Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,271 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen2.5-32B
+tags:
+- generated_from_trainer
+datasets:
+- datasets/Sugarquill10k_Clean.jsonl
+- datasets/Mixed-Novels-Completions.jsonl
+- datasets/Mixed-Novels-Completions-2.jsonl
+- datasets/recursal-scp-8k-filtered-4k.jsonl
+- datasets/disco.jsonl
+- datasets/disco-chat.json
+- datasets/competition-math-sharegpt.jsonl
+- datasets/systemchat-1k-sharegpt.jsonl
+- datasets/opencai_rp_sharegpt.json
+- datasets/floyd-instruct-8k.jsonl
+- datasets/woke-identity.jsonl
+- datasets/Claude-Sonnet35-Charcard-Unslop-v2.json
+- datasets/kalo-opus-22k-unslop.json
+- datasets/gryphe-4o-WP-sharegpt-cleaned.json
+- datasets/discord-logs-cleaned-sharegpt.json
+- datasets/creative-writing-multiturn-16k.json
+- datasets/limo-sharegpt.jsonl
+- datasets/tot-bio-2k-subset-sharegpt.json
+- datasets/gpqa-benchmaxxing.jsonl
+- datasets/UBW_Tapestries.json
+- datasets/medical-o1-reasoning-default-sys.jsonl
+model-index:
+- name: marigold-fft
+  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.dev0`
+```yaml
+base_model: Qwen/Qwen2.5-32B
+model_type: AutoModelForCausalLM
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+chat_template: jinja
+chat_template_jinja: "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{%- if messages[0]['role'] == 'system' %}{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}{%- else %}{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}{%- endif %}{%- for message in messages %}{%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}{%- elif message.role == \"assistant\" %}{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{- '<|im_start|>assistant\n' }}{%- endif %}"
+datasets:
+  # Continued pretrain: novels, short stories
+  - path: datasets/Sugarquill10k_Clean.jsonl
+    type: completion
+  - path: datasets/Mixed-Novels-Completions.jsonl
+    type: completion
+  - path: datasets/Mixed-Novels-Completions-2.jsonl
+    type: completion
+  - path: datasets/recursal-scp-8k-filtered-4k.jsonl
+    type: completion
+  # overfitting on disco elysium
+  - path: datasets/disco.jsonl
+    type: completion
+  - path: datasets/disco-chat.json
+    type: completion
+
+  # Instruct datasets (local)
+  - path: datasets/competition-math-sharegpt.jsonl
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/systemchat-1k-sharegpt.jsonl
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/opencai_rp_sharegpt.json
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/floyd-instruct-8k.jsonl
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/woke-identity.jsonl
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/Claude-Sonnet35-Charcard-Unslop-v2.json
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/kalo-opus-22k-unslop.json
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/gryphe-4o-WP-sharegpt-cleaned.json
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/discord-logs-cleaned-sharegpt.json
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/creative-writing-multiturn-16k.json
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/limo-sharegpt.jsonl
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/tot-bio-2k-subset-sharegpt.json
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/gpqa-benchmaxxing.jsonl
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/UBW_Tapestries.json
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+  - path: datasets/medical-o1-reasoning-default-sys.jsonl
+    type: chat_template
+    field_messages: conversations
+    message_field_role: from
+    message_field_content: value
+
+shuffle_merged_datasets: true
+
+special_tokens:
+  eos_token: "<|im_end|>"
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.02
+output_dir: ./marigold-fft
+
+sequence_len: 10240 # could try 10240 too?
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 3
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 5e-5
+
+weight_decay: 0.1
+max_grad_norm: 3
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: unsloth
+gradient_checkpointing_kwargs:
+  use_reentrant: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_ratio: 0.05
+evals_per_epoch: 4
+eval_table_size:
+
+saves_per_epoch: 4
+save_total_limit: 5
+
+debug:
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+liger_layer_norm: true
+liger_fused_linear_cross_entropy: true
+
+deepspeed: deepspeed_configs/zero3_bf16.json # multigpu only, maybe zero3_bf16_cpuoffload_params if OOM
+
+wandb_project: Qwen2.5-32B-Marigold-v0
+wandb_entity:
+wandb_name: Marigold-v0-fft
+
+```
+
+</details><br>
+
+# marigold-fft
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on the datasets/Sugarquill10k_Clean.jsonl, the datasets/Mixed-Novels-Completions.jsonl, the datasets/Mixed-Novels-Completions-2.jsonl, the datasets/recursal-scp-8k-filtered-4k.jsonl, the datasets/disco.jsonl, the datasets/disco-chat.json, the datasets/competition-math-sharegpt.jsonl, the datasets/systemchat-1k-sharegpt.jsonl, the datasets/opencai_rp_sharegpt.json, the datasets/floyd-instruct-8k.jsonl, the datasets/woke-identity.jsonl, the datasets/Claude-Sonnet35-Charcard-Unslop-v2.json, the datasets/kalo-opus-22k-unslop.json, the datasets/gryphe-4o-WP-sharegpt-cleaned.json, the datasets/discord-logs-cleaned-sharegpt.json, the datasets/creative-writing-multiturn-16k.json, the datasets/limo-sharegpt.jsonl, the datasets/tot-bio-2k-subset-sharegpt.json, the datasets/gpqa-benchmaxxing.jsonl, the datasets/UBW_Tapestries.json and the datasets/medical-o1-reasoning-default-sys.jsonl datasets.
+It achieves the following results on the evaluation set:
+- Loss: 2.2256
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Use paged_adamw_8bit 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: 27
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.0226        | 0.0054 | 1    | 3.5764          |
+| 1.8588        | 0.2522 | 47   | 2.2616          |
+| 1.7952        | 0.5044 | 94   | 2.1989          |
+| 1.8266        | 0.7565 | 141  | 2.1619          |
+| 1.5997        | 1.0107 | 188  | 2.1603          |
+| 1.5134        | 1.2629 | 235  | 2.1552          |
+| 1.4614        | 1.5151 | 282  | 2.1373          |
+| 1.6362        | 1.7673 | 329  | 2.1242          |
+| 1.1374        | 2.0215 | 376  | 2.2327          |
+| 1.2301        | 2.2736 | 423  | 2.2244          |
+| 1.1773        | 2.5258 | 470  | 2.2257          |
+| 1.1864        | 2.7780 | 517  | 2.2256          |
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-376/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-376/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-376/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

checkpoint-376/global_step376/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6519223794aeec7cba147ea83fda556f4816e177e91a2d056567943e8a5720cd
+size 381701

checkpoint-376/global_step376/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56eb32e0b83c43c190cadfe06f9d0222f6877801341b96ae59aae659f419616b
+size 381701

checkpoint-376/global_step376/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1a67beaf0bcfa4294858a257c72108021f3a0c60b58841167aa8fa7e3f5b75
+size 381701

checkpoint-376/global_step376/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e264a11482c721e3f78fb4405d5fae54a1c9e0fb1d36fca149d97dc331d468f
+size 381701

checkpoint-376/global_step376/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b170ca3fcd576069209c745af12c8677b3bfc8184fb7f63ae67e7c2562a4c18
+size 381701

checkpoint-376/global_step376/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030c63686ad188b43df5f716d3e9d740c265f98e488b5cd2fe59c61e84dac918
+size 381701

checkpoint-376/global_step376/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23a7f6033d0649873d0692ad857cfcca67ed08e2618349a312d8fad5d17229a
+size 381701

checkpoint-376/latest

@@ -0,0 +1 @@
+global_step376

checkpoint-376/model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

checkpoint-376/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb6462d333dbc5bb5e497ea9b0adb960f7616f79e6eea63222de6d5bd559516
+size 15984

checkpoint-376/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b045e1bfa728f51c8b51ab0faa20b128a4fbd350da006b9b39a19e24abdf5a74
+size 15984

checkpoint-376/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76a3d058d2628a61848c2441d313f251278bd8f74ce43dc44d8cd8ad3e619a8
+size 15984

checkpoint-376/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7f72fc498e6eaa671cdc0e8a627a668b8ef607063a22ddb4edbc05e791be830
+size 15984

checkpoint-376/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12889af98e175b734a788f4c5b8c4da91dd61ff3a05aaf61b9d4c66aa3dd8ad6
+size 15984

checkpoint-376/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe21a86abfceeac2cf2f48afd61a9a506cf61a287f3403f1adf391bb2ffa5a83
+size 15984

checkpoint-376/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73488bec91f9dee6d8105d06f99edaf4d27b6b064250d4c7023f33285b2f3132
+size 15984

checkpoint-376/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf6ee1cc2e1325b428a21172ec4e61b7220c5489751ea11c06bb66c77a0cd08
+size 15984

checkpoint-376/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16508495d4c8907ea78daea5096d2db67acfedc31b220db8562c4bb1e2de919
+size 1064

checkpoint-376/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-376/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-376/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{%- if messages[0]['role'] == 'system' %}{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}{%- else %}{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}{%- endif %}{%- for message in messages %}{%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}{%- elif message.role == \"assistant\" %}{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{- '<|im_start|>assistant\n' }}{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-376/trainer_state.json

