Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-301/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-602/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,175 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: NewEden/MistralAI-Nemo-Instruct-ChatML
+tags:
+- axolotl
+- generated_from_trainer
+datasets:
+- hardlyworking/HardlyRP
+- jeiku/Writing
+model-index:
+- name: Sapphire-12B
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.8.0`
+```yaml
+base_model: NewEden/MistralAI-Nemo-Instruct-ChatML
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: hardlyworking/HardlyRP
+    type: chat_template
+    chat_template: chatml
+    roles_to_train: ["gpt"]
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+    train_on_eos: turn
+  - path: jeiku/Writing
+    type: completion
+    field: text
+
+shuffle_merged_datasets: true
+dataset_prepared_path: dataset_preparedss
+val_set_size: 0.0025
+output_dir: 12b-out-0001-max_grad_norm
+
+hub_model_id: hardlyworking/Sapphire-12B
+hub_strategy: "all_checkpoints"
+push_dataset_to_hub:
+hf_use_auth_token: true
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_layer_norm: true
+liger_glu_activation: true
+liger_fused_linear_cross_entropy: true
+
+sequence_len: 8192
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+max_grad_norm: 0.001
+
+wandb_project: Sapphire
+wandb_entity:
+wandb_watch:
+wandb_name: Sapphire
+wandb_log_model:
+
+evals_per_epoch: 8
+eval_table_size:
+eval_max_new_tokens: 128
+
+gradient_accumulation_steps: 8
+micro_batch_size: 2
+num_epochs: 2
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 2e-6
+
+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
+s2_attention:
+
+warmup_ratio: 0.05
+saves_per_epoch: 1
+debug:
+weight_decay: 0.0001
+fsdp:
+fsdp_config:
+special_tokens:
+   pad_token: <pad>
+```
+
+</details><br>
+
+# Sapphire-12B
+
+This model is a fine-tuned version of [NewEden/MistralAI-Nemo-Instruct-ChatML](https://huggingface.co/NewEden/MistralAI-Nemo-Instruct-ChatML) on the hardlyworking/HardlyRP and the jeiku/Writing datasets.
+It achieves the following results on the evaluation set:
+- Loss: 1.6799
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 30
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.8932        | 0.0033 | 1    | 1.9155          |
+| 1.7729        | 0.1262 | 38   | 1.7802          |
+| 1.7163        | 0.2525 | 76   | 1.7111          |
+| 1.6484        | 0.3787 | 114  | 1.6970          |
+| 1.7006        | 0.5050 | 152  | 1.6907          |
+| 1.7276        | 0.6312 | 190  | 1.6874          |
+| 1.7042        | 0.7575 | 228  | 1.6847          |
+| 1.5575        | 0.8837 | 266  | 1.6825          |
+| 1.5451        | 1.0100 | 304  | 1.6816          |
+| 1.6592        | 1.1362 | 342  | 1.6807          |
+| 1.7344        | 1.2625 | 380  | 1.6805          |
+| 1.6953        | 1.3887 | 418  | 1.6798          |
+| 1.5799        | 1.5150 | 456  | 1.6799          |
+| 1.5241        | 1.6412 | 494  | 1.6799          |
+| 1.548         | 1.7674 | 532  | 1.6797          |
+| 1.6254        | 1.8937 | 570  | 1.6799          |
+
+
+### Framework versions
+
+- Transformers 4.51.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

checkpoint-301/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 131072
+}

checkpoint-301/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 1024000,
+  "pad_token_id": 10,
+  "transformers_version": "4.51.0"
+}

checkpoint-301/model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575a9c002d7e1c713a5dd1c2a2cb9babae9a45fc4ac37929322415b9a8b61a3a
+size 4865522496

checkpoint-301/model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b5fb3bb1d4acbf5b58e36649d3b16bdf56131dc9e77019d76f881c8725119d
+size 4907529424

checkpoint-301/model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c47e0c72aeb47fdce0b2b811f43cc8b27a78a0f7d07c675c8fdbcb5cfc92401
+size 4907529456

checkpoint-301/model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c045ee8362dd2002a0c8e7567a5529ad84178a61968fe8e5472d1164387dfa
+size 4907529456

checkpoint-301/model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5876a0acdaf1bbbeda1517093207c9fb9952f08168ff32ca6803883c47e741c6
+size 4907496272

checkpoint-301/model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 24495564800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

checkpoint-301/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131e50e7b14a29622d115df889446c34f2380aa8467f50afceccd200202917fc
+size 24878749708

checkpoint-301/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a6944c405a002fce05f295d08ea6650e2e2ad6dbf5d6da1e9053f7bf7f5827
+size 14244

checkpoint-301/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2484557978a2fe6c6378261a6c7d3f6207df09e4f40e7670ffa3875d12d2508d
+size 1064

checkpoint-301/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-301/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc07f4f61632a89d8248b43f25649d6cc45200f8709e9d9bcd0414b00a4064e2
+size 17078342

