Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+library_name: transformers
+license: other
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: R2EGym-32B-Agent-Coder-R2egym-mid-post-step1746
+  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. -->
+
+# R2EGym-32B-Agent-Coder-R2egym-mid-post-step1746
+
+This model is a fine-tuned version of the local checkpoint `v2v3_from_sample10_step1746` on the R2EGym_SFT_Trajectories 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: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.7.1+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 606591045337088.0,
+    "train_loss": 0.26673450984872216,
+    "train_runtime": 25532.5977,
+    "train_samples_per_second": 0.253,
+    "train_steps_per_second": 0.032
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.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' }}
+{%- endif %}

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc5fef21fa1c8ea5e7fad2b9f857fac32b53d3165bafc98777e4f39ac9e0467
+size 4876059416

model.safetensors.index.json

@@ -0,0 +1,779 @@
+{
+  "metadata": {
+    "total_parameters": 1119232,
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

trainer_log.jsonl

@@ -0,0 +1,84 @@
+{"current_steps": 10, "total_steps": 1616, "loss": 3.0077, "lr": 5.555555555555555e-07, "epoch": 0.012376237623762377, "percentage": 0.62, "elapsed_time": "0:09:55", "remaining_time": "1 day, 2:34:56"}
+{"current_steps": 20, "total_steps": 1616, "loss": 3.21, "lr": 1.1728395061728396e-06, "epoch": 0.024752475247524754, "percentage": 1.24, "elapsed_time": "0:18:57", "remaining_time": "1 day, 1:13:09"}
+{"current_steps": 30, "total_steps": 1616, "loss": 2.1669, "lr": 1.7901234567901235e-06, "epoch": 0.03712871287128713, "percentage": 1.86, "elapsed_time": "0:27:22", "remaining_time": "1 day, 0:07:11"}
+{"current_steps": 10, "total_steps": 808, "loss": 3.2158, "lr": 1.111111111111111e-06, "epoch": 0.024752475247524754, "percentage": 1.24, "elapsed_time": "0:05:52", "remaining_time": "7:48:37"}
+{"current_steps": 20, "total_steps": 808, "loss": 2.4344, "lr": 2.345679012345679e-06, "epoch": 0.04950495049504951, "percentage": 2.48, "elapsed_time": "0:11:48", "remaining_time": "7:45:09"}
+{"current_steps": 30, "total_steps": 808, "loss": 1.1085, "lr": 3.580246913580247e-06, "epoch": 0.07425742574257425, "percentage": 3.71, "elapsed_time": "0:16:21", "remaining_time": "7:04:23"}
+{"current_steps": 40, "total_steps": 808, "loss": 1.0109, "lr": 4.814814814814815e-06, "epoch": 0.09900990099009901, "percentage": 4.95, "elapsed_time": "0:22:09", "remaining_time": "7:05:21"}
+{"current_steps": 50, "total_steps": 808, "loss": 0.4737, "lr": 6.049382716049383e-06, "epoch": 0.12376237623762376, "percentage": 6.19, "elapsed_time": "0:26:49", "remaining_time": "6:46:41"}
+{"current_steps": 60, "total_steps": 808, "loss": 0.4355, "lr": 7.283950617283952e-06, "epoch": 0.1485148514851485, "percentage": 7.43, "elapsed_time": "0:32:15", "remaining_time": "6:42:11"}
+{"current_steps": 70, "total_steps": 808, "loss": 0.3468, "lr": 8.518518518518519e-06, "epoch": 0.17326732673267325, "percentage": 8.66, "elapsed_time": "0:37:39", "remaining_time": "6:37:03"}
+{"current_steps": 80, "total_steps": 808, "loss": 0.2905, "lr": 9.753086419753087e-06, "epoch": 0.19801980198019803, "percentage": 9.9, "elapsed_time": "0:42:18", "remaining_time": "6:25:01"}
+{"current_steps": 90, "total_steps": 808, "loss": 0.2852, "lr": 9.997012501794273e-06, "epoch": 0.22277227722772278, "percentage": 11.14, "elapsed_time": "0:47:46", "remaining_time": "6:21:04"}
+{"current_steps": 100, "total_steps": 808, "loss": 0.2626, "lr": 9.984881908680157e-06, "epoch": 0.24752475247524752, "percentage": 12.38, "elapsed_time": "0:52:35", "remaining_time": "6:12:24"}
+{"current_steps": 110, "total_steps": 808, "loss": 0.2696, "lr": 9.963444133394478e-06, "epoch": 0.2722772277227723, "percentage": 13.61, "elapsed_time": "0:58:00", "remaining_time": "6:08:02"}