@@ -0,0 +1,2737 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.021462105969148,
+  "eval_steps": 47,
+  "global_step": 376,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0053655264922870555,
+      "grad_norm": 1.2779298491774165,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 2.0226,
+      "step": 1
+    },
+    {
+      "epoch": 0.0053655264922870555,
+      "eval_loss": 3.5763909816741943,
+      "eval_runtime": 403.4915,
+      "eval_samples_per_second": 6.317,
+      "eval_steps_per_second": 0.791,
+      "step": 1
+    },
+    {
+      "epoch": 0.010731052984574111,
+      "grad_norm": 0.9868395151451838,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 2.0251,
+      "step": 2
+    },
+    {
+      "epoch": 0.01609657947686117,
+      "grad_norm": 1.124719320101948,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 2.0676,
+      "step": 3
+    },
+    {
+      "epoch": 0.021462105969148222,
+      "grad_norm": 0.8967993867216901,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 2.0685,
+      "step": 4
+    },
+    {
+      "epoch": 0.02682763246143528,
+      "grad_norm": 0.8530329942799596,
+      "learning_rate": 9.259259259259259e-06,
+      "loss": 1.975,
+      "step": 5
+    },
+    {
+      "epoch": 0.03219315895372234,
+      "grad_norm": 17.572932401470002,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 2.0319,
+      "step": 6
+    },
+    {
+      "epoch": 0.03755868544600939,
+      "grad_norm": 1.5955614660997672,
+      "learning_rate": 1.2962962962962962e-05,
+      "loss": 1.9776,
+      "step": 7
+    },
+    {
+      "epoch": 0.042924211938296444,
+      "grad_norm": 1.0305843114650708,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 1.9384,
+      "step": 8
+    },
+    {
+      "epoch": 0.0482897384305835,
+      "grad_norm": 0.7931768664816836,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 2.0357,
+      "step": 9
+    },
+    {
+      "epoch": 0.05365526492287056,
+      "grad_norm": 0.7458181490503686,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 1.9343,
+      "step": 10
+    },
+    {
+      "epoch": 0.05902079141515761,
+      "grad_norm": 1.0379874858551188,
+      "learning_rate": 2.037037037037037e-05,
+      "loss": 1.9069,
+      "step": 11
+    },
+    {
+      "epoch": 0.06438631790744467,
+      "grad_norm": 0.9634098196921086,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 1.8831,
+      "step": 12
+    },
+    {
+      "epoch": 0.06975184439973173,
+      "grad_norm": 0.8492217551097285,
+      "learning_rate": 2.4074074074074074e-05,
+      "loss": 1.9665,
+      "step": 13
+    },
+    {
+      "epoch": 0.07511737089201878,
+      "grad_norm": 0.8866414055564286,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.9859,
+      "step": 14
+    },
+    {
+      "epoch": 0.08048289738430583,
+      "grad_norm": 0.8975616587977772,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 1.9621,
+      "step": 15
+    },
+    {
+      "epoch": 0.08584842387659289,
+      "grad_norm": 0.8856060845121474,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 2.0504,
+      "step": 16
+    },
+    {
+      "epoch": 0.09121395036887994,
+      "grad_norm": 0.7934430921825818,
+      "learning_rate": 3.148148148148148e-05,
+      "loss": 1.8965,
+      "step": 17
+    },
+    {
+      "epoch": 0.096579476861167,
+      "grad_norm": 0.8411958882279533,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.834,
+      "step": 18
+    },
+    {
+      "epoch": 0.10194500335345406,
+      "grad_norm": 0.9605732267993595,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 2.0321,
+      "step": 19
+    },
+    {
+      "epoch": 0.10731052984574112,
+      "grad_norm": 0.8964432934098547,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 1.9165,
+      "step": 20
+    },
+    {
+      "epoch": 0.11267605633802817,
+      "grad_norm": 0.8325547065304583,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 2.0088,
+      "step": 21
+    },
+    {
+      "epoch": 0.11804158283031523,
+      "grad_norm": 0.7337982135739225,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 1.8652,
+      "step": 22
+    },
+    {
+      "epoch": 0.12340710932260228,
+      "grad_norm": 0.8703749413838572,
+      "learning_rate": 4.259259259259259e-05,
+      "loss": 1.9384,
+      "step": 23
+    },
+    {
+      "epoch": 0.12877263581488935,
+      "grad_norm": 0.752681510079145,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.84,
+      "step": 24
+    },
+    {
+      "epoch": 0.1341381623071764,
+      "grad_norm": 0.7664305287185245,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 1.917,
+      "step": 25
+    },
+    {
+      "epoch": 0.13950368879946345,
+      "grad_norm": 0.7376417365374465,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 1.8995,
+      "step": 26
+    },
+    {
+      "epoch": 0.1448692152917505,
+      "grad_norm": 0.6723119101020634,
+      "learning_rate": 5e-05,
+      "loss": 1.8572,
+      "step": 27
+    },
+    {
+      "epoch": 0.15023474178403756,
+      "grad_norm": 0.6636335261172684,
+      "learning_rate": 4.999956245830044e-05,
+      "loss": 1.8311,
+      "step": 28
+    },
+    {
+      "epoch": 0.15560026827632462,
+      "grad_norm": 0.7118137563548644,
+      "learning_rate": 4.9998249848517185e-05,
+      "loss": 1.9461,
+      "step": 29
+    },
+    {
+      "epoch": 0.16096579476861167,
+      "grad_norm": 0.5571924001587539,
+      "learning_rate": 4.999606221659595e-05,
+      "loss": 1.9125,
+      "step": 30
+    },
+    {
+      "epoch": 0.16633132126089872,
+      "grad_norm": 0.5895748551871794,
+      "learning_rate": 4.999299963911115e-05,
+      "loss": 1.9295,
+      "step": 31
+    },
+    {
+      "epoch": 0.17169684775318578,
+      "grad_norm": 0.5114717351226575,
+      "learning_rate": 4.9989062223263216e-05,
+      "loss": 1.8642,
+      "step": 32
+    },
+    {
+      "epoch": 0.17706237424547283,
+      "grad_norm": 0.5658751591114588,
+      "learning_rate": 4.998425010687484e-05,
+      "loss": 1.9465,
+      "step": 33
+    },
+    {
+      "epoch": 0.18242790073775988,
+      "grad_norm": 0.4198888613535172,
+      "learning_rate": 4.997856345838615e-05,
+      "loss": 1.7824,
+      "step": 34
+    },
+    {
+      "epoch": 0.18779342723004694,
+      "grad_norm": 0.558439585084249,
+      "learning_rate": 4.99720024768488e-05,
+      "loss": 1.9157,
+      "step": 35
+    },
+    {
+      "epoch": 0.193158953722334,
+      "grad_norm": 0.4888963940737741,
+      "learning_rate": 4.996456739191905e-05,
+      "loss": 1.9136,
+      "step": 36
+    },
+    {
+      "epoch": 0.19852448021462105,
+      "grad_norm": 0.5106753170932593,
+      "learning_rate": 4.995625846384966e-05,
+      "loss": 1.8623,
+      "step": 37
+    },
+    {
+      "epoch": 0.20389000670690813,
+      "grad_norm": 0.5942581620888907,
+      "learning_rate": 4.994707598348085e-05,
+      "loss": 1.8741,
+      "step": 38
+    },
+    {
+      "epoch": 0.20925553319919518,
+      "grad_norm": 0.5106367767120957,
+      "learning_rate": 4.993702027223004e-05,
+      "loss": 1.9413,
+      "step": 39
+    },
+    {
+      "epoch": 0.21462105969148224,
+      "grad_norm": 0.5113103948113709,
+      "learning_rate": 4.992609168208069e-05,
+      "loss": 1.9966,
+      "step": 40
+    },
+    {
+      "epoch": 0.2199865861837693,
+      "grad_norm": 0.5212461839914251,
+      "learning_rate": 4.9914290595569895e-05,
+      "loss": 1.8474,
+      "step": 41
+    },
+    {
+      "epoch": 0.22535211267605634,
+      "grad_norm": 0.5161668483087154,
+      "learning_rate": 4.9901617425775067e-05,
+      "loss": 1.8557,
+      "step": 42
+    },
+    {
+      "epoch": 0.2307176391683434,
+      "grad_norm": 0.5484719777790631,
+      "learning_rate": 4.988807261629942e-05,
+      "loss": 1.8769,
+      "step": 43
+    },
+    {
+      "epoch": 0.23608316566063045,
+      "grad_norm": 0.4937411819105057,
+      "learning_rate": 4.987365664125647e-05,
+      "loss": 1.8923,
+      "step": 44
+    },
+    {
+      "epoch": 0.2414486921529175,
+      "grad_norm": 0.5804971756745295,
+      "learning_rate": 4.985837000525343e-05,
+      "loss": 1.954,
+      "step": 45
+    },
+    {
+      "epoch": 0.24681421864520456,
+      "grad_norm": 0.531027559174979,
+      "learning_rate": 4.984221324337356e-05,
+      "loss": 1.9758,
+      "step": 46
+    },
+    {
+      "epoch": 0.25217974513749164,
+      "grad_norm": 0.5132447531432143,
+      "learning_rate": 4.982518692115744e-05,
+      "loss": 1.8588,
+      "step": 47
+    },
+    {
+      "epoch": 0.25217974513749164,
+      "eval_loss": 2.2616188526153564,
+      "eval_runtime": 403.9965,
+      "eval_samples_per_second": 6.309,
+      "eval_steps_per_second": 0.79,
+      "step": 47
+    },
+    {
+      "epoch": 0.2575452716297787,
+      "grad_norm": 0.4799971353542736,
+      "learning_rate": 4.980729163458312e-05,
+      "loss": 1.8558,
+      "step": 48
+    },
+    {
+      "epoch": 0.26291079812206575,
+      "grad_norm": 0.4318157242619782,
+      "learning_rate": 4.978852801004534e-05,
+      "loss": 1.9574,
+      "step": 49
+    },
+    {
+      "epoch": 0.2682763246143528,
+      "grad_norm": 0.44416051699732234,
+      "learning_rate": 4.976889670433355e-05,
+      "loss": 1.7988,
+      "step": 50
+    },
+    {
+      "epoch": 0.27364185110663986,
+      "grad_norm": 0.42380891285410505,
+      "learning_rate": 4.974839840460895e-05,
+      "loss": 1.8296,
+      "step": 51
+    },
+    {
+      "epoch": 0.2790073775989269,
+      "grad_norm": 0.4989220387491634,
+      "learning_rate": 4.97270338283804e-05,
+      "loss": 1.8996,
+      "step": 52
+    },
+    {
+      "epoch": 0.28437290409121396,
+      "grad_norm": 0.44554710351703636,
+      "learning_rate": 4.970480372347934e-05,
+      "loss": 1.9553,
+      "step": 53
+    },
+    {
+      "epoch": 0.289738430583501,
+      "grad_norm": 0.5597504355268026,
+      "learning_rate": 4.9681708868033616e-05,
+      "loss": 1.9979,
+      "step": 54
+    },
+    {
+      "epoch": 0.29510395707578807,
+      "grad_norm": 0.4758356280331154,
+      "learning_rate": 4.9657750070440196e-05,
+      "loss": 1.9244,
+      "step": 55
+    },
+    {
+      "epoch": 0.3004694835680751,
+      "grad_norm": 0.4337532785073617,
+      "learning_rate": 4.963292816933692e-05,
+      "loss": 1.9099,
+      "step": 56
+    },
+    {
+      "epoch": 0.3058350100603622,
+      "grad_norm": 0.48193864337289033,
+      "learning_rate": 4.9607244033573156e-05,
+      "loss": 1.8076,
+      "step": 57
+    },
+    {
+      "epoch": 0.31120053655264923,
+      "grad_norm": 0.5180685237569209,
+      "learning_rate": 4.9580698562179297e-05,
+      "loss": 1.9031,
+      "step": 58
+    },
+    {
+      "epoch": 0.3165660630449363,
+      "grad_norm": 0.4227856708321325,
+      "learning_rate": 4.955329268433543e-05,
+      "loss": 1.8111,
+      "step": 59
+    },
+    {
+      "epoch": 0.32193158953722334,
+      "grad_norm": 0.4457771321490526,
+      "learning_rate": 4.9525027359338696e-05,
+      "loss": 1.8771,
+      "step": 60
+    },
+    {
+      "epoch": 0.3272971160295104,
+      "grad_norm": 0.383809821251567,
+      "learning_rate": 4.949590357656975e-05,
+      "loss": 1.8384,
+      "step": 61
+    },
+    {
+      "epoch": 0.33266264252179745,
+      "grad_norm": 0.5245332667935808,
+      "learning_rate": 4.946592235545815e-05,
+      "loss": 1.948,
+      "step": 62
+    },
+    {
+      "epoch": 0.3380281690140845,
+      "grad_norm": 0.48131587989680386,
+      "learning_rate": 4.9435084745446666e-05,