checkpoint-301/trainer_state.json

@@ -0,0 +1,2205 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 38,
+  "global_step": 301,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0033222591362126247,
+      "grad_norm": 103.0,
+      "learning_rate": 0.0,
+      "loss": 1.8932,
+      "step": 1
+    },
+    {
+      "epoch": 0.0033222591362126247,
+      "eval_loss": 1.915544867515564,
+      "eval_runtime": 18.4554,
+      "eval_samples_per_second": 3.034,
+      "eval_steps_per_second": 1.517,
+      "step": 1
+    },
+    {
+      "epoch": 0.006644518272425249,
+      "grad_norm": 50.5,
+      "learning_rate": 6.666666666666667e-08,
+      "loss": 1.9696,
+      "step": 2
+    },
+    {
+      "epoch": 0.009966777408637873,
+      "grad_norm": 120.5,
+      "learning_rate": 1.3333333333333334e-07,
+      "loss": 1.8563,
+      "step": 3
+    },
+    {
+      "epoch": 0.013289036544850499,
+      "grad_norm": 133.0,
+      "learning_rate": 2e-07,
+      "loss": 1.6208,
+      "step": 4
+    },
+    {
+      "epoch": 0.016611295681063124,
+      "grad_norm": 115.0,
+      "learning_rate": 2.6666666666666667e-07,
+      "loss": 1.8607,
+      "step": 5
+    },
+    {
+      "epoch": 0.019933554817275746,
+      "grad_norm": 42.0,
+      "learning_rate": 3.333333333333333e-07,
+      "loss": 1.9029,
+      "step": 6
+    },
+    {
+      "epoch": 0.023255813953488372,
+      "grad_norm": 112.0,
+      "learning_rate": 4e-07,
+      "loss": 1.8704,
+      "step": 7
+    },
+    {
+      "epoch": 0.026578073089700997,
+      "grad_norm": 84.0,
+      "learning_rate": 4.6666666666666666e-07,
+      "loss": 1.9463,
+      "step": 8
+    },
+    {
+      "epoch": 0.029900332225913623,
+      "grad_norm": 87.5,
+      "learning_rate": 5.333333333333333e-07,
+      "loss": 1.9199,
+      "step": 9
+    },
+    {
+      "epoch": 0.03322259136212625,
+      "grad_norm": 98.0,
+      "learning_rate": 6e-07,
+      "loss": 1.7595,
+      "step": 10
+    },
+    {
+      "epoch": 0.036544850498338874,
+      "grad_norm": 74.5,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 1.8111,
+      "step": 11
+    },
+    {
+      "epoch": 0.03986710963455149,
+      "grad_norm": 38.0,
+      "learning_rate": 7.333333333333332e-07,
+      "loss": 2.0669,
+      "step": 12
+    },
+    {
+      "epoch": 0.04318936877076412,
+      "grad_norm": 17.875,
+      "learning_rate": 8e-07,
+      "loss": 1.9348,
+      "step": 13
+    },
+    {
+      "epoch": 0.046511627906976744,
+      "grad_norm": 27.125,
+      "learning_rate": 8.666666666666667e-07,
+      "loss": 1.7987,
+      "step": 14
+    },
+    {
+      "epoch": 0.04983388704318937,
+      "grad_norm": 15.75,
+      "learning_rate": 9.333333333333333e-07,
+      "loss": 1.7805,
+      "step": 15
+    },
+    {
+      "epoch": 0.053156146179401995,
+      "grad_norm": 22.375,
+      "learning_rate": 1e-06,
+      "loss": 1.8799,
+      "step": 16
+    },
+    {
+      "epoch": 0.05647840531561462,
+      "grad_norm": 14.5,
+      "learning_rate": 1.0666666666666667e-06,
+      "loss": 1.7922,
+      "step": 17
+    },
+    {
+      "epoch": 0.059800664451827246,
+      "grad_norm": 18.5,
+      "learning_rate": 1.1333333333333332e-06,
+      "loss": 1.6291,
+      "step": 18
+    },
+    {
+      "epoch": 0.06312292358803986,
+      "grad_norm": 32.75,
+      "learning_rate": 1.2e-06,
+      "loss": 1.8288,
+      "step": 19
+    },
+    {
+      "epoch": 0.0664451827242525,
+      "grad_norm": 35.0,
+      "learning_rate": 1.2666666666666665e-06,
+      "loss": 1.8509,
+      "step": 20
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "grad_norm": 21.25,
+      "learning_rate": 1.3333333333333332e-06,
+      "loss": 1.7168,
+      "step": 21
+    },
+    {
+      "epoch": 0.07308970099667775,
+      "grad_norm": 20.375,
+      "learning_rate": 1.4e-06,
+      "loss": 1.6161,
+      "step": 22
+    },
+    {
+      "epoch": 0.07641196013289037,
+      "grad_norm": 18.75,
+      "learning_rate": 1.4666666666666665e-06,
+      "loss": 1.8325,
+      "step": 23
+    },
+    {
+      "epoch": 0.07973421926910298,
+      "grad_norm": 31.875,
+      "learning_rate": 1.5333333333333334e-06,
+      "loss": 1.7156,
+      "step": 24
+    },
+    {
+      "epoch": 0.08305647840531562,
+      "grad_norm": 29.75,
+      "learning_rate": 1.6e-06,
+      "loss": 1.7127,
+      "step": 25
+    },
+    {
+      "epoch": 0.08637873754152824,
+      "grad_norm": 19.5,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.7001,
+      "step": 26
+    },
+    {
+      "epoch": 0.08970099667774087,
+      "grad_norm": 15.0,
+      "learning_rate": 1.7333333333333334e-06,
+      "loss": 1.9355,
+      "step": 27
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 11.125,
+      "learning_rate": 1.8e-06,
+      "loss": 1.8541,
+      "step": 28
+    },
+    {
+      "epoch": 0.09634551495016612,
+      "grad_norm": 11.5,
+      "learning_rate": 1.8666666666666667e-06,
+      "loss": 1.7974,
+      "step": 29
+    },
+    {
+      "epoch": 0.09966777408637874,
+      "grad_norm": 11.8125,
+      "learning_rate": 1.933333333333333e-06,
+      "loss": 1.7858,
+      "step": 30
+    },
+    {
+      "epoch": 0.10299003322259136,
+      "grad_norm": 24.5,
+      "learning_rate": 2e-06,
+      "loss": 1.8134,
+      "step": 31
+    },
+    {
+      "epoch": 0.10631229235880399,
+      "grad_norm": 17.75,
+      "learning_rate": 1.9999849173865606e-06,
+      "loss": 1.8065,
+      "step": 32
+    },
+    {
+      "epoch": 0.10963455149501661,
+      "grad_norm": 20.625,
+      "learning_rate": 1.9999396700012128e-06,
+      "loss": 1.7911,
+      "step": 33
+    },
+    {
+      "epoch": 0.11295681063122924,
+      "grad_norm": 17.0,
+      "learning_rate": 1.999864259208854e-06,
+      "loss": 1.8103,
+      "step": 34
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 12.0,
+      "learning_rate": 1.999758687284268e-06,
+      "loss": 1.8241,
+      "step": 35
+    },
+    {
+      "epoch": 0.11960132890365449,
+      "grad_norm": 6.875,
+      "learning_rate": 1.999622957412056e-06,
+      "loss": 1.6427,
+      "step": 36
+    },
+    {
+      "epoch": 0.12292358803986711,
+      "grad_norm": 11.0,
+      "learning_rate": 1.9994570736865402e-06,
+      "loss": 1.781,
+      "step": 37
+    },
+    {
+      "epoch": 0.12624584717607973,
+      "grad_norm": 6.09375,
+      "learning_rate": 1.999261041111641e-06,
+      "loss": 1.7729,
+      "step": 38
+    },
+    {
+      "epoch": 0.12624584717607973,
+      "eval_loss": 1.7802449464797974,
+      "eval_runtime": 18.2451,
+      "eval_samples_per_second": 3.069,
+      "eval_steps_per_second": 1.535,
+      "step": 38
+    },
+    {
+      "epoch": 0.12956810631229235,
+      "grad_norm": 6.875,
+      "learning_rate": 1.999034865600726e-06,
+      "loss": 1.6201,
+      "step": 39
+    },
+    {
+      "epoch": 0.132890365448505,
+      "grad_norm": 10.1875,
+      "learning_rate": 1.9987785539764298e-06,
+      "loss": 1.6546,
+      "step": 40
+    },
+    {
+      "epoch": 0.1362126245847176,
+      "grad_norm": 7.8125,
+      "learning_rate": 1.998492113970451e-06,
+      "loss": 1.7503,
+      "step": 41
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "grad_norm": 5.8125,
+      "learning_rate": 1.9981755542233175e-06,
+      "loss": 1.608,
+      "step": 42
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 4.875,
+      "learning_rate": 1.9978288842841257e-06,
+      "loss": 1.7755,
+      "step": 43
+    },
+    {
+      "epoch": 0.1461794019933555,
+      "grad_norm": 4.09375,
+      "learning_rate": 1.9974521146102534e-06,
+      "loss": 1.7116,
+      "step": 44
+    },
+    {
+      "epoch": 0.14950166112956811,
+      "grad_norm": 5.625,
+      "learning_rate": 1.997045256567043e-06,
+      "loss": 1.9239,
+      "step": 45
+    },
+    {
+      "epoch": 0.15282392026578073,
+      "grad_norm": 5.59375,
+      "learning_rate": 1.99660832242746e-06,
+      "loss": 1.7939,
+      "step": 46
+    },
+    {
+      "epoch": 0.15614617940199335,
+      "grad_norm": 6.75,
+      "learning_rate": 1.9961413253717214e-06,
+      "loss": 1.7379,
+      "step": 47
+    },
+    {
+      "epoch": 0.15946843853820597,
+      "grad_norm": 7.09375,
+      "learning_rate": 1.995644279486899e-06,
+      "loss": 1.6323,
+      "step": 48
+    },
+    {
+      "epoch": 0.16279069767441862,
+      "grad_norm": 9.4375,
+      "learning_rate": 1.9951171997664958e-06,
+      "loss": 1.4941,
+      "step": 49
+    },
+    {
+      "epoch": 0.16611295681063123,
+      "grad_norm": 6.90625,
+      "learning_rate": 1.99456010210999e-06,
