Upload kodcode-v1-qwq-secureplusplusplus

.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 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/QwQ-32B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: kodcode-v1-qwq-secureplusplusplus
+  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. -->
+
+# kodcode-v1-qwq-secureplusplusplus
+
+This model is a fine-tuned version of [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) on the kodcode-v1-secureplusplusplus dataset.
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 48
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.1
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.6.0
+- Pytorch 2.12.0+cu130
+- Datasets 4.0.0
+- Tokenizers 0.22.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 106024918253568.0,
+    "train_loss": 0.5945852278243928,
+    "train_runtime": 15268.5072,
+    "train_samples_per_second": 0.261,
+    "train_steps_per_second": 0.006
+}

chat_template.jinja

@@ -0,0 +1,62 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- '' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+  {%- endif %}
+{%- 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" and not message.tool_calls %}
+        {%- set content = message.content %}
+        {%- if not loop.last %}
+            {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+        {%- endif %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- if not loop.last %}
+            {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+        {%- endif %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n<think>\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,97 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.0,
+  "temperature": 0.6,
+  "top_k": 40,
+  "top_p": 0.95,
+  "transformers_version": "5.6.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa8af721d8ab7cb0d1d93659489cfcf38a0e394783833ee55282ba99bca56c8a
+size 49924452408

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:751b4e8483b7c64ae2cfbf7735e296e30bd0242e846b43ce9b88b28e62757e68
+size 15603390216

model.safetensors.index.json

@@ -0,0 +1,779 @@
+{
+  "metadata": {
+    "total_parameters": 1119232,
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 106024918253568.0,
+    "train_loss": 0.5945852278243928,
+    "train_runtime": 15268.5072,
+    "train_samples_per_second": 0.261,
+    "train_steps_per_second": 0.006
+}

trainer_log.jsonl

@@ -0,0 +1,85 @@
+{"current_steps": 1, "total_steps": 84, "loss": 0.8157972693443298, "lr": 0.0, "epoch": 0.03614457831325301, "percentage": 1.19, "elapsed_time": "0:03:02", "remaining_time": "4:12:43"}
+{"current_steps": 2, "total_steps": 84, "loss": 0.8220954537391663, "lr": 1.111111111111111e-06, "epoch": 0.07228915662650602, "percentage": 2.38, "elapsed_time": "0:06:12", "remaining_time": "4:14:22"}
+{"current_steps": 3, "total_steps": 84, "loss": 0.8105740547180176, "lr": 2.222222222222222e-06, "epoch": 0.10843373493975904, "percentage": 3.57, "elapsed_time": "0:09:07", "remaining_time": "4:06:19"}
+{"current_steps": 4, "total_steps": 84, "loss": 0.7965067028999329, "lr": 3.3333333333333333e-06, "epoch": 0.14457831325301204, "percentage": 4.76, "elapsed_time": "0:12:10", "remaining_time": "4:03:28"}
+{"current_steps": 5, "total_steps": 84, "loss": 0.7848137617111206, "lr": 4.444444444444444e-06, "epoch": 0.18072289156626506, "percentage": 5.95, "elapsed_time": "0:15:05", "remaining_time": "3:58:21"}
+{"current_steps": 6, "total_steps": 84, "loss": 0.7374380826950073, "lr": 5.555555555555557e-06, "epoch": 0.21686746987951808, "percentage": 7.14, "elapsed_time": "0:18:13", "remaining_time": "3:56:52"}
+{"current_steps": 7, "total_steps": 84, "loss": 0.7128661274909973, "lr": 6.666666666666667e-06, "epoch": 0.25301204819277107, "percentage": 8.33, "elapsed_time": "0:21:10", "remaining_time": "3:52:54"}
+{"current_steps": 8, "total_steps": 84, "loss": 0.7061306238174438, "lr": 7.77777777777778e-06, "epoch": 0.2891566265060241, "percentage": 9.52, "elapsed_time": "0:24:05", "remaining_time": "3:48:48"}
+{"current_steps": 9, "total_steps": 84, "loss": 0.7266426086425781, "lr": 8.888888888888888e-06, "epoch": 0.3253012048192771, "percentage": 10.71, "elapsed_time": "0:26:55", "remaining_time": "3:44:21"}
+{"current_steps": 10, "total_steps": 84, "loss": 0.7644096612930298, "lr": 1e-05, "epoch": 0.3614457831325301, "percentage": 11.9, "elapsed_time": "0:29:45", "remaining_time": "3:40:11"}
