61811f7651c2ad5d8b23f167ed531f5a0c969bfd7c31f342a76c3988e4ba9d95

README.md

@@ -0,0 +1,148 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: Mistral-7B-Instruct-KhanAcademy-v0.2
+  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)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+
+hub_model_id: MaziyarPanahi/Mistral-7B-Instruct-KhanAcademy-v0.2
+hf_use_auth_token: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: CohereForAI/aya_dataset
+    type:
+      system_prompt: ""
+      field_instruction: inputs
+      field_output: targets
+      format: "[INST] {instruction} [/INST]"
+      no_input_format: "[INST] {instruction} [/INST]"
+
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./models/MaziyarPanahi/Mistral-7B-Instruct-Aya-101
+
+sequence_len: 8192
+sample_packing: true
+pad_to_sequence_len: true
+eval_sample_packing: false
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.000005
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+```
+
+</details><br>
+
+# Mistral-7B-Instruct-KhanAcademy-v0.2
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1502
+
+## 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: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.9039        | 0.0   | 1    | 3.1495          |
+| 0.9933        | 0.25  | 101  | 1.2402          |
+| 0.9439        | 0.5   | 202  | 1.1683          |
+| 0.9762        | 0.75  | 303  | 1.1502          |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.0

checkpoint-401/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

checkpoint-401/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.0.dev0"
+}

checkpoint-401/model.safetensors.index.json

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

checkpoint-401/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5e18f922d0af74d820247ae97bee506ab412554a58345ddf2558abc94ee3e3
+size 15024

checkpoint-401/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a2dcca6d9741f46592359768ea2212b9321da6408d1fd7d3a80b017bf37f434
+size 15024

checkpoint-401/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69420ece2c255923c5cbb3c6c9c4a6b9cb38fb57e5d3033c8b7d436a1faf6f13
+size 15024

checkpoint-401/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f278b40a1e23b88a657c4e5d03afa8dbbbe14dfeb16f6b4beedaece6cdd0b9
+size 15024

checkpoint-401/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3786850cd5038038536913e263fba36a46fc209c59de74586162eba92bb42962
+size 1064

