789e-06,
+      "loss": 0.2196,
+      "step": 194
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.909333455729914e-06,
+      "loss": 0.1958,
+      "step": 195
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.898466148166333e-06,
+      "loss": 0.2318,
+      "step": 196
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.8875602440660635e-06,
+      "loss": 0.2034,
+      "step": 197
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.876616044423253e-06,
+      "loss": 0.2119,
+      "step": 198
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.865633851288975e-06,
+      "loss": 0.2177,
+      "step": 199
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.854613967762898e-06,
+      "loss": 0.1974,
+      "step": 200
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.843556697984907e-06,
+      "loss": 0.1902,
+      "step": 201
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.832462347126722e-06,
+      "loss": 0.1975,
+      "step": 202
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.821331221383471e-06,
+      "loss": 0.2083,
+      "step": 203
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.8101636279652375e-06,
+      "loss": 0.2247,
+      "step": 204
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.798959875088584e-06,
+      "loss": 0.2169,
+      "step": 205
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.787720271968046e-06,
+      "loss": 0.1854,
+      "step": 206
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.7764451288075944e-06,
+      "loss": 0.2269,
+      "step": 207
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.765134756792079e-06,
+      "loss": 0.1946,
+      "step": 208
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.753789468078636e-06,
+      "loss": 0.1944,
+      "step": 209
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.742409575788074e-06,
+      "loss": 0.2057,
+      "step": 210
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.730995393996234e-06,
+      "loss": 0.2427,
+      "step": 211
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.719547237725319e-06,
+      "loss": 0.227,
+      "step": 212
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.708065422935198e-06,
+      "loss": 0.2152,
+      "step": 213
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.6965502665146916e-06,
+      "loss": 0.2177,
+      "step": 214
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.6850020862728196e-06,
+      "loss": 0.2089,
+      "step": 215
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.6734212009300346e-06,
+      "loss": 0.2081,
+      "step": 216
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.661807930109422e-06,
+      "loss": 0.2167,
+      "step": 217
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 0.21709737181663513,
+      "eval_runtime": 15.5146,
+      "eval_samples_per_second": 6.123,
+      "eval_steps_per_second": 1.547,
+      "step": 217
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.650162594327881e-06,
+      "loss": 0.2135,
+      "step": 218
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.6384855149872776e-06,
+      "loss": 0.1976,
+      "step": 219
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.6267770143655743e-06,
+      "loss": 0.2073,
+      "step": 220
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.615037415607937e-06,
+      "loss": 0.2252,
+      "step": 221
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.603267042717813e-06,
+      "loss": 0.2296,
+      "step": 222
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5914662205479923e-06,
+      "loss": 0.181,
+      "step": 223
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.579635274791639e-06,
+      "loss": 0.2196,
+      "step": 224
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.567774531973305e-06,
+      "loss": 0.2063,
+      "step": 225
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.555884319439917e-06,
+      "loss": 0.2313,
+      "step": 226
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.5439649653517416e-06,
+      "loss": 0.1994,
+      "step": 227
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.532016798673329e-06,
+      "loss": 0.2143,
+      "step": 228
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.5200401491644333e-06,
+      "loss": 0.2118,
+      "step": 229
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.508035347370912e-06,
+      "loss": 0.2081,
+      "step": 230
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.4960027246156043e-06,
+      "loss": 0.2313,
+      "step": 231
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.483942612989183e-06,
+      "loss": 0.2071,
+      "step": 232
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.471855345340992e-06,
+      "loss": 0.2199,
+      "step": 233
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.4597412552698617e-06,
+      "loss": 0.1879,
+      "step": 234
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.447600677114898e-06,
+      "loss": 0.1717,
+      "step": 235
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.4354339459462556e-06,
+      "loss": 0.2273,
+      "step": 236
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.423241397555893e-06,
+      "loss": 0.2351,
+      "step": 237
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.4110233684483033e-06,
+      "loss": 0.2165,
+      "step": 238
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.3987801958312254e-06,
+      "loss": 0.2309,
+      "step": 239
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.386512217606339e-06,
+      "loss": 0.2023,
+      "step": 240
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.3742197723599403e-06,
+      "loss": 0.2189,
+      "step": 241
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.361903199353593e-06,
+      "loss": 0.205,
+      "step": 242
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.349562838514769e-06,
+      "loss": 0.1912,
+      "step": 243
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.3371990304274654e-06,
+      "loss": 0.1898,
+      "step": 244
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.3248121163228037e-06,
+      "loss": 0.2037,
+      "step": 245
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.3124024380696134e-06,
+      "loss": 0.1959,
+      "step": 246
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.299970338164995e-06,
+      "loss": 0.1972,
+      "step": 247
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.28751615972487e-06,
+      "loss": 0.2098,
+      "step": 248
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 0.20815877616405487,
+      "eval_runtime": 15.5231,
+      "eval_samples_per_second": 6.12,
+      "eval_steps_per_second": 1.546,
+      "step": 248
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.2750402464745084e-06,
+      "loss": 0.2322,
+      "step": 249
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.262542942739044e-06,
+      "loss": 0.1977,
+      "step": 250
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.2500245934339714e-06,
+      "loss": 0.1983,
+      "step": 251
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.2374855440556242e-06,
+      "loss": 0.1857,
+      "step": 252
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.224926140671643e-06,
+      "loss": 0.183,
+      "step": 253
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.2123467299114216e-06,
+      "loss": 0.2216,
+      "step": 254
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.199747658956541e-06,
+      "loss": 0.1808,
+      "step": 255
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.1871292755311887e-06,
+      "loss": 0.2278,
+      "step": 256
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.174491927892561e-06,
+      "loss": 0.203,
+      "step": 257
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.1618359648212492e-06,
+      "loss": 0.2209,
+      "step": 258
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.1491617356116167e-06,
+      "loss": 0.2131,
+      "step": 259
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.136469590062158e-06,
+      "loss": 0.2111,
+      "step": 260
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.1237598784658444e-06,
+      "loss": 0.1915,
+      "step": 261
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.1110329516004546e-06,
+      "loss": 0.2272,
+      "step": 262
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.0982891607188948e-06,
+      "loss": 0.1784,
+      "step": 263
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.085528857539506e-06,
+      "loss": 0.2064,
+      "step": 264
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.0727523942363547e-06,
+      "loss": 0.1857,
+      "step": 265
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.0599601234295124e-06,
+      "loss": 0.1981,
+      "step": 266
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.0471523981753266e-06,
+      "loss": 0.2429,
+      "step": 267
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.0343295719566747e-06,
+      "loss": 0.1755,
+      "step": 268
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.0214919986732076e-06,
+      "loss": 0.2024,
+      "step": 269
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.0086400326315853e-06,
+      "loss": 0.1859,
+      "step": 270
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.9957740285356933e-06,
+      "loss": 0.2056,
+      "step": 271
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.9828943414768583e-06,
+      "loss": 0.2183,
+      "step": 272
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.9700013269240463e-06,
+      "loss": 0.1892,
+      "step": 273
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.957095340714049e-06,
+      "loss": 0.2139,
+      "step": 274
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.9441767390416665e-06,
+      "loss": 0.2314,
+      "step": 275
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.9312458784498763e-06,
+      "loss": 0.1897,
+      "step": 276
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.918303115819992e-06,
+      "loss": 0.1698,
+      "step": 277
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.9053488083618118e-06,
+      "loss": 0.2147,
+      "step": 278
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.892383313603765e-06,
+      "loss": 0.1842,
+      "step": 279
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 0.20471937954425812,
+      "eval_runtime": 15.5241,
+      "eval_samples_per_second": 6.12,
+      "eval_steps_per_second": 1.546,
+      "step": 279
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8794069893830386e-06,
+      "loss": 0.178,
+      "step": 280
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8664201938357052e-06,
+      "loss": 0.2245,
+      "step": 281
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.8534232853868384e-06,
+      "loss": 0.1583,
+      "step": 282
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.840416622740617e-06,
+      "loss": 0.1752,
+      "step": 283
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.8274005648704316e-06,
+      "loss": 0.1981,
+      "step": 284
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8143754710089694e-06,
+      "loss": 0.2216,
+      "step": 285