+      "loss": 1.9546,
+      "step": 63
+    },
+    {
+      "epoch": 0.34339369550637155,
+      "grad_norm": 0.47579745445020977,
+      "learning_rate": 4.940339182595451e-05,
+      "loss": 1.9085,
+      "step": 64
+    },
+    {
+      "epoch": 0.3487592219986586,
+      "grad_norm": 0.5162389548444078,
+      "learning_rate": 4.9370844706339594e-05,
+      "loss": 1.9263,
+      "step": 65
+    },
+    {
+      "epoch": 0.35412474849094566,
+      "grad_norm": 0.4430593262438425,
+      "learning_rate": 4.933744452585966e-05,
+      "loss": 1.8264,
+      "step": 66
+    },
+    {
+      "epoch": 0.3594902749832327,
+      "grad_norm": 0.4564426740705147,
+      "learning_rate": 4.930319245363248e-05,
+      "loss": 1.7974,
+      "step": 67
+    },
+    {
+      "epoch": 0.36485580147551977,
+      "grad_norm": 0.4896650401826788,
+      "learning_rate": 4.926808968859483e-05,
+      "loss": 1.8567,
+      "step": 68
+    },
+    {
+      "epoch": 0.3702213279678068,
+      "grad_norm": 0.4051071793789495,
+      "learning_rate": 4.923213745946059e-05,
+      "loss": 1.8201,
+      "step": 69
+    },
+    {
+      "epoch": 0.3755868544600939,
+      "grad_norm": 0.48978661474326063,
+      "learning_rate": 4.919533702467771e-05,
+      "loss": 1.8006,
+      "step": 70
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.5175966382748892,
+      "learning_rate": 4.9157689672384174e-05,
+      "loss": 1.7904,
+      "step": 71
+    },
+    {
+      "epoch": 0.386317907444668,
+      "grad_norm": 0.49081107125596507,
+      "learning_rate": 4.91191967203629e-05,
+      "loss": 1.9606,
+      "step": 72
+    },
+    {
+      "epoch": 0.39168343393695504,
+      "grad_norm": 0.5920859101699153,
+      "learning_rate": 4.907985951599563e-05,
+      "loss": 1.8124,
+      "step": 73
+    },
+    {
+      "epoch": 0.3970489604292421,
+      "grad_norm": 0.4106853545996278,
+      "learning_rate": 4.9039679436215734e-05,
+      "loss": 1.9402,
+      "step": 74
+    },
+    {
+      "epoch": 0.4024144869215292,
+      "grad_norm": 0.6429573337250454,
+      "learning_rate": 4.899865788746005e-05,
+      "loss": 1.8233,
+      "step": 75
+    },
+    {
+      "epoch": 0.40778001341381626,
+      "grad_norm": 0.5770635817407002,
+      "learning_rate": 4.895679630561963e-05,
+      "loss": 1.8909,
+      "step": 76
+    },
+    {
+      "epoch": 0.4131455399061033,
+      "grad_norm": 0.8202937145800111,
+      "learning_rate": 4.891409615598949e-05,
+      "loss": 1.8635,
+      "step": 77
+    },
+    {
+      "epoch": 0.41851106639839036,
+      "grad_norm": 0.6871160286583309,
+      "learning_rate": 4.88705589332173e-05,
+      "loss": 1.9497,
+      "step": 78
+    },
+    {
+      "epoch": 0.4238765928906774,
+      "grad_norm": 0.4438407032445468,
+      "learning_rate": 4.882618616125111e-05,
+      "loss": 1.9336,
+      "step": 79
+    },
+    {
+      "epoch": 0.42924211938296447,
+      "grad_norm": 0.545225076259868,
+      "learning_rate": 4.878097939328596e-05,
+      "loss": 1.843,
+      "step": 80
+    },
+    {
+      "epoch": 0.4346076458752515,
+      "grad_norm": 0.5120969176703908,
+      "learning_rate": 4.873494021170953e-05,
+      "loss": 1.9019,
+      "step": 81
+    },
+    {
+      "epoch": 0.4399731723675386,
+      "grad_norm": 0.41579446347477983,
+      "learning_rate": 4.868807022804678e-05,
+      "loss": 1.8617,
+      "step": 82
+    },
+    {
+      "epoch": 0.44533869885982563,
+      "grad_norm": 0.5510693357302907,
+      "learning_rate": 4.864037108290347e-05,
+      "loss": 1.9433,
+      "step": 83
+    },
+    {
+      "epoch": 0.4507042253521127,
+      "grad_norm": 0.40913367019675556,
+      "learning_rate": 4.859184444590882e-05,
+      "loss": 1.8353,
+      "step": 84
+    },
+    {
+      "epoch": 0.45606975184439974,
+      "grad_norm": 0.3763529830498608,
+      "learning_rate": 4.854249201565701e-05,
+      "loss": 1.7299,
+      "step": 85
+    },
+    {
+      "epoch": 0.4614352783366868,
+      "grad_norm": 0.47448012995411376,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 1.8547,
+      "step": 86
+    },
+    {
+      "epoch": 0.46680080482897385,
+      "grad_norm": 0.4181797287844973,
+      "learning_rate": 4.84413167142257e-05,
+      "loss": 1.8186,
+      "step": 87
+    },
+    {
+      "epoch": 0.4721663313212609,
+      "grad_norm": 0.4781785535505977,
+      "learning_rate": 4.838949738451929e-05,
+      "loss": 1.8965,
+      "step": 88
+    },
+    {
+      "epoch": 0.47753185781354796,
+      "grad_norm": 0.4351347675471463,
+      "learning_rate": 4.833685934437787e-05,
+      "loss": 1.863,
+      "step": 89
+    },
+    {
+      "epoch": 0.482897384305835,
+      "grad_norm": 0.3874884362959953,
+      "learning_rate": 4.8283404436308464e-05,
+      "loss": 1.7396,
+      "step": 90
+    },
+    {
+      "epoch": 0.48826291079812206,
+      "grad_norm": 0.49444219921157534,
+      "learning_rate": 4.8229134531411166e-05,
+      "loss": 1.8444,
+      "step": 91
+    },
+    {
+      "epoch": 0.4936284372904091,
+      "grad_norm": 0.39922493357750344,
+      "learning_rate": 4.8174051529313704e-05,
+      "loss": 1.8247,
+      "step": 92
+    },
+    {
+      "epoch": 0.49899396378269617,
+      "grad_norm": 0.5511215543224721,
+      "learning_rate": 4.81181573581049e-05,
+      "loss": 1.9533,
+      "step": 93
+    },
+    {
+      "epoch": 0.5043594902749833,
+      "grad_norm": 0.41108793496635143,
+      "learning_rate": 4.8061453974267195e-05,
+      "loss": 1.7952,
+      "step": 94
+    },
+    {
+      "epoch": 0.5043594902749833,
+      "eval_loss": 2.198935031890869,
+      "eval_runtime": 403.21,
+      "eval_samples_per_second": 6.322,
+      "eval_steps_per_second": 0.791,
+      "step": 94
+    },
+    {
+      "epoch": 0.5097250167672703,
+      "grad_norm": 0.43234228757508586,
+      "learning_rate": 4.80039433626082e-05,
+      "loss": 1.8667,
+      "step": 95
+    },
+    {
+      "epoch": 0.5150905432595574,
+      "grad_norm": 0.40707489762011484,
+      "learning_rate": 4.7945627536191166e-05,
+      "loss": 1.9081,
+      "step": 96
+    },
+    {
+      "epoch": 0.5204560697518444,
+      "grad_norm": 0.41662703960667113,
+      "learning_rate": 4.788650853626456e-05,
+      "loss": 1.7536,
+      "step": 97
+    },
+    {
+      "epoch": 0.5258215962441315,
+      "grad_norm": 0.39754454922458654,
+      "learning_rate": 4.7826588432190614e-05,
+      "loss": 1.8851,
+      "step": 98
+    },
+    {
+      "epoch": 0.5311871227364185,
+      "grad_norm": 0.41218018944985396,
+      "learning_rate": 4.7765869321372836e-05,
+      "loss": 1.8062,
+      "step": 99
+    },
+    {
+      "epoch": 0.5365526492287056,
+      "grad_norm": 0.41546782428712065,
+      "learning_rate": 4.7704353329182673e-05,
+      "loss": 1.8491,
+      "step": 100
+    },
+    {
+      "epoch": 0.5419181757209927,
+      "grad_norm": 0.47175537335479406,
+      "learning_rate": 4.7642042608885064e-05,
+      "loss": 1.7917,
+      "step": 101
+    },
+    {
+      "epoch": 0.5472837022132797,
+      "grad_norm": 0.4373071645022652,
+      "learning_rate": 4.7578939341563095e-05,
+      "loss": 1.8632,
+      "step": 102
+    },
+    {
+      "epoch": 0.5526492287055668,
+      "grad_norm": 0.4369286574512984,
+      "learning_rate": 4.751504573604162e-05,
+      "loss": 1.8377,
+      "step": 103
+    },
+    {
+      "epoch": 0.5580147551978538,
+      "grad_norm": 0.40840919093725575,
+      "learning_rate": 4.745036402880999e-05,
+      "loss": 1.8397,
+      "step": 104
+    },
+    {
+      "epoch": 0.5633802816901409,
+      "grad_norm": 0.4023593789216688,
+      "learning_rate": 4.738489648394373e-05,
+      "loss": 1.9389,
+      "step": 105
+    },
+    {
+      "epoch": 0.5687458081824279,
+      "grad_norm": 0.45139851873493203,
+      "learning_rate": 4.731864539302531e-05,
+      "loss": 1.9384,
+      "step": 106
+    },
+    {
+      "epoch": 0.574111334674715,
+      "grad_norm": 0.518973698127367,
+      "learning_rate": 4.725161307506391e-05,
+      "loss": 1.8388,
+      "step": 107
+    },
+    {
+      "epoch": 0.579476861167002,
+      "grad_norm": 0.41440109186821383,
+      "learning_rate": 4.7183801876414294e-05,
+      "loss": 1.9807,
+      "step": 108
+    },
+    {
+      "epoch": 0.5848423876592891,
+      "grad_norm": 0.485066583270121,
+      "learning_rate": 4.711521417069462e-05,
+      "loss": 1.9518,
+      "step": 109
+    },
+    {
+      "epoch": 0.5902079141515761,
+      "grad_norm": 0.453283667200083,
+      "learning_rate": 4.70458523587034e-05,
+      "loss": 1.8874,
+      "step": 110
+    },
+    {
+      "epoch": 0.5955734406438632,
+      "grad_norm": 0.40638037542695366,
+      "learning_rate": 4.697571886833544e-05,
+      "loss": 1.8138,
+      "step": 111
+    },
+    {
+      "epoch": 0.6009389671361502,
+      "grad_norm": 0.47718260435002885,
+      "learning_rate": 4.6904816154496854e-05,
+      "loss": 1.8409,
+      "step": 112
+    },
+    {
+      "epoch": 0.6063044936284373,
+      "grad_norm": 0.45172842172725275,
+      "learning_rate": 4.683314669901918e-05,
+      "loss": 1.9261,
+      "step": 113
+    },
+    {
+      "epoch": 0.6116700201207244,
+      "grad_norm": 0.4713867113135493,
+      "learning_rate": 4.676071301057243e-05,
+      "loss": 1.8502,
+      "step": 114
+    },
+    {
+      "epoch": 0.6170355466130114,
+      "grad_norm": 0.42451831321750794,
+      "learning_rate": 4.668751762457734e-05,
+      "loss": 1.8489,
+      "step": 115
+    },
+    {
+      "epoch": 0.6224010731052985,
+      "grad_norm": 0.3958564758105134,
+      "learning_rate": 4.6613563103116594e-05,
+      "loss": 1.8922,
+      "step": 116
+    },
+    {
+      "epoch": 0.6277665995975855,
+      "grad_norm": 0.4009292301802374,
+      "learning_rate": 4.653885203484515e-05,
+      "loss": 1.8685,
+      "step": 117
+    },
+    {
+      "epoch": 0.6331321260898726,
+      "grad_norm": 0.37598195515170946,
+      "learning_rate": 4.6463387034899645e-05,
+      "loss": 1.7889,
+      "step": 118
+    },
+    {
+      "epoch": 0.6384976525821596,
+      "grad_norm": 0.4710597532282601,
+      "learning_rate": 4.638717074480682e-05,
+      "loss": 1.8739,
+      "step": 119
+    },
+    {
+      "epoch": 0.6438631790744467,
+      "grad_norm": 0.4146663267990981,
+      "learning_rate": 4.631020583239107e-05,
+      "loss": 1.8988,
+      "step": 120
+    },
+    {
+      "epoch": 0.6492287055667337,
+      "grad_norm": 0.4354294422619394,
+      "learning_rate": 4.6232494991681094e-05,
+      "loss": 1.8517,
+      "step": 121
+    },
+    {
+      "epoch": 0.6545942320590208,
+      "grad_norm": 0.5470562094587934,
+      "learning_rate": 4.615404094281554e-05,
+      "loss": 1.812,
+      "step": 122
+    },
+    {
+      "epoch": 0.6599597585513078,
+      "grad_norm": 0.37147901827060426,
+      "learning_rate": 4.607484643194788e-05,
+      "loss": 1.8447,
+      "step": 123
+    },
+    {
+      "epoch": 0.6653252850435949,
+      "grad_norm": 0.462225949803499,
+      "learning_rate": 4.599491423115014e-05,
+      "loss": 1.8442,
+      "step": 124
+    },
+    {
+      "epoch": 0.670690811535882,
+      "grad_norm": 0.4600536423365438,
+      "learning_rate": 4.5914247138316025e-05,
+      "loss": 1.926,
+      "step": 125
+    },
+    {
+      "epoch": 0.676056338028169,
+      "grad_norm": 0.4049920788749757,
+      "learning_rate": 4.5832847977062874e-05,
+      "loss": 1.8001,
+      "step": 126
+    },
+    {
+      "epoch": 0.681421864520456,
+      "grad_norm": 0.4052262687972146,