checkpoint-401/trainer_state.json

@@ -0,0 +1,2860 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9981331673926571,
+  "eval_steps": 101,
+  "global_step": 401,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 53.25,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.9039,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 3.1495237350463867,
+      "eval_runtime": 1687.5261,
+      "eval_samples_per_second": 5.968,
+      "eval_steps_per_second": 0.746,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 57.75,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.1549,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 45.75,
+      "learning_rate": 1.5e-06,
+      "loss": 1.85,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 43.75,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.8815,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 26.875,
+      "learning_rate": 2.5e-06,
+      "loss": 1.7001,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 15.8125,
+      "learning_rate": 3e-06,
+      "loss": 1.4792,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 12.25,
+      "learning_rate": 3.5e-06,
+      "loss": 1.6061,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 10.3125,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.4366,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 8.0,
+      "learning_rate": 4.5e-06,
+      "loss": 1.4531,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 7.0,
+      "learning_rate": 5e-06,
+      "loss": 1.5216,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 6.96875,
+      "learning_rate": 4.9999193036470786e-06,
+      "loss": 1.2768,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 7.09375,
+      "learning_rate": 4.999677219797834e-06,
+      "loss": 1.3153,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.875,
+      "learning_rate": 4.999273764080493e-06,
+      "loss": 1.425,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 6.40625,
+      "learning_rate": 4.9987089625409815e-06,
+      "loss": 1.3616,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.40625,
+      "learning_rate": 4.997982851641236e-06,
+      "loss": 1.3301,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.5625,
+      "learning_rate": 4.99709547825686e-06,
+      "loss": 1.4655,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.6875,
+      "learning_rate": 4.996046899674091e-06,
+      "loss": 1.3226,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.75,
+      "learning_rate": 4.9948371835861e-06,
+      "loss": 1.3406,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.4375,
+      "learning_rate": 4.993466408088629e-06,
+      "loss": 1.304,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.75,
+      "learning_rate": 4.991934661674945e-06,
+      "loss": 1.2712,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.53125,
+      "learning_rate": 4.990242043230129e-06,
+      "loss": 1.3149,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.46875,
+      "learning_rate": 4.988388662024687e-06,
+      "loss": 1.2938,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.34375,
+      "learning_rate": 4.9863746377075025e-06,
+      "loss": 1.242,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.46875,
+      "learning_rate": 4.98420010029811e-06,
+      "loss": 1.2161,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.15625,
+      "learning_rate": 4.981865190178299e-06,
+      "loss": 1.294,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.125,
+      "learning_rate": 4.979370058083056e-06,
+      "loss": 1.1972,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 3.890625,
+      "learning_rate": 4.976714865090827e-06,
+      "loss": 1.2295,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.09375,
+      "learning_rate": 4.973899782613127e-06,
+      "loss": 1.1852,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.28125,
+      "learning_rate": 4.970924992383465e-06,
+      "loss": 1.323,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.96779068644562e-06,
+      "loss": 1.3008,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.875,
+      "learning_rate": 4.964497067141239e-06,
+      "loss": 1.2526,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.921875,
+      "learning_rate": 4.961044347096773e-06,
+      "loss": 1.3551,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.84375,
+      "learning_rate": 4.957432749209755e-06,
+      "loss": 1.1906,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.796875,
+      "learning_rate": 4.953662506634408e-06,
+      "loss": 1.2391,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.0,
+      "learning_rate": 4.949733862766591e-06,
+      "loss": 1.1611,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.94564707122809e-06,
+      "loss": 1.213,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 3.84375,
+      "learning_rate": 4.941402395850244e-06,
+      "loss": 1.1394,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 3.796875,
+      "learning_rate": 4.93700011065691e-06,
+      "loss": 1.2633,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.6875,
+      "learning_rate": 4.9324404998467755e-06,
+      "loss": 1.1892,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.734375,
+      "learning_rate": 4.927723857775012e-06,
+      "loss": 1.2087,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.84375,
+      "learning_rate": 4.922850488934268e-06,
+      "loss": 1.2898,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.765625,
+      "learning_rate": 4.917820707935019e-06,
+      "loss": 1.2064,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 3.71875,
+      "learning_rate": 4.912634839485251e-06,
+      "loss": 1.1967,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 3.625,
+      "learning_rate": 4.907293218369499e-06,
+      "loss": 1.215,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 4.0,
+      "learning_rate": 4.901796189427238e-06,
+      "loss": 1.1548,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 3.53125,
+      "learning_rate": 4.896144107530618e-06,
+      "loss": 1.1007,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.53125,
+      "learning_rate": 4.890337337561556e-06,
+      "loss": 1.0993,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.25,
+      "learning_rate": 4.884376254388179e-06,
+      "loss": 1.0616,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.984375,
+      "learning_rate": 4.878261242840624e-06,
+      "loss": 1.1689,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.90625,
+      "learning_rate": 4.8719926976861934e-06,
+      "loss": 1.1147,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.890625,
+      "learning_rate": 4.865571023603875e-06,
+      "loss": 1.0578,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 4.21875,
+      "learning_rate": 4.858996635158211e-06,
+      "loss": 1.1676,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.852269956772536e-06,
+      "loss": 1.0989,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.6875,
+      "learning_rate": 4.845391422701582e-06,
+      "loss": 1.2259,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.838361477003439e-06,
+      "loss": 1.1906,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.828125,
+      "learning_rate": 4.83118057351089e-06,
+      "loss": 1.0726,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.828125,
+      "learning_rate": 4.823849175802114e-06,
+      "loss": 1.1111,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.640625,
+      "learning_rate": 4.816367757170754e-06,
+      "loss": 1.3362,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.671875,
+      "learning_rate": 4.808736800595372e-06,
+      "loss": 1.1101,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.796875,
+      "learning_rate": 4.800956798708256e-06,
+      "loss": 1.131,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.890625,
+      "learning_rate": 4.793028253763633e-06,