+{"current_steps": 120, "total_steps": 808, "loss": 0.254, "lr": 9.93273920201681e-06, "epoch": 0.297029702970297, "percentage": 14.85, "elapsed_time": "1:03:54", "remaining_time": "6:06:21"}
+{"current_steps": 130, "total_steps": 808, "loss": 0.2412, "lr": 9.892824443164987e-06, "epoch": 0.3217821782178218, "percentage": 16.09, "elapsed_time": "1:08:37", "remaining_time": "5:57:52"}
+{"current_steps": 140, "total_steps": 808, "loss": 0.2374, "lr": 9.84377438095789e-06, "epoch": 0.3465346534653465, "percentage": 17.33, "elapsed_time": "1:14:05", "remaining_time": "5:53:31"}
+{"current_steps": 150, "total_steps": 808, "loss": 0.2236, "lr": 9.785680595872824e-06, "epoch": 0.3712871287128713, "percentage": 18.56, "elapsed_time": "1:18:27", "remaining_time": "5:44:11"}
+{"current_steps": 160, "total_steps": 808, "loss": 0.2294, "lr": 9.718651553757266e-06, "epoch": 0.39603960396039606, "percentage": 19.8, "elapsed_time": "1:23:58", "remaining_time": "5:40:07"}
+{"current_steps": 170, "total_steps": 808, "loss": 0.2266, "lr": 9.642812403314272e-06, "epoch": 0.4207920792079208, "percentage": 21.04, "elapsed_time": "1:29:35", "remaining_time": "5:36:14"}
+{"current_steps": 180, "total_steps": 808, "loss": 0.2266, "lr": 9.55830474243961e-06, "epoch": 0.44554455445544555, "percentage": 22.28, "elapsed_time": "1:33:48", "remaining_time": "5:27:17"}
+{"current_steps": 190, "total_steps": 808, "loss": 0.2192, "lr": 9.465286353846905e-06, "epoch": 0.47029702970297027, "percentage": 23.51, "elapsed_time": "1:39:14", "remaining_time": "5:22:49"}
+{"current_steps": 200, "total_steps": 808, "loss": 0.2212, "lr": 9.36393091047441e-06, "epoch": 0.49504950495049505, "percentage": 24.75, "elapsed_time": "1:44:07", "remaining_time": "5:16:32"}
+{"current_steps": 210, "total_steps": 808, "loss": 0.2194, "lr": 9.254427651223434e-06, "epoch": 0.5198019801980198, "percentage": 25.99, "elapsed_time": "1:49:48", "remaining_time": "5:12:41"}
+{"current_steps": 220, "total_steps": 808, "loss": 0.2207, "lr": 9.136981027633834e-06, "epoch": 0.5445544554455446, "percentage": 27.23, "elapsed_time": "1:55:22", "remaining_time": "5:08:20"}
+{"current_steps": 230, "total_steps": 808, "loss": 0.217, "lr": 9.011810322156269e-06, "epoch": 0.5693069306930693, "percentage": 28.47, "elapsed_time": "1:59:49", "remaining_time": "5:01:08"}
+{"current_steps": 240, "total_steps": 808, "loss": 0.2142, "lr": 8.879149238733932e-06, "epoch": 0.594059405940594, "percentage": 29.7, "elapsed_time": "2:05:03", "remaining_time": "4:55:58"}
+{"current_steps": 250, "total_steps": 808, "loss": 0.2009, "lr": 8.739245466458187e-06, "epoch": 0.6188118811881188, "percentage": 30.94, "elapsed_time": "2:09:46", "remaining_time": "4:49:40"}
+{"current_steps": 260, "total_steps": 808, "loss": 0.2276, "lr": 8.592360217112759e-06, "epoch": 0.6435643564356436, "percentage": 32.18, "elapsed_time": "2:15:01", "remaining_time": "4:44:36"}
+{"current_steps": 270, "total_steps": 808, "loss": 0.2122, "lr": 8.438767737469995e-06, "epoch": 0.6683168316831684, "percentage": 33.42, "elapsed_time": "2:20:50", "remaining_time": "4:40:38"}
+{"current_steps": 280, "total_steps": 808, "loss": 0.2032, "lr": 8.278754797249702e-06, "epoch": 0.693069306930693, "percentage": 34.65, "elapsed_time": "2:25:33", "remaining_time": "4:34:28"}
+{"current_steps": 290, "total_steps": 808, "loss": 0.2195, "lr": 8.11262015369663e-06, "epoch": 0.7178217821782178, "percentage": 35.89, "elapsed_time": "2:30:43", "remaining_time": "4:29:13"}
+{"current_steps": 300, "total_steps": 808, "loss": 0.21, "lr": 7.940673993776258e-06, "epoch": 0.7425742574257426, "percentage": 37.13, "elapsed_time": "2:35:22", "remaining_time": "4:23:06"}
+{"current_steps": 310, "total_steps": 808, "loss": 0.2142, "lr": 7.763237355030384e-06, "epoch": 0.7673267326732673, "percentage": 38.37, "elapsed_time": "2:40:55", "remaining_time": "4:18:31"}
+{"current_steps": 320, "total_steps": 808, "loss": 0.2167, "lr": 7.580641526173758e-06, "epoch": 0.7920792079207921, "percentage": 39.6, "elapsed_time": "2:46:43", "remaining_time": "4:14:15"}