+      "loss": 1.7755,
+      "step": 50
+    },
+    {
+      "epoch": 0.16943521594684385,
+      "grad_norm": 6.5,
+      "learning_rate": 1.99397300332236e-06,
+      "loss": 1.725,
+      "step": 51
+    },
+    {
+      "epoch": 0.17275747508305647,
+      "grad_norm": 4.1875,
+      "learning_rate": 1.993355921113573e-06,
+      "loss": 1.8318,
+      "step": 52
+    },
+    {
+      "epoch": 0.1760797342192691,
+      "grad_norm": 3.78125,
+      "learning_rate": 1.9927088740980536e-06,
+      "loss": 1.6346,
+      "step": 53
+    },
+    {
+      "epoch": 0.17940199335548174,
+      "grad_norm": 3.625,
+      "learning_rate": 1.992031881794123e-06,
+      "loss": 1.6807,
+      "step": 54
+    },
+    {
+      "epoch": 0.18272425249169436,
+      "grad_norm": 3.5625,
+      "learning_rate": 1.9913249646234067e-06,
+      "loss": 1.8396,
+      "step": 55
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 6.875,
+      "learning_rate": 1.990588143910222e-06,
+      "loss": 1.5897,
+      "step": 56
+    },
+    {
+      "epoch": 0.1893687707641196,
+      "grad_norm": 6.0,
+      "learning_rate": 1.9898214418809326e-06,
+      "loss": 1.7284,
+      "step": 57
+    },
+    {
+      "epoch": 0.19269102990033224,
+      "grad_norm": 5.90625,
+      "learning_rate": 1.989024881663279e-06,
+      "loss": 1.6945,
+      "step": 58
+    },
+    {
+      "epoch": 0.19601328903654486,
+      "grad_norm": 4.28125,
+      "learning_rate": 1.9881984872856818e-06,
+      "loss": 1.6839,
+      "step": 59
+    },
+    {
+      "epoch": 0.19933554817275748,
+      "grad_norm": 4.15625,
+      "learning_rate": 1.9873422836765135e-06,
+      "loss": 1.6582,
+      "step": 60
+    },
+    {
+      "epoch": 0.2026578073089701,
+      "grad_norm": 3.8125,
+      "learning_rate": 1.9864562966633515e-06,
+      "loss": 1.8207,
+      "step": 61
+    },
+    {
+      "epoch": 0.2059800664451827,
+      "grad_norm": 4.78125,
+      "learning_rate": 1.9855405529721944e-06,
+      "loss": 1.6543,
+      "step": 62
+    },
+    {
+      "epoch": 0.20930232558139536,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.9845950802266584e-06,
+      "loss": 1.817,
+      "step": 63
+    },
+    {
+      "epoch": 0.21262458471760798,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.9836199069471437e-06,
+      "loss": 1.5228,
+      "step": 64
+    },
+    {
+      "epoch": 0.2159468438538206,
+      "grad_norm": 3.328125,
+      "learning_rate": 1.982615062549973e-06,
+      "loss": 1.6324,
+      "step": 65
+    },
+    {
+      "epoch": 0.21926910299003322,
+      "grad_norm": 3.25,
+      "learning_rate": 1.9815805773465063e-06,
+      "loss": 1.7938,
+      "step": 66
+    },
+    {
+      "epoch": 0.22259136212624583,
+      "grad_norm": 3.265625,
+      "learning_rate": 1.9805164825422237e-06,
+      "loss": 1.7176,
+      "step": 67
+    },
+    {
+      "epoch": 0.22591362126245848,
+      "grad_norm": 3.6875,
+      "learning_rate": 1.9794228102357864e-06,
+      "loss": 1.8079,
+      "step": 68
+    },
+    {
+      "epoch": 0.2292358803986711,
+      "grad_norm": 2.953125,
+      "learning_rate": 1.9782995934180687e-06,
+      "loss": 1.6981,
+      "step": 69
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 3.046875,
+      "learning_rate": 1.9771468659711594e-06,
+      "loss": 1.6665,
+      "step": 70
+    },
+    {
+      "epoch": 0.23588039867109634,
+      "grad_norm": 3.296875,
+      "learning_rate": 1.9759646626673444e-06,
+      "loss": 1.7792,
+      "step": 71
+    },
+    {
+      "epoch": 0.23920265780730898,
+      "grad_norm": 3.515625,
+      "learning_rate": 1.974753019168054e-06,
+      "loss": 1.7666,
+      "step": 72
+    },
+    {
+      "epoch": 0.2425249169435216,
+      "grad_norm": 3.234375,
+      "learning_rate": 1.97351197202279e-06,
+      "loss": 1.7061,
+      "step": 73
+    },
+    {
+      "epoch": 0.24584717607973422,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.9722415586680203e-06,
+      "loss": 1.6216,
+      "step": 74
+    },
+    {
+      "epoch": 0.24916943521594684,
+      "grad_norm": 6.6875,
+      "learning_rate": 1.970941817426052e-06,
+      "loss": 1.6851,
+      "step": 75
+    },
+    {
+      "epoch": 0.25249169435215946,
+      "grad_norm": 2.84375,
+      "learning_rate": 1.969612787503875e-06,
+      "loss": 1.7163,
+      "step": 76
+    },
+    {
+      "epoch": 0.25249169435215946,
+      "eval_loss": 1.7110573053359985,
+      "eval_runtime": 18.248,
+      "eval_samples_per_second": 3.069,
+      "eval_steps_per_second": 1.534,
+      "step": 76
+    },
+    {
+      "epoch": 0.2558139534883721,
+      "grad_norm": 3.484375,
+      "learning_rate": 1.968254508991978e-06,
+      "loss": 1.6136,
+      "step": 77
+    },
+    {
+      "epoch": 0.2591362126245847,
+      "grad_norm": 2.84375,
+      "learning_rate": 1.9668670228631416e-06,
+      "loss": 1.6798,
+      "step": 78
+    },
+    {
+      "epoch": 0.26245847176079734,
+      "grad_norm": 2.6875,
+      "learning_rate": 1.965450370971198e-06,
+      "loss": 1.6868,
+      "step": 79
+    },
+    {
+      "epoch": 0.26578073089701,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.964004596049774e-06,
+      "loss": 1.8666,
+      "step": 80
+    },
+    {
+      "epoch": 0.2691029900332226,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.962529741710998e-06,
+      "loss": 1.5132,
+      "step": 81
+    },
+    {
+      "epoch": 0.2724252491694352,
+      "grad_norm": 4.125,
+      "learning_rate": 1.961025852444185e-06,
+      "loss": 1.7368,
+      "step": 82
+    },
+    {
+      "epoch": 0.2757475083056478,
+      "grad_norm": 2.953125,
+      "learning_rate": 1.9594929736144973e-06,
+      "loss": 1.766,
+      "step": 83
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.9579311514615715e-06,
+      "loss": 1.742,
+      "step": 84
+    },
+    {
+      "epoch": 0.2823920265780731,
+      "grad_norm": 5.25,
+      "learning_rate": 1.9563404330981273e-06,
+      "loss": 1.6776,
+      "step": 85
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.9547208665085457e-06,
+      "loss": 1.665,
+      "step": 86
+    },
+    {
+      "epoch": 0.28903654485049834,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.9530725005474194e-06,
+      "loss": 1.7081,
+      "step": 87
+    },
+    {
+      "epoch": 0.292358803986711,
+      "grad_norm": 2.890625,
+      "learning_rate": 1.951395384938082e-06,
+      "loss": 1.6911,
+      "step": 88
+    },
+    {
+      "epoch": 0.2956810631229236,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.9496895702711067e-06,
+      "loss": 1.722,
+      "step": 89
+    },
+    {
+      "epoch": 0.29900332225913623,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.9479551080027796e-06,
+      "loss": 1.5948,
+      "step": 90
+    },
+    {
+      "epoch": 0.3023255813953488,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.9461920504535483e-06,
+      "loss": 1.6996,
+      "step": 91
+    },
+    {
+      "epoch": 0.30564784053156147,
+      "grad_norm": 2.6875,
+      "learning_rate": 1.9444004508064445e-06,
+      "loss": 1.8464,
+      "step": 92
+    },
+    {
+      "epoch": 0.3089700996677741,
+      "grad_norm": 2.890625,
+      "learning_rate": 1.942580363105477e-06,
+      "loss": 1.6863,
+      "step": 93
+    },
+    {
+      "epoch": 0.3122923588039867,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.9407318422540057e-06,
+      "loss": 1.6463,
+      "step": 94
+    },
+    {
+      "epoch": 0.31561461794019935,
+      "grad_norm": 11.4375,
+      "learning_rate": 1.9388549440130797e-06,
+      "loss": 1.7122,
+      "step": 95
+    },
+    {
+      "epoch": 0.31893687707641194,
+      "grad_norm": 3.046875,
+      "learning_rate": 1.936949724999762e-06,
+      "loss": 1.6855,
+      "step": 96
+    },
+    {
+      "epoch": 0.3222591362126246,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.9350162426854148e-06,
+      "loss": 1.6138,
+      "step": 97
+    },
+    {
+      "epoch": 0.32558139534883723,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.9330545553939717e-06,
+      "loss": 1.6139,
+      "step": 98
+    },
+    {
+      "epoch": 0.3289036544850498,
+      "grad_norm": 3.046875,
+      "learning_rate": 1.9310647223001747e-06,
+      "loss": 1.5904,
+      "step": 99
+    },
+    {
+      "epoch": 0.33222591362126247,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.9290468034277907e-06,
+      "loss": 1.5604,
+      "step": 100
+    },
+    {
+      "epoch": 0.33554817275747506,
+      "grad_norm": 3.234375,
+      "learning_rate": 1.9270008596478004e-06,
+      "loss": 1.6564,