+      "loss": 1.0771,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.3125,
+      "learning_rate": 4.784951677605229e-06,
+      "loss": 1.1331,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.776727591633235e-06,
+      "loss": 1.1704,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.875,
+      "learning_rate": 4.76835652677065e-06,
+      "loss": 1.1436,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.65625,
+      "learning_rate": 4.759839023428994e-06,
+      "loss": 1.1931,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.15625,
+      "learning_rate": 4.751175631473433e-06,
+      "loss": 1.2202,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 3.84375,
+      "learning_rate": 4.742366910187275e-06,
+      "loss": 1.2113,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 3.859375,
+      "learning_rate": 4.733413428235864e-06,
+      "loss": 1.1091,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 3.859375,
+      "learning_rate": 4.724315763629874e-06,
+      "loss": 1.0952,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 3.828125,
+      "learning_rate": 4.715074503687987e-06,
+      "loss": 1.2604,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.1875,
+      "learning_rate": 4.705690244998981e-06,
+      "loss": 1.177,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.78125,
+      "learning_rate": 4.696163593383217e-06,
+      "loss": 1.1761,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.9375,
+      "learning_rate": 4.686495163853528e-06,
+      "loss": 1.2345,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.859375,
+      "learning_rate": 4.676685580575516e-06,
+      "loss": 1.1289,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 3.71875,
+      "learning_rate": 4.6667354768272565e-06,
+      "loss": 1.1536,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 3.53125,
+      "learning_rate": 4.656645494958415e-06,
+      "loss": 1.1625,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 3.875,
+      "learning_rate": 4.646416286348783e-06,
+      "loss": 1.1441,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 3.71875,
+      "learning_rate": 4.636048511366222e-06,
+      "loss": 1.0877,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.96875,
+      "learning_rate": 4.625542839324036e-06,
+      "loss": 0.998,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.6875,
+      "learning_rate": 4.61489994843776e-06,
+      "loss": 1.1651,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.604120525781376e-06,
+      "loss": 1.1657,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.15625,
+      "learning_rate": 4.593205267242962e-06,
+      "loss": 1.1362,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 3.9375,
+      "learning_rate": 4.582154877479762e-06,
+      "loss": 1.1169,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 3.90625,
+      "learning_rate": 4.570970069872695e-06,
+      "loss": 1.1175,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 3.78125,
+      "learning_rate": 4.55965156648031e-06,
+      "loss": 1.0583,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 3.921875,
+      "learning_rate": 4.548200097992161e-06,
+      "loss": 1.0436,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.0625,
+      "learning_rate": 4.5366164036816415e-06,
+      "loss": 1.036,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.859375,
+      "learning_rate": 4.524901231358261e-06,
+      "loss": 1.2137,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.375,
+      "learning_rate": 4.513055337319361e-06,
+      "loss": 1.1137,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.984375,
+      "learning_rate": 4.501079486301299e-06,
+      "loss": 1.1229,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.734375,
+      "learning_rate": 4.488974451430077e-06,
+      "loss": 1.0657,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.671875,
+      "learning_rate": 4.4767410141714265e-06,
+      "loss": 1.1326,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.921875,
+      "learning_rate": 4.464379964280365e-06,
+      "loss": 1.1957,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.75,
+      "learning_rate": 4.451892099750206e-06,
+      "loss": 1.1726,
+      "step": 94
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.96875,
+      "learning_rate": 4.43927822676105e-06,
+      "loss": 1.0951,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.921875,
+      "learning_rate": 4.426539159627733e-06,
+      "loss": 1.1512,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.413675720747262e-06,
+      "loss": 1.0428,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.875,
+      "learning_rate": 4.40068874054572e-06,
+      "loss": 1.1005,
+      "step": 98
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.65625,
+      "learning_rate": 4.387579057424655e-06,
+      "loss": 1.0811,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.96875,
+      "learning_rate": 4.374347517706963e-06,
+      "loss": 1.1457,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.796875,
+      "learning_rate": 4.36099497558224e-06,
+      "loss": 0.9933,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.2402405738830566,
+      "eval_runtime": 1697.4894,
+      "eval_samples_per_second": 5.933,
+      "eval_steps_per_second": 0.742,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.96875,
+      "learning_rate": 4.3475222930516484e-06,
+      "loss": 1.0559,
+      "step": 102
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.0625,
+      "learning_rate": 4.3339303398722645e-06,
+      "loss": 1.1506,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.671875,
+      "learning_rate": 4.320219993500927e-06,
+      "loss": 1.0673,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.828125,
+      "learning_rate": 4.306392139037598e-06,
+      "loss": 1.0358,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.292447669168215e-06,
+      "loss": 1.2526,
+      "step": 106
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.8125,
+      "learning_rate": 4.278387484107067e-06,
+      "loss": 1.1494,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 4.15625,
+      "learning_rate": 4.26421249153868e-06,
+      "loss": 1.1066,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.734375,
+      "learning_rate": 4.2499236065592154e-06,
+      "loss": 1.129,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 3.875,
+      "learning_rate": 4.235521751617398e-06,
+      "loss": 0.9961,
+      "step": 110
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.953125,
+      "learning_rate": 4.221007856454963e-06,
+      "loss": 1.1145,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.96875,
+      "learning_rate": 4.206382858046636e-06,
+      "loss": 1.1684,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.984375,
+      "learning_rate": 4.191647700539642e-06,
+      "loss": 1.1654,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.640625,
+      "learning_rate": 4.176803335192757e-06,
+      "loss": 1.0714,
+      "step": 114
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 3.53125,
+      "learning_rate": 4.1618507203149e-06,
+      "loss": 1.0937,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 3.859375,
+      "learning_rate": 4.1467908212032586e-06,
+      "loss": 1.0441,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 3.8125,
+      "learning_rate": 4.1316246100809786e-06,
+      "loss": 1.0788,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 4.0625,
+      "learning_rate": 4.116353066034403e-06,
+      "loss": 1.0276,
+      "step": 118
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.78125,
+      "learning_rate": 4.100977174949856e-06,
+      "loss": 1.0827,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.90625,
+      "learning_rate": 4.085497929450005e-06,
+      "loss": 1.0748,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.78125,
+      "learning_rate": 4.069916328829779e-06,
+      "loss": 1.0433,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.0,