+{"current_steps": 11, "total_steps": 84, "loss": 0.7518090009689331, "lr": 9.995614150494293e-06, "epoch": 0.39759036144578314, "percentage": 13.1, "elapsed_time": "0:32:38", "remaining_time": "3:36:39"}
+{"current_steps": 12, "total_steps": 84, "loss": 0.7258176803588867, "lr": 9.982464296247523e-06, "epoch": 0.43373493975903615, "percentage": 14.29, "elapsed_time": "0:35:41", "remaining_time": "3:34:09"}
+{"current_steps": 13, "total_steps": 84, "loss": 0.7168642282485962, "lr": 9.960573506572391e-06, "epoch": 0.46987951807228917, "percentage": 15.48, "elapsed_time": "0:38:46", "remaining_time": "3:31:46"}
+{"current_steps": 14, "total_steps": 84, "loss": 0.7147663831710815, "lr": 9.929980185352525e-06, "epoch": 0.5060240963855421, "percentage": 16.67, "elapsed_time": "0:41:50", "remaining_time": "3:29:14"}
+{"current_steps": 15, "total_steps": 84, "loss": 0.7102792263031006, "lr": 9.890738003669029e-06, "epoch": 0.5421686746987951, "percentage": 17.86, "elapsed_time": "0:44:45", "remaining_time": "3:25:52"}
+{"current_steps": 16, "total_steps": 84, "loss": 0.6803984045982361, "lr": 9.842915805643156e-06, "epoch": 0.5783132530120482, "percentage": 19.05, "elapsed_time": "0:47:56", "remaining_time": "3:23:46"}
+{"current_steps": 17, "total_steps": 84, "loss": 0.6794809699058533, "lr": 9.786597487660336e-06, "epoch": 0.6144578313253012, "percentage": 20.24, "elapsed_time": "0:51:05", "remaining_time": "3:21:23"}
+{"current_steps": 18, "total_steps": 84, "loss": 0.6609358787536621, "lr": 9.721881851187406e-06, "epoch": 0.6506024096385542, "percentage": 21.43, "elapsed_time": "0:54:12", "remaining_time": "3:18:46"}
+{"current_steps": 19, "total_steps": 84, "loss": 0.6601911783218384, "lr": 9.648882429441258e-06, "epoch": 0.6867469879518072, "percentage": 22.62, "elapsed_time": "0:57:19", "remaining_time": "3:16:05"}
+{"current_steps": 20, "total_steps": 84, "loss": 0.6362742781639099, "lr": 9.567727288213005e-06, "epoch": 0.7228915662650602, "percentage": 23.81, "elapsed_time": "1:00:21", "remaining_time": "3:13:09"}
+{"current_steps": 21, "total_steps": 84, "loss": 0.6495505571365356, "lr": 9.478558801197065e-06, "epoch": 0.7590361445783133, "percentage": 25.0, "elapsed_time": "1:03:19", "remaining_time": "3:09:58"}
+{"current_steps": 22, "total_steps": 84, "loss": 0.6754122972488403, "lr": 9.381533400219319e-06, "epoch": 0.7951807228915663, "percentage": 26.19, "elapsed_time": "1:06:12", "remaining_time": "3:06:36"}
+{"current_steps": 23, "total_steps": 84, "loss": 0.6430672407150269, "lr": 9.276821300802535e-06, "epoch": 0.8313253012048193, "percentage": 27.38, "elapsed_time": "1:09:09", "remaining_time": "3:03:25"}
+{"current_steps": 24, "total_steps": 84, "loss": 0.658618152141571, "lr": 9.164606203550498e-06, "epoch": 0.8674698795180723, "percentage": 28.57, "elapsed_time": "1:12:08", "remaining_time": "3:00:21"}
+{"current_steps": 25, "total_steps": 84, "loss": 0.6351467370986938, "lr": 9.045084971874738e-06, "epoch": 0.9036144578313253, "percentage": 29.76, "elapsed_time": "1:15:03", "remaining_time": "2:57:08"}
+{"current_steps": 26, "total_steps": 84, "loss": 0.6528507471084595, "lr": 8.9184672866292e-06, "epoch": 0.9397590361445783, "percentage": 30.95, "elapsed_time": "1:18:11", "remaining_time": "2:54:26"}
+{"current_steps": 27, "total_steps": 84, "loss": 0.6266601085662842, "lr": 8.784975278258783e-06, "epoch": 0.9759036144578314, "percentage": 32.14, "elapsed_time": "1:21:19", "remaining_time": "2:51:40"}
+{"current_steps": 28, "total_steps": 84, "loss": 0.6392745971679688, "lr": 8.644843137107058e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:23:40", "remaining_time": "2:47:21"}
+{"current_steps": 29, "total_steps": 84, "loss": 0.5894884467124939, "lr": 8.498316702566828e-06, "epoch": 1.036144578313253, "percentage": 34.52, "elapsed_time": "1:26:55", "remaining_time": "2:44:50"}
+{"current_steps": 30, "total_steps": 84, "loss": 0.5866576433181763, "lr": 8.345653031794292e-06, "epoch": 1.072289156626506, "percentage": 35.71, "elapsed_time": "1:29:53", "remaining_time": "2:41:48"}
+{"current_steps": 31, "total_steps": 84, "loss": 0.5744427442550659, "lr": 8.18711994874345e-06, "epoch": 1.108433734939759, "percentage": 36.9, "elapsed_time": "1:32:42", "remaining_time": "2:38:30"}
+{"current_steps": 32, "total_steps": 84, "loss": 0.576800525188446, "lr": 8.022995574311876e-06, "epoch": 1.144578313253012, "percentage": 38.1, "elapsed_time": "1:35:42", "remaining_time": "2:35:32"}