+      "step": 101
+    },
+    {
+      "epoch": 0.3388704318936877,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.9249269526765616e-06,
+      "loss": 1.6987,
+      "step": 102
+    },
+    {
+      "epoch": 0.34219269102990035,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.922825145073949e-06,
+      "loss": 1.7714,
+      "step": 103
+    },
+    {
+      "epoch": 0.34551495016611294,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.9206955002414657e-06,
+      "loss": 1.7206,
+      "step": 104
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 2.890625,
+      "learning_rate": 1.9185380824203314e-06,
+      "loss": 1.8164,
+      "step": 105
+    },
+    {
+      "epoch": 0.3521594684385382,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.9163529566895437e-06,
+      "loss": 1.7213,
+      "step": 106
+    },
+    {
+      "epoch": 0.3554817275747508,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.9141401889639164e-06,
+      "loss": 1.7515,
+      "step": 107
+    },
+    {
+      "epoch": 0.3588039867109635,
+      "grad_norm": 2.796875,
+      "learning_rate": 1.91189984599209e-06,
+      "loss": 1.7709,
+      "step": 108
+    },
+    {
+      "epoch": 0.36212624584717606,
+      "grad_norm": 2.75,
+      "learning_rate": 1.9096319953545185e-06,
+      "loss": 1.7297,
+      "step": 109
+    },
+    {
+      "epoch": 0.3654485049833887,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.9073367054614305e-06,
+      "loss": 1.709,
+      "step": 110
+    },
+    {
+      "epoch": 0.3687707641196013,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.9050140455507666e-06,
+      "loss": 1.6388,
+      "step": 111
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.9026640856860902e-06,
+      "loss": 1.7441,
+      "step": 112
+    },
+    {
+      "epoch": 0.3754152823920266,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.900286896754474e-06,
+      "loss": 1.6313,
+      "step": 113
+    },
+    {
+      "epoch": 0.3787375415282392,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.8978825504643607e-06,
+      "loss": 1.6484,
+      "step": 114
+    },
+    {
+      "epoch": 0.3787375415282392,
+      "eval_loss": 1.697015404701233,
+      "eval_runtime": 18.2245,
+      "eval_samples_per_second": 3.073,
+      "eval_steps_per_second": 1.536,
+      "step": 114
+    },
+    {
+      "epoch": 0.38205980066445183,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.8954511193434021e-06,
+      "loss": 1.5279,
+      "step": 115
+    },
+    {
+      "epoch": 0.3853820598006645,
+      "grad_norm": 2.859375,
+      "learning_rate": 1.8929926767362697e-06,
+      "loss": 1.7743,
+      "step": 116
+    },
+    {
+      "epoch": 0.38870431893687707,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.8905072968024423e-06,
+      "loss": 1.9903,
+      "step": 117
+    },
+    {
+      "epoch": 0.3920265780730897,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.8879950545139692e-06,
+      "loss": 1.6696,
+      "step": 118
+    },
+    {
+      "epoch": 0.3953488372093023,
+      "grad_norm": 3.6875,
+      "learning_rate": 1.8854560256532098e-06,
+      "loss": 1.5742,
+      "step": 119
+    },
+    {
+      "epoch": 0.39867109634551495,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.8828902868105452e-06,
+      "loss": 1.6362,
+      "step": 120
+    },
+    {
+      "epoch": 0.4019933554817276,
+      "grad_norm": 3.21875,
+      "learning_rate": 1.8802979153820696e-06,
+      "loss": 1.7119,
+      "step": 121
+    },
+    {
+      "epoch": 0.4053156146179402,
+      "grad_norm": 2.296875,
+      "learning_rate": 1.8776789895672556e-06,
+      "loss": 1.6249,
+      "step": 122
+    },
+    {
+      "epoch": 0.40863787375415284,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.8750335883665945e-06,
+      "loss": 1.7243,
+      "step": 123
+    },
+    {
+      "epoch": 0.4119601328903654,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.8723617915792135e-06,
+      "loss": 1.7061,
+      "step": 124
+    },
+    {
+      "epoch": 0.4152823920265781,
+      "grad_norm": 2.5,
+      "learning_rate": 1.869663679800469e-06,
+      "loss": 1.7035,
+      "step": 125
+    },
+    {
+      "epoch": 0.4186046511627907,
+      "grad_norm": 2.5,
+      "learning_rate": 1.866939334419515e-06,
+      "loss": 1.6081,
+      "step": 126
+    },
+    {
+      "epoch": 0.4219269102990033,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.8641888376168483e-06,
+      "loss": 1.5159,
+      "step": 127
+    },
+    {
+      "epoch": 0.42524916943521596,
+      "grad_norm": 3.3125,
+      "learning_rate": 1.8614122723618283e-06,
+      "loss": 1.6889,
+      "step": 128
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.8586097224101765e-06,
+      "loss": 1.8138,
+      "step": 129
+    },
+    {
+      "epoch": 0.4318936877076412,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.8557812723014475e-06,
+      "loss": 1.6101,
+      "step": 130
+    },
+    {
+      "epoch": 0.43521594684385384,
+      "grad_norm": 2.6875,
+      "learning_rate": 1.852927007356481e-06,
+      "loss": 1.7078,
+      "step": 131
+    },
+    {
+      "epoch": 0.43853820598006643,
+      "grad_norm": 2.5625,
+      "learning_rate": 1.8500470136748263e-06,
+      "loss": 1.7445,
+      "step": 132
+    },
+    {
+      "epoch": 0.4418604651162791,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.8471413781321465e-06,
+      "loss": 1.7156,
+      "step": 133
+    },
+    {
+      "epoch": 0.44518272425249167,
+      "grad_norm": 4.4375,
+      "learning_rate": 1.8442101883775967e-06,
+      "loss": 1.6427,
+      "step": 134
+    },
+    {
+      "epoch": 0.4485049833887043,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.8412535328311812e-06,
+      "loss": 1.7093,
+      "step": 135
+    },
+    {
+      "epoch": 0.45182724252491696,
+      "grad_norm": 3.484375,
+      "learning_rate": 1.838271500681085e-06,
+      "loss": 1.5621,
+      "step": 136
+    },
+    {
+      "epoch": 0.45514950166112955,
+      "grad_norm": 2.953125,
+      "learning_rate": 1.8352641818809846e-06,
+      "loss": 1.8257,
+      "step": 137
+    },
+    {
+      "epoch": 0.4584717607973422,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.8322316671473342e-06,
+      "loss": 1.6519,
+      "step": 138
+    },
+    {
+      "epoch": 0.46179401993355484,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.8291740479566282e-06,
+      "loss": 1.7275,
+      "step": 139
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.8260914165426438e-06,
+      "loss": 1.6894,
+      "step": 140
+    },
+    {
+      "epoch": 0.4684385382059801,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.8229838658936564e-06,
+      "loss": 1.6601,
+      "step": 141
+    },
+    {
+      "epoch": 0.4717607973421927,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.8198514897496367e-06,
+      "loss": 1.6062,
+      "step": 142
+    },
+    {
+      "epoch": 0.4750830564784053,
+      "grad_norm": 2.5,
+      "learning_rate": 1.8166943825994216e-06,
+      "loss": 1.5786,
+      "step": 143
+    },
+    {
+      "epoch": 0.47840531561461797,
+      "grad_norm": 2.875,
+      "learning_rate": 1.813512639677865e-06,
+      "loss": 1.7378,
+      "step": 144
+    },
+    {
+      "epoch": 0.48172757475083056,
+      "grad_norm": 3.390625,
+      "learning_rate": 1.8103063569629632e-06,
+      "loss": 1.6687,
+      "step": 145
+    },
+    {
+      "epoch": 0.4850498338870432,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.8070756311729625e-06,
+      "loss": 1.714,
+      "step": 146
+    },
+    {
+      "epoch": 0.4883720930232558,
+      "grad_norm": 2.375,
+      "learning_rate": 1.803820559763439e-06,
+      "loss": 1.7529,
+      "step": 147
+    },
+    {
+      "epoch": 0.49169435215946844,
+      "grad_norm": 2.859375,
+      "learning_rate": 1.8005412409243603e-06,
+      "loss": 1.7381,
+      "step": 148
+    },
+    {
+      "epoch": 0.4950166112956811,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.7972377735771232e-06,
+      "loss": 1.6673,
+      "step": 149
+    },
+    {
+      "epoch": 0.4983388704318937,
+      "grad_norm": 2.5,
+      "learning_rate": 1.7939102573715696e-06,
+      "loss": 1.7715,
+      "step": 150
+    },
+    {
+      "epoch": 0.5016611295681063,
+      "grad_norm": 2.359375,
+      "learning_rate": 1.7905587926829812e-06,
+      "loss": 1.7926,
+      "step": 151
+    },
+    {
+      "epoch": 0.5049833887043189,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.78718348060905e-06,
+      "loss": 1.7006,
+      "step": 152
+    },