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8013417006383078e-06,
+      "loss": 0.2075,
+      "step": 286
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.7882996134799854e-06,
+      "loss": 0.1978,
+      "step": 287
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.775249569485079e-06,
+      "loss": 0.2302,
+      "step": 288
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.762191928824267e-06,
+      "loss": 0.2218,
+      "step": 289
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.7491270518778913e-06,
+      "loss": 0.2033,
+      "step": 290
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.736055299226007e-06,
+      "loss": 0.2055,
+      "step": 291
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.722977031638435e-06,
+      "loss": 0.2231,
+      "step": 292
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.709892610064801e-06,
+      "loss": 0.2233,
+      "step": 293
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.696802395624579e-06,
+      "loss": 0.2354,
+      "step": 294
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.683706749597118e-06,
+      "loss": 0.2136,
+      "step": 295
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.670606033411678e-06,
+      "loss": 0.181,
+      "step": 296
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.657500608637448e-06,
+      "loss": 0.2051,
+      "step": 297
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.6443908369735715e-06,
+      "loss": 0.209,
+      "step": 298
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.631277080239163e-06,
+      "loss": 0.2184,
+      "step": 299
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.6181597003633218e-06,
+      "loss": 0.1988,
+      "step": 300
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.605039059375143e-06,
+      "loss": 0.2223,
+      "step": 301
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.5919155193937244e-06,
+      "loss": 0.2029,
+      "step": 302
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.578789442618176e-06,
+      "loss": 0.2089,
+      "step": 303
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.565661191317618e-06,
+      "loss": 0.2065,
+      "step": 304
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 608,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.7027813817943327e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-304/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f17f663326682e34d06194ed091725483adeebe21013fe1752885513b5506a8
+size 4411

checkpoint-608/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32002
+}

checkpoint-608/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "transformers_version": "4.34.1"
+}

checkpoint-608/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9283358f828e552d22cde3331bba60c448519fe00765841d28afef5bb46e83c
+size 14512135879

checkpoint-608/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d00e12428ee23606c20c0cb82491d564848080e13e6dc427e94e14700ee502d
+size 9886765428

checkpoint-608/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e0a4e903b17ca571e3d14a89e7bf7d4ed70334289ba4353fe58f9fd95789fd
+size 5121688491

checkpoint-608/pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 15008350208
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

checkpoint-608/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b79fdab1d04d2fef64e6cc48d12f3c84ce5b8c1a21bebdb7dbe2a42d800421e
+size 15607

checkpoint-608/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31694b994f0607cfe91452414877c57b870598c9a4bd9bae0760f822c13a1461
+size 15607

checkpoint-608/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2118335bc95c668e5c08172cad5e5298abff867f2c1dbf61efb10cdaf94b2750
+size 627

checkpoint-608/trainer_state.json

@@ -0,0 +1,3827 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9967159277504105,
+  "eval_steps": 31,
+  "global_step": 608,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.1498,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.1952733993530273,
+      "eval_runtime": 15.2597,
+      "eval_samples_per_second": 6.226,
+      "eval_steps_per_second": 1.573,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.176,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5e-06,
+      "loss": 1.1287,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.0172,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.5e-06,
+      "loss": 0.8997,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3e-06,
+      "loss": 0.8616,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.5e-06,
+      "loss": 0.7128,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6826,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.5e-06,
+      "loss": 0.5946,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-06,
+      "loss": 0.5616,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.999965501009142e-06,
+      "loss": 0.4778,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.999862004988709e-06,
+      "loss": 0.5264,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.999689514795112e-06,
+      "loss": 0.4518,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9994480351889364e-06,
+      "loss": 0.46,
+      "step": 14
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.999137572834828e-06,
+      "loss": 0.4111,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.998758136301295e-06,
+      "loss": 0.3646,
+      "step": 16
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.99830973606048e-06,
+      "loss": 0.4024,
+      "step": 17
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.997792384487867e-06,
+      "loss": 0.4042,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.997206095861944e-06,
+      "loss": 0.3659,
+      "step": 19
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.996550886363801e-06,
+      "loss": 0.3527,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.995826774076693e-06,
+      "loss": 0.3726,
+      "step": 21
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.995033778985534e-06,
+      "loss": 0.3551,
+      "step": 22
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.994171922976349e-06,
+      "loss": 0.382,
+      "step": 23
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.993241229835666e-06,
+      "loss": 0.3694,
+      "step": 24
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.992241725249866e-06,
+      "loss": 0.3603,
+      "step": 25
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.991173436804468e-06,
+      "loss": 0.3383,
+      "step": 26
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.990036393983372e-06,
+      "loss": 0.3455,
+      "step": 27
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9888306281680405e-06,
+      "loss": 0.3428,
+      "step": 28
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.987556172636637e-06,
+      "loss": 0.3001,
+      "step": 29
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.986213062563104e-06,
+      "loss": 0.307,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.984801335016198e-06,
+      "loss": 0.321,
+      "step": 31
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.3176000714302063,
+      "eval_runtime": 15.512,
+      "eval_samples_per_second": 6.124,
+      "eval_steps_per_second": 1.547,
+      "step": 31
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.9833210289584574e-06,
+      "loss": 0.2925,
+      "step": 32
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.981772185245135e-06,
+      "loss": 0.311,
+      "step": 33
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.980154846623067e-06,
+      "loss": 0.3066,
+      "step": 34
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.978469057729493e-06,
+      "loss": 0.2879,
+      "step": 35
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.976714865090827e-06,
+      "loss": 0.3001,
+      "step": 36
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.974892317121368e-06,
+      "loss": 0.3111,
+      "step": 37
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.97300146412197e-06,
+      "loss": 0.3067,
+      "step": 38
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.9710423582786485e-06,
+      "loss": 0.3091,
+      "step": 39
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.969015053661142e-06,
+      "loss": 0.302,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.966919606221423e-06,
+      "loss": 0.2991,
+      "step": 41
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.964756073792148e-06,
+      "loss": 0.3034,
+      "step": 42
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.9625245160850674e-06,
+      "loss": 0.2877,
+      "step": 43
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.960224994689371e-06,
+      "loss": 0.283,
+      "step": 44
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.957857573069992e-06,
+      "loss": 0.2993,
+      "step": 45
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.955422316565856e-06,
+      "loss": 0.2738,
+      "step": 46
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.952919292388079e-06,
+      "loss": 0.293,
+      "step": 47
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.950348569618105e-06,
+      "loss": 0.3053,
+      "step": 48
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.947710219205808e-06,
+      "loss": 0.2875,
+      "step": 49
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.9450043139675284e-06,
+      "loss": 0.2798,
+      "step": 50
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.9422309285840684e-06,
+      "loss": 0.3172,
+      "step": 51
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.939390139598623e-06,
+      "loss": 0.2713,
+      "step": 52
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.936482025414677e-06,
+      "loss": 0.2372,
+      "step": 53
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.933506666293834e-06,
+      "loss": 0.3125,
+      "step": 54
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.9304641443536015e-06,
+      "loss": 0.2687,
+      "step": 55
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.927354543565131e-06,
+      "loss": 0.2701,
+      "step": 56
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.924177949750893e-06,
+      "loss": 0.2681,
+      "step": 57
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.920934450582311e-06,
+      "loss": 0.2751,
+      "step": 58
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.917624135577346e-06,
+      "loss": 0.2902,
+      "step": 59
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.914247096098019e-06,
+      "loss": 0.2618,
+      "step": 60
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.910803425347892e-06,
+      "loss": 0.2569,
+      "step": 61
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.907293218369499e-06,
+      "loss": 0.2693,
+      "step": 62
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.27119407057762146,
+      "eval_runtime": 15.5684,
+      "eval_samples_per_second": 6.102,
+      "eval_steps_per_second": 1.542,
+      "step": 62
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.903716572041718e-06,
+      "loss": 0.2475,
+      "step": 63
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.9000735850771e-06,
+      "loss": 0.2492,
+      "step": 64