+{"current_steps": 33, "total_steps": 84, "loss": 0.5835787057876587, "lr": 7.85356783842216e-06, "epoch": 1.180722891566265, "percentage": 39.29, "elapsed_time": "1:38:38", "remaining_time": "2:32:26"}
+{"current_steps": 34, "total_steps": 84, "loss": 0.5828098654747009, "lr": 7.679133974894984e-06, "epoch": 1.216867469879518, "percentage": 40.48, "elapsed_time": "1:41:43", "remaining_time": "2:29:35"}
+{"current_steps": 35, "total_steps": 84, "loss": 0.576937198638916, "lr": 7.500000000000001e-06, "epoch": 1.2530120481927711, "percentage": 41.67, "elapsed_time": "1:44:42", "remaining_time": "2:26:35"}
+{"current_steps": 36, "total_steps": 84, "loss": 0.5882814526557922, "lr": 7.31648017559931e-06, "epoch": 1.2891566265060241, "percentage": 42.86, "elapsed_time": "1:47:51", "remaining_time": "2:23:48"}
+{"current_steps": 37, "total_steps": 84, "loss": 0.6010534763336182, "lr": 7.128896457825364e-06, "epoch": 1.3253012048192772, "percentage": 44.05, "elapsed_time": "1:50:48", "remaining_time": "2:20:45"}
+{"current_steps": 38, "total_steps": 84, "loss": 0.5684958696365356, "lr": 6.9375779322605154e-06, "epoch": 1.3614457831325302, "percentage": 45.24, "elapsed_time": "1:53:44", "remaining_time": "2:17:41"}
+{"current_steps": 39, "total_steps": 84, "loss": 0.5608981251716614, "lr": 6.7428602366090764e-06, "epoch": 1.3975903614457832, "percentage": 46.43, "elapsed_time": "1:56:48", "remaining_time": "2:14:46"}
+{"current_steps": 40, "total_steps": 84, "loss": 0.5603346824645996, "lr": 6.545084971874738e-06, "epoch": 1.4337349397590362, "percentage": 47.62, "elapsed_time": "1:59:46", "remaining_time": "2:11:44"}
+{"current_steps": 41, "total_steps": 84, "loss": 0.559664785861969, "lr": 6.344599103076329e-06, "epoch": 1.4698795180722892, "percentage": 48.81, "elapsed_time": "2:02:48", "remaining_time": "2:08:47"}
+{"current_steps": 42, "total_steps": 84, "loss": 0.5493080615997314, "lr": 6.141754350553279e-06, "epoch": 1.5060240963855422, "percentage": 50.0, "elapsed_time": "2:06:05", "remaining_time": "2:06:05"}
+{"current_steps": 43, "total_steps": 84, "loss": 0.5648080110549927, "lr": 5.936906572928625e-06, "epoch": 1.5421686746987953, "percentage": 51.19, "elapsed_time": "2:09:02", "remaining_time": "2:03:02"}
+{"current_steps": 44, "total_steps": 84, "loss": 0.5434543490409851, "lr": 5.730415142812059e-06, "epoch": 1.5783132530120483, "percentage": 52.38, "elapsed_time": "2:11:55", "remaining_time": "1:59:55"}
+{"current_steps": 45, "total_steps": 84, "loss": 0.5768675804138184, "lr": 5.522642316338268e-06, "epoch": 1.6144578313253013, "percentage": 53.57, "elapsed_time": "2:14:40", "remaining_time": "1:56:42"}
+{"current_steps": 46, "total_steps": 84, "loss": 0.5745658874511719, "lr": 5.3139525976465675e-06, "epoch": 1.6506024096385543, "percentage": 54.76, "elapsed_time": "2:17:37", "remaining_time": "1:53:41"}
+{"current_steps": 47, "total_steps": 84, "loss": 0.5468243360519409, "lr": 5.1047120994167855e-06, "epoch": 1.6867469879518073, "percentage": 55.95, "elapsed_time": "2:20:48", "remaining_time": "1:50:50"}
+{"current_steps": 48, "total_steps": 84, "loss": 0.5729954242706299, "lr": 4.895287900583216e-06, "epoch": 1.7228915662650603, "percentage": 57.14, "elapsed_time": "2:23:52", "remaining_time": "1:47:54"}
+{"current_steps": 49, "total_steps": 84, "loss": 0.5846940875053406, "lr": 4.686047402353433e-06, "epoch": 1.7590361445783134, "percentage": 58.33, "elapsed_time": "2:26:43", "remaining_time": "1:44:47"}
+{"current_steps": 50, "total_steps": 84, "loss": 0.5727739334106445, "lr": 4.477357683661734e-06, "epoch": 1.7951807228915664, "percentage": 59.52, "elapsed_time": "2:29:46", "remaining_time": "1:41:50"}
+{"current_steps": 51, "total_steps": 84, "loss": 0.5597992539405823, "lr": 4.269584857187942e-06, "epoch": 1.8313253012048194, "percentage": 60.71, "elapsed_time": "2:32:37", "remaining_time": "1:38:45"}
+{"current_steps": 52, "total_steps": 84, "loss": 0.5638898611068726, "lr": 4.063093427071376e-06, "epoch": 1.8674698795180724, "percentage": 61.9, "elapsed_time": "2:35:37", "remaining_time": "1:35:46"}
+{"current_steps": 53, "total_steps": 84, "loss": 0.582793653011322, "lr": 3.8582456494467214e-06, "epoch": 1.9036144578313254, "percentage": 63.1, "elapsed_time": "2:38:41", "remaining_time": "1:32:48"}
+{"current_steps": 54, "total_steps": 84, "loss": 0.5641998052597046, "lr": 3.655400896923672e-06, "epoch": 1.9397590361445785, "percentage": 64.29, "elapsed_time": "2:41:50", "remaining_time": "1:29:54"}