+{"current_steps": 330, "total_steps": 808, "loss": 0.1964, "lr": 7.39322742855097e-06, "epoch": 0.8168316831683168, "percentage": 40.84, "elapsed_time": "2:51:17", "remaining_time": "4:08:06"}
+{"current_steps": 340, "total_steps": 808, "loss": 0.2146, "lr": 7.201344979608423e-06, "epoch": 0.8415841584158416, "percentage": 42.08, "elapsed_time": "2:56:56", "remaining_time": "4:03:33"}
+{"current_steps": 350, "total_steps": 808, "loss": 0.2037, "lr": 7.0053524395698345e-06, "epoch": 0.8663366336633663, "percentage": 43.32, "elapsed_time": "3:01:44", "remaining_time": "3:57:49"}
+{"current_steps": 360, "total_steps": 808, "loss": 0.2063, "lr": 6.805615742535117e-06, "epoch": 0.8910891089108911, "percentage": 44.55, "elapsed_time": "3:07:27", "remaining_time": "3:53:16"}
+{"current_steps": 370, "total_steps": 808, "loss": 0.2133, "lr": 6.602507813251478e-06, "epoch": 0.9158415841584159, "percentage": 45.79, "elapsed_time": "3:13:21", "remaining_time": "3:48:54"}
+{"current_steps": 380, "total_steps": 808, "loss": 0.1935, "lr": 6.396407870832419e-06, "epoch": 0.9405940594059405, "percentage": 47.03, "elapsed_time": "3:18:06", "remaining_time": "3:43:08"}
+{"current_steps": 390, "total_steps": 808, "loss": 0.19, "lr": 6.187700720724648e-06, "epoch": 0.9653465346534653, "percentage": 48.27, "elapsed_time": "3:23:13", "remaining_time": "3:37:48"}
+{"current_steps": 400, "total_steps": 808, "loss": 0.1969, "lr": 5.976776036244833e-06, "epoch": 0.9900990099009901, "percentage": 49.5, "elapsed_time": "3:27:36", "remaining_time": "3:31:45"}
+{"current_steps": 410, "total_steps": 808, "loss": 0.16, "lr": 5.764027631027659e-06, "epoch": 1.0148514851485149, "percentage": 50.74, "elapsed_time": "3:33:16", "remaining_time": "3:27:02"}
+{"current_steps": 420, "total_steps": 808, "loss": 0.1317, "lr": 5.549852723743564e-06, "epoch": 1.0396039603960396, "percentage": 51.98, "elapsed_time": "3:38:53", "remaining_time": "3:22:12"}
+{"current_steps": 430, "total_steps": 808, "loss": 0.1326, "lr": 5.334651196459003e-06, "epoch": 1.0643564356435644, "percentage": 53.22, "elapsed_time": "3:43:58", "remaining_time": "3:16:53"}
+{"current_steps": 440, "total_steps": 808, "loss": 0.1282, "lr": 5.118824848023926e-06, "epoch": 1.0891089108910892, "percentage": 54.46, "elapsed_time": "3:48:35", "remaining_time": "3:11:10"}
+{"current_steps": 450, "total_steps": 808, "loss": 0.1298, "lr": 4.902776643880461e-06, "epoch": 1.113861386138614, "percentage": 55.69, "elapsed_time": "3:54:23", "remaining_time": "3:06:28"}
+{"current_steps": 460, "total_steps": 808, "loss": 0.1324, "lr": 4.686909963693498e-06, "epoch": 1.1386138613861387, "percentage": 56.93, "elapsed_time": "3:58:49", "remaining_time": "3:00:40"}
+{"current_steps": 470, "total_steps": 808, "loss": 0.1318, "lr": 4.47162784820784e-06, "epoch": 1.1633663366336633, "percentage": 58.17, "elapsed_time": "4:04:30", "remaining_time": "2:55:50"}
+{"current_steps": 480, "total_steps": 808, "loss": 0.1267, "lr": 4.257332246738201e-06, "epoch": 1.188118811881188, "percentage": 59.41, "elapsed_time": "4:10:15", "remaining_time": "2:51:00"}
+{"current_steps": 490, "total_steps": 808, "loss": 0.1286, "lr": 4.04442326669695e-06, "epoch": 1.2128712871287128, "percentage": 60.64, "elapsed_time": "4:15:23", "remaining_time": "2:45:44"}
+{"current_steps": 500, "total_steps": 808, "loss": 0.135, "lr": 3.833298426560851e-06, "epoch": 1.2376237623762376, "percentage": 61.88, "elapsed_time": "4:21:05", "remaining_time": "2:40:50"}
+{"current_steps": 510, "total_steps": 808, "loss": 0.1219, "lr": 3.624351913671571e-06, "epoch": 1.2623762376237624, "percentage": 63.12, "elapsed_time": "4:25:23", "remaining_time": "2:35:04"}
+{"current_steps": 520, "total_steps": 808, "loss": 0.1401, "lr": 3.4179738482556648e-06, "epoch": 1.2871287128712872, "percentage": 64.36, "elapsed_time": "4:31:13", "remaining_time": "2:30:13"}
+{"current_steps": 530, "total_steps": 808, "loss": 0.1311, "lr": 3.214549555038218e-06, "epoch": 1.311881188118812, "percentage": 65.59, "elapsed_time": "4:36:21", "remaining_time": "2:24:57"}