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.8963643580191446e-06,
+      "loss": 0.273,
+      "step": 65
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.8925889932395246e-06,
+      "loss": 0.2193,
+      "step": 66
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.888747594935259e-06,
+      "loss": 0.2637,
+      "step": 67
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.88484026912584e-06,
+      "loss": 0.3141,
+      "step": 68
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.880867123650306e-06,
+      "loss": 0.254,
+      "step": 69
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.876828268164264e-06,
+      "loss": 0.2778,
+      "step": 70
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.872723814136866e-06,
+      "loss": 0.2809,
+      "step": 71
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.868553874847728e-06,
+      "loss": 0.266,
+      "step": 72
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.864318565383809e-06,
+      "loss": 0.2174,
+      "step": 73
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.86001800263623e-06,
+      "loss": 0.2732,
+      "step": 74
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.855652305297052e-06,
+      "loss": 0.2507,
+      "step": 75
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.8512215938559955e-06,
+      "loss": 0.2514,
+      "step": 76
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.846725990597122e-06,
+      "loss": 0.268,
+      "step": 77
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.84216561959545e-06,
+      "loss": 0.228,
+      "step": 78
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.837540606713538e-06,
+      "loss": 0.2606,
+      "step": 79
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.832851079598007e-06,
+      "loss": 0.2554,
+      "step": 80
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.82809716767602e-06,
+      "loss": 0.257,
+      "step": 81
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.8232790021517094e-06,
+      "loss": 0.2475,
+      "step": 82
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.818396716002553e-06,
+      "loss": 0.2636,
+      "step": 83
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.813450443975705e-06,
+      "loss": 0.2076,
+      "step": 84
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.808440322584283e-06,
+      "loss": 0.2336,
+      "step": 85
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.803366490103593e-06,
+      "loss": 0.2664,
+      "step": 86
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.798229086567312e-06,
+      "loss": 0.2559,
+      "step": 87
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.793028253763633e-06,
+      "loss": 0.2687,
+      "step": 88
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.787764135231342e-06,
+      "loss": 0.2263,
+      "step": 89
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.7824368762558595e-06,
+      "loss": 0.2058,
+      "step": 90
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.7770466238652336e-06,
+      "loss": 0.246,
+      "step": 91
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.771593526826078e-06,
+      "loss": 0.2592,
+      "step": 92
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.76607773563947e-06,
+      "loss": 0.2701,
+      "step": 93
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.25227251648902893,
+      "eval_runtime": 15.5184,
+      "eval_samples_per_second": 6.122,
+      "eval_steps_per_second": 1.547,
+      "step": 93
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.760499402536792e-06,
+      "loss": 0.2154,
+      "step": 94
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.754858681475534e-06,
+      "loss": 0.2748,
+      "step": 95
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.7491557281350455e-06,
+      "loss": 0.2461,
+      "step": 96
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.743390699912232e-06,
+      "loss": 0.2245,
+      "step": 97
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.737563755917219e-06,
+      "loss": 0.2446,
+      "step": 98
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.731675056968958e-06,
+      "loss": 0.2563,
+      "step": 99
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.7257247655907854e-06,
+      "loss": 0.2512,
+      "step": 100
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.7197130460059385e-06,
+      "loss": 0.2613,
+      "step": 101
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.7136400641330245e-06,
+      "loss": 0.2294,
+      "step": 102
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.7075059875814424e-06,
+      "loss": 0.2162,
+      "step": 103
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.70131098564675e-06,
+      "loss": 0.251,
+      "step": 104
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.695055229306001e-06,
+      "loss": 0.2468,
+      "step": 105
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.6887388912130206e-06,
+      "loss": 0.2467,
+      "step": 106
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.68236214569364e-06,
+      "loss": 0.2588,
+      "step": 107
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.675925168740887e-06,
+      "loss": 0.2592,
+      "step": 108
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.6694281380101304e-06,
+      "loss": 0.2225,
+      "step": 109
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.662871232814171e-06,
+      "loss": 0.2411,
+      "step": 110
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.656254634118301e-06,
+      "loss": 0.2512,
+      "step": 111
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.649578524535302e-06,
+      "loss": 0.2252,
+      "step": 112
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.642843088320408e-06,
+      "loss": 0.2288,
+      "step": 113
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.636048511366222e-06,
+      "loss": 0.2339,
+      "step": 114
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.6291949811975814e-06,
+      "loss": 0.2252,
+      "step": 115
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.622282686966387e-06,
+      "loss": 0.2497,
+      "step": 116
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.615311819446379e-06,
+      "loss": 0.2339,
+      "step": 117
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.6082825710278724e-06,
+      "loss": 0.2946,
+      "step": 118
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.60119513571245e-06,
+      "loss": 0.2797,
+      "step": 119
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.594049709107604e-06,
+      "loss": 0.272,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.58684648842134e-06,
+      "loss": 0.2437,
+      "step": 121
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.5795856724567344e-06,
+      "loss": 0.2328,
+      "step": 122
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.572267461606446e-06,
+      "loss": 0.2333,
+      "step": 123
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.564892057847184e-06,
+      "loss": 0.27,
+      "step": 124
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.2362014800310135,
+      "eval_runtime": 15.5362,
+      "eval_samples_per_second": 6.115,
+      "eval_steps_per_second": 1.545,
+      "step": 124
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.5574596647341414e-06,
+      "loss": 0.2202,
+      "step": 125
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.549970487395365e-06,
+      "loss": 0.2129,
+      "step": 126
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.542424732526105e-06,
+      "loss": 0.2343,
+      "step": 127
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.534822608383104e-06,
+      "loss": 0.2527,
+      "step": 128
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.5271643247788496e-06,
+      "loss": 0.2622,
+      "step": 129
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.519450093075787e-06,
+      "loss": 0.247,
+      "step": 130
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.5116801261804846e-06,
+      "loss": 0.2612,
+      "step": 131
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.503854638537756e-06,
+      "loss": 0.2515,
+      "step": 132
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.49597384612474e-06,
+      "loss": 0.2164,
+      "step": 133
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.488037966444948e-06,
+      "loss": 0.2545,
+      "step": 134
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.48004721852225e-06,
+      "loss": 0.2547,
+      "step": 135
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.472001822894839e-06,
+      "loss": 0.1869,
+      "step": 136
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.463902001609139e-06,
+      "loss": 0.2383,
+      "step": 137
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.455747978213679e-06,
+      "loss": 0.2234,
+      "step": 138
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.44753997775292e-06,
+      "loss": 0.2356,
+      "step": 139
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.43927822676105e-06,
+      "loss": 0.232,
+      "step": 140
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.430962953255725e-06,
+      "loss": 0.2352,
+      "step": 141
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.4225943867317835e-06,
+      "loss": 0.2199,
+      "step": 142
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.4141727581549025e-06,
+      "loss": 0.2175,
+      "step": 143
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.405698299955234e-06,
+      "loss": 0.221,
+      "step": 144
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.39717124602098e-06,
+      "loss": 0.2522,
+      "step": 145
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.388591831691948e-06,
+      "loss": 0.2412,
+      "step": 146
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.3799602937530464e-06,
+      "loss": 0.2176,
+      "step": 147
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.3712768704277535e-06,
+      "loss": 0.2242,
+      "step": 148
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.362541801371542e-06,
+      "loss": 0.2156,
+      "step": 149
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.353755327665268e-06,
+      "loss": 0.2077,
+      "step": 150
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.344917691808511e-06,
+      "loss": 0.2285,
+      "step": 151
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.3360291377128864e-06,
+      "loss": 0.2364,
+      "step": 152
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.32708991069531e-06,
+      "loss": 0.2577,
+      "step": 153
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.318100257471233e-06,
+      "loss": 0.2347,
+      "step": 154
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.309060426147826e-06,
+      "loss": 0.2244,
+      "step": 155
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.22840476036071777,
+      "eval_runtime": 15.5442,
+      "eval_samples_per_second": 6.112,
+      "eval_steps_per_second": 1.544,
+      "step": 155
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.299970666217135e-06,
+      "loss": 0.2197,
+      "step": 156
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.290831228549196e-06,