+      "learning_rate": 4.0542333789918474e-06,
+      "loss": 1.0983,
+      "step": 122
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.038450092381697e-06,
+      "loss": 1.1221,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 4.125,
+      "learning_rate": 4.02256748792226e-06,
+      "loss": 1.0123,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 3.609375,
+      "learning_rate": 4.006586590948141e-06,
+      "loss": 1.0935,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 4.15625,
+      "learning_rate": 3.990508433139421e-06,
+      "loss": 1.0307,
+      "step": 126
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.9375,
+      "learning_rate": 3.97433405245506e-06,
+      "loss": 1.0694,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.84375,
+      "learning_rate": 3.958064493065881e-06,
+      "loss": 0.9683,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.953125,
+      "learning_rate": 3.941700805287169e-06,
+      "loss": 1.1073,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.84375,
+      "learning_rate": 3.925244045510863e-06,
+      "loss": 0.9876,
+      "step": 130
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 3.875,
+      "learning_rate": 3.9086952761373605e-06,
+      "loss": 1.0082,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 3.734375,
+      "learning_rate": 3.892055565506929e-06,
+      "loss": 0.9779,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 3.6875,
+      "learning_rate": 3.8753259878307355e-06,
+      "loss": 1.0722,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 3.703125,
+      "learning_rate": 3.858507623121506e-06,
+      "loss": 1.0229,
+      "step": 134
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.703125,
+      "learning_rate": 3.841601557123793e-06,
+      "loss": 1.081,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.8125,
+      "learning_rate": 3.824608881243893e-06,
+      "loss": 1.2165,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.765625,
+      "learning_rate": 3.807530692479382e-06,
+      "loss": 1.1001,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.671875,
+      "learning_rate": 3.7903680933482965e-06,
+      "loss": 1.0578,
+      "step": 138
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 3.828125,
+      "learning_rate": 3.7731221918179645e-06,
+      "loss": 0.9931,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 3.890625,
+      "learning_rate": 3.7557941012334687e-06,
+      "loss": 1.0884,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 3.984375,
+      "learning_rate": 3.7383849402457807e-06,
+      "loss": 1.0741,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 3.71875,
+      "learning_rate": 3.72089583273954e-06,
+      "loss": 1.1207,
+      "step": 142
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.890625,
+      "learning_rate": 3.703327907760499e-06,
+      "loss": 1.057,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.734375,
+      "learning_rate": 3.685682299442638e-06,
+      "loss": 1.0551,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.78125,
+      "learning_rate": 3.6679601469349456e-06,
+      "loss": 0.9792,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.703125,
+      "learning_rate": 3.650162594327881e-06,
+      "loss": 0.967,
+      "step": 146
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 4.0625,
+      "learning_rate": 3.632290790579512e-06,
+      "loss": 1.1393,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.953125,
+      "learning_rate": 3.6143458894413463e-06,
+      "loss": 1.0892,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.75,
+      "learning_rate": 3.596329049383843e-06,
+      "loss": 1.0478,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.765625,
+      "learning_rate": 3.5782414335216297e-06,
+      "loss": 1.0014,
+      "step": 150
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.84375,
+      "learning_rate": 3.5600842095384125e-06,
+      "loss": 1.0601,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.90625,
+      "learning_rate": 3.541858549611596e-06,
+      "loss": 1.1093,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.84375,
+      "learning_rate": 3.523565630336607e-06,
+      "loss": 0.9811,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.8125,
+      "learning_rate": 3.505206632650944e-06,
+      "loss": 1.1626,
+      "step": 154
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 3.875,
+      "learning_rate": 3.48678274175793e-06,
+      "loss": 1.0518,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 3.75,
+      "learning_rate": 3.468295147050207e-06,
+      "loss": 1.0028,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 3.953125,
+      "learning_rate": 3.4497450420329486e-06,
+      "loss": 1.0596,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 3.8125,
+      "learning_rate": 3.431133624246812e-06,
+      "loss": 1.08,
+      "step": 158
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.90625,
+      "learning_rate": 3.4124620951906283e-06,
+      "loss": 1.02,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.828125,
+      "learning_rate": 3.3937316602438352e-06,
+      "loss": 1.0798,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.953125,
+      "learning_rate": 3.3749435285886638e-06,
+      "loss": 1.1169,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.75,
+      "learning_rate": 3.356098913132077e-06,
+      "loss": 1.0584,
+      "step": 162
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 3.859375,
+      "learning_rate": 3.3371990304274654e-06,
+      "loss": 1.0337,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.3182451005961146e-06,
+      "loss": 1.1088,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.0,
+      "learning_rate": 3.2992383472484318e-06,
+      "loss": 0.9837,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 3.609375,
+      "learning_rate": 3.280179997404958e-06,
+      "loss": 1.0732,
+      "step": 166
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.765625,
+      "learning_rate": 3.2610712814171535e-06,
+      "loss": 1.1187,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.125,
+      "learning_rate": 3.2419134328879703e-06,
+      "loss": 1.104,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.09375,
+      "learning_rate": 3.2227076885922137e-06,
+      "loss": 0.9941,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.890625,
+      "learning_rate": 3.2034552883966972e-06,
+      "loss": 1.1258,
+      "step": 170
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.515625,
+      "learning_rate": 3.184157475180208e-06,
+      "loss": 0.9484,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.71875,
+      "learning_rate": 3.1648154947532607e-06,
+      "loss": 1.0749,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.96875,
+      "learning_rate": 3.1454305957776797e-06,
+      "loss": 0.9447,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.8125,
+      "learning_rate": 3.126004029685984e-06,
+      "loss": 1.1009,
+      "step": 174
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.90625,
+      "learning_rate": 3.106537050600601e-06,
+      "loss": 1.0355,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.9375,
+      "learning_rate": 3.0870309152529006e-06,
+      "loss": 1.0504,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.734375,
+      "learning_rate": 3.0674868829020692e-06,
+      "loss": 1.0575,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.71875,
+      "learning_rate": 3.0479062152538137e-06,
+      "loss": 1.0417,
+      "step": 178
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.78125,
+      "learning_rate": 3.0282901763789064e-06,
+      "loss": 0.962,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.890625,
+      "learning_rate": 3.0086400326315853e-06,
+      "loss": 1.0601,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.796875,
+      "learning_rate": 2.988957052567797e-06,