+{"current_steps": 55, "total_steps": 84, "loss": 0.5672302842140198, "lr": 3.4549150281252635e-06, "epoch": 1.9759036144578315, "percentage": 65.48, "elapsed_time": "2:44:46", "remaining_time": "1:26:52"}
+{"current_steps": 56, "total_steps": 84, "loss": 0.5661230087280273, "lr": 3.2571397633909252e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:46:54", "remaining_time": "1:23:27"}
+{"current_steps": 57, "total_steps": 84, "loss": 0.5152542591094971, "lr": 3.0624220677394854e-06, "epoch": 2.036144578313253, "percentage": 67.86, "elapsed_time": "2:49:57", "remaining_time": "1:20:30"}
+{"current_steps": 58, "total_steps": 84, "loss": 0.5110700130462646, "lr": 2.871103542174637e-06, "epoch": 2.072289156626506, "percentage": 69.05, "elapsed_time": "2:53:04", "remaining_time": "1:17:35"}
+{"current_steps": 59, "total_steps": 84, "loss": 0.5136343240737915, "lr": 2.683519824400693e-06, "epoch": 2.108433734939759, "percentage": 70.24, "elapsed_time": "2:56:09", "remaining_time": "1:14:38"}
+{"current_steps": 60, "total_steps": 84, "loss": 0.5048317909240723, "lr": 2.5000000000000015e-06, "epoch": 2.144578313253012, "percentage": 71.43, "elapsed_time": "2:59:01", "remaining_time": "1:11:36"}
+{"current_steps": 61, "total_steps": 84, "loss": 0.5214716196060181, "lr": 2.320866025105016e-06, "epoch": 2.180722891566265, "percentage": 72.62, "elapsed_time": "3:01:55", "remaining_time": "1:08:35"}
+{"current_steps": 62, "total_steps": 84, "loss": 0.5121402740478516, "lr": 2.146432161577842e-06, "epoch": 2.216867469879518, "percentage": 73.81, "elapsed_time": "3:05:01", "remaining_time": "1:05:39"}
+{"current_steps": 63, "total_steps": 84, "loss": 0.49233055114746094, "lr": 1.977004425688126e-06, "epoch": 2.253012048192771, "percentage": 75.0, "elapsed_time": "3:08:04", "remaining_time": "1:02:41"}
+{"current_steps": 64, "total_steps": 84, "loss": 0.5020605325698853, "lr": 1.8128800512565514e-06, "epoch": 2.289156626506024, "percentage": 76.19, "elapsed_time": "3:11:09", "remaining_time": "0:59:44"}
+{"current_steps": 65, "total_steps": 84, "loss": 0.5020735263824463, "lr": 1.6543469682057105e-06, "epoch": 2.325301204819277, "percentage": 77.38, "elapsed_time": "3:14:14", "remaining_time": "0:56:46"}
+{"current_steps": 66, "total_steps": 84, "loss": 0.5086070895195007, "lr": 1.5016832974331725e-06, "epoch": 2.36144578313253, "percentage": 78.57, "elapsed_time": "3:17:29", "remaining_time": "0:53:51"}
+{"current_steps": 67, "total_steps": 84, "loss": 0.5086838006973267, "lr": 1.3551568628929434e-06, "epoch": 2.397590361445783, "percentage": 79.76, "elapsed_time": "3:20:34", "remaining_time": "0:50:53"}
+{"current_steps": 68, "total_steps": 84, "loss": 0.5006733536720276, "lr": 1.2150247217412186e-06, "epoch": 2.433734939759036, "percentage": 80.95, "elapsed_time": "3:23:52", "remaining_time": "0:47:58"}
+{"current_steps": 69, "total_steps": 84, "loss": 0.4901826083660126, "lr": 1.0815327133708015e-06, "epoch": 2.4698795180722892, "percentage": 82.14, "elapsed_time": "3:26:48", "remaining_time": "0:44:57"}
+{"current_steps": 70, "total_steps": 84, "loss": 0.509224534034729, "lr": 9.549150281252633e-07, "epoch": 2.5060240963855422, "percentage": 83.33, "elapsed_time": "3:29:40", "remaining_time": "0:41:56"}
+{"current_steps": 71, "total_steps": 84, "loss": 0.5090753436088562, "lr": 8.353937964495029e-07, "epoch": 2.5421686746987953, "percentage": 84.52, "elapsed_time": "3:32:51", "remaining_time": "0:38:58"}
+{"current_steps": 72, "total_steps": 84, "loss": 0.5140612721443176, "lr": 7.23178699197467e-07, "epoch": 2.5783132530120483, "percentage": 85.71, "elapsed_time": "3:35:46", "remaining_time": "0:35:57"}
+{"current_steps": 73, "total_steps": 84, "loss": 0.47711265087127686, "lr": 6.184665997806832e-07, "epoch": 2.6144578313253013, "percentage": 86.9, "elapsed_time": "3:38:58", "remaining_time": "0:32:59"}
+{"current_steps": 74, "total_steps": 84, "loss": 0.49803662300109863, "lr": 5.214411988029355e-07, "epoch": 2.6506024096385543, "percentage": 88.1, "elapsed_time": "3:41:54", "remaining_time": "0:29:59"}
+{"current_steps": 75, "total_steps": 84, "loss": 0.5065058469772339, "lr": 4.322727117869951e-07, "epoch": 2.6867469879518073, "percentage": 89.29, "elapsed_time": "3:45:09", "remaining_time": "0:27:01"}
+{"current_steps": 76, "total_steps": 84, "loss": 0.49857965111732483, "lr": 3.511175705587433e-07, "epoch": 2.7228915662650603, "percentage": 90.48, "elapsed_time": "3:48:08", "remaining_time": "0:24:00"}