+      "loss": 0.2618,
+      "step": 157
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.281642365385111e-06,
+      "loss": 0.2498,
+      "step": 158
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.272404330330084e-06,
+      "loss": 0.2309,
+      "step": 159
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.263117378346425e-06,
+      "loss": 0.2163,
+      "step": 160
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.253781765746511e-06,
+      "loss": 0.1968,
+      "step": 161
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.244397750185714e-06,
+      "loss": 0.2127,
+      "step": 162
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.234965590655287e-06,
+      "loss": 0.2088,
+      "step": 163
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.225485547475217e-06,
+      "loss": 0.2082,
+      "step": 164
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.215957882287044e-06,
+      "loss": 0.2549,
+      "step": 165
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.206382858046636e-06,
+      "loss": 0.2131,
+      "step": 166
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.19676073901693e-06,
+      "loss": 0.2048,
+      "step": 167
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.187091790760644e-06,
+      "loss": 0.2451,
+      "step": 168
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.177376280132946e-06,
+      "loss": 0.1896,
+      "step": 169
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.167614475274082e-06,
+      "loss": 0.2253,
+      "step": 170
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.1578066456019885e-06,
+      "loss": 0.2167,
+      "step": 171
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.147953061804845e-06,
+      "loss": 0.2262,
+      "step": 172
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.1380539958336095e-06,
+      "loss": 0.2483,
+      "step": 173
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.128109720894512e-06,
+      "loss": 0.2824,
+      "step": 174
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.118120511441512e-06,
+      "loss": 0.2273,
+      "step": 175
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.108086643168724e-06,
+      "loss": 0.2177,
+      "step": 176
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.098008393002816e-06,
+      "loss": 0.2147,
+      "step": 177
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.087886039095353e-06,
+      "loss": 0.1915,
+      "step": 178
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.077719860815132e-06,
+      "loss": 0.2123,
+      "step": 179
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.067510138740467e-06,
+      "loss": 0.2418,
+      "step": 180
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.057257154651444e-06,
+      "loss": 0.2055,
+      "step": 181
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.046961191522147e-06,
+      "loss": 0.2098,
+      "step": 182
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.036622533512845e-06,
+      "loss": 0.2304,
+      "step": 183
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.026241465962154e-06,
+      "loss": 0.2018,
+      "step": 184
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.0158182753791566e-06,
+      "loss": 0.2009,
+      "step": 185
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.0053532494354985e-06,
+      "loss": 0.2227,
+      "step": 186
+    },
+    {
+      "epoch": 0.61,
+      "eval_loss": 0.2260431945323944,
+      "eval_runtime": 15.5286,
+      "eval_samples_per_second": 6.118,
+      "eval_steps_per_second": 1.546,
+      "step": 186
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.994846676957448e-06,
+      "loss": 0.1973,
+      "step": 187
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.984298847917923e-06,
+      "loss": 0.2192,
+      "step": 188
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.973710053428487e-06,
+      "loss": 0.2016,
+      "step": 189
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.963080585731324e-06,
+      "loss": 0.2118,
+      "step": 190
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.952410738191158e-06,
+      "loss": 0.2361,
+      "step": 191
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.941700805287169e-06,
+      "loss": 0.2132,
+      "step": 192
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.9309510826048556e-06,
+      "loss": 0.2117,
+      "step": 193
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.92016186682789e-06,
+      "loss": 0.2196,
+      "step": 194
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.909333455729914e-06,
+      "loss": 0.1958,
+      "step": 195
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.898466148166333e-06,
+      "loss": 0.2318,
+      "step": 196
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.8875602440660635e-06,
+      "loss": 0.2034,
+      "step": 197
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.876616044423253e-06,
+      "loss": 0.2119,
+      "step": 198
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.865633851288975e-06,
+      "loss": 0.2177,
+      "step": 199
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.854613967762898e-06,
+      "loss": 0.1974,
+      "step": 200
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.843556697984907e-06,
+      "loss": 0.1902,
+      "step": 201
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.832462347126722e-06,
+      "loss": 0.1975,
+      "step": 202
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.821331221383471e-06,
+      "loss": 0.2083,
+      "step": 203
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.8101636279652375e-06,
+      "loss": 0.2247,
+      "step": 204
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.798959875088584e-06,
+      "loss": 0.2169,
+      "step": 205
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.787720271968046e-06,
+      "loss": 0.1854,
+      "step": 206
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.7764451288075944e-06,
+      "loss": 0.2269,
+      "step": 207
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.765134756792079e-06,
+      "loss": 0.1946,
+      "step": 208
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.753789468078636e-06,
+      "loss": 0.1944,
+      "step": 209
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.742409575788074e-06,
+      "loss": 0.2057,
+      "step": 210
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.730995393996234e-06,
+      "loss": 0.2427,
+      "step": 211
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.719547237725319e-06,
+      "loss": 0.227,
+      "step": 212
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.708065422935198e-06,
+      "loss": 0.2152,
+      "step": 213
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.6965502665146916e-06,
+      "loss": 0.2177,
+      "step": 214
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.6850020862728196e-06,
+      "loss": 0.2089,
+      "step": 215
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.6734212009300346e-06,
+      "loss": 0.2081,
+      "step": 216
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.661807930109422e-06,
+      "loss": 0.2167,
+      "step": 217
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 0.21709737181663513,
+      "eval_runtime": 15.5146,
+      "eval_samples_per_second": 6.123,
+      "eval_steps_per_second": 1.547,
+      "step": 217
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.650162594327881e-06,
+      "loss": 0.2135,
+      "step": 218
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.6384855149872776e-06,
+      "loss": 0.1976,
+      "step": 219
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.6267770143655743e-06,
+      "loss": 0.2073,
+      "step": 220
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.615037415607937e-06,
+      "loss": 0.2252,
+      "step": 221
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.603267042717813e-06,
+      "loss": 0.2296,
+      "step": 222
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5914662205479923e-06,
+      "loss": 0.181,
+      "step": 223
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.579635274791639e-06,
+      "loss": 0.2196,
+      "step": 224
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.567774531973305e-06,
+      "loss": 0.2063,
+      "step": 225
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.555884319439917e-06,
+      "loss": 0.2313,
+      "step": 226
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.5439649653517416e-06,
+      "loss": 0.1994,
+      "step": 227
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.532016798673329e-06,
+      "loss": 0.2143,
+      "step": 228
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.5200401491644333e-06,
+      "loss": 0.2118,
+      "step": 229
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.508035347370912e-06,
+      "loss": 0.2081,
+      "step": 230
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.4960027246156043e-06,
+      "loss": 0.2313,
+      "step": 231
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.483942612989183e-06,
+      "loss": 0.2071,
+      "step": 232
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.471855345340992e-06,
+      "loss": 0.2199,
+      "step": 233
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.4597412552698617e-06,
+      "loss": 0.1879,
+      "step": 234
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.447600677114898e-06,
+      "loss": 0.1717,
+      "step": 235
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.4354339459462556e-06,
+      "loss": 0.2273,
+      "step": 236
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.423241397555893e-06,
+      "loss": 0.2351,
+      "step": 237
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.4110233684483033e-06,
+      "loss": 0.2165,
+      "step": 238
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.3987801958312254e-06,
+      "loss": 0.2309,
+      "step": 239
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.386512217606339e-06,
+      "loss": 0.2023,
+      "step": 240
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.3742197723599403e-06,
+      "loss": 0.2189,
+      "step": 241
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.361903199353593e-06,
+      "loss": 0.205,
+      "step": 242
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.349562838514769e-06,
+      "loss": 0.1912,
+      "step": 243
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.3371990304274654e-06,
+      "loss": 0.1898,
+      "step": 244
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.3248121163228037e-06,
+      "loss": 0.2037,
+      "step": 245
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.3124024380696134e-06,
+      "loss": 0.1959,
+      "step": 246
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.299970338164995e-06,
+      "loss": 0.1972,
+      "step": 247
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.28751615972487e-06,
+      "loss": 0.2098,
+      "step": 248
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 0.20815877616405487,
+      "eval_runtime": 15.5231,
+      "eval_samples_per_second": 6.12,
+      "eval_steps_per_second": 1.546,
+      "step": 248