+{"current_steps": 540, "total_steps": 808, "loss": 0.1254, "lr": 3.0144588438100693e-06, "epoch": 1.3366336633663367, "percentage": 66.83, "elapsed_time": "4:40:56", "remaining_time": "2:19:25"}
+{"current_steps": 550, "total_steps": 808, "loss": 0.1332, "lr": 2.8180753002918735e-06, "epoch": 1.3613861386138613, "percentage": 68.07, "elapsed_time": "4:46:47", "remaining_time": "2:14:31"}
+{"current_steps": 560, "total_steps": 808, "loss": 0.1211, "lr": 2.6257655886190147e-06, "epoch": 1.386138613861386, "percentage": 69.31, "elapsed_time": "4:50:54", "remaining_time": "2:08:49"}
+{"current_steps": 570, "total_steps": 808, "loss": 0.1368, "lr": 2.4378887667496696e-06, "epoch": 1.4108910891089108, "percentage": 70.54, "elapsed_time": "4:56:42", "remaining_time": "2:03:53"}
+{"current_steps": 580, "total_steps": 808, "loss": 0.1267, "lr": 2.2547956160742473e-06, "epoch": 1.4356435643564356, "percentage": 71.78, "elapsed_time": "5:01:47", "remaining_time": "1:58:38"}
+{"current_steps": 590, "total_steps": 808, "loss": 0.1206, "lr": 2.0768279864778475e-06, "epoch": 1.4603960396039604, "percentage": 73.02, "elapsed_time": "5:06:47", "remaining_time": "1:53:21"}
+{"current_steps": 600, "total_steps": 808, "loss": 0.1383, "lr": 1.9043181580785597e-06, "epoch": 1.4851485148514851, "percentage": 74.26, "elapsed_time": "5:12:09", "remaining_time": "1:48:13"}
+{"current_steps": 610, "total_steps": 808, "loss": 0.1122, "lr": 1.73758822083332e-06, "epoch": 1.50990099009901, "percentage": 75.5, "elapsed_time": "5:16:25", "remaining_time": "1:42:42"}
+{"current_steps": 620, "total_steps": 808, "loss": 0.1296, "lr": 1.5769494731696206e-06, "epoch": 1.5346534653465347, "percentage": 76.73, "elapsed_time": "5:22:19", "remaining_time": "1:37:44"}
+{"current_steps": 630, "total_steps": 808, "loss": 0.1264, "lr": 1.4227018407658822e-06, "epoch": 1.5594059405940595, "percentage": 77.97, "elapsed_time": "5:27:31", "remaining_time": "1:32:32"}
+{"current_steps": 640, "total_steps": 808, "loss": 0.1229, "lr": 1.275133316565691e-06, "epoch": 1.5841584158415842, "percentage": 79.21, "elapsed_time": "5:32:23", "remaining_time": "1:27:15"}
+{"current_steps": 650, "total_steps": 808, "loss": 0.1248, "lr": 1.1345194230714235e-06, "epoch": 1.608910891089109, "percentage": 80.45, "elapsed_time": "5:38:13", "remaining_time": "1:22:12"}
+{"current_steps": 660, "total_steps": 808, "loss": 0.1141, "lr": 1.001122697921197e-06, "epoch": 1.6336633663366338, "percentage": 81.68, "elapsed_time": "5:42:42", "remaining_time": "1:16:50"}
+{"current_steps": 670, "total_steps": 808, "loss": 0.131, "lr": 8.751922037096328e-07, "epoch": 1.6584158415841586, "percentage": 82.92, "elapsed_time": "5:48:22", "remaining_time": "1:11:45"}
+{"current_steps": 680, "total_steps": 808, "loss": 0.1229, "lr": 7.569630629676294e-07, "epoch": 1.6831683168316833, "percentage": 84.16, "elapsed_time": "5:53:38", "remaining_time": "1:06:34"}
+{"current_steps": 690, "total_steps": 808, "loss": 0.1208, "lr": 6.466560191693566e-07, "epoch": 1.7079207920792079, "percentage": 85.4, "elapsed_time": "5:58:25", "remaining_time": "1:01:17"}
+{"current_steps": 700, "total_steps": 808, "loss": 0.1305, "lr": 5.444770245861553e-07, "epoch": 1.7326732673267327, "percentage": 86.63, "elapsed_time": "6:03:52", "remaining_time": "0:56:08"}
+{"current_steps": 710, "total_steps": 808, "loss": 0.1161, "lr": 4.506168557567886e-07, "epoch": 1.7574257425742574, "percentage": 87.87, "elapsed_time": "6:07:48", "remaining_time": "0:50:46"}
+{"current_steps": 720, "total_steps": 808, "loss": 0.1221, "lr": 3.6525075729205274e-07, "epoch": 1.7821782178217822, "percentage": 89.11, "elapsed_time": "6:13:29", "remaining_time": "0:45:38"}
+{"current_steps": 730, "total_steps": 808, "loss": 0.1203, "lr": 2.8853811467875413e-07, "epoch": 1.806930693069307, "percentage": 90.35, "elapsed_time": "6:18:58", "remaining_time": "0:40:29"}
+{"current_steps": 740, "total_steps": 808, "loss": 0.1191, "lr": 2.2062215669397201e-07, "epoch": 1.8316831683168315, "percentage": 91.58, "elapsed_time": "6:23:56", "remaining_time": "0:35:16"}