+{"current_steps": 77, "total_steps": 84, "loss": 0.5032105445861816, "lr": 2.7811814881259503e-07, "epoch": 2.7590361445783134, "percentage": 91.67, "elapsed_time": "3:51:10", "remaining_time": "0:21:00"}
+{"current_steps": 78, "total_steps": 84, "loss": 0.48751121759414673, "lr": 2.134025123396638e-07, "epoch": 2.7951807228915664, "percentage": 92.86, "elapsed_time": "3:54:03", "remaining_time": "0:18:00"}
+{"current_steps": 79, "total_steps": 84, "loss": 0.5210248231887817, "lr": 1.5708419435684463e-07, "epoch": 2.8313253012048194, "percentage": 94.05, "elapsed_time": "3:57:05", "remaining_time": "0:15:00"}
+{"current_steps": 80, "total_steps": 84, "loss": 0.4980379343032837, "lr": 1.0926199633097156e-07, "epoch": 2.8674698795180724, "percentage": 95.24, "elapsed_time": "4:00:07", "remaining_time": "0:12:00"}
+{"current_steps": 81, "total_steps": 84, "loss": 0.5095956325531006, "lr": 7.001981464747565e-08, "epoch": 2.9036144578313254, "percentage": 96.43, "elapsed_time": "4:03:04", "remaining_time": "0:09:00"}
+{"current_steps": 82, "total_steps": 84, "loss": 0.5043609738349915, "lr": 3.9426493427611177e-08, "epoch": 2.9397590361445785, "percentage": 97.62, "elapsed_time": "4:05:51", "remaining_time": "0:05:59"}
+{"current_steps": 83, "total_steps": 84, "loss": 0.5091077089309692, "lr": 1.753570375247815e-08, "epoch": 2.9759036144578315, "percentage": 98.81, "elapsed_time": "4:08:59", "remaining_time": "0:02:59"}
+{"current_steps": 84, "total_steps": 84, "loss": 0.5222575664520264, "lr": 4.385849505708084e-09, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:11:18", "remaining_time": "0:00:00"}
+{"current_steps": 84, "total_steps": 84, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:14:27", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,631 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 84,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03614457831325301,
+      "grad_norm": 3.553168296813965,
+      "learning_rate": 0.0,
+      "loss": 0.8157972693443298,
+      "step": 1
+    },
+    {
+      "epoch": 0.07228915662650602,
+      "grad_norm": 3.4760236740112305,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.8220954537391663,
+      "step": 2
+    },
+    {
+      "epoch": 0.10843373493975904,
+      "grad_norm": 3.3894028663635254,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.8105740547180176,
+      "step": 3
+    },
+    {
+      "epoch": 0.14457831325301204,
+      "grad_norm": 3.293134927749634,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.7965067028999329,
+      "step": 4
+    },
+    {
+      "epoch": 0.18072289156626506,
+      "grad_norm": 2.8860864639282227,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.7848137617111206,
+      "step": 5
+    },
+    {
+      "epoch": 0.21686746987951808,
+      "grad_norm": 2.0125129222869873,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.7374380826950073,
+      "step": 6
+    },
+    {
+      "epoch": 0.25301204819277107,
+      "grad_norm": 1.5207632780075073,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.7128661274909973,
+      "step": 7
+    },
+    {
+      "epoch": 0.2891566265060241,
+      "grad_norm": 1.3406639099121094,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.7061306238174438,
+      "step": 8
+    },
+    {
+      "epoch": 0.3253012048192771,
+      "grad_norm": 1.3483136892318726,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.7266426086425781,
+      "step": 9
+    },
+    {
+      "epoch": 0.3614457831325301,
+      "grad_norm": 2.7021946907043457,
+      "learning_rate": 1e-05,
+      "loss": 0.7644096612930298,
+      "step": 10
+    },
+    {
+      "epoch": 0.39759036144578314,
+      "grad_norm": 2.3240082263946533,
+      "learning_rate": 9.995614150494293e-06,
+      "loss": 0.7518090009689331,
+      "step": 11
+    },
+    {
+      "epoch": 0.43373493975903615,
+      "grad_norm": 1.8651138544082642,
+      "learning_rate": 9.982464296247523e-06,
+      "loss": 0.7258176803588867,
+      "step": 12
+    },
+    {
+      "epoch": 0.46987951807228917,
+      "grad_norm": 1.595149278640747,
+      "learning_rate": 9.960573506572391e-06,
+      "loss": 0.7168642282485962,
+      "step": 13
+    },
+    {
+      "epoch": 0.5060240963855421,
+      "grad_norm": 1.355558156967163,
+      "learning_rate": 9.929980185352525e-06,
+      "loss": 0.7147663831710815,
+      "step": 14
+    },
+    {
+      "epoch": 0.5421686746987951,
+      "grad_norm": 1.1974090337753296,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 0.7102792263031006,