+      "loss": 1.0731,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.8125,
+      "learning_rate": 2.969242506863306e-06,
+      "loss": 1.0532,
+      "step": 182
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.890625,
+      "learning_rate": 2.949497668231663e-06,
+      "loss": 0.995,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.09375,
+      "learning_rate": 2.929723811342042e-06,
+      "loss": 0.9706,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.5625,
+      "learning_rate": 2.9099222127369496e-06,
+      "loss": 1.0618,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.890625,
+      "learning_rate": 2.890094150749818e-06,
+      "loss": 1.0437,
+      "step": 186
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 3.859375,
+      "learning_rate": 2.870240905422476e-06,
+      "loss": 1.0314,
+      "step": 187
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 3.75,
+      "learning_rate": 2.850363758422519e-06,
+      "loss": 0.9562,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 3.84375,
+      "learning_rate": 2.830463992960561e-06,
+      "loss": 1.1011,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 4.125,
+      "learning_rate": 2.8105428937073997e-06,
+      "loss": 0.9929,
+      "step": 190
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.78125,
+      "learning_rate": 2.7906017467110806e-06,
+      "loss": 1.0573,
+      "step": 191
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.671875,
+      "learning_rate": 2.770641839313871e-06,
+      "loss": 1.0478,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.953125,
+      "learning_rate": 2.750664460069157e-06,
+      "loss": 1.047,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.8125,
+      "learning_rate": 2.730670898658255e-06,
+      "loss": 1.0945,
+      "step": 194
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 3.84375,
+      "learning_rate": 2.710662445807156e-06,
+      "loss": 0.9587,
+      "step": 195
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 3.84375,
+      "learning_rate": 2.6906403932031973e-06,
+      "loss": 1.0648,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 3.90625,
+      "learning_rate": 2.670606033411678e-06,
+      "loss": 1.1022,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 3.8125,
+      "learning_rate": 2.6505606597924122e-06,
+      "loss": 1.1515,
+      "step": 198
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.53125,
+      "learning_rate": 2.630505566416235e-06,
+      "loss": 1.0288,
+      "step": 199
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.125,
+      "learning_rate": 2.610442047981462e-06,
+      "loss": 0.9577,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.765625,
+      "learning_rate": 2.5903713997303033e-06,
+      "loss": 0.9455,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.75,
+      "learning_rate": 2.5702949173652515e-06,
+      "loss": 0.9439,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.1682730913162231,
+      "eval_runtime": 1697.6225,
+      "eval_samples_per_second": 5.932,
+      "eval_steps_per_second": 0.742,
+      "step": 202
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 3.8125,
+      "learning_rate": 2.550213896965431e-06,
+      "loss": 1.0939,
+      "step": 203
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 3.5625,
+      "learning_rate": 2.53012963490293e-06,
+      "loss": 1.0256,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 3.8125,
+      "learning_rate": 2.5100434277591077e-06,
+      "loss": 1.0595,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 3.890625,
+      "learning_rate": 2.4899565722408927e-06,
+      "loss": 1.1182,
+      "step": 206
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.6875,
+      "learning_rate": 2.4698703650970706e-06,
+      "loss": 1.0328,
+      "step": 207
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.65625,
+      "learning_rate": 2.449786103034569e-06,
+      "loss": 0.9872,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.796875,
+      "learning_rate": 2.4297050826347498e-06,
+      "loss": 1.0855,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.984375,
+      "learning_rate": 2.409628600269697e-06,
+      "loss": 1.0982,
+      "step": 210
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 3.8125,
+      "learning_rate": 2.3895579520185393e-06,
+      "loss": 1.1318,
+      "step": 211
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 3.640625,
+      "learning_rate": 2.3694944335837653e-06,
+      "loss": 0.9962,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 3.765625,
+      "learning_rate": 2.349439340207588e-06,
+      "loss": 0.968,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 3.96875,
+      "learning_rate": 2.3293939665883233e-06,
+      "loss": 0.9732,
+      "step": 214
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.71875,
+      "learning_rate": 2.3093596067968027e-06,
+      "loss": 0.9373,
+      "step": 215
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.609375,
+      "learning_rate": 2.2893375541928447e-06,
+      "loss": 1.0306,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.84375,
+      "learning_rate": 2.269329101341745e-06,
+      "loss": 1.1107,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.875,
+      "learning_rate": 2.249335539930843e-06,
+      "loss": 1.0235,
+      "step": 218
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.546875,
+      "learning_rate": 2.2293581606861298e-06,
+      "loss": 1.0638,
+      "step": 219
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.640625,
+      "learning_rate": 2.20939825328892e-06,
+      "loss": 1.0233,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.6875,
+      "learning_rate": 2.1894571062926008e-06,
+      "loss": 0.9618,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.84375,
+      "learning_rate": 2.1695360070394396e-06,
+      "loss": 0.9921,
+      "step": 222
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.90625,
+      "learning_rate": 2.1496362415774814e-06,
+      "loss": 1.0143,
+      "step": 223
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.59375,
+      "learning_rate": 2.1297590945775244e-06,
+      "loss": 0.9744,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.59375,
+      "learning_rate": 2.1099058492501825e-06,
+      "loss": 1.0126,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.96875,
+      "learning_rate": 2.0900777872630513e-06,
+      "loss": 1.1166,
+      "step": 226
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.515625,
+      "learning_rate": 2.070276188657959e-06,
+      "loss": 0.9741,
+      "step": 227
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.546875,
+      "learning_rate": 2.0505023317683374e-06,
+      "loss": 0.9359,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.734375,
+      "learning_rate": 2.0307574931366954e-06,
+      "loss": 1.0426,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.765625,
+      "learning_rate": 2.011042947432204e-06,
+      "loss": 1.0191,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.734375,
+      "learning_rate": 1.991359967368416e-06,
+      "loss": 1.0692,
+      "step": 231
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.875,
+      "learning_rate": 1.9717098236210944e-06,
+      "loss": 0.9858,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.90625,
+      "learning_rate": 1.9520937847461867e-06,
+      "loss": 0.9709,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.90625,
+      "learning_rate": 1.9325131170979316e-06,
+      "loss": 1.1824,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.859375,
+      "learning_rate": 1.9129690847471e-06,
+      "loss": 0.9967,
+      "step": 235
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.8934629493994005e-06,
+      "loss": 0.9896,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.8739959703140167e-06,
+      "loss": 1.0194,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.8545694042223205e-06,