+      "learning_rate": 4.5750719596632885e-05,
+      "loss": 1.8616,
+      "step": 127
+    },
+    {
+      "epoch": 0.6867873910127431,
+      "grad_norm": 0.455611587260568,
+      "learning_rate": 4.5667864871793345e-05,
+      "loss": 1.7792,
+      "step": 128
+    },
+    {
+      "epoch": 0.6921529175050302,
+      "grad_norm": 0.4321930788528261,
+      "learning_rate": 4.558428670273601e-05,
+      "loss": 1.911,
+      "step": 129
+    },
+    {
+      "epoch": 0.6975184439973172,
+      "grad_norm": 0.3922798652619637,
+      "learning_rate": 4.549998801497564e-05,
+      "loss": 1.8979,
+      "step": 130
+    },
+    {
+      "epoch": 0.7028839704896043,
+      "grad_norm": 0.4338149926251678,
+      "learning_rate": 4.54149717592475e-05,
+      "loss": 1.793,
+      "step": 131
+    },
+    {
+      "epoch": 0.7082494969818913,
+      "grad_norm": 0.42943405977885124,
+      "learning_rate": 4.532924091140417e-05,
+      "loss": 1.8606,
+      "step": 132
+    },
+    {
+      "epoch": 0.7136150234741784,
+      "grad_norm": 0.4145321079739444,
+      "learning_rate": 4.524279847231131e-05,
+      "loss": 1.906,
+      "step": 133
+    },
+    {
+      "epoch": 0.7189805499664654,
+      "grad_norm": 0.38959038753607894,
+      "learning_rate": 4.515564746774265e-05,
+      "loss": 1.7323,
+      "step": 134
+    },
+    {
+      "epoch": 0.7243460764587525,
+      "grad_norm": 0.49146581928185773,
+      "learning_rate": 4.5067790948274094e-05,
+      "loss": 1.8303,
+      "step": 135
+    },
+    {
+      "epoch": 0.7297116029510395,
+      "grad_norm": 0.4638570517033698,
+      "learning_rate": 4.49792319891769e-05,
+      "loss": 1.8243,
+      "step": 136
+    },
+    {
+      "epoch": 0.7350771294433266,
+      "grad_norm": 0.38160033679573113,
+      "learning_rate": 4.4889973690310085e-05,
+      "loss": 1.8186,
+      "step": 137
+    },
+    {
+      "epoch": 0.7404426559356136,
+      "grad_norm": 0.5253837731077495,
+      "learning_rate": 4.480001917601185e-05,
+      "loss": 1.9086,
+      "step": 138
+    },
+    {
+      "epoch": 0.7458081824279007,
+      "grad_norm": 0.5010255463058967,
+      "learning_rate": 4.470937159499029e-05,
+      "loss": 1.9014,
+      "step": 139
+    },
+    {
+      "epoch": 0.7511737089201878,
+      "grad_norm": 0.44408252888412136,
+      "learning_rate": 4.461803412021314e-05,
+      "loss": 1.886,
+      "step": 140
+    },
+    {
+      "epoch": 0.7565392354124748,
+      "grad_norm": 0.5189286834612553,
+      "learning_rate": 4.4526009948796703e-05,
+      "loss": 1.8266,
+      "step": 141
+    },
+    {
+      "epoch": 0.7565392354124748,
+      "eval_loss": 2.1618716716766357,
+      "eval_runtime": 403.938,
+      "eval_samples_per_second": 6.31,
+      "eval_steps_per_second": 0.79,
+      "step": 141
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.4334524920814895,
+      "learning_rate": 4.4433302301893987e-05,
+      "loss": 1.8863,
+      "step": 142
+    },
+    {
+      "epoch": 0.7672702883970489,
+      "grad_norm": 0.4809144135248221,
+      "learning_rate": 4.433991442458188e-05,
+      "loss": 1.9075,
+      "step": 143
+    },
+    {
+      "epoch": 0.772635814889336,
+      "grad_norm": 0.5258910256081301,
+      "learning_rate": 4.4245849585747654e-05,
+      "loss": 1.9616,
+      "step": 144
+    },
+    {
+      "epoch": 0.778001341381623,
+      "grad_norm": 0.5131536872616902,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 1.8953,
+      "step": 145
+    },
+    {
+      "epoch": 0.7833668678739101,
+      "grad_norm": 0.45216150555891305,
+      "learning_rate": 4.4055702217426084e-05,
+      "loss": 1.8867,
+      "step": 146
+    },
+    {
+      "epoch": 0.7887323943661971,
+      "grad_norm": 0.47907057676705184,
+      "learning_rate": 4.395962634373097e-05,
+      "loss": 1.8335,
+      "step": 147
+    },
+    {
+      "epoch": 0.7940979208584842,
+      "grad_norm": 0.4945502094720473,
+      "learning_rate": 4.386288681986516e-05,
+      "loss": 1.9218,
+      "step": 148
+    },
+    {
+      "epoch": 0.7994634473507712,
+      "grad_norm": 0.4595838282230734,
+      "learning_rate": 4.376548703203474e-05,
+      "loss": 1.8603,
+      "step": 149
+    },
+    {
+      "epoch": 0.8048289738430584,
+      "grad_norm": 0.45448249598162854,
+      "learning_rate": 4.36674303895572e-05,
+      "loss": 1.8615,
+      "step": 150
+    },
+    {
+      "epoch": 0.8101945003353455,
+      "grad_norm": 0.4238860646236377,
+      "learning_rate": 4.356872032474213e-05,
+      "loss": 1.8374,
+      "step": 151
+    },
+    {
+      "epoch": 0.8155600268276325,
+      "grad_norm": 0.4519762198634726,
+      "learning_rate": 4.34693602927711e-05,
+      "loss": 1.8174,
+      "step": 152
+    },
+    {
+      "epoch": 0.8209255533199196,
+      "grad_norm": 0.45624612554196736,
+      "learning_rate": 4.336935377157668e-05,
+      "loss": 1.9105,
+      "step": 153
+    },
+    {
+      "epoch": 0.8262910798122066,
+      "grad_norm": 0.4076679531263349,
+      "learning_rate": 4.326870426172075e-05,
+      "loss": 1.8865,
+      "step": 154
+    },
+    {
+      "epoch": 0.8316566063044937,
+      "grad_norm": 0.4514412896189259,
+      "learning_rate": 4.3167415286271905e-05,
+      "loss": 1.9272,
+      "step": 155
+    },
+    {
+      "epoch": 0.8370221327967807,
+      "grad_norm": 0.40433175857719245,
+      "learning_rate": 4.3065490390682186e-05,
+      "loss": 1.814,
+      "step": 156
+    },
+    {
+      "epoch": 0.8423876592890678,
+      "grad_norm": 0.4159285646615437,
+      "learning_rate": 4.296293314266294e-05,
+      "loss": 1.8064,
+      "step": 157
+    },
+    {
+      "epoch": 0.8477531857813548,
+      "grad_norm": 0.4270220599999327,
+      "learning_rate": 4.2859747132060006e-05,
+      "loss": 1.7482,
+      "step": 158
+    },
+    {
+      "epoch": 0.8531187122736419,
+      "grad_norm": 0.5162993182758251,
+      "learning_rate": 4.275593597072796e-05,
+      "loss": 1.7763,
+      "step": 159
+    },
+    {
+      "epoch": 0.8584842387659289,
+      "grad_norm": 0.4065368416357515,
+      "learning_rate": 4.265150329240376e-05,
+      "loss": 1.885,
+      "step": 160
+    },
+    {
+      "epoch": 0.863849765258216,
+      "grad_norm": 0.5523980888304064,
+      "learning_rate": 4.2546452752579536e-05,
+      "loss": 1.971,
+      "step": 161
+    },
+    {
+      "epoch": 0.869215291750503,
+      "grad_norm": 0.4121779650999884,
+      "learning_rate": 4.2440788028374624e-05,
+      "loss": 1.9301,
+      "step": 162
+    },
+    {
+      "epoch": 0.8745808182427901,
+      "grad_norm": 0.4612759438023989,
+      "learning_rate": 4.233451281840686e-05,
+      "loss": 1.8564,
+      "step": 163
+    },
+    {
+      "epoch": 0.8799463447350772,
+      "grad_norm": 0.3977527412707747,
+      "learning_rate": 4.2227630842663136e-05,
+      "loss": 1.8876,
+      "step": 164
+    },
+    {
+      "epoch": 0.8853118712273642,
+      "grad_norm": 0.45276964005664955,
+      "learning_rate": 4.212014584236914e-05,
+      "loss": 1.8098,
+      "step": 165
+    },
+    {
+      "epoch": 0.8906773977196513,
+      "grad_norm": 0.37349476483277844,
+      "learning_rate": 4.2012061579858465e-05,
+      "loss": 1.8247,
+      "step": 166
+    },
+    {
+      "epoch": 0.8960429242119383,
+      "grad_norm": 0.39676844111499676,
+      "learning_rate": 4.190338183844086e-05,
+      "loss": 1.914,
+      "step": 167
+    },
+    {
+      "epoch": 0.9014084507042254,
+      "grad_norm": 0.3625691966854791,
+      "learning_rate": 4.1794110422269825e-05,
+      "loss": 1.92,
+      "step": 168
+    },
+    {
+      "epoch": 0.9067739771965124,
+      "grad_norm": 0.39688352111910685,
+      "learning_rate": 4.168425115620944e-05,
+      "loss": 1.8103,
+      "step": 169
+    },
+    {
+      "epoch": 0.9121395036887995,
+      "grad_norm": 0.3737222783168723,
+      "learning_rate": 4.157380788570053e-05,
+      "loss": 1.8215,
+      "step": 170
+    },
+    {
+      "epoch": 0.9175050301810865,
+      "grad_norm": 0.43842445138079555,
+      "learning_rate": 4.146278447662597e-05,
+      "loss": 1.8029,
+      "step": 171
+    },
+    {
+      "epoch": 0.9228705566733736,
+      "grad_norm": 0.47414715687042996,
+      "learning_rate": 4.1351184815175456e-05,
+      "loss": 1.8974,
+      "step": 172
+    },
+    {
+      "epoch": 0.9282360831656606,
+      "grad_norm": 0.4146539941665616,
+      "learning_rate": 4.123901280770945e-05,
+      "loss": 1.8871,
+      "step": 173
+    },
+    {
+      "epoch": 0.9336016096579477,
+      "grad_norm": 0.4088656394439229,
+      "learning_rate": 4.112627238062239e-05,
+      "loss": 1.8594,
+      "step": 174
+    },
+    {
+      "epoch": 0.9389671361502347,
+      "grad_norm": 0.40239314445747604,
+      "learning_rate": 4.101296748020533e-05,
+      "loss": 1.8207,
+      "step": 175
+    },
+    {
+      "epoch": 0.9443326626425218,
+      "grad_norm": 0.36389736696587754,
+      "learning_rate": 4.089910207250778e-05,
+      "loss": 1.8423,
+      "step": 176
+    },
+    {
+      "epoch": 0.9496981891348089,
+      "grad_norm": 0.41161031740209597,
+      "learning_rate": 4.0784680143198836e-05,
+      "loss": 1.8954,
+      "step": 177
+    },
+    {
+      "epoch": 0.9550637156270959,
+      "grad_norm": 0.3613771597005119,
+      "learning_rate": 4.0669705697427754e-05,
+      "loss": 1.9036,
+      "step": 178
+    },
+    {
+      "epoch": 0.960429242119383,
+      "grad_norm": 0.36880689305175635,
+      "learning_rate": 4.055418275968368e-05,
+      "loss": 1.8676,
+      "step": 179
+    },
+    {
+      "epoch": 0.96579476861167,
+      "grad_norm": 0.3892009514188599,
+      "learning_rate": 4.04381153736548e-05,
+      "loss": 1.8545,
+      "step": 180
+    },
+    {
+      "epoch": 0.9711602951039571,
+      "grad_norm": 0.39386413560247385,
+      "learning_rate": 4.032150760208684e-05,
+      "loss": 1.9306,
+      "step": 181
+    },
+    {
+      "epoch": 0.9765258215962441,
+      "grad_norm": 0.38085985815329654,
+      "learning_rate": 4.02043635266408e-05,
+      "loss": 1.9339,
+      "step": 182
+    },
+    {
+      "epoch": 0.9818913480885312,
+      "grad_norm": 0.3502551322824309,
+      "learning_rate": 4.00866872477501e-05,
+      "loss": 1.8438,
+      "step": 183
+    },
+    {
+      "epoch": 0.9872568745808182,
+      "grad_norm": 0.42923155491093273,
+      "learning_rate": 3.9968482884477075e-05,
+      "loss": 1.8326,
+      "step": 184
+    },
+    {
+      "epoch": 0.9926224010731053,
+      "grad_norm": 0.37629854526288287,
+      "learning_rate": 3.9849754574368766e-05,
+      "loss": 1.8521,
+      "step": 185
+    },
+    {
+      "epoch": 0.9979879275653923,
+      "grad_norm": 0.43648587047407056,
+      "learning_rate": 3.973050647331209e-05,
+      "loss": 1.9192,
+      "step": 186
+    },
+    {
+      "epoch": 1.0053655264922872,
+      "grad_norm": 1.1037688215019685,
+      "learning_rate": 3.9610742755388406e-05,
+      "loss": 3.5179,
+      "step": 187
+    },
+    {
+      "epoch": 1.010731052984574,
+      "grad_norm": 0.5315167109100908,
+      "learning_rate": 3.949046761272736e-05,
+      "loss": 1.5997,
+      "step": 188
+    },
+    {
+      "epoch": 1.010731052984574,
+      "eval_loss": 2.160255193710327,
+      "eval_runtime": 403.1754,
+      "eval_samples_per_second": 6.322,
+      "eval_steps_per_second": 0.791,
+      "step": 188
+    },
+    {
+      "epoch": 1.0160965794768613,
+      "grad_norm": 1.034163349005432,
+      "learning_rate": 3.9369685255360175e-05,