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.2750402464745084e-06,
+      "loss": 0.2322,
+      "step": 249
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.262542942739044e-06,
+      "loss": 0.1977,
+      "step": 250
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.2500245934339714e-06,
+      "loss": 0.1983,
+      "step": 251
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.2374855440556242e-06,
+      "loss": 0.1857,
+      "step": 252
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.224926140671643e-06,
+      "loss": 0.183,
+      "step": 253
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.2123467299114216e-06,
+      "loss": 0.2216,
+      "step": 254
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.199747658956541e-06,
+      "loss": 0.1808,
+      "step": 255
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.1871292755311887e-06,
+      "loss": 0.2278,
+      "step": 256
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.174491927892561e-06,
+      "loss": 0.203,
+      "step": 257
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.1618359648212492e-06,
+      "loss": 0.2209,
+      "step": 258
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.1491617356116167e-06,
+      "loss": 0.2131,
+      "step": 259
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.136469590062158e-06,
+      "loss": 0.2111,
+      "step": 260
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.1237598784658444e-06,
+      "loss": 0.1915,
+      "step": 261
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.1110329516004546e-06,
+      "loss": 0.2272,
+      "step": 262
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.0982891607188948e-06,
+      "loss": 0.1784,
+      "step": 263
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.085528857539506e-06,
+      "loss": 0.2064,
+      "step": 264
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.0727523942363547e-06,
+      "loss": 0.1857,
+      "step": 265
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.0599601234295124e-06,
+      "loss": 0.1981,
+      "step": 266
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.0471523981753266e-06,
+      "loss": 0.2429,
+      "step": 267
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.0343295719566747e-06,
+      "loss": 0.1755,
+      "step": 268
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.0214919986732076e-06,
+      "loss": 0.2024,
+      "step": 269
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.0086400326315853e-06,
+      "loss": 0.1859,
+      "step": 270
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.9957740285356933e-06,
+      "loss": 0.2056,
+      "step": 271
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.9828943414768583e-06,
+      "loss": 0.2183,
+      "step": 272
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.9700013269240463e-06,
+      "loss": 0.1892,
+      "step": 273
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.957095340714049e-06,
+      "loss": 0.2139,
+      "step": 274
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.9441767390416665e-06,
+      "loss": 0.2314,
+      "step": 275
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.9312458784498763e-06,
+      "loss": 0.1897,
+      "step": 276
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.918303115819992e-06,
+      "loss": 0.1698,
+      "step": 277
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.9053488083618118e-06,
+      "loss": 0.2147,
+      "step": 278
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.892383313603765e-06,
+      "loss": 0.1842,
+      "step": 279
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 0.20471937954425812,
+      "eval_runtime": 15.5241,
+      "eval_samples_per_second": 6.12,
+      "eval_steps_per_second": 1.546,
+      "step": 279
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8794069893830386e-06,
+      "loss": 0.178,
+      "step": 280
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8664201938357052e-06,
+      "loss": 0.2245,
+      "step": 281
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.8534232853868384e-06,
+      "loss": 0.1583,
+      "step": 282
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.840416622740617e-06,
+      "loss": 0.1752,
+      "step": 283
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.8274005648704316e-06,
+      "loss": 0.1981,
+      "step": 284
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8143754710089694e-06,
+      "loss": 0.2216,
+      "step": 285
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8013417006383078e-06,
+      "loss": 0.2075,
+      "step": 286
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.7882996134799854e-06,
+      "loss": 0.1978,
+      "step": 287
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.775249569485079e-06,
+      "loss": 0.2302,
+      "step": 288
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.762191928824267e-06,
+      "loss": 0.2218,
+      "step": 289
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.7491270518778913e-06,
+      "loss": 0.2033,
+      "step": 290
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.736055299226007e-06,
+      "loss": 0.2055,
+      "step": 291
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.722977031638435e-06,
+      "loss": 0.2231,
+      "step": 292
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.709892610064801e-06,
+      "loss": 0.2233,
+      "step": 293
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.696802395624579e-06,
+      "loss": 0.2354,
+      "step": 294
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.683706749597118e-06,
+      "loss": 0.2136,
+      "step": 295
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.670606033411678e-06,
+      "loss": 0.181,
+      "step": 296
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.657500608637448e-06,
+      "loss": 0.2051,
+      "step": 297
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.6443908369735715e-06,
+      "loss": 0.209,
+      "step": 298
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.631277080239163e-06,
+      "loss": 0.2184,
+      "step": 299
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.6181597003633218e-06,
+      "loss": 0.1988,
+      "step": 300
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.605039059375143e-06,
+      "loss": 0.2223,
+      "step": 301
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.5919155193937244e-06,
+      "loss": 0.2029,
+      "step": 302
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.578789442618176e-06,
+      "loss": 0.2089,
+      "step": 303
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.565661191317618e-06,
+      "loss": 0.2065,
+      "step": 304
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5525311278211888e-06,
+      "loss": 0.1977,
+      "step": 305
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5393996145080413e-06,
+      "loss": 0.1748,
+      "step": 306
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.5262670137973413e-06,
+      "loss": 0.2128,
+      "step": 307
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.5131336881382658e-06,
+      "loss": 0.1876,
+      "step": 308
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.5e-06,
+      "loss": 0.1947,
+      "step": 309
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.4868663118617355e-06,
+      "loss": 0.1917,
+      "step": 310
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 0.2012825459241867,
+      "eval_runtime": 15.4963,
+      "eval_samples_per_second": 6.131,
+      "eval_steps_per_second": 1.549,
+      "step": 310
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.47373298620266e-06,
+      "loss": 0.1904,
+      "step": 311
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.4606003854919595e-06,
+      "loss": 0.1792,
+      "step": 312
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.4474688721788116e-06,
+      "loss": 0.1886,
+      "step": 313
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.4343388086823828e-06,
+      "loss": 0.201,
+      "step": 314
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.421210557381825e-06,
+      "loss": 0.1776,
+      "step": 315
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.4080844806062764e-06,
+      "loss": 0.1957,
+      "step": 316
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.3949609406248576e-06,
+      "loss": 0.1744,
+      "step": 317
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.3818402996366786e-06,
+      "loss": 0.2017,
+      "step": 318
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.3687229197608373e-06,
+      "loss": 0.1586,
+      "step": 319
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.3556091630264294e-06,
+      "loss": 0.1481,
+      "step": 320
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.3424993913625534e-06,
+      "loss": 0.1696,
+      "step": 321
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.3293939665883233e-06,
+      "loss": 0.1974,
+      "step": 322
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.3162932504028828e-06,
+      "loss": 0.1698,
+      "step": 323
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.303197604375422e-06,
+      "loss": 0.184,
+      "step": 324
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.2901073899351997e-06,
+      "loss": 0.1806,
+      "step": 325
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.277022968361566e-06,
+      "loss": 0.1741,
+      "step": 326
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.2639447007739933e-06,
+      "loss": 0.1906,
+      "step": 327
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.2508729481221096e-06,
+      "loss": 0.19,
+      "step": 328
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.2378080711757332e-06,
+      "loss": 0.1954,
+      "step": 329
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.2247504305149217e-06,
+      "loss": 0.1755,
+      "step": 330
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.2117003865200154e-06,
+      "loss": 0.1932,
+      "step": 331
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.1986582993616926e-06,
+      "loss": 0.1795,
+      "step": 332
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.185624528991031e-06,
+      "loss": 0.1586,
+      "step": 333
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.1725994351295697e-06,
+      "loss": 0.1746,
+      "step": 334
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.159583377259384e-06,
+      "loss": 0.1744,
+      "step": 335
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.1465767146131633e-06,
+      "loss": 0.1553,
+      "step": 336
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.1335798061642956e-06,
+      "loss": 0.1589,
+      "step": 337
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.1205930106169626e-06,
+      "loss": 0.1624,
+      "step": 338
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.1076166863962358e-06,
+      "loss": 0.1823,
+      "step": 339
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.094651191638189e-06,
+      "loss": 0.1658,
+      "step": 340
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.0816968841800094e-06,
+      "loss": 0.1639,
+      "step": 341
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 0.19820626080036163,