+      "loss": 0.9915,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.8351845052467403e-06,
+      "loss": 1.0117,
+      "step": 239
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.625,
+      "learning_rate": 1.8158425248197931e-06,
+      "loss": 0.9527,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.375,
+      "learning_rate": 1.7965447116033036e-06,
+      "loss": 0.9097,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.7772923114077871e-06,
+      "loss": 0.9966,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.96875,
+      "learning_rate": 1.7580865671120295e-06,
+      "loss": 1.0222,
+      "step": 243
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 3.6875,
+      "learning_rate": 1.738928718582847e-06,
+      "loss": 0.9598,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 3.625,
+      "learning_rate": 1.7198200025950423e-06,
+      "loss": 1.0023,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 3.84375,
+      "learning_rate": 1.7007616527515695e-06,
+      "loss": 1.0632,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.6817548994038862e-06,
+      "loss": 1.054,
+      "step": 247
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.6628009695725348e-06,
+      "loss": 1.0083,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.84375,
+      "learning_rate": 1.643901086867924e-06,
+      "loss": 1.0685,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.734375,
+      "learning_rate": 1.6250564714113364e-06,
+      "loss": 0.9871,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.6875,
+      "learning_rate": 1.606268339756166e-06,
+      "loss": 1.0499,
+      "step": 251
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.75,
+      "learning_rate": 1.5875379048093723e-06,
+      "loss": 1.0568,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.921875,
+      "learning_rate": 1.568866375753188e-06,
+      "loss": 1.0213,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.59375,
+      "learning_rate": 1.5502549579670522e-06,
+      "loss": 1.0704,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.96875,
+      "learning_rate": 1.5317048529497938e-06,
+      "loss": 1.055,
+      "step": 255
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.4375,
+      "learning_rate": 1.5132172582420713e-06,
+      "loss": 0.9842,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.75,
+      "learning_rate": 1.4947933673490566e-06,
+      "loss": 1.0064,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.84375,
+      "learning_rate": 1.4764343696633933e-06,
+      "loss": 1.0286,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.921875,
+      "learning_rate": 1.4581414503884051e-06,
+      "loss": 0.9656,
+      "step": 259
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.734375,
+      "learning_rate": 1.439915790461588e-06,
+      "loss": 1.0944,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.625,
+      "learning_rate": 1.421758566478371e-06,
+      "loss": 1.0269,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.875,
+      "learning_rate": 1.4036709506161577e-06,
+      "loss": 0.9061,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.734375,
+      "learning_rate": 1.3856541105586545e-06,
+      "loss": 0.9597,
+      "step": 263
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.671875,
+      "learning_rate": 1.3677092094204886e-06,
+      "loss": 1.0282,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.671875,
+      "learning_rate": 1.3498374056721198e-06,
+      "loss": 1.0582,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.734375,
+      "learning_rate": 1.332039853065055e-06,
+      "loss": 1.0319,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.71875,
+      "learning_rate": 1.3143177005573626e-06,
+      "loss": 1.0384,
+      "step": 267
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 3.75,
+      "learning_rate": 1.2966720922395015e-06,
+      "loss": 0.9468,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 3.59375,
+      "learning_rate": 1.2791041672604609e-06,
+      "loss": 1.0335,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 3.8125,
+      "learning_rate": 1.2616150597542197e-06,
+      "loss": 0.9515,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 3.609375,
+      "learning_rate": 1.244205898766532e-06,
+      "loss": 1.0266,
+      "step": 271
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.625,
+      "learning_rate": 1.2268778081820363e-06,
+      "loss": 1.0266,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.59375,
+      "learning_rate": 1.2096319066517037e-06,
+      "loss": 0.8807,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.0,
+      "learning_rate": 1.192469307520619e-06,
+      "loss": 1.066,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.1753911187561075e-06,
+      "loss": 1.002,
+      "step": 275
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 3.71875,
+      "learning_rate": 1.1583984428762076e-06,
+      "loss": 1.006,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 3.859375,
+      "learning_rate": 1.1414923768784952e-06,
+      "loss": 1.0167,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 3.921875,
+      "learning_rate": 1.1246740121692649e-06,
+      "loss": 1.0791,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 3.984375,
+      "learning_rate": 1.1079444344930717e-06,
+      "loss": 1.013,
+      "step": 279
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.75,
+      "learning_rate": 1.0913047238626394e-06,
+      "loss": 1.0024,
+      "step": 280
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.0,
+      "learning_rate": 1.0747559544891376e-06,
+      "loss": 1.0406,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.578125,
+      "learning_rate": 1.0582991947128324e-06,
+      "loss": 1.0518,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.75,
+      "learning_rate": 1.0419355069341206e-06,
+      "loss": 1.0486,
+      "step": 283
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 3.65625,
+      "learning_rate": 1.025665947544941e-06,
+      "loss": 0.9368,
+      "step": 284
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 3.515625,
+      "learning_rate": 1.0094915668605786e-06,
+      "loss": 0.958,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 3.765625,
+      "learning_rate": 9.934134090518593e-07,
+      "loss": 1.0873,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 3.34375,
+      "learning_rate": 9.774325120777406e-07,
+      "loss": 1.0053,
+      "step": 287
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.859375,
+      "learning_rate": 9.61549907618304e-07,
+      "loss": 1.1148,
+      "step": 288
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.546875,
+      "learning_rate": 9.457666210081537e-07,
+      "loss": 1.1638,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.6875,
+      "learning_rate": 9.300836711702224e-07,
+      "loss": 1.017,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.609375,
+      "learning_rate": 9.145020705499947e-07,
+      "loss": 1.0333,
+      "step": 291
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.953125,
+      "learning_rate": 8.990228250501446e-07,
+      "loss": 1.099,
+      "step": 292
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.671875,
+      "learning_rate": 8.836469339655979e-07,
+      "loss": 0.9876,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.578125,
+      "learning_rate": 8.68375389919022e-07,
+      "loss": 1.0734,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.8125,
+      "learning_rate": 8.532091787967428e-07,
+      "loss": 1.1269,
+      "step": 295
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.65625,
+      "learning_rate": 8.38149279685101e-07,
+      "loss": 0.9446,
+      "step": 296
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.0625,
+      "learning_rate": 8.231966648072431e-07,
+      "loss": 1.0824,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.765625,