+{"current_steps": 750, "total_steps": 808, "loss": 0.1279, "lr": 1.616296879852175e-07, "epoch": 1.8564356435643563, "percentage": 92.82, "elapsed_time": "6:29:47", "remaining_time": "0:30:08"}
+{"current_steps": 760, "total_steps": 808, "loss": 0.1146, "lr": 1.1167085231579111e-07, "epoch": 1.881188118811881, "percentage": 94.06, "elapsed_time": "6:34:01", "remaining_time": "0:24:53"}
+{"current_steps": 770, "total_steps": 808, "loss": 0.1196, "lr": 7.083892691736428e-08, "epoch": 1.9059405940594059, "percentage": 95.3, "elapsed_time": "6:39:42", "remaining_time": "0:19:43"}
+{"current_steps": 780, "total_steps": 808, "loss": 0.1217, "lr": 3.9210148333763135e-08, "epoch": 1.9306930693069306, "percentage": 96.53, "elapsed_time": "6:45:15", "remaining_time": "0:14:32"}
+{"current_steps": 790, "total_steps": 808, "loss": 0.1153, "lr": 1.684357008110593e-08, "epoch": 1.9554455445544554, "percentage": 97.77, "elapsed_time": "6:50:02", "remaining_time": "0:09:20"}
+{"current_steps": 800, "total_steps": 808, "loss": 0.1268, "lr": 3.780952390058379e-09, "epoch": 1.9801980198019802, "percentage": 99.01, "elapsed_time": "6:55:52", "remaining_time": "0:04:09"}
+{"current_steps": 808, "total_steps": 808, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "7:05:32", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,603 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 808,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024752475247524754,
+      "grad_norm": 38.749080099489724,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 3.2158,
+      "step": 10
+    },
+    {
+      "epoch": 0.04950495049504951,
+      "grad_norm": 39.64900559019991,
+      "learning_rate": 2.345679012345679e-06,
+      "loss": 2.4344,
+      "step": 20
+    },
+    {
+      "epoch": 0.07425742574257425,
+      "grad_norm": 2.416463732570817,
+      "learning_rate": 3.580246913580247e-06,
+      "loss": 1.1085,
+      "step": 30
+    },
+    {
+      "epoch": 0.09900990099009901,
+      "grad_norm": 4.162559676174374,
+      "learning_rate": 4.814814814814815e-06,
+      "loss": 1.0109,
+      "step": 40
+    },
+    {
+      "epoch": 0.12376237623762376,
+      "grad_norm": 1.4037017225614896,
+      "learning_rate": 6.049382716049383e-06,
+      "loss": 0.4737,
+      "step": 50
+    },
+    {
+      "epoch": 0.1485148514851485,
+      "grad_norm": 1.6166445320035476,
+      "learning_rate": 7.283950617283952e-06,
+      "loss": 0.4355,
+      "step": 60
+    },
+    {
+      "epoch": 0.17326732673267325,
+      "grad_norm": 1.141640311828574,
+      "learning_rate": 8.518518518518519e-06,
+      "loss": 0.3468,
+      "step": 70
+    },
+    {
+      "epoch": 0.19801980198019803,
+      "grad_norm": 1.197800510887127,
+      "learning_rate": 9.753086419753087e-06,
+      "loss": 0.2905,
+      "step": 80
+    },
+    {
+      "epoch": 0.22277227722772278,
+      "grad_norm": 1.0980962734091972,
+      "learning_rate": 9.997012501794273e-06,
+      "loss": 0.2852,
+      "step": 90
+    },
+    {
+      "epoch": 0.24752475247524752,
+      "grad_norm": 0.8706925934126661,
+      "learning_rate": 9.984881908680157e-06,
+      "loss": 0.2626,
+      "step": 100
+    },
+    {
+      "epoch": 0.2722772277227723,
+      "grad_norm": 0.9744111977727423,
+      "learning_rate": 9.963444133394478e-06,
+      "loss": 0.2696,
+      "step": 110
+    },
+    {
+      "epoch": 0.297029702970297,
+      "grad_norm": 2.203688809185736,
+      "learning_rate": 9.93273920201681e-06,
+      "loss": 0.254,
+      "step": 120
+    },
+    {
+      "epoch": 0.3217821782178218,
+      "grad_norm": 0.6909534190939396,
+      "learning_rate": 9.892824443164987e-06,
+      "loss": 0.2412,
+      "step": 130
+    },
+    {
+      "epoch": 0.3465346534653465,
+      "grad_norm": 0.9726066930137242,
+      "learning_rate": 9.84377438095789e-06,
+      "loss": 0.2374,
+      "step": 140
+    },
+    {
+      "epoch": 0.3712871287128713,
+      "grad_norm": 0.9033174763116004,