+      "loss": 1.6376,
+      "step": 189
+    },
+    {
+      "epoch": 1.0214621059691482,
+      "grad_norm": 0.5297370695526916,
+      "learning_rate": 3.924839991107229e-05,
+      "loss": 1.5196,
+      "step": 190
+    },
+    {
+      "epoch": 1.0268276324614354,
+      "grad_norm": 0.49978902813452,
+      "learning_rate": 3.9126615825255364e-05,
+      "loss": 1.4628,
+      "step": 191
+    },
+    {
+      "epoch": 1.0321931589537223,
+      "grad_norm": 0.5207450843338,
+      "learning_rate": 3.900433726075865e-05,
+      "loss": 1.5808,
+      "step": 192
+    },
+    {
+      "epoch": 1.0375586854460095,
+      "grad_norm": 0.5502855697944308,
+      "learning_rate": 3.888156849773985e-05,
+      "loss": 1.5445,
+      "step": 193
+    },
+    {
+      "epoch": 1.0429242119382964,
+      "grad_norm": 0.5175112784168553,
+      "learning_rate": 3.875831383351519e-05,
+      "loss": 1.6456,
+      "step": 194
+    },
+    {
+      "epoch": 1.0482897384305836,
+      "grad_norm": 0.4649959629509902,
+      "learning_rate": 3.863457758240912e-05,
+      "loss": 1.5508,
+      "step": 195
+    },
+    {
+      "epoch": 1.0536552649228705,
+      "grad_norm": 0.48136239187851326,
+      "learning_rate": 3.851036407560319e-05,
+      "loss": 1.4848,
+      "step": 196
+    },
+    {
+      "epoch": 1.0590207914151577,
+      "grad_norm": 0.48389312973032594,
+      "learning_rate": 3.838567766098452e-05,
+      "loss": 1.5123,
+      "step": 197
+    },
+    {
+      "epoch": 1.0643863179074446,
+      "grad_norm": 0.45180450785183063,
+      "learning_rate": 3.826052270299356e-05,
+      "loss": 1.5807,
+      "step": 198
+    },
+    {
+      "epoch": 1.0697518443997318,
+      "grad_norm": 0.48079670948977926,
+      "learning_rate": 3.813490358247137e-05,
+      "loss": 1.5426,
+      "step": 199
+    },
+    {
+      "epoch": 1.0751173708920188,
+      "grad_norm": 0.510291013526601,
+      "learning_rate": 3.800882469650621e-05,
+      "loss": 1.5845,
+      "step": 200
+    },
+    {
+      "epoch": 1.080482897384306,
+      "grad_norm": 0.41649615075440893,
+      "learning_rate": 3.78822904582797e-05,
+      "loss": 1.5003,
+      "step": 201
+    },
+    {
+      "epoch": 1.0858484238765929,
+      "grad_norm": 0.4499681852447958,
+      "learning_rate": 3.7755305296912276e-05,
+      "loss": 1.4751,
+      "step": 202
+    },
+    {
+      "epoch": 1.09121395036888,
+      "grad_norm": 0.5088284534955508,
+      "learning_rate": 3.762787365730821e-05,
+      "loss": 1.5982,
+      "step": 203
+    },
+    {
+      "epoch": 1.096579476861167,
+      "grad_norm": 0.3929831451008196,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.4991,
+      "step": 204
+    },
+    {
+      "epoch": 1.1019450033534541,
+      "grad_norm": 0.41107315409379536,
+      "learning_rate": 3.7371688800992235e-05,
+      "loss": 1.4837,
+      "step": 205
+    },
+    {
+      "epoch": 1.107310529845741,
+      "grad_norm": 0.415588978346341,
+      "learning_rate": 3.7242944551604914e-05,
+      "loss": 1.5345,
+      "step": 206
+    },
+    {
+      "epoch": 1.1126760563380282,
+      "grad_norm": 0.4044749735529877,
+      "learning_rate": 3.711377175831626e-05,
+      "loss": 1.4545,
+      "step": 207
+    },
+    {
+      "epoch": 1.1180415828303152,
+      "grad_norm": 0.44865460732176465,
+      "learning_rate": 3.698417494260494e-05,
+      "loss": 1.6391,
+      "step": 208
+    },
+    {
+      "epoch": 1.1234071093226023,
+      "grad_norm": 0.4479424002899852,
+      "learning_rate": 3.685415864079185e-05,
+      "loss": 1.508,
+      "step": 209
+    },
+    {
+      "epoch": 1.1287726358148893,
+      "grad_norm": 0.429927217929734,
+      "learning_rate": 3.6723727403881284e-05,
+      "loss": 1.5501,
+      "step": 210
+    },
+    {
+      "epoch": 1.1341381623071765,
+      "grad_norm": 0.5044115066105113,
+      "learning_rate": 3.659288579740163e-05,
+      "loss": 1.5615,
+      "step": 211
+    },
+    {
+      "epoch": 1.1395036887994634,
+      "grad_norm": 0.424575600191598,
+      "learning_rate": 3.646163840124561e-05,
+      "loss": 1.4835,
+      "step": 212
+    },
+    {
+      "epoch": 1.1448692152917506,
+      "grad_norm": 0.43480586168977786,
+      "learning_rate": 3.632998980950993e-05,
+      "loss": 1.5371,
+      "step": 213
+    },
+    {
+      "epoch": 1.1502347417840375,
+      "grad_norm": 0.40322150224409975,
+      "learning_rate": 3.619794463033447e-05,
+      "loss": 1.5376,
+      "step": 214
+    },
+    {
+      "epoch": 1.1556002682763247,
+      "grad_norm": 0.42637706485283583,
+      "learning_rate": 3.6065507485741e-05,
+      "loss": 1.5631,
+      "step": 215
+    },
+    {
+      "epoch": 1.1609657947686116,
+      "grad_norm": 0.4259143981435151,
+      "learning_rate": 3.593268301147139e-05,
+      "loss": 1.5741,
+      "step": 216
+    },
+    {
+      "epoch": 1.1663313212608988,
+      "grad_norm": 0.45826011738708783,
+      "learning_rate": 3.5799475856825326e-05,
+      "loss": 1.5298,
+      "step": 217
+    },
+    {
+      "epoch": 1.1716968477531857,
+      "grad_norm": 0.4030875431169561,
+      "learning_rate": 3.566589068449761e-05,
+      "loss": 1.5574,
+      "step": 218
+    },
+    {
+      "epoch": 1.1770623742454729,
+      "grad_norm": 0.409604426981432,
+      "learning_rate": 3.5531932170414896e-05,
+      "loss": 1.4859,
+      "step": 219
+    },
+    {
+      "epoch": 1.1824279007377598,
+      "grad_norm": 0.37439697455127857,
+      "learning_rate": 3.539760500357207e-05,
+      "loss": 1.5221,
+      "step": 220
+    },
+    {
+      "epoch": 1.187793427230047,
+      "grad_norm": 0.3600455315943667,
+      "learning_rate": 3.5262913885868066e-05,
+      "loss": 1.479,
+      "step": 221
+    },
+    {
+      "epoch": 1.193158953722334,
+      "grad_norm": 0.39515964344444054,
+      "learning_rate": 3.512786353194134e-05,
+      "loss": 1.6002,
+      "step": 222
+    },
+    {
+      "epoch": 1.198524480214621,
+      "grad_norm": 0.3903215407425732,
+      "learning_rate": 3.49924586690048e-05,
+      "loss": 1.5627,
+      "step": 223
+    },
+    {
+      "epoch": 1.203890006706908,
+      "grad_norm": 0.3863928913911809,
+      "learning_rate": 3.485670403668036e-05,
+      "loss": 1.4894,
+      "step": 224
+    },
+    {
+      "epoch": 1.2092555331991952,
+      "grad_norm": 0.39120322752660747,
+      "learning_rate": 3.472060438683302e-05,
+      "loss": 1.5576,
+      "step": 225
+    },
+    {
+      "epoch": 1.2146210596914822,
+      "grad_norm": 0.4012276022035902,
+      "learning_rate": 3.4584164483404544e-05,
+      "loss": 1.5661,
+      "step": 226
+    },
+    {
+      "epoch": 1.2199865861837693,
+      "grad_norm": 0.359333036872216,
+      "learning_rate": 3.444738910224671e-05,
+      "loss": 1.6043,
+      "step": 227
+    },
+    {
+      "epoch": 1.2253521126760563,
+      "grad_norm": 0.4169926695855886,
+      "learning_rate": 3.431028303095415e-05,
+      "loss": 1.5162,
+      "step": 228
+    },
+    {
+      "epoch": 1.2307176391683434,
+      "grad_norm": 0.3666243644496504,
+      "learning_rate": 3.417285106869673e-05,
+      "loss": 1.5182,
+      "step": 229
+    },
+    {
+      "epoch": 1.2360831656606304,
+      "grad_norm": 0.3732640706992433,
+      "learning_rate": 3.403509802605159e-05,
+      "loss": 1.6136,
+      "step": 230
+    },
+    {
+      "epoch": 1.2414486921529175,
+      "grad_norm": 0.38533992909636827,
+      "learning_rate": 3.389702872483477e-05,
+      "loss": 1.5763,
+      "step": 231
+    },
+    {
+      "epoch": 1.2468142186452045,
+      "grad_norm": 0.3621197211070038,
+      "learning_rate": 3.3758647997932417e-05,
+      "loss": 1.5977,
+      "step": 232
+    },
+    {
+      "epoch": 1.2521797451374916,
+      "grad_norm": 0.39624430912627595,
+      "learning_rate": 3.361996068913159e-05,
+      "loss": 1.5794,
+      "step": 233
+    },
+    {
+      "epoch": 1.2575452716297786,
+      "grad_norm": 0.38404789088021773,
+      "learning_rate": 3.348097165295076e-05,
+      "loss": 1.5633,
+      "step": 234
+    },
+    {
+      "epoch": 1.2629107981220657,
+      "grad_norm": 0.35832957307552504,
+      "learning_rate": 3.3341685754469856e-05,
+      "loss": 1.5134,
+      "step": 235
+    },
+    {
+      "epoch": 1.2629107981220657,
+      "eval_loss": 2.15519642829895,
+      "eval_runtime": 403.4218,
+      "eval_samples_per_second": 6.318,
+      "eval_steps_per_second": 0.791,
+      "step": 235
+    },
+    {
+      "epoch": 1.268276324614353,
+      "grad_norm": 0.34366404066845024,
+      "learning_rate": 3.320210786915997e-05,
+      "loss": 1.4825,
+      "step": 236
+    },
+    {
+      "epoch": 1.2736418511066399,
+      "grad_norm": 0.45636968737684863,
+      "learning_rate": 3.3062242882712724e-05,
+      "loss": 1.5146,
+      "step": 237
+    },
+    {
+      "epoch": 1.2790073775989268,
+      "grad_norm": 0.3804000236233779,
+      "learning_rate": 3.2922095690869224e-05,
+      "loss": 1.5501,
+      "step": 238
+    },
+    {
+      "epoch": 1.284372904091214,
+      "grad_norm": 0.3699794774550946,
+      "learning_rate": 3.278167119924872e-05,
+      "loss": 1.4956,
+      "step": 239
+    },
+    {
+      "epoch": 1.2897384305835011,
+      "grad_norm": 0.38134052511434596,
+      "learning_rate": 3.2640974323176846e-05,
+      "loss": 1.4926,
+      "step": 240
+    },
+    {
+      "epoch": 1.295103957075788,
+      "grad_norm": 0.4001577679575819,
+      "learning_rate": 3.2500009987513655e-05,
+      "loss": 1.5339,
+      "step": 241
+    },
+    {
+      "epoch": 1.300469483568075,
+      "grad_norm": 0.33599496371938614,
+      "learning_rate": 3.235878312648112e-05,
+      "loss": 1.3329,
+      "step": 242
+    },
+    {
+      "epoch": 1.3058350100603622,
+      "grad_norm": 0.3780832169945631,
+      "learning_rate": 3.2217298683490525e-05,
+      "loss": 1.5711,
+      "step": 243
+    },
+    {
+      "epoch": 1.3112005365526493,
+      "grad_norm": 0.37979912787014874,
+      "learning_rate": 3.207556161096935e-05,
+      "loss": 1.559,
+      "step": 244
+    },
+    {
+      "epoch": 1.3165660630449363,
+      "grad_norm": 0.34013678855872914,
+      "learning_rate": 3.193357687018798e-05,
+      "loss": 1.5112,
+      "step": 245
+    },
+    {
+      "epoch": 1.3219315895372232,
+      "grad_norm": 0.3761770494247479,
+      "learning_rate": 3.179134943108597e-05,
+      "loss": 1.5195,
+      "step": 246
+    },
+    {
+      "epoch": 1.3272971160295104,
+      "grad_norm": 0.36046502801340735,
+      "learning_rate": 3.164888427209818e-05,
+      "loss": 1.4648,
+      "step": 247
+    },
+    {
+      "epoch": 1.3326626425217976,
+      "grad_norm": 0.4163102856970103,
+      "learning_rate": 3.150618637998041e-05,
+      "loss": 1.6488,
+      "step": 248
+    },
+    {
+      "epoch": 1.3380281690140845,
+      "grad_norm": 0.37250576413738173,
+      "learning_rate": 3.136326074963494e-05,
+      "loss": 1.5966,
+      "step": 249
+    },
+    {
+      "epoch": 1.3433936955063714,
+      "grad_norm": 0.3717314773044194,
+      "learning_rate": 3.122011238393562e-05,
+      "loss": 1.4555,
+      "step": 250
+    },
+    {
+      "epoch": 1.3487592219986586,
+      "grad_norm": 0.4233051858413458,
+      "learning_rate": 3.1076746293552786e-05,
+      "loss": 1.5931,
+      "step": 251
+    },
+    {
+      "epoch": 1.3541247484909458,
+      "grad_norm": 0.3538900779699424,
+      "learning_rate": 3.093316749677788e-05,
+      "loss": 1.5041,
+      "step": 252
+    },
+    {
+      "epoch": 1.3594902749832327,