+      "eval_runtime": 15.5045,
+      "eval_samples_per_second": 6.127,
+      "eval_steps_per_second": 1.548,
+      "step": 341
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.0687541215501245e-06,
+      "loss": 0.1776,
+      "step": 342
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.0558232609583343e-06,
+      "loss": 0.1674,
+      "step": 343
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.0429046592859524e-06,
+      "loss": 0.2104,
+      "step": 344
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.0299986730759553e-06,
+      "loss": 0.1598,
+      "step": 345
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.0171056585231425e-06,
+      "loss": 0.1741,
+      "step": 346
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.004225971464308e-06,
+      "loss": 0.1508,
+      "step": 347
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.991359967368416e-06,
+      "loss": 0.1735,
+      "step": 348
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.9785080013267933e-06,
+      "loss": 0.1834,
+      "step": 349
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.965670428043326e-06,
+      "loss": 0.1538,
+      "step": 350
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.952847601824674e-06,
+      "loss": 0.1905,
+      "step": 351
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.940039876570489e-06,
+      "loss": 0.1745,
+      "step": 352
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.927247605763647e-06,
+      "loss": 0.1847,
+      "step": 353
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.914471142460495e-06,
+      "loss": 0.1672,
+      "step": 354
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.9017108392811065e-06,
+      "loss": 0.1881,
+      "step": 355
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.888967048399547e-06,
+      "loss": 0.1712,
+      "step": 356
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.8762401215341569e-06,
+      "loss": 0.1437,
+      "step": 357
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.8635304099378426e-06,
+      "loss": 0.1589,
+      "step": 358
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.8508382643883837e-06,
+      "loss": 0.192,
+      "step": 359
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.8381640351787516e-06,
+      "loss": 0.1691,
+      "step": 360
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.8255080721074391e-06,
+      "loss": 0.15,
+      "step": 361
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.8128707244688109e-06,
+      "loss": 0.166,
+      "step": 362
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.800252341043459e-06,
+      "loss": 0.1661,
+      "step": 363
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.7876532700885788e-06,
+      "loss": 0.192,
+      "step": 364
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.7750738593283573e-06,
+      "loss": 0.1597,
+      "step": 365
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.7625144559443758e-06,
+      "loss": 0.1562,
+      "step": 366
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.7499754065660288e-06,
+      "loss": 0.1527,
+      "step": 367
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.7374570572609559e-06,
+      "loss": 0.1631,
+      "step": 368
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.7249597535254916e-06,
+      "loss": 0.1552,
+      "step": 369
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.7124838402751304e-06,
+      "loss": 0.1469,
+      "step": 370
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.7000296618350054e-06,
+      "loss": 0.1476,
+      "step": 371
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.6875975619303872e-06,
+      "loss": 0.1835,
+      "step": 372
+    },
+    {
+      "epoch": 1.22,
+      "eval_loss": 0.19680581986904144,
+      "eval_runtime": 15.5171,
+      "eval_samples_per_second": 6.122,
+      "eval_steps_per_second": 1.547,
+      "step": 372
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.6751878836771965e-06,
+      "loss": 0.177,
+      "step": 373
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.6628009695725348e-06,
+      "loss": 0.1641,
+      "step": 374
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.650437161485231e-06,
+      "loss": 0.1827,
+      "step": 375
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.6380968006464073e-06,
+      "loss": 0.1648,
+      "step": 376
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.6257802276400604e-06,
+      "loss": 0.152,
+      "step": 377
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.613487782393661e-06,
+      "loss": 0.157,
+      "step": 378
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.6012198041687748e-06,
+      "loss": 0.166,
+      "step": 379
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.588976631551697e-06,
+      "loss": 0.1634,
+      "step": 380
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.5767586024441066e-06,
+      "loss": 0.1697,
+      "step": 381
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.5645660540537444e-06,
+      "loss": 0.157,
+      "step": 382
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.552399322885103e-06,
+      "loss": 0.1533,
+      "step": 383
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.5402587447301387e-06,
+      "loss": 0.1762,
+      "step": 384
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.5281446546590084e-06,
+      "loss": 0.1389,
+      "step": 385
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.516057387010818e-06,
+      "loss": 0.1616,
+      "step": 386
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.5039972753843966e-06,
+      "loss": 0.1534,
+      "step": 387
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.4919646526290884e-06,
+      "loss": 0.1617,
+      "step": 388
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.4799598508355678e-06,
+      "loss": 0.1318,
+      "step": 389
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.4679832013266721e-06,
+      "loss": 0.1536,
+      "step": 390
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.4560350346482599e-06,
+      "loss": 0.1957,
+      "step": 391
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.4441156805600842e-06,
+      "loss": 0.1608,
+      "step": 392
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.4322254680266962e-06,
+      "loss": 0.1706,
+      "step": 393
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.4203647252083619e-06,
+      "loss": 0.1256,
+      "step": 394
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.4085337794520087e-06,
+      "loss": 0.1561,
+      "step": 395
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.3967329572821875e-06,
+      "loss": 0.1634,
+      "step": 396
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.3849625843920633e-06,
+      "loss": 0.1753,
+      "step": 397
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3732229856344259e-06,
+      "loss": 0.1589,
+      "step": 398
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3615144850127232e-06,
+      "loss": 0.1764,
+      "step": 399
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3498374056721198e-06,
+      "loss": 0.1534,
+      "step": 400
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.3381920698905788e-06,
+      "loss": 0.159,
+      "step": 401
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.326578799069966e-06,
+      "loss": 0.152,
+      "step": 402
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.3149979137271806e-06,
+      "loss": 0.1666,
+      "step": 403
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.19529137015342712,
+      "eval_runtime": 15.5082,
+      "eval_samples_per_second": 6.126,
+      "eval_steps_per_second": 1.548,
+      "step": 403
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.3034497334853092e-06,
+      "loss": 0.1778,
+      "step": 404
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2919345770648023e-06,
+      "loss": 0.1733,
+      "step": 405
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.280452762274682e-06,
+      "loss": 0.1577,
+      "step": 406
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2690046060037661e-06,
+      "loss": 0.1548,
+      "step": 407
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2575904242119264e-06,
+      "loss": 0.1437,
+      "step": 408
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2462105319213643e-06,
+      "loss": 0.1652,
+      "step": 409
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.234865243207921e-06,
+      "loss": 0.167,
+      "step": 410
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2235548711924056e-06,
+      "loss": 0.1693,
+      "step": 411
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2122797280319543e-06,
+      "loss": 0.1714,
+      "step": 412
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2010401249114166e-06,
+      "loss": 0.1752,
+      "step": 413
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.1898363720347635e-06,
+      "loss": 0.1439,
+      "step": 414
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.1786687786165302e-06,
+      "loss": 0.1663,
+      "step": 415
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.167537652873279e-06,
+      "loss": 0.1644,
+      "step": 416
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1564433020150946e-06,
+      "loss": 0.1385,
+      "step": 417
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1453860322371032e-06,
+      "loss": 0.1617,
+      "step": 418
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.134366148711025e-06,
+      "loss": 0.1725,
+      "step": 419
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1233839555767482e-06,
+      "loss": 0.1487,
+      "step": 420
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1124397559339373e-06,
+      "loss": 0.1636,
+      "step": 421
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1015338518336672e-06,
+      "loss": 0.1607,
+      "step": 422
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.0906665442700868e-06,
+      "loss": 0.2252,
+      "step": 423
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.079838133172111e-06,
+      "loss": 0.1901,
+      "step": 424
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.0690489173951446e-06,
+      "loss": 0.1576,
+      "step": 425
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.0582991947128324e-06,
+      "loss": 0.1734,
+      "step": 426
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.0475892618088426e-06,
+      "loss": 0.1654,
+      "step": 427
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.0369194142686766e-06,
+      "loss": 0.1608,
+      "step": 428
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.0262899465715128e-06,
+      "loss": 0.18,
+      "step": 429
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.0157011520820784e-06,
+      "loss": 0.1379,
+      "step": 430
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.0051533230425527e-06,
+      "loss": 0.1584,
+      "step": 431
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 9.946467505645019e-07,
+      "loss": 0.1488,
+      "step": 432
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 9.84181724620844e-07,
+      "loss": 0.1863,