+      "learning_rate": 9.785680595872824e-06,
+      "loss": 0.2236,
+      "step": 150
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 0.9978308920092659,
+      "learning_rate": 9.718651553757266e-06,
+      "loss": 0.2294,
+      "step": 160
+    },
+    {
+      "epoch": 0.4207920792079208,
+      "grad_norm": 4.058405361629531,
+      "learning_rate": 9.642812403314272e-06,
+      "loss": 0.2266,
+      "step": 170
+    },
+    {
+      "epoch": 0.44554455445544555,
+      "grad_norm": 1.3629688635899981,
+      "learning_rate": 9.55830474243961e-06,
+      "loss": 0.2266,
+      "step": 180
+    },
+    {
+      "epoch": 0.47029702970297027,
+      "grad_norm": 1.2375201071505648,
+      "learning_rate": 9.465286353846905e-06,
+      "loss": 0.2192,
+      "step": 190
+    },
+    {
+      "epoch": 0.49504950495049505,
+      "grad_norm": 0.7234385452967922,
+      "learning_rate": 9.36393091047441e-06,
+      "loss": 0.2212,
+      "step": 200
+    },
+    {
+      "epoch": 0.5198019801980198,
+      "grad_norm": 0.7326619260019385,
+      "learning_rate": 9.254427651223434e-06,
+      "loss": 0.2194,
+      "step": 210
+    },
+    {
+      "epoch": 0.5445544554455446,
+      "grad_norm": 1.160310177931889,
+      "learning_rate": 9.136981027633834e-06,
+      "loss": 0.2207,
+      "step": 220
+    },
+    {
+      "epoch": 0.5693069306930693,
+      "grad_norm": 0.8422477849196854,
+      "learning_rate": 9.011810322156269e-06,
+      "loss": 0.217,
+      "step": 230
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 1.5735296786321598,
+      "learning_rate": 8.879149238733932e-06,
+      "loss": 0.2142,
+      "step": 240
+    },
+    {
+      "epoch": 0.6188118811881188,
+      "grad_norm": 1.05917908340436,
+      "learning_rate": 8.739245466458187e-06,
+      "loss": 0.2009,
+      "step": 250
+    },
+    {
+      "epoch": 0.6435643564356436,
+      "grad_norm": 0.8374503267424538,
+      "learning_rate": 8.592360217112759e-06,
+      "loss": 0.2276,
+      "step": 260
+    },
+    {
+      "epoch": 0.6683168316831684,
+      "grad_norm": 3.9597090992745034,
+      "learning_rate": 8.438767737469995e-06,
+      "loss": 0.2122,
+      "step": 270
+    },
+    {
+      "epoch": 0.693069306930693,
+      "grad_norm": 0.7976525324791283,
+      "learning_rate": 8.278754797249702e-06,
+      "loss": 0.2032,
+      "step": 280
+    },
+    {
+      "epoch": 0.7178217821782178,
+      "grad_norm": 0.7744706010278902,
+      "learning_rate": 8.11262015369663e-06,
+      "loss": 0.2195,
+      "step": 290
+    },
+    {
+      "epoch": 0.7425742574257426,
+      "grad_norm": 0.8161719072903669,
+      "learning_rate": 7.940673993776258e-06,
+      "loss": 0.21,
+      "step": 300
+    },
+    {
+      "epoch": 0.7673267326732673,
+      "grad_norm": 1.0715150167394496,
+      "learning_rate": 7.763237355030384e-06,
+      "loss": 0.2142,
+      "step": 310
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 2.803631363059706,
+      "learning_rate": 7.580641526173758e-06,
+      "loss": 0.2167,
+      "step": 320
+    },
+    {
+      "epoch": 0.8168316831683168,
+      "grad_norm": 1.6402074825817914,
+      "learning_rate": 7.39322742855097e-06,
+      "loss": 0.1964,
+      "step": 330
+    },
+    {
+      "epoch": 0.8415841584158416,
+      "grad_norm": 2.7431663603349308,
+      "learning_rate": 7.201344979608423e-06,
+      "loss": 0.2146,
+      "step": 340
+    },
+    {
+      "epoch": 0.8663366336633663,
+      "grad_norm": 0.6620649226382208,
+      "learning_rate": 7.0053524395698345e-06,
+      "loss": 0.2037,
+      "step": 350
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 1.0418484850219463,
+      "learning_rate": 6.805615742535117e-06,
+      "loss": 0.2063,
+      "step": 360
+    },
+    {
+      "epoch": 0.9158415841584159,
+      "grad_norm": 1.0624343454733385,
+      "learning_rate": 6.602507813251478e-06,
+      "loss": 0.2133,
+      "step": 370
+    },
+    {
+      "epoch": 0.9405940594059405,