+      "step": 15
+    },
+    {
+      "epoch": 0.5783132530120482,
+      "grad_norm": 0.9845958352088928,
+      "learning_rate": 9.842915805643156e-06,
+      "loss": 0.6803984045982361,
+      "step": 16
+    },
+    {
+      "epoch": 0.6144578313253012,
+      "grad_norm": 1.0079755783081055,
+      "learning_rate": 9.786597487660336e-06,
+      "loss": 0.6794809699058533,
+      "step": 17
+    },
+    {
+      "epoch": 0.6506024096385542,
+      "grad_norm": 0.9282218813896179,
+      "learning_rate": 9.721881851187406e-06,
+      "loss": 0.6609358787536621,
+      "step": 18
+    },
+    {
+      "epoch": 0.6867469879518072,
+      "grad_norm": 0.847620964050293,
+      "learning_rate": 9.648882429441258e-06,
+      "loss": 0.6601911783218384,
+      "step": 19
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 0.7623603343963623,
+      "learning_rate": 9.567727288213005e-06,
+      "loss": 0.6362742781639099,
+      "step": 20
+    },
+    {
+      "epoch": 0.7590361445783133,
+      "grad_norm": 0.7723239660263062,
+      "learning_rate": 9.478558801197065e-06,
+      "loss": 0.6495505571365356,
+      "step": 21
+    },
+    {
+      "epoch": 0.7951807228915663,
+      "grad_norm": 0.9192399382591248,
+      "learning_rate": 9.381533400219319e-06,
+      "loss": 0.6754122972488403,
+      "step": 22
+    },
+    {
+      "epoch": 0.8313253012048193,
+      "grad_norm": 0.6796345114707947,
+      "learning_rate": 9.276821300802535e-06,
+      "loss": 0.6430672407150269,
+      "step": 23
+    },
+    {
+      "epoch": 0.8674698795180723,
+      "grad_norm": 0.6662194728851318,
+      "learning_rate": 9.164606203550498e-06,
+      "loss": 0.658618152141571,
+      "step": 24
+    },
+    {
+      "epoch": 0.9036144578313253,
+      "grad_norm": 0.6152909398078918,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.6351467370986938,
+      "step": 25
+    },
+    {
+      "epoch": 0.9397590361445783,
+      "grad_norm": 0.6219061613082886,
+      "learning_rate": 8.9184672866292e-06,
+      "loss": 0.6528507471084595,
+      "step": 26
+    },
+    {
+      "epoch": 0.9759036144578314,
+      "grad_norm": 0.5178506970405579,
+      "learning_rate": 8.784975278258783e-06,
+      "loss": 0.6266601085662842,
+      "step": 27
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6238970160484314,
+      "learning_rate": 8.644843137107058e-06,
+      "loss": 0.6392745971679688,
+      "step": 28
+    },
+    {
+      "epoch": 1.036144578313253,
+      "grad_norm": 0.5749419927597046,
+      "learning_rate": 8.498316702566828e-06,
+      "loss": 0.5894884467124939,
+      "step": 29
+    },
+    {
+      "epoch": 1.072289156626506,
+      "grad_norm": 0.54451584815979,
+      "learning_rate": 8.345653031794292e-06,
+      "loss": 0.5866576433181763,
+      "step": 30
+    },
+    {
+      "epoch": 1.108433734939759,
+      "grad_norm": 0.7175883650779724,
+      "learning_rate": 8.18711994874345e-06,
+      "loss": 0.5744427442550659,
+      "step": 31
+    },
+    {
+      "epoch": 1.144578313253012,
+      "grad_norm": 0.5757364630699158,
+      "learning_rate": 8.022995574311876e-06,
+      "loss": 0.576800525188446,
+      "step": 32
+    },
+    {
+      "epoch": 1.180722891566265,
+      "grad_norm": 0.5273779034614563,
+      "learning_rate": 7.85356783842216e-06,
+      "loss": 0.5835787057876587,
+      "step": 33
+    },
+    {
+      "epoch": 1.216867469879518,
+      "grad_norm": 0.4972248375415802,
+      "learning_rate": 7.679133974894984e-06,
+      "loss": 0.5828098654747009,
+      "step": 34
+    },
+    {
+      "epoch": 1.2530120481927711,
+      "grad_norm": 0.5350473523139954,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.576937198638916,
+      "step": 35
+    },
+    {
+      "epoch": 1.2891566265060241,
+      "grad_norm": 0.5231545567512512,
+      "learning_rate": 7.31648017559931e-06,
+      "loss": 0.5882814526557922,
+      "step": 36
+    },
+    {
+      "epoch": 1.3253012048192772,
+      "grad_norm": 0.506576657295227,
+      "learning_rate": 7.128896457825364e-06,
+      "loss": 0.6010534763336182,
+      "step": 37
+    },
+    {
+      "epoch": 1.3614457831325302,
+      "grad_norm": 0.45483383536338806,
+      "learning_rate": 6.9375779322605154e-06,
+      "loss": 0.5684958696365356,
+      "step": 38
+    },
+    {
+      "epoch": 1.3975903614457832,
+      "grad_norm": 0.5004634261131287,