+      "grad_norm": 0.4239252371757693,
+      "learning_rate": 3.078938101934773e-05,
+      "loss": 1.5986,
+      "step": 253
+    },
+    {
+      "epoch": 1.3648558014755197,
+      "grad_norm": 0.40455165331708126,
+      "learning_rate": 3.064539189426874e-05,
+      "loss": 1.5956,
+      "step": 254
+    },
+    {
+      "epoch": 1.3702213279678068,
+      "grad_norm": 0.35682161127333073,
+      "learning_rate": 3.050120516164062e-05,
+      "loss": 1.4983,
+      "step": 255
+    },
+    {
+      "epoch": 1.375586854460094,
+      "grad_norm": 0.366685178903664,
+      "learning_rate": 3.0356825868480017e-05,
+      "loss": 1.6384,
+      "step": 256
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 0.3615423341669086,
+      "learning_rate": 3.0212259068543837e-05,
+      "loss": 1.4734,
+      "step": 257
+    },
+    {
+      "epoch": 1.3863179074446679,
+      "grad_norm": 0.3469703962175405,
+      "learning_rate": 3.006750982215234e-05,
+      "loss": 1.4386,
+      "step": 258
+    },
+    {
+      "epoch": 1.391683433936955,
+      "grad_norm": 0.3757992095280783,
+      "learning_rate": 2.9922583196012037e-05,
+      "loss": 1.5479,
+      "step": 259
+    },
+    {
+      "epoch": 1.3970489604292422,
+      "grad_norm": 0.3696529318558144,
+      "learning_rate": 2.9777484263038306e-05,
+      "loss": 1.4613,
+      "step": 260
+    },
+    {
+      "epoch": 1.4024144869215291,
+      "grad_norm": 0.36763443681114544,
+      "learning_rate": 2.9632218102177862e-05,
+      "loss": 1.4707,
+      "step": 261
+    },
+    {
+      "epoch": 1.4077800134138163,
+      "grad_norm": 0.3330227260573098,
+      "learning_rate": 2.9486789798230917e-05,
+      "loss": 1.5196,
+      "step": 262
+    },
+    {
+      "epoch": 1.4131455399061033,
+      "grad_norm": 0.3401075705229897,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 1.5713,
+      "step": 263
+    },
+    {
+      "epoch": 1.4185110663983904,
+      "grad_norm": 0.38589937071982083,
+      "learning_rate": 2.9195467128478044e-05,
+      "loss": 1.5658,
+      "step": 264
+    },
+    {
+      "epoch": 1.4238765928906774,
+      "grad_norm": 0.36187499541792045,
+      "learning_rate": 2.9049582959937392e-05,
+      "loss": 1.5645,
+      "step": 265
+    },
+    {
+      "epoch": 1.4292421193829645,
+      "grad_norm": 0.3727884692802974,
+      "learning_rate": 2.8903557042483887e-05,
+      "loss": 1.5195,
+      "step": 266
+    },
+    {
+      "epoch": 1.4346076458752515,
+      "grad_norm": 0.3423144867083204,
+      "learning_rate": 2.875739448751176e-05,
+      "loss": 1.4897,
+      "step": 267
+    },
+    {
+      "epoch": 1.4399731723675386,
+      "grad_norm": 0.3809610047831763,
+      "learning_rate": 2.8611100411198037e-05,
+      "loss": 1.6107,
+      "step": 268
+    },
+    {
+      "epoch": 1.4453386988598256,
+      "grad_norm": 0.3466660038008262,
+      "learning_rate": 2.8464679934323424e-05,
+      "loss": 1.5203,
+      "step": 269
+    },
+    {
+      "epoch": 1.4507042253521127,
+      "grad_norm": 0.3858219936970091,
+      "learning_rate": 2.8318138182093052e-05,
+      "loss": 1.5211,
+      "step": 270
+    },
+    {
+      "epoch": 1.4560697518443997,
+      "grad_norm": 0.3457606288538911,
+      "learning_rate": 2.8171480283957118e-05,
+      "loss": 1.4825,
+      "step": 271
+    },
+    {
+      "epoch": 1.4614352783366868,
+      "grad_norm": 0.4097169980235964,
+      "learning_rate": 2.80247113734313e-05,
+      "loss": 1.5276,
+      "step": 272
+    },
+    {
+      "epoch": 1.4668008048289738,
+      "grad_norm": 0.39937404860513825,
+      "learning_rate": 2.7877836587917072e-05,
+      "loss": 1.5022,
+      "step": 273
+    },
+    {
+      "epoch": 1.472166331321261,
+      "grad_norm": 0.36070057912441533,
+      "learning_rate": 2.773086106852192e-05,
+      "loss": 1.4587,
+      "step": 274
+    },
+    {
+      "epoch": 1.477531857813548,
+      "grad_norm": 0.4013616820391148,
+      "learning_rate": 2.7583789959879303e-05,
+      "loss": 1.5908,
+      "step": 275
+    },
+    {
+      "epoch": 1.482897384305835,
+      "grad_norm": 0.4150531718746046,
+      "learning_rate": 2.7436628409968664e-05,
+      "loss": 1.4511,
+      "step": 276
+    },
+    {
+      "epoch": 1.488262910798122,
+      "grad_norm": 0.38578622280087393,
+      "learning_rate": 2.728938156993517e-05,
+      "loss": 1.5407,
+      "step": 277
+    },
+    {
+      "epoch": 1.4936284372904092,
+      "grad_norm": 0.3844783258031986,
+      "learning_rate": 2.7142054593909422e-05,
+      "loss": 1.5349,
+      "step": 278
+    },
+    {
+      "epoch": 1.4989939637826961,
+      "grad_norm": 0.4144431176495637,
+      "learning_rate": 2.6994652638827078e-05,
+      "loss": 1.602,
+      "step": 279
+    },
+    {
+      "epoch": 1.5043594902749833,
+      "grad_norm": 0.402711914294424,
+      "learning_rate": 2.6847180864248283e-05,
+      "loss": 1.5902,
+      "step": 280
+    },
+    {
+      "epoch": 1.5097250167672702,
+      "grad_norm": 0.3378799881196754,
+      "learning_rate": 2.6699644432177112e-05,
+      "loss": 1.5514,
+      "step": 281
+    },
+    {
+      "epoch": 1.5150905432595574,
+      "grad_norm": 0.4113537256498264,
+      "learning_rate": 2.655204850688085e-05,
+      "loss": 1.4614,
+      "step": 282
+    },
+    {
+      "epoch": 1.5150905432595574,
+      "eval_loss": 2.1373159885406494,
+      "eval_runtime": 403.7482,
+      "eval_samples_per_second": 6.313,
+      "eval_steps_per_second": 0.79,
+      "step": 282
+    },
+    {
+      "epoch": 1.5204560697518446,
+      "grad_norm": 0.3645339916373801,
+      "learning_rate": 2.6404398254709284e-05,
+      "loss": 1.4716,
+      "step": 283
+    },
+    {
+      "epoch": 1.5258215962441315,
+      "grad_norm": 0.3662916121671904,
+      "learning_rate": 2.625669884391377e-05,
+      "loss": 1.5145,
+      "step": 284
+    },
+    {
+      "epoch": 1.5311871227364184,
+      "grad_norm": 0.4062086365442157,
+      "learning_rate": 2.610895544446641e-05,
+      "loss": 1.5513,
+      "step": 285
+    },
+    {
+      "epoch": 1.5365526492287056,
+      "grad_norm": 0.3693755738805308,
+      "learning_rate": 2.596117322787907e-05,
+      "loss": 1.5498,
+      "step": 286
+    },
+    {
+      "epoch": 1.5419181757209928,
+      "grad_norm": 0.3589026792727439,
+      "learning_rate": 2.5813357367022305e-05,
+      "loss": 1.5211,
+      "step": 287
+    },
+    {
+      "epoch": 1.5472837022132797,
+      "grad_norm": 0.38017444587432575,
+      "learning_rate": 2.566551303594437e-05,
+      "loss": 1.5342,
+      "step": 288
+    },
+    {
+      "epoch": 1.5526492287055667,
+      "grad_norm": 0.3537300073106448,
+      "learning_rate": 2.551764540969005e-05,
+      "loss": 1.5109,
+      "step": 289
+    },
+    {
+      "epoch": 1.5580147551978538,
+      "grad_norm": 0.3752836981822812,
+      "learning_rate": 2.5369759664119537e-05,
+      "loss": 1.5015,
+      "step": 290
+    },
+    {
+      "epoch": 1.563380281690141,
+      "grad_norm": 0.3810876452684417,
+      "learning_rate": 2.5221860975727275e-05,
+      "loss": 1.5686,
+      "step": 291
+    },
+    {
+      "epoch": 1.568745808182428,
+      "grad_norm": 0.3688966465073692,
+      "learning_rate": 2.5073954521460745e-05,
+      "loss": 1.5666,
+      "step": 292
+    },
+    {
+      "epoch": 1.5741113346747149,
+      "grad_norm": 0.3740373962224673,
+      "learning_rate": 2.4926045478539257e-05,
+      "loss": 1.5541,
+      "step": 293
+    },
+    {
+      "epoch": 1.579476861167002,
+      "grad_norm": 0.4415523054571514,
+      "learning_rate": 2.4778139024272724e-05,
+      "loss": 1.62,
+      "step": 294
+    },
+    {
+      "epoch": 1.5848423876592892,
+      "grad_norm": 0.3291219023047839,
+      "learning_rate": 2.4630240335880462e-05,
+      "loss": 1.5,
+      "step": 295
+    },
+    {
+      "epoch": 1.5902079141515761,
+      "grad_norm": 0.39622699819562734,
+      "learning_rate": 2.4482354590309962e-05,
+      "loss": 1.5358,
+      "step": 296
+    },
+    {
+      "epoch": 1.595573440643863,
+      "grad_norm": 0.35147156988608064,
+      "learning_rate": 2.433448696405563e-05,
+      "loss": 1.469,
+      "step": 297
+    },
+    {
+      "epoch": 1.6009389671361502,
+      "grad_norm": 0.3458967842322882,
+      "learning_rate": 2.4186642632977697e-05,
+      "loss": 1.5368,
+      "step": 298
+    },
+    {
+      "epoch": 1.6063044936284374,
+      "grad_norm": 0.45919555248078225,
+      "learning_rate": 2.4038826772120932e-05,
+      "loss": 1.6126,
+      "step": 299
+    },
+    {
+      "epoch": 1.6116700201207244,
+      "grad_norm": 0.397298560652149,
+      "learning_rate": 2.3891044555533588e-05,
+      "loss": 1.5273,
+      "step": 300
+    },
+    {
+      "epoch": 1.6170355466130113,
+      "grad_norm": 0.33950881912700964,
+      "learning_rate": 2.3743301156086244e-05,
+      "loss": 1.5844,
+      "step": 301
+    },
+    {
+      "epoch": 1.6224010731052985,
+      "grad_norm": 0.3685147478174407,
+      "learning_rate": 2.359560174529073e-05,
+      "loss": 1.5306,
+      "step": 302
+    },
+    {
+      "epoch": 1.6277665995975856,
+      "grad_norm": 0.3668847123777601,
+      "learning_rate": 2.3447951493119152e-05,
+      "loss": 1.5114,
+      "step": 303
+    },
+    {
+      "epoch": 1.6331321260898726,
+      "grad_norm": 0.3532238202377609,
+      "learning_rate": 2.3300355567822897e-05,
+      "loss": 1.5568,
+      "step": 304
+    },
+    {
+      "epoch": 1.6384976525821595,
+      "grad_norm": 0.3810645993344603,
+      "learning_rate": 2.3152819135751722e-05,
+      "loss": 1.5121,
+      "step": 305
+    },
+    {
+      "epoch": 1.6438631790744467,
+      "grad_norm": 0.37909917013988087,
+      "learning_rate": 2.300534736117292e-05,
+      "loss": 1.4904,
+      "step": 306
+    },
+    {
+      "epoch": 1.6492287055667338,
+      "grad_norm": 0.38885366059907706,
+      "learning_rate": 2.285794540609058e-05,
+      "loss": 1.5852,
+      "step": 307
+    },
+    {
+      "epoch": 1.6545942320590208,
+      "grad_norm": 0.3657756765079751,
+      "learning_rate": 2.2710618430064843e-05,
+      "loss": 1.5529,
+      "step": 308
+    },
+    {
+      "epoch": 1.6599597585513077,
+      "grad_norm": 0.3397163303578702,
+      "learning_rate": 2.256337159003134e-05,
+      "loss": 1.4903,
+      "step": 309
+    },
+    {
+      "epoch": 1.665325285043595,
+      "grad_norm": 0.39777082501030225,
+      "learning_rate": 2.2416210040120703e-05,
+      "loss": 1.5159,
+      "step": 310
+    },
+    {
+      "epoch": 1.670690811535882,
+      "grad_norm": 0.3658755281773237,
+      "learning_rate": 2.2269138931478084e-05,
+      "loss": 1.5848,
+      "step": 311
+    },
+    {
+      "epoch": 1.676056338028169,
+      "grad_norm": 0.42665798217406753,
+      "learning_rate": 2.2122163412082927e-05,
+      "loss": 1.6133,
+      "step": 312
+    },
+    {
+      "epoch": 1.681421864520456,
+      "grad_norm": 0.40969972656814363,
+      "learning_rate": 2.1975288626568713e-05,
+      "loss": 1.6264,
+      "step": 313
+    },
+    {
+      "epoch": 1.686787391012743,
+      "grad_norm": 0.3283642172163527,
+      "learning_rate": 2.1828519716042888e-05,
+      "loss": 1.4812,
+      "step": 314
+    },
+    {
+      "epoch": 1.6921529175050303,
+      "grad_norm": 0.4058354316614303,
+      "learning_rate": 2.1681861817906954e-05,
+      "loss": 1.4827,
+      "step": 315
+    },
+    {
+      "epoch": 1.6975184439973172,
+      "grad_norm": 0.3466585039953347,
+      "learning_rate": 2.153532006567658e-05,
+      "loss": 1.5768,