+      "grad_norm": 0.8571908786810298,
+      "learning_rate": 6.396407870832419e-06,
+      "loss": 0.1935,
+      "step": 380
+    },
+    {
+      "epoch": 0.9653465346534653,
+      "grad_norm": 1.1625392933521244,
+      "learning_rate": 6.187700720724648e-06,
+      "loss": 0.19,
+      "step": 390
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 0.7676371278259425,
+      "learning_rate": 5.976776036244833e-06,
+      "loss": 0.1969,
+      "step": 400
+    },
+    {
+      "epoch": 1.0148514851485149,
+      "grad_norm": 0.5723958610359834,
+      "learning_rate": 5.764027631027659e-06,
+      "loss": 0.16,
+      "step": 410
+    },
+    {
+      "epoch": 1.0396039603960396,
+      "grad_norm": 0.6439856648791892,
+      "learning_rate": 5.549852723743564e-06,
+      "loss": 0.1317,
+      "step": 420
+    },
+    {
+      "epoch": 1.0643564356435644,
+      "grad_norm": 0.8430846385011965,
+      "learning_rate": 5.334651196459003e-06,
+      "loss": 0.1326,
+      "step": 430
+    },
+    {
+      "epoch": 1.0891089108910892,
+      "grad_norm": 0.7075121256426331,
+      "learning_rate": 5.118824848023926e-06,
+      "loss": 0.1282,
+      "step": 440
+    },
+    {
+      "epoch": 1.113861386138614,
+      "grad_norm": 0.7098250623843386,
+      "learning_rate": 4.902776643880461e-06,
+      "loss": 0.1298,
+      "step": 450
+    },
+    {
+      "epoch": 1.1386138613861387,
+      "grad_norm": 0.5746472756447318,
+      "learning_rate": 4.686909963693498e-06,
+      "loss": 0.1324,
+      "step": 460
+    },
+    {
+      "epoch": 1.1633663366336633,
+      "grad_norm": 0.752011250724735,
+      "learning_rate": 4.47162784820784e-06,
+      "loss": 0.1318,
+      "step": 470
+    },
+    {
+      "epoch": 1.188118811881188,
+      "grad_norm": 0.7690625261604315,
+      "learning_rate": 4.257332246738201e-06,
+      "loss": 0.1267,
+      "step": 480
+    },
+    {
+      "epoch": 1.2128712871287128,
+      "grad_norm": 0.7370929567026177,
+      "learning_rate": 4.04442326669695e-06,
+      "loss": 0.1286,
+      "step": 490
+    },
+    {
+      "epoch": 1.2376237623762376,
+      "grad_norm": 2.60432798001788,
+      "learning_rate": 3.833298426560851e-06,
+      "loss": 0.135,
+      "step": 500
+    },
+    {
+      "epoch": 1.2623762376237624,
+      "grad_norm": 0.5943041120513542,
+      "learning_rate": 3.624351913671571e-06,
+      "loss": 0.1219,
+      "step": 510
+    },
+    {
+      "epoch": 1.2871287128712872,
+      "grad_norm": 0.838743852289041,
+      "learning_rate": 3.4179738482556648e-06,
+      "loss": 0.1401,
+      "step": 520
+    },
+    {
+      "epoch": 1.311881188118812,
+      "grad_norm": 0.9067824903652668,
+      "learning_rate": 3.214549555038218e-06,
+      "loss": 0.1311,
+      "step": 530
+    },
+    {
+      "epoch": 1.3366336633663367,
+      "grad_norm": 0.6227118274844176,
+      "learning_rate": 3.0144588438100693e-06,
+      "loss": 0.1254,
+      "step": 540
+    },
+    {
+      "epoch": 1.3613861386138613,
+      "grad_norm": 0.7977679577819297,
+      "learning_rate": 2.8180753002918735e-06,
+      "loss": 0.1332,
+      "step": 550
+    },
+    {
+      "epoch": 1.386138613861386,
+      "grad_norm": 0.6196310809476595,
+      "learning_rate": 2.6257655886190147e-06,
+      "loss": 0.1211,
+      "step": 560
+    },
+    {
+      "epoch": 1.4108910891089108,
+      "grad_norm": 0.6084298472807999,
+      "learning_rate": 2.4378887667496696e-06,
+      "loss": 0.1368,
+      "step": 570
+    },
+    {
+      "epoch": 1.4356435643564356,
+      "grad_norm": 1.4399382283539155,
+      "learning_rate": 2.2547956160742473e-06,
+      "loss": 0.1267,
+      "step": 580
+    },
+    {
+      "epoch": 1.4603960396039604,
+      "grad_norm": 0.7985993051553937,
+      "learning_rate": 2.0768279864778475e-06,
+      "loss": 0.1206,
+      "step": 590
+    },
+    {
+      "epoch": 1.4851485148514851,
+      "grad_norm": 0.7931208510059602,
+      "learning_rate": 1.9043181580785597e-06,
+      "loss": 0.1383,