+    {
+      "epoch": 0.5049833887043189,
+      "eval_loss": 1.690727949142456,
+      "eval_runtime": 18.2527,
+      "eval_samples_per_second": 3.068,
+      "eval_steps_per_second": 1.534,
+      "step": 152
+    },
+    {
+      "epoch": 0.5083056478405316,
+      "grad_norm": 2.375,
+      "learning_rate": 1.7837844229668311e-06,
+      "loss": 1.6887,
+      "step": 153
+    },
+    {
+      "epoch": 0.5116279069767442,
+      "grad_norm": 3.1875,
+      "learning_rate": 1.7803617222896694e-06,
+      "loss": 1.6259,
+      "step": 154
+    },
+    {
+      "epoch": 0.5149501661129569,
+      "grad_norm": 3.0,
+      "learning_rate": 1.776915481824107e-06,
+      "loss": 1.7458,
+      "step": 155
+    },
+    {
+      "epoch": 0.5182724252491694,
+      "grad_norm": 3.359375,
+      "learning_rate": 1.7734458055267699e-06,
+      "loss": 1.5833,
+      "step": 156
+    },
+    {
+      "epoch": 0.521594684385382,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.7699527980612304e-06,
+      "loss": 1.6552,
+      "step": 157
+    },
+    {
+      "epoch": 0.5249169435215947,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.766436564794851e-06,
+      "loss": 1.697,
+      "step": 158
+    },
+    {
+      "epoch": 0.5282392026578073,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.7628972117956066e-06,
+      "loss": 1.6248,
+      "step": 159
+    },
+    {
+      "epoch": 0.53156146179402,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.7593348458288833e-06,
+      "loss": 1.7622,
+      "step": 160
+    },
+    {
+      "epoch": 0.5348837209302325,
+      "grad_norm": 3.296875,
+      "learning_rate": 1.7557495743542582e-06,
+      "loss": 1.7791,
+      "step": 161
+    },
+    {
+      "epoch": 0.5382059800664452,
+      "grad_norm": 2.84375,
+      "learning_rate": 1.7521415055222592e-06,
+      "loss": 1.7372,
+      "step": 162
+    },
+    {
+      "epoch": 0.5415282392026578,
+      "grad_norm": 6.625,
+      "learning_rate": 1.748510748171101e-06,
+      "loss": 1.6665,
+      "step": 163
+    },
+    {
+      "epoch": 0.5448504983388704,
+      "grad_norm": 2.953125,
+      "learning_rate": 1.744857411823403e-06,
+      "loss": 1.5668,
+      "step": 164
+    },
+    {
+      "epoch": 0.5481727574750831,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.7411816066828849e-06,
+      "loss": 1.5494,
+      "step": 165
+    },
+    {
+      "epoch": 0.5514950166112956,
+      "grad_norm": 3.578125,
+      "learning_rate": 1.7374834436310426e-06,
+      "loss": 1.6968,
+      "step": 166
+    },
+    {
+      "epoch": 0.5548172757475083,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.7337630342238039e-06,
+      "loss": 1.5636,
+      "step": 167
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 2.78125,
+      "learning_rate": 1.7300204906881626e-06,
+      "loss": 1.7675,
+      "step": 168
+    },
+    {
+      "epoch": 0.5614617940199336,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.7262559259187931e-06,
+      "loss": 1.7314,
+      "step": 169
+    },
+    {
+      "epoch": 0.5647840531561462,
+      "grad_norm": 4.25,
+      "learning_rate": 1.7224694534746464e-06,
+      "loss": 1.8208,
+      "step": 170
+    },
+    {
+      "epoch": 0.5681063122923588,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.7186611875755225e-06,
+      "loss": 1.7366,
+      "step": 171
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.7148312430986262e-06,
+      "loss": 1.6048,
+      "step": 172
+    },
+    {
+      "epoch": 0.574750830564784,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.7109797355751016e-06,
+      "loss": 1.7103,
+      "step": 173
+    },
+    {
+      "epoch": 0.5780730897009967,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.7071067811865474e-06,
+      "loss": 1.6318,
+      "step": 174
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 2.21875,
+      "learning_rate": 1.7032124967615109e-06,
+      "loss": 1.5906,
+      "step": 175
+    },
+    {
+      "epoch": 0.584717607973422,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.6992969997719657e-06,
+      "loss": 1.5532,
+      "step": 176
+    },
+    {
+      "epoch": 0.5880398671096345,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.6953604083297663e-06,
+      "loss": 1.6565,
+      "step": 177
+    },
+    {
+      "epoch": 0.5913621262458472,
+      "grad_norm": 3.03125,
+      "learning_rate": 1.6914028411830877e-06,
+      "loss": 1.6321,
+      "step": 178
+    },
+    {
+      "epoch": 0.5946843853820598,
+      "grad_norm": 3.484375,
+      "learning_rate": 1.6874244177128393e-06,
+      "loss": 1.63,
+      "step": 179
+    },
+    {
+      "epoch": 0.5980066445182725,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.6834252579290688e-06,
+      "loss": 1.7393,
+      "step": 180
+    },
+    {
+      "epoch": 0.6013289036544851,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.679405482467338e-06,
+      "loss": 1.6178,
+      "step": 181
+    },
+    {
+      "epoch": 0.6046511627906976,
+      "grad_norm": 2.9375,
+      "learning_rate": 1.6753652125850862e-06,
+      "loss": 1.7313,
+      "step": 182
+    },
+    {
+      "epoch": 0.6079734219269103,
+      "grad_norm": 4.53125,
+      "learning_rate": 1.6713045701579702e-06,
+      "loss": 1.5631,
+      "step": 183
+    },
+    {
+      "epoch": 0.6112956810631229,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.6672236776761906e-06,
+      "loss": 1.5669,
+      "step": 184
+    },
+    {
+      "epoch": 0.6146179401993356,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.6631226582407952e-06,
+      "loss": 1.753,
+      "step": 185
+    },
+    {
+      "epoch": 0.6179401993355482,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.6590016355599652e-06,
+      "loss": 1.5346,
+      "step": 186
+    },
+    {
+      "epoch": 0.6212624584717608,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.6548607339452852e-06,
+      "loss": 1.6781,
+      "step": 187
+    },
+    {
+      "epoch": 0.6245847176079734,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.6507000783079911e-06,
+      "loss": 1.5406,
+      "step": 188
+    },
+    {
+      "epoch": 0.627906976744186,
+      "grad_norm": 3.09375,
+      "learning_rate": 1.6465197941552053e-06,
+      "loss": 1.6581,
+      "step": 189
+    },
+    {
+      "epoch": 0.6312292358803987,
+      "grad_norm": 3.140625,
+      "learning_rate": 1.642320007586147e-06,
+      "loss": 1.7276,
+      "step": 190
+    },
+    {
+      "epoch": 0.6312292358803987,
+      "eval_loss": 1.6873770952224731,
+      "eval_runtime": 18.1896,
+      "eval_samples_per_second": 3.079,
+      "eval_steps_per_second": 1.539,
+      "step": 190
+    },
+    {
+      "epoch": 0.6345514950166113,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.6381008452883307e-06,
+      "loss": 1.7267,
+      "step": 191
+    },
+    {
+      "epoch": 0.6378737541528239,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.6338624345337451e-06,
+      "loss": 1.7332,
+      "step": 192
+    },
+    {
+      "epoch": 0.6411960132890365,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.6296049031750111e-06,
+      "loss": 1.8304,
+      "step": 193
+    },
+    {
+      "epoch": 0.6445182724252492,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.6253283796415293e-06,
+      "loss": 1.659,
+      "step": 194
+    },
+    {
+      "epoch": 0.6478405315614618,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.6210329929356017e-06,
+      "loss": 1.5788,
+      "step": 195
+    },
+    {
+      "epoch": 0.6511627906976745,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.6167188726285433e-06,
+      "loss": 1.6042,
+      "step": 196
+    },
+    {
+      "epoch": 0.654485049833887,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.6123861488567708e-06,
+      "loss": 1.5796,
+      "step": 197
+    },
+    {
+      "epoch": 0.6578073089700996,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.608034952317881e-06,
+      "loss": 1.7463,
+      "step": 198
+    },
+    {
+      "epoch": 0.6611295681063123,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.603665414266704e-06,
+      "loss": 1.563,
+      "step": 199
+    },
+    {
+      "epoch": 0.6644518272425249,
+      "grad_norm": 2.25,
+      "learning_rate": 1.5992776665113468e-06,
+      "loss": 1.6348,
+      "step": 200
+    },
+    {
+      "epoch": 0.6677740863787376,
+      "grad_norm": 2.21875,
+      "learning_rate": 1.594871841409216e-06,
+      "loss": 1.6304,
+      "step": 201
+    },
+    {
+      "epoch": 0.6710963455149501,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.5904480718630252e-06,