+      "step": 316
+    },
+    {
+      "epoch": 1.7028839704896042,
+      "grad_norm": 0.33329283442783797,
+      "learning_rate": 2.1388899588801965e-05,
+      "loss": 1.577,
+      "step": 317
+    },
+    {
+      "epoch": 1.7082494969818913,
+      "grad_norm": 0.3513005805125947,
+      "learning_rate": 2.1242605512488248e-05,
+      "loss": 1.5835,
+      "step": 318
+    },
+    {
+      "epoch": 1.7136150234741785,
+      "grad_norm": 0.3294934417641562,
+      "learning_rate": 2.109644295751612e-05,
+      "loss": 1.4758,
+      "step": 319
+    },
+    {
+      "epoch": 1.7189805499664654,
+      "grad_norm": 0.33415233723527016,
+      "learning_rate": 2.095041704006261e-05,
+      "loss": 1.4853,
+      "step": 320
+    },
+    {
+      "epoch": 1.7243460764587524,
+      "grad_norm": 0.3283653112019817,
+      "learning_rate": 2.080453287152196e-05,
+      "loss": 1.4554,
+      "step": 321
+    },
+    {
+      "epoch": 1.7297116029510395,
+      "grad_norm": 0.32083254638693504,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 1.5284,
+      "step": 322
+    },
+    {
+      "epoch": 1.7350771294433267,
+      "grad_norm": 0.37794249417672565,
+      "learning_rate": 2.0513210201769085e-05,
+      "loss": 1.5521,
+      "step": 323
+    },
+    {
+      "epoch": 1.7404426559356136,
+      "grad_norm": 0.3431657733658665,
+      "learning_rate": 2.0367781897822147e-05,
+      "loss": 1.5067,
+      "step": 324
+    },
+    {
+      "epoch": 1.7458081824279006,
+      "grad_norm": 0.33934139214309345,
+      "learning_rate": 2.0222515736961696e-05,
+      "loss": 1.4801,
+      "step": 325
+    },
+    {
+      "epoch": 1.7511737089201878,
+      "grad_norm": 0.3795356143714155,
+      "learning_rate": 2.0077416803987965e-05,
+      "loss": 1.6264,
+      "step": 326
+    },
+    {
+      "epoch": 1.756539235412475,
+      "grad_norm": 0.3507795265759812,
+      "learning_rate": 1.993249017784766e-05,
+      "loss": 1.4967,
+      "step": 327
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 0.3648489232026123,
+      "learning_rate": 1.9787740931456165e-05,
+      "loss": 1.5561,
+      "step": 328
+    },
+    {
+      "epoch": 1.7672702883970488,
+      "grad_norm": 0.39626816117060937,
+      "learning_rate": 1.9643174131519986e-05,
+      "loss": 1.6362,
+      "step": 329
+    },
+    {
+      "epoch": 1.7672702883970488,
+      "eval_loss": 2.1242423057556152,
+      "eval_runtime": 403.1029,
+      "eval_samples_per_second": 6.323,
+      "eval_steps_per_second": 0.791,
+      "step": 329
+    },
+    {
+      "epoch": 1.772635814889336,
+      "grad_norm": 0.35313890178416246,
+      "learning_rate": 1.949879483835939e-05,
+      "loss": 1.5147,
+      "step": 330
+    },
+    {
+      "epoch": 1.7780013413816231,
+      "grad_norm": 0.3269413977690858,
+      "learning_rate": 1.935460810573127e-05,
+      "loss": 1.5032,
+      "step": 331
+    },
+    {
+      "epoch": 1.78336686787391,
+      "grad_norm": 0.3521215800086969,
+      "learning_rate": 1.9210618980652277e-05,
+      "loss": 1.5734,
+      "step": 332
+    },
+    {
+      "epoch": 1.788732394366197,
+      "grad_norm": 0.3813859592452455,
+      "learning_rate": 1.9066832503222128e-05,
+      "loss": 1.4488,
+      "step": 333
+    },
+    {
+      "epoch": 1.7940979208584842,
+      "grad_norm": 0.31690523060028536,
+      "learning_rate": 1.892325370644721e-05,
+      "loss": 1.432,
+      "step": 334
+    },
+    {
+      "epoch": 1.7994634473507714,
+      "grad_norm": 0.3364023400710833,
+      "learning_rate": 1.8779887616064383e-05,
+      "loss": 1.4871,
+      "step": 335
+    },
+    {
+      "epoch": 1.8048289738430583,
+      "grad_norm": 0.3350534986332929,
+      "learning_rate": 1.863673925036506e-05,
+      "loss": 1.5055,
+      "step": 336
+    },
+    {
+      "epoch": 1.8101945003353455,
+      "grad_norm": 0.33398900975140067,
+      "learning_rate": 1.8493813620019594e-05,
+      "loss": 1.5005,
+      "step": 337
+    },
+    {
+      "epoch": 1.8155600268276326,
+      "grad_norm": 0.31906353499540524,
+      "learning_rate": 1.835111572790183e-05,
+      "loss": 1.4626,
+      "step": 338
+    },
+    {
+      "epoch": 1.8209255533199196,
+      "grad_norm": 0.34716461667960885,
+      "learning_rate": 1.8208650568914033e-05,
+      "loss": 1.509,
+      "step": 339
+    },
+    {
+      "epoch": 1.8262910798122065,
+      "grad_norm": 0.34582309441917697,
+      "learning_rate": 1.8066423129812027e-05,
+      "loss": 1.4824,
+      "step": 340
+    },
+    {
+      "epoch": 1.8316566063044937,
+      "grad_norm": 0.32325626999744855,
+      "learning_rate": 1.792443838903065e-05,
+      "loss": 1.4303,
+      "step": 341
+    },
+    {
+      "epoch": 1.8370221327967808,
+      "grad_norm": 0.32008576746121775,
+      "learning_rate": 1.778270131650948e-05,
+      "loss": 1.6245,
+      "step": 342
+    },
+    {
+      "epoch": 1.8423876592890678,
+      "grad_norm": 0.37457992451894306,
+      "learning_rate": 1.7641216873518878e-05,
+      "loss": 1.4618,
+      "step": 343
+    },
+    {
+      "epoch": 1.8477531857813547,
+      "grad_norm": 0.35750145316045384,
+      "learning_rate": 1.749999001248635e-05,
+      "loss": 1.5959,
+      "step": 344
+    },
+    {
+      "epoch": 1.8531187122736419,
+      "grad_norm": 0.3306845841796733,
+      "learning_rate": 1.735902567682315e-05,
+      "loss": 1.5816,
+      "step": 345
+    },
+    {
+      "epoch": 1.858484238765929,
+      "grad_norm": 0.38970827119176255,
+      "learning_rate": 1.7218328800751288e-05,
+      "loss": 1.5529,
+      "step": 346
+    },
+    {
+      "epoch": 1.863849765258216,
+      "grad_norm": 0.3217477415509899,
+      "learning_rate": 1.7077904309130782e-05,
+      "loss": 1.5559,
+      "step": 347
+    },
+    {
+      "epoch": 1.869215291750503,
+      "grad_norm": 0.36288548537121584,
+      "learning_rate": 1.6937757117287278e-05,
+      "loss": 1.4984,
+      "step": 348
+    },
+    {
+      "epoch": 1.87458081824279,
+      "grad_norm": 0.3460179189739247,
+      "learning_rate": 1.6797892130840036e-05,
+      "loss": 1.5385,
+      "step": 349
+    },
+    {
+      "epoch": 1.8799463447350773,
+      "grad_norm": 0.31554481787674976,
+      "learning_rate": 1.665831424553015e-05,
+      "loss": 1.504,
+      "step": 350
+    },
+    {
+      "epoch": 1.8853118712273642,
+      "grad_norm": 0.30549498763968225,
+      "learning_rate": 1.651902834704924e-05,
+      "loss": 1.5228,
+      "step": 351
+    },
+    {
+      "epoch": 1.8906773977196512,
+      "grad_norm": 0.3277064150411407,
+      "learning_rate": 1.6380039310868416e-05,
+      "loss": 1.4852,
+      "step": 352
+    },
+    {
+      "epoch": 1.8960429242119383,
+      "grad_norm": 0.31968263622304366,
+      "learning_rate": 1.624135200206759e-05,
+      "loss": 1.4611,
+      "step": 353
+    },
+    {
+      "epoch": 1.9014084507042255,
+      "grad_norm": 0.32902733969646153,
+      "learning_rate": 1.6102971275165228e-05,
+      "loss": 1.4833,
+      "step": 354
+    },
+    {
+      "epoch": 1.9067739771965124,
+      "grad_norm": 0.3299428742675132,
+      "learning_rate": 1.596490197394841e-05,
+      "loss": 1.4439,
+      "step": 355
+    },
+    {
+      "epoch": 1.9121395036887994,
+      "grad_norm": 0.34500427705894593,
+      "learning_rate": 1.5827148931303277e-05,
+      "loss": 1.5616,
+      "step": 356
+    },
+    {
+      "epoch": 1.9175050301810865,
+      "grad_norm": 0.32458276939765035,
+      "learning_rate": 1.5689716969045848e-05,
+      "loss": 1.4334,
+      "step": 357
+    },
+    {
+      "epoch": 1.9228705566733737,
+      "grad_norm": 0.3342429982300284,
+      "learning_rate": 1.5552610897753292e-05,
+      "loss": 1.5311,
+      "step": 358
+    },
+    {
+      "epoch": 1.9282360831656606,
+      "grad_norm": 0.3483438918440925,
+      "learning_rate": 1.5415835516595465e-05,
+      "loss": 1.4642,
+      "step": 359
+    },
+    {
+      "epoch": 1.9336016096579476,
+      "grad_norm": 0.324692472057597,
+      "learning_rate": 1.5279395613166986e-05,
+      "loss": 1.5336,
+      "step": 360
+    },
+    {
+      "epoch": 1.9389671361502347,
+      "grad_norm": 0.4011901483013197,
+      "learning_rate": 1.5143295963319643e-05,
+      "loss": 1.5634,
+      "step": 361
+    },
+    {
+      "epoch": 1.944332662642522,
+      "grad_norm": 0.3791986336861211,
+      "learning_rate": 1.5007541330995197e-05,
+      "loss": 1.5722,
+      "step": 362
+    },
+    {
+      "epoch": 1.9496981891348089,
+      "grad_norm": 0.3318324328550346,
+      "learning_rate": 1.4872136468058661e-05,
+      "loss": 1.6214,
+      "step": 363
+    },
+    {
+      "epoch": 1.9550637156270958,
+      "grad_norm": 0.3865281831290857,
+      "learning_rate": 1.4737086114131943e-05,
+      "loss": 1.548,
+      "step": 364
+    },
+    {
+      "epoch": 1.960429242119383,
+      "grad_norm": 0.3317269613634914,
+      "learning_rate": 1.4602394996427942e-05,
+      "loss": 1.5024,
+      "step": 365
+    },
+    {
+      "epoch": 1.9657947686116701,
+      "grad_norm": 0.36387655313468187,
+      "learning_rate": 1.4468067829585108e-05,
+      "loss": 1.5256,
+      "step": 366
+    },
+    {
+      "epoch": 1.971160295103957,
+      "grad_norm": 0.3494371010379711,
+      "learning_rate": 1.4334109315502395e-05,
+      "loss": 1.5559,
+      "step": 367
+    },
+    {
+      "epoch": 1.976525821596244,
+      "grad_norm": 0.36135083308665883,
+      "learning_rate": 1.4200524143174677e-05,
+      "loss": 1.5669,
+      "step": 368
+    },
+    {
+      "epoch": 1.9818913480885312,
+      "grad_norm": 0.34824673781683024,
+      "learning_rate": 1.4067316988528617e-05,
+      "loss": 1.6642,
+      "step": 369
+    },
+    {
+      "epoch": 1.9872568745808183,
+      "grad_norm": 0.36134664903507996,
+      "learning_rate": 1.3934492514259003e-05,
+      "loss": 1.5003,
+      "step": 370
+    },
+    {
+      "epoch": 1.9926224010731053,
+      "grad_norm": 0.3315306163140975,
+      "learning_rate": 1.3802055369665534e-05,
+      "loss": 1.3959,
+      "step": 371
+    },
+    {
+      "epoch": 1.9979879275653922,
+      "grad_norm": 0.3179771784326003,
+      "learning_rate": 1.3670010190490073e-05,
+      "loss": 1.5285,
+      "step": 372
+    },
+    {
+      "epoch": 2.005365526492287,
+      "grad_norm": 0.9915595865019317,
+      "learning_rate": 1.3538361598754384e-05,
+      "loss": 2.456,
+      "step": 373
+    },
+    {
+      "epoch": 2.0107310529845743,
+      "grad_norm": 0.6291566214590382,
+      "learning_rate": 1.3407114202598369e-05,
+      "loss": 1.1708,
+      "step": 374
+    },
+    {
+      "epoch": 2.0160965794768613,
+      "grad_norm": 0.5593895609190137,
+      "learning_rate": 1.327627259611873e-05,
+      "loss": 1.1864,
+      "step": 375
+    },
+    {
+      "epoch": 2.021462105969148,
+      "grad_norm": 0.4205563210949494,
+      "learning_rate": 1.314584135920815e-05,
+      "loss": 1.1374,
+      "step": 376
+    },
+    {
+      "epoch": 2.021462105969148,
+      "eval_loss": 2.232717752456665,
+      "eval_runtime": 403.1787,
+      "eval_samples_per_second": 6.322,
+      "eval_steps_per_second": 0.791,
+      "step": 376
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 558,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 47,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0096298209438597e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-376/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5727b190dfc4585176e91dd00249738e0c6d16f3c0cdf2808b52246323abda10
+size 9208