+      "step": 600
+    },
+    {
+      "epoch": 1.50990099009901,
+      "grad_norm": 0.512755394763236,
+      "learning_rate": 1.73758822083332e-06,
+      "loss": 0.1122,
+      "step": 610
+    },
+    {
+      "epoch": 1.5346534653465347,
+      "grad_norm": 0.6491078299788842,
+      "learning_rate": 1.5769494731696206e-06,
+      "loss": 0.1296,
+      "step": 620
+    },
+    {
+      "epoch": 1.5594059405940595,
+      "grad_norm": 0.7130269697667891,
+      "learning_rate": 1.4227018407658822e-06,
+      "loss": 0.1264,
+      "step": 630
+    },
+    {
+      "epoch": 1.5841584158415842,
+      "grad_norm": 0.5915982928372153,
+      "learning_rate": 1.275133316565691e-06,
+      "loss": 0.1229,
+      "step": 640
+    },
+    {
+      "epoch": 1.608910891089109,
+      "grad_norm": 2.214393925964167,
+      "learning_rate": 1.1345194230714235e-06,
+      "loss": 0.1248,
+      "step": 650
+    },
+    {
+      "epoch": 1.6336633663366338,
+      "grad_norm": 0.7240627506654617,
+      "learning_rate": 1.001122697921197e-06,
+      "loss": 0.1141,
+      "step": 660
+    },
+    {
+      "epoch": 1.6584158415841586,
+      "grad_norm": 0.5350731786159315,
+      "learning_rate": 8.751922037096328e-07,
+      "loss": 0.131,
+      "step": 670
+    },
+    {
+      "epoch": 1.6831683168316833,
+      "grad_norm": 0.7015404378394352,
+      "learning_rate": 7.569630629676294e-07,
+      "loss": 0.1229,
+      "step": 680
+    },
+    {
+      "epoch": 1.7079207920792079,
+      "grad_norm": 0.5929124037254383,
+      "learning_rate": 6.466560191693566e-07,
+      "loss": 0.1208,
+      "step": 690
+    },
+    {
+      "epoch": 1.7326732673267327,
+      "grad_norm": 0.7861365186727924,
+      "learning_rate": 5.444770245861553e-07,
+      "loss": 0.1305,
+      "step": 700
+    },
+    {
+      "epoch": 1.7574257425742574,
+      "grad_norm": 0.6518766942066165,
+      "learning_rate": 4.506168557567886e-07,
+      "loss": 0.1161,
+      "step": 710
+    },
+    {
+      "epoch": 1.7821782178217822,
+      "grad_norm": 0.683101648152514,
+      "learning_rate": 3.6525075729205274e-07,
+      "loss": 0.1221,
+      "step": 720
+    },
+    {
+      "epoch": 1.806930693069307,
+      "grad_norm": 0.6879134500414074,
+      "learning_rate": 2.8853811467875413e-07,
+      "loss": 0.1203,
+      "step": 730
+    },
+    {
+      "epoch": 1.8316831683168315,
+      "grad_norm": 1.8254784501234913,
+      "learning_rate": 2.2062215669397201e-07,
+      "loss": 0.1191,
+      "step": 740
+    },
+    {
+      "epoch": 1.8564356435643563,
+      "grad_norm": 1.0911513255316725,
+      "learning_rate": 1.616296879852175e-07,
+      "loss": 0.1279,
+      "step": 750
+    },
+    {
+      "epoch": 1.881188118811881,
+      "grad_norm": 0.7511673072617823,
+      "learning_rate": 1.1167085231579111e-07,
+      "loss": 0.1146,
+      "step": 760
+    },
+    {
+      "epoch": 1.9059405940594059,
+      "grad_norm": 0.6796776730908214,
+      "learning_rate": 7.083892691736428e-08,
+      "loss": 0.1196,
+      "step": 770
+    },
+    {
+      "epoch": 1.9306930693069306,
+      "grad_norm": 0.6872639303078989,
+      "learning_rate": 3.9210148333763135e-08,
+      "loss": 0.1217,
+      "step": 780
+    },
+    {
+      "epoch": 1.9554455445544554,
+      "grad_norm": 0.582235081912157,
+      "learning_rate": 1.684357008110593e-08,
+      "loss": 0.1153,
+      "step": 790
+    },
+    {
+      "epoch": 1.9801980198019802,
+      "grad_norm": 0.7623957535259693,
+      "learning_rate": 3.780952390058379e-09,
+      "loss": 0.1268,
+      "step": 800
+    },
+    {
+      "epoch": 2.0,
+      "step": 808,
+      "total_flos": 606591045337088.0,
+      "train_loss": 0.26673450984872216,
+      "train_runtime": 25532.5977,
+      "train_samples_per_second": 0.253,
+      "train_steps_per_second": 0.032
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 808,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 606591045337088.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}