+      "loss": 1.7017,
+      "step": 202
+    },
+    {
+      "epoch": 0.6744186046511628,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.5860064913167862e-06,
+      "loss": 1.5088,
+      "step": 203
+    },
+    {
+      "epoch": 0.6777408637873754,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.581547233751784e-06,
+      "loss": 1.6744,
+      "step": 204
+    },
+    {
+      "epoch": 0.6810631229235881,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.577070433682535e-06,
+      "loss": 1.7003,
+      "step": 205
+    },
+    {
+      "epoch": 0.6843853820598007,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.572576226152729e-06,
+      "loss": 1.6027,
+      "step": 206
+    },
+    {
+      "epoch": 0.6877076411960132,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.5680647467311555e-06,
+      "loss": 1.6389,
+      "step": 207
+    },
+    {
+      "epoch": 0.6910299003322259,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.5635361315076154e-06,
+      "loss": 1.5774,
+      "step": 208
+    },
+    {
+      "epoch": 0.6943521594684385,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.5589905170888133e-06,
+      "loss": 1.5609,
+      "step": 209
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 3.90625,
+      "learning_rate": 1.5544280405942406e-06,
+      "loss": 1.6494,
+      "step": 210
+    },
+    {
+      "epoch": 0.7009966777408638,
+      "grad_norm": 2.25,
+      "learning_rate": 1.5498488396520347e-06,
+      "loss": 1.7061,
+      "step": 211
+    },
+    {
+      "epoch": 0.7043189368770764,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.5452530523948321e-06,
+      "loss": 1.6194,
+      "step": 212
+    },
+    {
+      "epoch": 0.707641196013289,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.5406408174555977e-06,
+      "loss": 1.8289,
+      "step": 213
+    },
+    {
+      "epoch": 0.7109634551495017,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.5360122739634442e-06,
+      "loss": 1.793,
+      "step": 214
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 2.21875,
+      "learning_rate": 1.5313675615394372e-06,
+      "loss": 1.7017,
+      "step": 215
+    },
+    {
+      "epoch": 0.717607973421927,
+      "grad_norm": 2.78125,
+      "learning_rate": 1.52670682029238e-06,
+      "loss": 1.5668,
+      "step": 216
+    },
+    {
+      "epoch": 0.7209302325581395,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.5220301908145903e-06,
+      "loss": 1.6355,
+      "step": 217
+    },
+    {
+      "epoch": 0.7242524916943521,
+      "grad_norm": 2.265625,
+      "learning_rate": 1.5173378141776567e-06,
+      "loss": 1.5903,
+      "step": 218
+    },
+    {
+      "epoch": 0.7275747508305648,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.5126298319281855e-06,
+      "loss": 1.6904,
+      "step": 219
+    },
+    {
+      "epoch": 0.7308970099667774,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.5079063860835292e-06,
+      "loss": 1.603,
+      "step": 220
+    },
+    {
+      "epoch": 0.7342192691029901,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.5031676191275037e-06,
+      "loss": 1.5458,
+      "step": 221
+    },
+    {
+      "epoch": 0.7375415282392026,
+      "grad_norm": 3.578125,
+      "learning_rate": 1.498413674006089e-06,
+      "loss": 1.8769,
+      "step": 222
+    },
+    {
+      "epoch": 0.7408637873754153,
+      "grad_norm": 2.90625,
+      "learning_rate": 1.4936446941231185e-06,
+      "loss": 1.6354,
+      "step": 223
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.4888608233359518e-06,
+      "loss": 1.6826,
+      "step": 224
+    },
+    {
+      "epoch": 0.7475083056478405,
+      "grad_norm": 2.796875,
+      "learning_rate": 1.4840622059511374e-06,
+      "loss": 1.7523,
+      "step": 225
+    },
+    {
+      "epoch": 0.7508305647840532,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.4792489867200568e-06,
+      "loss": 1.7502,
+      "step": 226
+    },
+    {
+      "epoch": 0.7541528239202658,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.4744213108345602e-06,
+      "loss": 1.6862,
+      "step": 227
+    },
+    {
+      "epoch": 0.7574750830564784,
+      "grad_norm": 3.140625,
+      "learning_rate": 1.4695793239225863e-06,
+      "loss": 1.7042,
+      "step": 228
+    },
+    {
+      "epoch": 0.7574750830564784,
+      "eval_loss": 1.6847137212753296,
+      "eval_runtime": 18.2782,
+      "eval_samples_per_second": 3.064,
+      "eval_steps_per_second": 1.532,
+      "step": 228
+    },
+    {
+      "epoch": 0.760797342192691,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.4647231720437684e-06,
+      "loss": 1.7811,
+      "step": 229
+    },
+    {
+      "epoch": 0.7641196013289037,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.4598530016850301e-06,
+      "loss": 1.6068,
+      "step": 230
+    },
+    {
+      "epoch": 0.7674418604651163,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.454968959756165e-06,
+      "loss": 1.7465,
+      "step": 231
+    },
+    {
+      "epoch": 0.770764119601329,
+      "grad_norm": 3.125,
+      "learning_rate": 1.450071193585406e-06,
+      "loss": 1.5262,
+      "step": 232
+    },
+    {
+      "epoch": 0.7740863787375415,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.4451598509149806e-06,
+      "loss": 1.6686,
+      "step": 233
+    },
+    {
+      "epoch": 0.7774086378737541,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.4402350798966554e-06,
+      "loss": 1.6948,
+      "step": 234
+    },
+    {
+      "epoch": 0.7807308970099668,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.435297029087265e-06,
+      "loss": 1.7236,
+      "step": 235
+    },
+    {
+      "epoch": 0.7840531561461794,
+      "grad_norm": 2.796875,
+      "learning_rate": 1.4303458474442322e-06,
+      "loss": 1.8507,
+      "step": 236
+    },
+    {
+      "epoch": 0.7873754152823921,
+      "grad_norm": 2.796875,
+      "learning_rate": 1.4253816843210748e-06,
+      "loss": 1.6888,
+      "step": 237
+    },
+    {
+      "epoch": 0.7906976744186046,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.4204046894629e-06,
+      "loss": 1.6293,
+      "step": 238
+    },
+    {
+      "epoch": 0.7940199335548173,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.4154150130018865e-06,
+      "loss": 1.6534,
+      "step": 239
+    },
+    {
+      "epoch": 0.7973421926910299,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.410412805452757e-06,
+      "loss": 1.6228,
+      "step": 240
+    },
+    {
+      "epoch": 0.8006644518272426,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.4053982177082366e-06,
+      "loss": 1.7322,
+      "step": 241
+    },
+    {
+      "epoch": 0.8039867109634552,
+      "grad_norm": 3.1875,
+      "learning_rate": 1.400371401034503e-06,
+      "loss": 1.6871,
+      "step": 242
+    },
+    {
+      "epoch": 0.8073089700996677,
+      "grad_norm": 2.640625,
+      "learning_rate": 1.3953325070666213e-06,
+      "loss": 1.6272,
+      "step": 243
+    },
+    {
+      "epoch": 0.8106312292358804,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.3902816878039713e-06,
+      "loss": 1.5389,
+      "step": 244
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 2.375,
+      "learning_rate": 1.3852190956056622e-06,
+      "loss": 1.6966,
+      "step": 245
+    },
+    {
+      "epoch": 0.8172757475083057,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.3801448831859362e-06,
+      "loss": 1.7712,
+      "step": 246
+    },
+    {
+      "epoch": 0.8205980066445183,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.3750592036095619e-06,
+      "loss": 1.6111,
+      "step": 247
+    },
+    {
+      "epoch": 0.8239202657807309,
+      "grad_norm": 2.75,
+      "learning_rate": 1.3699622102872174e-06,
+      "loss": 1.6272,
+      "step": 248
+    },
+    {
+      "epoch": 0.8272425249169435,
+      "grad_norm": 2.25,
+      "learning_rate": 1.3648540569708635e-06,
+      "loss": 1.8452,
+      "step": 249
+    },
+    {
+      "epoch": 0.8305647840531561,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.359734897749103e-06,
+      "loss": 1.6621,
+      "step": 250
+    },
+    {
+      "epoch": 0.8338870431893688,
+      "grad_norm": 2.296875,
+      "learning_rate": 1.3546048870425354e-06,
+      "loss": 1.6064,
+      "step": 251
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "grad_norm": 3.53125,
+      "learning_rate": 1.3494641795990985e-06,
+      "loss": 1.6591,
+      "step": 252
+    },
+    {
+      "epoch": 0.840531561461794,
+      "grad_norm": 2.296875,