+      "learning_rate": 8.083522994603593e-07,
+      "loss": 1.0151,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.703125,
+      "learning_rate": 7.936171419533653e-07,
+      "loss": 1.0191,
+      "step": 299
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.46875,
+      "learning_rate": 7.789921435450373e-07,
+      "loss": 1.0482,
+      "step": 300
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.8125,
+      "learning_rate": 7.644782483826016e-07,
+      "loss": 1.0616,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.859375,
+      "learning_rate": 7.500763934407851e-07,
+      "loss": 0.958,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.65625,
+      "learning_rate": 7.357875084613208e-07,
+      "loss": 0.9762,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.1502219438552856,
+      "eval_runtime": 1698.3617,
+      "eval_samples_per_second": 5.93,
+      "eval_steps_per_second": 0.741,
+      "step": 303
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.484375,
+      "learning_rate": 7.216125158929337e-07,
+      "loss": 1.0086,
+      "step": 304
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.734375,
+      "learning_rate": 7.075523308317863e-07,
+      "loss": 0.9599,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.53125,
+      "learning_rate": 6.936078609624023e-07,
+      "loss": 0.9755,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.65625,
+      "learning_rate": 6.797800064990734e-07,
+      "loss": 0.8239,
+      "step": 307
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 3.671875,
+      "learning_rate": 6.660696601277369e-07,
+      "loss": 1.0655,
+      "step": 308
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 3.609375,
+      "learning_rate": 6.524777069483526e-07,
+      "loss": 1.0598,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 3.609375,
+      "learning_rate": 6.390050244177615e-07,
+      "loss": 1.0022,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 3.546875,
+      "learning_rate": 6.256524822930379e-07,
+      "loss": 1.0651,
+      "step": 311
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.984375,
+      "learning_rate": 6.124209425753455e-07,
+      "loss": 0.9499,
+      "step": 312
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.546875,
+      "learning_rate": 5.993112594542813e-07,
+      "loss": 0.9701,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.734375,
+      "learning_rate": 5.863242792527385e-07,
+      "loss": 1.0464,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.6875,
+      "learning_rate": 5.734608403722674e-07,
+      "loss": 1.0288,
+      "step": 315
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 4.1875,
+      "learning_rate": 5.607217732389503e-07,
+      "loss": 1.0578,
+      "step": 316
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 3.921875,
+      "learning_rate": 5.481079002497946e-07,
+      "loss": 1.0421,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 4.25,
+      "learning_rate": 5.356200357196362e-07,
+      "loss": 1.0306,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 3.71875,
+      "learning_rate": 5.232589858285734e-07,
+      "loss": 1.0028,
+      "step": 319
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.25,
+      "learning_rate": 5.110255485699237e-07,
+      "loss": 0.9517,
+      "step": 320
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.625,
+      "learning_rate": 4.989205136987007e-07,
+      "loss": 0.9468,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.703125,
+      "learning_rate": 4.869446626806404e-07,
+      "loss": 1.0133,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.578125,
+      "learning_rate": 4.750987686417405e-07,
+      "loss": 0.9474,
+      "step": 323
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 3.625,
+      "learning_rate": 4.633835963183583e-07,
+      "loss": 0.9537,
+      "step": 324
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 3.578125,
+      "learning_rate": 4.5179990200784006e-07,
+      "loss": 0.9295,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 3.53125,
+      "learning_rate": 4.4034843351969005e-07,
+      "loss": 1.0759,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 3.546875,
+      "learning_rate": 4.2902993012730543e-07,
+      "loss": 0.9895,
+      "step": 327
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.609375,
+      "learning_rate": 4.178451225202396e-07,
+      "loss": 1.0568,
+      "step": 328
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.578125,
+      "learning_rate": 4.067947327570379e-07,
+      "loss": 1.0846,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.875,
+      "learning_rate": 3.958794742186245e-07,
+      "loss": 1.0305,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.625,
+      "learning_rate": 3.851000515622408e-07,
+      "loss": 0.9988,
+      "step": 331
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 3.6875,
+      "learning_rate": 3.7445716067596506e-07,
+      "loss": 1.0955,
+      "step": 332
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 3.796875,
+      "learning_rate": 3.639514886337786e-07,
+      "loss": 1.0371,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 3.796875,
+      "learning_rate": 3.5358371365121766e-07,
+      "loss": 1.0718,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 3.6875,
+      "learning_rate": 3.43354505041586e-07,
+      "loss": 0.9978,
+      "step": 335
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.6875,
+      "learning_rate": 3.332645231727441e-07,
+      "loss": 1.0067,
+      "step": 336
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.5625,
+      "learning_rate": 3.2331441942448446e-07,
+      "loss": 0.9888,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.484375,
+      "learning_rate": 3.135048361464721e-07,
+      "loss": 0.9309,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.859375,
+      "learning_rate": 3.0383640661678344e-07,
+      "loss": 1.0667,
+      "step": 339
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 3.71875,
+      "learning_rate": 2.943097550010204e-07,
+      "loss": 1.0255,
+      "step": 340
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 3.6875,
+      "learning_rate": 2.8492549631201376e-07,
+      "loss": 1.03,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 3.703125,
+      "learning_rate": 2.7568423637012646e-07,
+      "loss": 1.019,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 3.703125,
+      "learning_rate": 2.6658657176413527e-07,
+      "loss": 1.017,
+      "step": 343
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.703125,
+      "learning_rate": 2.5763308981272525e-07,
+      "loss": 1.0516,
+      "step": 344
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.34375,
+      "learning_rate": 2.488243685265676e-07,
+      "loss": 0.9736,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.828125,
+      "learning_rate": 2.401609765710064e-07,
+      "loss": 0.9969,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.609375,
+      "learning_rate": 2.3164347322935127e-07,
+      "loss": 0.9944,
+      "step": 347
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 3.53125,
+      "learning_rate": 2.232724083667645e-07,
+      "loss": 1.0454,
+      "step": 348
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 3.453125,
+      "learning_rate": 2.1504832239477192e-07,
+      "loss": 0.8774,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 3.71875,
+      "learning_rate": 2.0697174623636795e-07,
+      "loss": 1.0629,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 3.671875,
+      "learning_rate": 1.9904320129174343e-07,
+      "loss": 0.993,
+      "step": 351
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.828125,
+      "learning_rate": 1.9126319940462935e-07,
+      "loss": 1.0039,
+      "step": 352
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.53125,
+      "learning_rate": 1.836322428292464e-07,