checkpoint-376/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

checkpoint-423/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-423/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-423/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

checkpoint-423/global_step423/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d53ca88cc115bac807bc0564f458a6366c6e2cf92f372a741345b211de66b8f
+size 381701

checkpoint-423/global_step423/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c904f45f340885129b19d06d5d845703cba23da90e32143b0026cc65253907
+size 381701

checkpoint-423/global_step423/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed5006c84a8e6eeaf4a8a9329310aca597aae03ab1241ee7eae611aeef4c413
+size 381701

checkpoint-423/global_step423/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e98139254d94a00efc8ea5720890b5842389ca1c42da27a278c37b2edbcef636
+size 381701

checkpoint-423/global_step423/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5b9dc875d827454e6d30db3bf597218b7d693a8321974bb1fc9664dd488d24
+size 381701

checkpoint-423/global_step423/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:670208ef1105ec0111dd85f9abede0b1c106ca6f228593822ce6754d0c358876
+size 381701

checkpoint-423/global_step423/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5649bdee963e15c7fe20f1dd709499e47323fd897ef7300ff54328fe5e63e6f
+size 381701

checkpoint-423/global_step423/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd827cfa844eda7cfc9addb70fb972c44ac28ea8c537d0d31e3380e4c31d421c
+size 381701

checkpoint-423/latest

@@ -0,0 +1 @@
+global_step423

checkpoint-423/model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

checkpoint-423/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1bec598899f9d59e70c1b4705ce420a1e0a670957b6c8153a589880068ae5a4
+size 15984

checkpoint-423/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60d2348aae518f4c44693db9c9b4b3a3299c556e7f0a86c188b2e4c3e364a7c
+size 15984

checkpoint-423/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe5a79d3bcb4ce033de360bc765e616316e3562aba25887cd85c4adbb935abf
+size 15984

checkpoint-423/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a9d1f6e22677721841890e6a27855857e6840137650d609eb8e4ac13b71d29
+size 15984