+      "learning_rate": 1.3443129304893973e-06,
+      "loss": 1.6282,
+      "step": 253
+    },
+    {
+      "epoch": 0.8438538205980066,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.339151295102031e-06,
+      "loss": 1.5982,
+      "step": 254
+    },
+    {
+      "epoch": 0.8471760797342193,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.3339794291389012e-06,
+      "loss": 1.6695,
+      "step": 255
+    },
+    {
+      "epoch": 0.8504983388704319,
+      "grad_norm": 2.234375,
+      "learning_rate": 1.3287974886105188e-06,
+      "loss": 1.6515,
+      "step": 256
+    },
+    {
+      "epoch": 0.8538205980066446,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.3236056298312956e-06,
+      "loss": 1.595,
+      "step": 257
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.3184040094148289e-06,
+      "loss": 1.653,
+      "step": 258
+    },
+    {
+      "epoch": 0.8604651162790697,
+      "grad_norm": 3.0625,
+      "learning_rate": 1.313192784269179e-06,
+      "loss": 1.6397,
+      "step": 259
+    },
+    {
+      "epoch": 0.8637873754152824,
+      "grad_norm": 2.359375,
+      "learning_rate": 1.3079721115921346e-06,
+      "loss": 1.7935,
+      "step": 260
+    },
+    {
+      "epoch": 0.867109634551495,
+      "grad_norm": 2.75,
+      "learning_rate": 1.302742148866472e-06,
+      "loss": 1.6791,
+      "step": 261
+    },
+    {
+      "epoch": 0.8704318936877077,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.297503053855203e-06,
+      "loss": 1.7556,
+      "step": 262
+    },
+    {
+      "epoch": 0.8737541528239202,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.2922549845968172e-06,
+      "loss": 1.6982,
+      "step": 263
+    },
+    {
+      "epoch": 0.8770764119601329,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.2869980994005146e-06,
+      "loss": 1.8154,
+      "step": 264
+    },
+    {
+      "epoch": 0.8803986710963455,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.2817325568414297e-06,
+      "loss": 1.6978,
+      "step": 265
+    },
+    {
+      "epoch": 0.8837209302325582,
+      "grad_norm": 2.859375,
+      "learning_rate": 1.2764585157558485e-06,
+      "loss": 1.5575,
+      "step": 266
+    },
+    {
+      "epoch": 0.8837209302325582,
+      "eval_loss": 1.6824702024459839,
+      "eval_runtime": 18.5874,
+      "eval_samples_per_second": 3.013,
+      "eval_steps_per_second": 1.506,
+      "step": 266
+    },
+    {
+      "epoch": 0.8870431893687708,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.271176135236417e-06,
+      "loss": 1.7344,
+      "step": 267
+    },
+    {
+      "epoch": 0.8903654485049833,
+      "grad_norm": 3.984375,
+      "learning_rate": 1.2658855746273418e-06,
+      "loss": 1.6611,
+      "step": 268
+    },
+    {
+      "epoch": 0.893687707641196,
+      "grad_norm": 2.828125,
+      "learning_rate": 1.2605869935195844e-06,
+      "loss": 1.8148,
+      "step": 269
+    },
+    {
+      "epoch": 0.8970099667774086,
+      "grad_norm": 3.3125,
+      "learning_rate": 1.2552805517460456e-06,
+      "loss": 1.7148,
+      "step": 270
+    },
+    {
+      "epoch": 0.9003322259136213,
+      "grad_norm": 3.453125,
+      "learning_rate": 1.2499664093767458e-06,
+      "loss": 1.7084,
+      "step": 271
+    },
+    {
+      "epoch": 0.9036544850498339,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.2446447267139945e-06,
+      "loss": 1.6583,
+      "step": 272
+    },
+    {
+      "epoch": 0.9069767441860465,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.2393156642875577e-06,
+      "loss": 1.6741,
+      "step": 273
+    },
+    {
+      "epoch": 0.9102990033222591,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.2339793828498118e-06,
+      "loss": 1.6266,
+      "step": 274
+    },
+    {
+      "epoch": 0.9136212624584718,
+      "grad_norm": 2.375,
+      "learning_rate": 1.2286360433708973e-06,
+      "loss": 1.7373,
+      "step": 275
+    },
+    {
+      "epoch": 0.9169435215946844,
+      "grad_norm": 3.03125,
+      "learning_rate": 1.2232858070338617e-06,
+      "loss": 1.7677,
+      "step": 276
+    },
+    {
+      "epoch": 0.920265780730897,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.2179288352297982e-06,
+      "loss": 1.5966,
+      "step": 277
+    },
+    {
+      "epoch": 0.9235880398671097,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.2125652895529766e-06,
+      "loss": 1.7274,
+      "step": 278
+    },
+    {
+      "epoch": 0.9269102990033222,
+      "grad_norm": 3.265625,
+      "learning_rate": 1.207195331795969e-06,
+      "loss": 1.7407,
+      "step": 279
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 3.859375,
+      "learning_rate": 1.2018191239447696e-06,
+      "loss": 1.7359,
+      "step": 280
+    },
+    {
+      "epoch": 0.9335548172757475,
+      "grad_norm": 3.203125,
+      "learning_rate": 1.1964368281739076e-06,
+      "loss": 1.6033,
+      "step": 281
+    },
+    {
+      "epoch": 0.9368770764119602,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.191048606841557e-06,
+      "loss": 1.6048,
+      "step": 282
+    },
+    {
+      "epoch": 0.9401993355481728,
+      "grad_norm": 2.875,
+      "learning_rate": 1.1856546224846353e-06,
+      "loss": 1.6088,
+      "step": 283
+    },
+    {
+      "epoch": 0.9435215946843853,
+      "grad_norm": 2.875,
+      "learning_rate": 1.1802550378139057e-06,
+      "loss": 1.7292,
+      "step": 284
+    },
+    {
+      "epoch": 0.946843853820598,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.1748500157090644e-06,
+      "loss": 1.6852,
+      "step": 285
+    },
+    {
+      "epoch": 0.9501661129568106,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.1694397192138294e-06,
+      "loss": 1.6983,
+      "step": 286
+    },
+    {
+      "epoch": 0.9534883720930233,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.1640243115310217e-06,
+      "loss": 1.6619,
+      "step": 287
+    },
+    {
+      "epoch": 0.9568106312292359,
+      "grad_norm": 2.21875,
+      "learning_rate": 1.1586039560176432e-06,
+      "loss": 1.7379,
+      "step": 288
+    },
+    {
+      "epoch": 0.9601328903654485,
+      "grad_norm": 2.53125,
+      "learning_rate": 1.1531788161799478e-06,
+      "loss": 1.6973,
+      "step": 289
+    },
+    {
+      "epoch": 0.9634551495016611,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.1477490556685091e-06,
+      "loss": 1.66,
+      "step": 290
+    },
+    {
+      "epoch": 0.9667774086378738,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.1423148382732853e-06,
+      "loss": 1.6192,
+      "step": 291
+    },
+    {
+      "epoch": 0.9700996677740864,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.1368763279186763e-06,
+      "loss": 1.5784,
+      "step": 292
+    },
+    {
+      "epoch": 0.973421926910299,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.1314336886585816e-06,
+      "loss": 1.6717,
+      "step": 293
+    },
+    {
+      "epoch": 0.9767441860465116,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.1259870846714488e-06,
+      "loss": 1.7301,
+      "step": 294
+    },
+    {
+      "epoch": 0.9800664451827242,
+      "grad_norm": 2.25,
+      "learning_rate": 1.1205366802553228e-06,
+      "loss": 1.6053,
+      "step": 295
+    },
+    {
+      "epoch": 0.9833887043189369,
+      "grad_norm": 2.359375,
+      "learning_rate": 1.1150826398228903e-06,
+      "loss": 1.5935,
+      "step": 296
+    },
+    {
+      "epoch": 0.9867109634551495,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.1096251278965172e-06,
+      "loss": 1.6469,
+      "step": 297
+    },
+    {
+      "epoch": 0.9900332225913622,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.10416430910329e-06,
+      "loss": 1.5799,
+      "step": 298
+    },
+    {
+      "epoch": 0.9933554817275747,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.0987003481700454e-06,
+      "loss": 1.5128,
+      "step": 299
+    },
+    {
+      "epoch": 0.9966777408637874,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.0932334099184058e-06,
+      "loss": 1.6065,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.171875,
+      "learning_rate": 1.087763659259803e-06,
+      "loss": 1.6959,
+      "step": 301
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 602,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 301,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.7403890105463603e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-301/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f068bf39065e2d2447ecd75968d1cdd55febe6373ac5d659a8ba8da543e600
+size 6648