+      "step": 433
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 9.73758534037847e-07,
+      "loss": 0.1694,
+      "step": 434
+    },
+    {
+      "epoch": 1.43,
+      "eval_loss": 0.19318194687366486,
+      "eval_runtime": 15.505,
+      "eval_samples_per_second": 6.127,
+      "eval_steps_per_second": 1.548,
+      "step": 434
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 9.633774664871557e-07,
+      "loss": 0.1826,
+      "step": 435
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 9.530388084778541e-07,
+      "loss": 0.1892,
+      "step": 436
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.427428453485573e-07,
+      "loss": 0.1377,
+      "step": 437
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.32489861259534e-07,
+      "loss": 0.1576,
+      "step": 438
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.222801391848688e-07,
+      "loss": 0.1988,
+      "step": 439
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.121139609046484e-07,
+      "loss": 0.1426,
+      "step": 440
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 9.019916069971857e-07,
+      "loss": 0.1467,
+      "step": 441
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 8.919133568312768e-07,
+      "loss": 0.1558,
+      "step": 442
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 8.818794885584902e-07,
+      "loss": 0.1593,
+      "step": 443
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 8.718902791054895e-07,
+      "loss": 0.1443,
+      "step": 444
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 8.619460041663915e-07,
+      "loss": 0.1779,
+      "step": 445
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 8.52046938195156e-07,
+      "loss": 0.1454,
+      "step": 446
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.421933543980126e-07,
+      "loss": 0.1607,
+      "step": 447
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.323855247259185e-07,
+      "loss": 0.1558,
+      "step": 448
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.226237198670556e-07,
+      "loss": 0.1748,
+      "step": 449
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 8.129082092393562e-07,
+      "loss": 0.1754,
+      "step": 450
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 8.032392609830708e-07,
+      "loss": 0.1418,
+      "step": 451
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 7.936171419533653e-07,
+      "loss": 0.1553,
+      "step": 452
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.840421177129564e-07,
+      "loss": 0.1576,
+      "step": 453
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.745144525247839e-07,
+      "loss": 0.1405,
+      "step": 454
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.650344093447145e-07,
+      "loss": 0.1495,
+      "step": 455
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.55602249814287e-07,
+      "loss": 0.1631,
+      "step": 456
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.462182342534896e-07,
+      "loss": 0.1728,
+      "step": 457
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.368826216535758e-07,
+      "loss": 0.1756,
+      "step": 458
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.275956696699169e-07,
+      "loss": 0.164,
+      "step": 459
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.183576346148899e-07,
+      "loss": 0.1417,
+      "step": 460
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.091687714508044e-07,
+      "loss": 0.1871,
+      "step": 461
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.000293337828656e-07,
+      "loss": 0.1651,
+      "step": 462
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 6.909395738521745e-07,
+      "loss": 0.1705,
+      "step": 463
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 6.818997425287671e-07,
+      "loss": 0.1633,
+      "step": 464
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 6.729100893046897e-07,
+      "loss": 0.1461,
+      "step": 465
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 0.19294388592243195,
+      "eval_runtime": 15.5273,
+      "eval_samples_per_second": 6.118,
+      "eval_steps_per_second": 1.546,
+      "step": 465
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 6.639708622871144e-07,
+      "loss": 0.1411,
+      "step": 466
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 6.550823081914892e-07,
+      "loss": 0.1586,
+      "step": 467
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.462446723347324e-07,
+      "loss": 0.1364,
+      "step": 468
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.374581986284578e-07,
+      "loss": 0.1651,
+      "step": 469
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.28723129572247e-07,
+      "loss": 0.1633,
+      "step": 470
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.200397062469541e-07,
+      "loss": 0.1462,
+      "step": 471
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.11408168308052e-07,
+      "loss": 0.1466,
+      "step": 472
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 6.0282875397902e-07,
+      "loss": 0.1469,
+      "step": 473
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 5.943017000447671e-07,
+      "loss": 0.1357,
+      "step": 474
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 5.858272418450978e-07,
+      "loss": 0.1592,
+      "step": 475
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 5.774056132682168e-07,
+      "loss": 0.1649,
+      "step": 476
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 5.690370467442743e-07,
+      "loss": 0.1612,
+      "step": 477
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 5.607217732389503e-07,
+      "loss": 0.1916,
+      "step": 478
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 5.5246002224708e-07,
+      "loss": 0.2088,
+      "step": 479
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.442520217863215e-07,
+      "loss": 0.1536,
+      "step": 480
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.360979983908615e-07,
+      "loss": 0.152,
+      "step": 481
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.279981771051615e-07,
+      "loss": 0.1389,
+      "step": 482
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5.199527814777509e-07,
+      "loss": 0.1164,
+      "step": 483
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5.119620335550532e-07,
+      "loss": 0.1821,
+      "step": 484
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 5.040261538752606e-07,
+      "loss": 0.1525,
+      "step": 485
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.961453614622453e-07,
+      "loss": 0.1384,
+      "step": 486
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.883198738195157e-07,
+      "loss": 0.1791,
+      "step": 487
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.805499069242131e-07,
+      "loss": 0.1391,
+      "step": 488
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.72835675221151e-07,
+      "loss": 0.1324,
+      "step": 489
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.651773916168967e-07,
+      "loss": 0.1548,
+      "step": 490
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.5757526747389506e-07,
+      "loss": 0.1615,
+      "step": 491
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.5002951260463503e-07,
+      "loss": 0.1391,
+      "step": 492
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.4254033526585917e-07,
+      "loss": 0.1596,
+      "step": 493
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.3510794215281595e-07,
+      "loss": 0.1344,
+      "step": 494
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.277325383935549e-07,
+      "loss": 0.1831,
+      "step": 495
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.2041432754326593e-07,
+      "loss": 0.1535,
+      "step": 496
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": 0.1927250325679779,
+      "eval_runtime": 15.5004,
+      "eval_samples_per_second": 6.129,
+      "eval_steps_per_second": 1.548,
+      "step": 496
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.1315351157866003e-07,
+      "loss": 0.1262,
+      "step": 497
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.059502908923962e-07,
+      "loss": 0.1685,
+      "step": 498
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.988048642875503e-07,
+      "loss": 0.1435,
+      "step": 499
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.917174289721276e-07,
+      "loss": 0.1423,
+      "step": 500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.8468818055362153e-07,
+      "loss": 0.1434,
+      "step": 501
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.7771731303361314e-07,
+      "loss": 0.1656,
+      "step": 502
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.708050188024187e-07,
+      "loss": 0.1553,
+      "step": 503
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.639514886337786e-07,
+      "loss": 0.1503,
+      "step": 504
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.571569116795928e-07,
+      "loss": 0.1227,
+      "step": 505
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.5042147546469894e-07,
+      "loss": 0.1365,
+      "step": 506
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.437453658816994e-07,
+      "loss": 0.1508,
+      "step": 507
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.371287671858292e-07,
+      "loss": 0.1571,
+      "step": 508
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.3057186198987066e-07,
+      "loss": 0.1518,
+      "step": 509
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.2407483125911354e-07,
+      "loss": 0.1502,
+      "step": 510
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.1763785430636073e-07,
+      "loss": 0.1273,
+      "step": 511
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.112611087869799e-07,
+      "loss": 0.1738,
+      "step": 512
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.04944770693999e-07,
+      "loss": 0.143,
+      "step": 513
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.9868901435325033e-07,
+      "loss": 0.1424,
+      "step": 514
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.924940124185585e-07,
+      "loss": 0.1749,
+      "step": 515
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.8635993586697555e-07,
+      "loss": 0.1547,
+      "step": 516
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.80286953994062e-07,
+      "loss": 0.1725,
+      "step": 517
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.7427523440921534e-07,
+      "loss": 0.1373,
+      "step": 518
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.6832494303104195e-07,
+      "loss": 0.1434,
+      "step": 519
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.62436244082781e-07,
+      "loss": 0.147,
+      "step": 520
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.566093000877687e-07,
+      "loss": 0.1673,
+      "step": 521
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.5084427186495566e-07,
+      "loss": 0.1618,
+      "step": 522
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.451413185244661e-07,
+      "loss": 0.1618,
+      "step": 523
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.3950059746320864e-07,
+      "loss": 0.1507,
+      "step": 524