+      "loss": 0.9873,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.71875,
+      "learning_rate": 1.761508241978871e-07,
+      "loss": 1.1026,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.6881942648911077e-07,
+      "loss": 1.0244,
+      "step": 355
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 3.75,
+      "learning_rate": 1.6163852299656142e-07,
+      "loss": 1.0486,
+      "step": 356
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 3.671875,
+      "learning_rate": 1.5460857729841877e-07,
+      "loss": 0.9962,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 3.375,
+      "learning_rate": 1.477300432274645e-07,
+      "loss": 1.0021,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.4100336484178995e-07,
+      "loss": 0.9262,
+      "step": 359
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.71875,
+      "learning_rate": 1.344289763961257e-07,
+      "loss": 1.1243,
+      "step": 360
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.671875,
+      "learning_rate": 1.2800730231380675e-07,
+      "loss": 1.0262,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.59375,
+      "learning_rate": 1.2173875715937726e-07,
+      "loss": 0.9252,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.5,
+      "learning_rate": 1.1562374561182143e-07,
+      "loss": 0.9864,
+      "step": 363
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 3.90625,
+      "learning_rate": 1.0966266243844392e-07,
+      "loss": 1.0454,
+      "step": 364
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 3.75,
+      "learning_rate": 1.0385589246938194e-07,
+      "loss": 0.9809,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 3.75,
+      "learning_rate": 9.82038105727623e-08,
+      "loss": 1.0173,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 3.609375,
+      "learning_rate": 9.270678163050218e-08,
+      "loss": 1.0639,
+      "step": 367
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.984375,
+      "learning_rate": 8.736516051474992e-08,
+      "loss": 0.9877,
+      "step": 368
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.625,
+      "learning_rate": 8.217929206498137e-08,
+      "loss": 0.9758,
+      "step": 369
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.453125,
+      "learning_rate": 7.71495110657322e-08,
+      "loss": 1.0034,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.953125,
+      "learning_rate": 7.227614222498875e-08,
+      "loss": 1.1404,
+      "step": 371
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 3.609375,
+      "learning_rate": 6.755950015322477e-08,
+      "loss": 1.0372,
+      "step": 372
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 3.5625,
+      "learning_rate": 6.299988934309026e-08,
+      "loss": 0.975,
+      "step": 373
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 3.640625,
+      "learning_rate": 5.859760414975601e-08,
+      "loss": 0.9614,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 3.640625,
+      "learning_rate": 5.435292877190995e-08,
+      "loss": 1.0394,
+      "step": 375
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.640625,
+      "learning_rate": 5.026613723340956e-08,
+      "loss": 0.9794,
+      "step": 376
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.890625,
+      "learning_rate": 4.6337493365592736e-08,
+      "loss": 1.015,
+      "step": 377
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.71875,
+      "learning_rate": 4.256725079024554e-08,
+      "loss": 1.087,
+      "step": 378
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.625,
+      "learning_rate": 3.8955652903228114e-08,
+      "loss": 0.9599,
+      "step": 379
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.875,
+      "learning_rate": 3.550293285876222e-08,
+      "loss": 0.964,
+      "step": 380
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.515625,
+      "learning_rate": 3.220931355438051e-08,
+      "loss": 0.9747,
+      "step": 381
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.515625,
+      "learning_rate": 2.907500761653581e-08,
+      "loss": 1.0822,
+      "step": 382
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.609375,
+      "learning_rate": 2.6100217386873794e-08,
+      "loss": 1.0306,
+      "step": 383
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.546875,
+      "learning_rate": 2.3285134909173113e-08,
+      "loss": 1.0334,
+      "step": 384
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.71875,
+      "learning_rate": 2.0629941916944785e-08,
+      "loss": 1.0246,
+      "step": 385
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 6.8125,
+      "learning_rate": 1.8134809821701016e-08,
+      "loss": 0.9324,
+      "step": 386
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.8125,
+      "learning_rate": 1.579989970189044e-08,
+      "loss": 1.1022,
+      "step": 387
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 3.9375,
+      "learning_rate": 1.3625362292497835e-08,
+      "loss": 1.0338,
+      "step": 388
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 4.09375,
+      "learning_rate": 1.1611337975313553e-08,
+      "loss": 0.9934,
+      "step": 389
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 3.53125,
+      "learning_rate": 9.757956769871624e-09,
+      "loss": 0.9822,
+      "step": 390
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 3.65625,
+      "learning_rate": 8.065338325054795e-09,
+      "loss": 1.0552,
+      "step": 391
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.53125,
+      "learning_rate": 6.533591911371262e-09,
+      "loss": 0.9611,
+      "step": 392
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.6875,
+      "learning_rate": 5.162816413900873e-09,
+      "loss": 0.954,
+      "step": 393
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.75,
+      "learning_rate": 3.953100325909953e-09,
+      "loss": 1.0505,
+      "step": 394
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.765625,
+      "learning_rate": 2.9045217431397655e-09,
+      "loss": 1.0135,
+      "step": 395
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 3.59375,
+      "learning_rate": 2.017148358763876e-09,
+      "loss": 1.0444,
+      "step": 396
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 3.65625,
+      "learning_rate": 1.2910374590194286e-09,
+      "loss": 1.0298,
+      "step": 397
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 3.625,
+      "learning_rate": 7.262359195070456e-10,
+      "loss": 1.1188,
+      "step": 398
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 3.765625,
+      "learning_rate": 3.227802021665838e-10,
+      "loss": 0.9863,
+      "step": 399
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.6875,
+      "learning_rate": 8.069635292179412e-11,
+      "loss": 1.0449,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.4375,
+      "learning_rate": 0.0,
+      "loss": 0.9839,
+      "step": 401
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 401,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 4.4848246137752125e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-401/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362ced6da0d7898d52ab2020fd33ac38835b0ffbc42b9542d2f86d5dcaedabb4
+size 5688

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.0.dev0"
+}

model.safetensors.index.json

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

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc48b9bd38dfab31354873b7d9ffea79fe57580f8c169135a96770978c612da
+size 772370432

pytorch_model.bin.index.json

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

runs/Feb27_12-22-56_zen/events.out.tfevents.1709036578.zen.3377863.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad338e52505f858013217ca40dee95726831c1a04d40a3cbaee25b61ffbb9054
+size 90945

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 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362ced6da0d7898d52ab2020fd33ac38835b0ffbc42b9542d2f86d5dcaedabb4
+size 5688