checkpoint-602/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 131072
+}

checkpoint-602/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 1024000,
+  "pad_token_id": 10,
+  "transformers_version": "4.51.0"
+}

checkpoint-602/model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acfa7e0d5b706fc4a78bde2f2330febe655d0ab2db4f78dbfecee20c356e808a
+size 4865522496

checkpoint-602/model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7591fae00e44857bdbaf90f4a72a0957de341df5cc8ddcfbf77d94e9c0c339eb
+size 4907529424

checkpoint-602/model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90546050eacb77f0ff852f7ce903d03205662330c899bdaff306f5e11191223f
+size 4907529456

checkpoint-602/model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe924de0c8131926cfa602d5b59ef587fa79787dc9225e301c43d2b17e21bc1
+size 4907529456

checkpoint-602/model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d623a801b0b8bdd10b1905236a05766be4d51ad366ea7d9e9c2265cac894ebaf
+size 4907496272

checkpoint-602/model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 24495564800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

checkpoint-602/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7b3c5dba03346c7a72772a53e17467aab96b2c6401e7063f5da10e66b39a6f
+size 24878749708

checkpoint-602/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9213080fe2b45399b87036ca9ff9164533abe6b368e5c828136ee184486749d4
+size 14244

checkpoint-602/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a41fce2fdc6ca92fcca972f29cb3d0dcf70f9a63c920ef9b54688eec81f6fb
+size 1064

checkpoint-602/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-602/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc07f4f61632a89d8248b43f25649d6cc45200f8709e9d9bcd0414b00a4064e2
+size 17078342

checkpoint-602/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f068bf39065e2d2447ecd75968d1cdd55febe6373ac5d659a8ba8da543e600
+size 6648

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 1024000,
+  "pad_token_id": 10,
+  "transformers_version": "4.51.0"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acfa7e0d5b706fc4a78bde2f2330febe655d0ab2db4f78dbfecee20c356e808a
+size 4865522496

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7591fae00e44857bdbaf90f4a72a0957de341df5cc8ddcfbf77d94e9c0c339eb
+size 4907529424

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90546050eacb77f0ff852f7ce903d03205662330c899bdaff306f5e11191223f
+size 4907529456

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe924de0c8131926cfa602d5b59ef587fa79787dc9225e301c43d2b17e21bc1
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d623a801b0b8bdd10b1905236a05766be4d51ad366ea7d9e9c2265cac894ebaf
+size 4907496272

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 24495564800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc07f4f61632a89d8248b43f25649d6cc45200f8709e9d9bcd0414b00a4064e2
+size 17078342

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f068bf39065e2d2447ecd75968d1cdd55febe6373ac5d659a8ba8da543e600
+size 6648