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.3392226436053073e-07,
+      "loss": 0.1582,
+      "step": 525
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.2840647317392218e-07,
+      "loss": 0.1691,
+      "step": 526
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.2295337613476714e-07,
+      "loss": 0.1419,
+      "step": 527
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 0.1925160139799118,
+      "eval_runtime": 15.4967,
+      "eval_samples_per_second": 6.13,
+      "eval_steps_per_second": 1.549,
+      "step": 527
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.1756312374414113e-07,
+      "loss": 0.1648,
+      "step": 528
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.1223586476865953e-07,
+      "loss": 0.1488,
+      "step": 529
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.0697174623636795e-07,
+      "loss": 0.1691,
+      "step": 530
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.017709134326884e-07,
+      "loss": 0.1669,
+      "step": 531
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.9663350989640812e-07,
+      "loss": 0.1548,
+      "step": 532
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.915596774157169e-07,
+      "loss": 0.161,
+      "step": 533
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.8654955602429499e-07,
+      "loss": 0.1763,
+      "step": 534
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.8160328399744825e-07,
+      "loss": 0.1813,
+      "step": 535
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.7672099784829116e-07,
+      "loss": 0.155,
+      "step": 536
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.719028323239802e-07,
+      "loss": 0.1718,
+      "step": 537
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.6714892040199383e-07,
+      "loss": 0.1486,
+      "step": 538
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.6245939328646322e-07,
+      "loss": 0.1465,
+      "step": 539
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.5783438040455097e-07,
+      "loss": 0.1261,
+      "step": 540
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.5327400940287868e-07,
+      "loss": 0.2032,
+      "step": 541
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.4877840614400452e-07,
+      "loss": 0.1648,
+      "step": 542
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.44347694702949e-07,
+      "loss": 0.1614,
+      "step": 543
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.399819973637706e-07,
+      "loss": 0.1783,
+      "step": 544
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.3568143461619193e-07,
+      "loss": 0.1642,
+      "step": 545
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.3144612515227278e-07,
+      "loss": 0.1615,
+      "step": 546
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.2727618586313495e-07,
+      "loss": 0.1474,
+      "step": 547
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.2317173183573616e-07,
+      "loss": 0.1432,
+      "step": 548
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.1913287634969461e-07,
+      "loss": 0.1582,
+      "step": 549
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.151597308741606e-07,
+      "loss": 0.1579,
+      "step": 550
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.1125240506474178e-07,
+      "loss": 0.1533,
+      "step": 551
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.0741100676047639e-07,
+      "loss": 0.1517,
+      "step": 552
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.0363564198085624e-07,
+      "loss": 0.1716,
+      "step": 553
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 9.992641492290094e-08,
+      "loss": 0.1709,
+      "step": 554
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 9.628342795828333e-08,
+      "loss": 0.1439,
+      "step": 555
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 9.270678163050218e-08,
+      "loss": 0.1568,
+      "step": 556
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 8.919657465210867e-08,
+      "loss": 0.1306,
+      "step": 557
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 8.575290390198193e-08,
+      "loss": 0.1612,
+      "step": 558
+    },
+    {
+      "epoch": 1.83,
+      "eval_loss": 0.19228258728981018,
+      "eval_runtime": 15.5027,
+      "eval_samples_per_second": 6.128,
+      "eval_steps_per_second": 1.548,
+      "step": 558
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.237586442265411e-08,
+      "loss": 0.1491,
+      "step": 559
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.906554941768896e-08,
+      "loss": 0.1692,
+      "step": 560
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.582205024910805e-08,
+      "loss": 0.1775,
+      "step": 561
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 7.264545643486997e-08,
+      "loss": 0.1526,
+      "step": 562
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.953585564639903e-08,
+      "loss": 0.1716,
+      "step": 563
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.649333370616712e-08,
+      "loss": 0.177,
+      "step": 564
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.351797458532316e-08,
+      "loss": 0.1542,
+      "step": 565
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.060986040137689e-08,
+      "loss": 0.1603,
+      "step": 566
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 5.776907141593235e-08,
+      "loss": 0.1542,
+      "step": 567
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.4995686032471575e-08,
+      "loss": 0.1629,
+      "step": 568
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.2289780794192726e-08,
+      "loss": 0.1614,
+      "step": 569
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.96514303818954e-08,
+      "loss": 0.1267,
+      "step": 570
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.708070761192146e-08,
+      "loss": 0.1888,
+      "step": 571
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.457768343414382e-08,
+      "loss": 0.168,
+      "step": 572
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.2142426930008584e-08,
+      "loss": 0.1492,
+      "step": 573
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.9775005310629946e-08,
+      "loss": 0.1382,
+      "step": 574
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.747548391493272e-08,
+      "loss": 0.1682,
+      "step": 575
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.5243926207851606e-08,
+      "loss": 0.1833,
+      "step": 576
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.3080393778577305e-08,
+      "loss": 0.1451,
+      "step": 577
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.09849463388584e-08,
+      "loss": 0.1741,
+      "step": 578
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.8957641721352735e-08,
+      "loss": 0.1765,
+      "step": 579
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.6998535878030584e-08,
+      "loss": 0.1684,
+      "step": 580
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.510768287863202e-08,
+      "loss": 0.1543,
+      "step": 581
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.3285134909173113e-08,
+      "loss": 0.1558,
+      "step": 582
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.1530942270506504e-08,
+      "loss": 0.1654,
+      "step": 583
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.9845153376933102e-08,
+      "loss": 0.1381,
+      "step": 584
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.822781475486507e-08,
+      "loss": 0.164,
+      "step": 585
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.6678971041542702e-08,
+      "loss": 0.153,
+      "step": 586
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.5198664983802346e-08,
+      "loss": 0.1168,
+      "step": 587
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.3786937436895686e-08,
+      "loss": 0.1425,
+      "step": 588
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.2443827363363693e-08,
+      "loss": 0.1857,
+      "step": 589
+    },
+    {
+      "epoch": 1.93,
+      "eval_loss": 0.19226355850696564,
+      "eval_runtime": 15.5264,
+      "eval_samples_per_second": 6.119,
+      "eval_steps_per_second": 1.546,
+      "step": 589
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.1169371831959986e-08,
+      "loss": 0.1804,
+      "step": 590
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 9.963606016628325e-09,
+      "loss": 0.1569,
+      "step": 591
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 8.826563195531713e-09,
+      "loss": 0.1867,
+      "step": 592
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 7.758274750134243e-09,
+      "loss": 0.1755,
+      "step": 593
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 6.758770164334572e-09,
+      "loss": 0.1796,
+      "step": 594
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.828077023651846e-09,
+      "loss": 0.1559,
+      "step": 595
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 4.96622101446631e-09,
+      "loss": 0.1851,
+      "step": 596
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 4.1732259233071004e-09,
+      "loss": 0.1833,
+      "step": 597
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.449113636199153e-09,
+      "loss": 0.1786,
+      "step": 598
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.793904138056469e-09,
+      "loss": 0.1979,
+      "step": 599
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2.2076155121328326e-09,
+      "loss": 0.1566,
+      "step": 600
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.6902639395208197e-09,
+      "loss": 0.1636,
+      "step": 601
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.2418636987057697e-09,
+      "loss": 0.1439,
+      "step": 602
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 8.624271651727634e-10,
+      "loss": 0.1967,
+      "step": 603
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.519648110638431e-10,
+      "loss": 0.1715,
+      "step": 604
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 3.1048520488907717e-10,
+      "loss": 0.1833,
+      "step": 605
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.3799501129063698e-10,
+      "loss": 0.1692,
+      "step": 606
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 3.4498990858777835e-11,
+      "loss": 0.1697,
+      "step": 607
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.1712,
+      "step": 608
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 608,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 3.399970706505597e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-608/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f17f663326682e34d06194ed091725483adeebe21013fe1752885513b5506a8
+size 4411

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "transformers_version": "4.34.1"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d00e12428ee23606c20c0cb82491d564848080e13e6dc427e94e14700ee502d
+size 9886765428

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e0a4e903b17ca571e3d14a89e7bf7d4ed70334289ba4353fe58f9fd95789fd
+size 5121688491

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 15008350208
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% 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": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}