+      "learning_rate": 6.7428602366090764e-06,
+      "loss": 0.5608981251716614,
+      "step": 39
+    },
+    {
+      "epoch": 1.4337349397590362,
+      "grad_norm": 0.4696190655231476,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.5603346824645996,
+      "step": 40
+    },
+    {
+      "epoch": 1.4698795180722892,
+      "grad_norm": 0.4757210612297058,
+      "learning_rate": 6.344599103076329e-06,
+      "loss": 0.559664785861969,
+      "step": 41
+    },
+    {
+      "epoch": 1.5060240963855422,
+      "grad_norm": 0.4191446006298065,
+      "learning_rate": 6.141754350553279e-06,
+      "loss": 0.5493080615997314,
+      "step": 42
+    },
+    {
+      "epoch": 1.5421686746987953,
+      "grad_norm": 0.45142653584480286,
+      "learning_rate": 5.936906572928625e-06,
+      "loss": 0.5648080110549927,
+      "step": 43
+    },
+    {
+      "epoch": 1.5783132530120483,
+      "grad_norm": 0.42723336815834045,
+      "learning_rate": 5.730415142812059e-06,
+      "loss": 0.5434543490409851,
+      "step": 44
+    },
+    {
+      "epoch": 1.6144578313253013,
+      "grad_norm": 0.5359069108963013,
+      "learning_rate": 5.522642316338268e-06,
+      "loss": 0.5768675804138184,
+      "step": 45
+    },
+    {
+      "epoch": 1.6506024096385543,
+      "grad_norm": 0.52814781665802,
+      "learning_rate": 5.3139525976465675e-06,
+      "loss": 0.5745658874511719,
+      "step": 46
+    },
+    {
+      "epoch": 1.6867469879518073,
+      "grad_norm": 0.3892335891723633,
+      "learning_rate": 5.1047120994167855e-06,
+      "loss": 0.5468243360519409,
+      "step": 47
+    },
+    {
+      "epoch": 1.7228915662650603,
+      "grad_norm": 0.4192783236503601,
+      "learning_rate": 4.895287900583216e-06,
+      "loss": 0.5729954242706299,
+      "step": 48
+    },
+    {
+      "epoch": 1.7590361445783134,
+      "grad_norm": 0.4870302379131317,
+      "learning_rate": 4.686047402353433e-06,
+      "loss": 0.5846940875053406,
+      "step": 49
+    },
+    {
+      "epoch": 1.7951807228915664,
+      "grad_norm": 0.43588584661483765,
+      "learning_rate": 4.477357683661734e-06,
+      "loss": 0.5727739334106445,
+      "step": 50
+    },
+    {
+      "epoch": 1.8313253012048194,
+      "grad_norm": 0.4209176301956177,
+      "learning_rate": 4.269584857187942e-06,
+      "loss": 0.5597992539405823,
+      "step": 51
+    },
+    {
+      "epoch": 1.8674698795180724,
+      "grad_norm": 0.4455879330635071,
+      "learning_rate": 4.063093427071376e-06,
+      "loss": 0.5638898611068726,
+      "step": 52
+    },
+    {
+      "epoch": 1.9036144578313254,
+      "grad_norm": 0.41628143191337585,
+      "learning_rate": 3.8582456494467214e-06,
+      "loss": 0.582793653011322,
+      "step": 53
+    },
+    {
+      "epoch": 1.9397590361445785,
+      "grad_norm": 0.40379446744918823,
+      "learning_rate": 3.655400896923672e-06,
+      "loss": 0.5641998052597046,
+      "step": 54
+    },
+    {
+      "epoch": 1.9759036144578315,
+      "grad_norm": 0.4030258357524872,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.5672302842140198,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4758393466472626,
+      "learning_rate": 3.2571397633909252e-06,
+      "loss": 0.5661230087280273,
+      "step": 56
+    },
+    {
+      "epoch": 2.036144578313253,
+      "grad_norm": 0.4000002443790436,
+      "learning_rate": 3.0624220677394854e-06,
+      "loss": 0.5152542591094971,
+      "step": 57
+    },
+    {
+      "epoch": 2.072289156626506,
+      "grad_norm": 0.4034959375858307,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 0.5110700130462646,
+      "step": 58
+    },
+    {
+      "epoch": 2.108433734939759,
+      "grad_norm": 0.42032384872436523,
+      "learning_rate": 2.683519824400693e-06,
+      "loss": 0.5136343240737915,
+      "step": 59
+    },
+    {
+      "epoch": 2.144578313253012,
+      "grad_norm": 0.417923241853714,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.5048317909240723,
+      "step": 60
+    },
+    {
+      "epoch": 2.180722891566265,
+      "grad_norm": 0.4598260223865509,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.5214716196060181,
+      "step": 61
+    },
+    {
+      "epoch": 2.216867469879518,
+      "grad_norm": 0.41124001145362854,
+      "learning_rate": 2.146432161577842e-06,
+      "loss": 0.5121402740478516,
+      "step": 62
+    },
+    {
+      "epoch": 2.253012048192771,
+      "grad_norm": 0.4205818772315979,
+      "learning_rate": 1.977004425688126e-06,
+      "loss": 0.49233055114746094,
+      "step": 63
+    },
+    {
+      "epoch": 2.289156626506024,
+      "grad_norm": 0.37304773926734924,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 0.5020605325698853,
+      "step": 64
+    },
+    {
+      "epoch": 2.325301204819277,
+      "grad_norm": 0.3686327040195465,
+      "learning_rate": 1.6543469682057105e-06,
+      "loss": 0.5020735263824463,
+      "step": 65
+    },
+    {
+      "epoch": 2.36144578313253,
+      "grad_norm": 0.3757750689983368,
+      "learning_rate": 1.5016832974331725e-06,
+      "loss": 0.5086070895195007,
+      "step": 66
+    },
+    {
+      "epoch": 2.397590361445783,
+      "grad_norm": 0.3529624044895172,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 0.5086838006973267,
+      "step": 67
+    },
+    {
+      "epoch": 2.433734939759036,
+      "grad_norm": 0.35332420468330383,
+      "learning_rate": 1.2150247217412186e-06,
+      "loss": 0.5006733536720276,
+      "step": 68
+    },
+    {
+      "epoch": 2.4698795180722892,
+      "grad_norm": 0.4140400290489197,
+      "learning_rate": 1.0815327133708015e-06,
+      "loss": 0.4901826083660126,
+      "step": 69
+    },
+    {
+      "epoch": 2.5060240963855422,
+      "grad_norm": 0.45728668570518494,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.509224534034729,
+      "step": 70
+    },
+    {
+      "epoch": 2.5421686746987953,
+      "grad_norm": 0.3587833046913147,
+      "learning_rate": 8.353937964495029e-07,
+      "loss": 0.5090753436088562,
+      "step": 71
+    },
+    {
+      "epoch": 2.5783132530120483,
+      "grad_norm": 0.37985914945602417,
+      "learning_rate": 7.23178699197467e-07,
+      "loss": 0.5140612721443176,
+      "step": 72
+    },
+    {
+      "epoch": 2.6144578313253013,
+      "grad_norm": 0.36439454555511475,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 0.47711265087127686,
+      "step": 73
+    },
+    {
+      "epoch": 2.6506024096385543,
+      "grad_norm": 0.3805203437805176,
+      "learning_rate": 5.214411988029355e-07,
+      "loss": 0.49803662300109863,
+      "step": 74
+    },
+    {
+      "epoch": 2.6867469879518073,
+      "grad_norm": 0.3537060618400574,
+      "learning_rate": 4.322727117869951e-07,
+      "loss": 0.5065058469772339,
+      "step": 75
+    },
+    {
+      "epoch": 2.7228915662650603,
+      "grad_norm": 0.388337105512619,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.49857965111732483,
+      "step": 76
+    },
+    {
+      "epoch": 2.7590361445783134,
+      "grad_norm": 0.38901862502098083,
+      "learning_rate": 2.7811814881259503e-07,
+      "loss": 0.5032105445861816,
+      "step": 77
+    },
+    {
+      "epoch": 2.7951807228915664,
+      "grad_norm": 0.3811405599117279,
+      "learning_rate": 2.134025123396638e-07,
+      "loss": 0.48751121759414673,
+      "step": 78
+    },
+    {
+      "epoch": 2.8313253012048194,
+      "grad_norm": 0.358225017786026,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 0.5210248231887817,
+      "step": 79
+    },
+    {
+      "epoch": 2.8674698795180724,
+      "grad_norm": 0.37859153747558594,
+      "learning_rate": 1.0926199633097156e-07,
+      "loss": 0.4980379343032837,
+      "step": 80
+    },
+    {
+      "epoch": 2.9036144578313254,
+      "grad_norm": 0.37158218026161194,
+      "learning_rate": 7.001981464747565e-08,
+      "loss": 0.5095956325531006,
+      "step": 81
+    },
+    {
+      "epoch": 2.9397590361445785,
+      "grad_norm": 0.3750190734863281,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 0.5043609738349915,
+      "step": 82
+    },
+    {
+      "epoch": 2.9759036144578315,
+      "grad_norm": 0.36136147379875183,
+      "learning_rate": 1.753570375247815e-08,
+      "loss": 0.5091077089309692,
+      "step": 83
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.4021438956260681,
+      "learning_rate": 4.385849505708084e-09,
+      "loss": 0.5222575664520264,
+      "step": 84
+    },
+    {
+      "epoch": 3.0,
+      "step": 84,
+      "total_flos": 106024918253568.0,
+      "train_loss": 0.5945852278243928,
+      "train_runtime": 15268.5072,
+      "train_samples_per_second": 0.261,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 84,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 106024918253568.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595eec95620647b32c4b9a6bbdd7896718a00afc1c705f55145205ef47d6d6b6
+size 7953