Upload folder using huggingface_hub

.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 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B) on the train_multi_rag_3_python2cpp_full 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.56.0
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.0

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.635906903930726e+19,
+    "train_loss": 0.07772063925954106,
+    "train_runtime": 22087.4933,
+    "train_samples_per_second": 11.286,
+    "train_steps_per_second": 0.044
+}

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 %}

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "eos_token_id": [
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.56.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd963a40d1ec88cb7cc87d82ee20ffc0f5805cf8c9e3bee5606e5336640df8d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc4f9928e96bf3195cd836042d0bd89d81af6e9ce06983b012e9a7bdb093500
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c109eed792431c8149da1c944607f94701b8f25989cb1979b024f76a0baa8e6
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c90b90aa8f1d3b9dfe2eb8f30f5a8b91fc484527e92e6cc094997c4d2f821d
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 7615616512,
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.635906903930726e+19,
+    "train_loss": 0.07772063925954106,
+    "train_runtime": 22087.4933,
+    "train_samples_per_second": 11.286,
+    "train_steps_per_second": 0.044
+}

trainer_log.jsonl

@@ -0,0 +1,98 @@
+{"current_steps": 10, "total_steps": 974, "loss": 0.1517, "lr": 9.99789342773948e-06, "epoch": 0.02053915275994865, "percentage": 1.03, "elapsed_time": "0:03:47", "remaining_time": "6:05:24"}
+{"current_steps": 20, "total_steps": 974, "loss": 0.1347, "lr": 9.99061372843304e-06, "epoch": 0.0410783055198973, "percentage": 2.05, "elapsed_time": "0:07:34", "remaining_time": "6:01:18"}
+{"current_steps": 30, "total_steps": 974, "loss": 0.12, "lr": 9.978142466031648e-06, "epoch": 0.06161745827984596, "percentage": 3.08, "elapsed_time": "0:11:22", "remaining_time": "5:57:51"}
+{"current_steps": 40, "total_steps": 974, "loss": 0.1187, "lr": 9.960492613958845e-06, "epoch": 0.0821566110397946, "percentage": 4.11, "elapsed_time": "0:15:08", "remaining_time": "5:53:23"}
+{"current_steps": 50, "total_steps": 974, "loss": 0.1146, "lr": 9.937682532746152e-06, "epoch": 0.10269576379974327, "percentage": 5.13, "elapsed_time": "0:18:51", "remaining_time": "5:48:35"}
+{"current_steps": 60, "total_steps": 974, "loss": 0.1111, "lr": 9.90973595093323e-06, "epoch": 0.12323491655969192, "percentage": 6.16, "elapsed_time": "0:22:38", "remaining_time": "5:44:49"}
+{"current_steps": 70, "total_steps": 974, "loss": 0.1073, "lr": 9.87668194038392e-06, "epoch": 0.14377406931964057, "percentage": 7.19, "elapsed_time": "0:26:22", "remaining_time": "5:40:41"}
+{"current_steps": 80, "total_steps": 974, "loss": 0.1077, "lr": 9.838554886043768e-06, "epoch": 0.1643132220795892, "percentage": 8.21, "elapsed_time": "0:30:08", "remaining_time": "5:36:44"}
+{"current_steps": 90, "total_steps": 974, "loss": 0.1087, "lr": 9.795394450170566e-06, "epoch": 0.18485237483953787, "percentage": 9.24, "elapsed_time": "0:33:53", "remaining_time": "5:32:57"}
+{"current_steps": 100, "total_steps": 974, "loss": 0.1052, "lr": 9.747245531075069e-06, "epoch": 0.20539152759948653, "percentage": 10.27, "elapsed_time": "0:37:40", "remaining_time": "5:29:12"}
+{"current_steps": 110, "total_steps": 974, "loss": 0.1061, "lr": 9.694158216414836e-06, "epoch": 0.22593068035943517, "percentage": 11.29, "elapsed_time": "0:41:27", "remaining_time": "5:25:38"}
+{"current_steps": 120, "total_steps": 974, "loss": 0.1024, "lr": 9.63618773108977e-06, "epoch": 0.24646983311938384, "percentage": 12.32, "elapsed_time": "0:45:11", "remaining_time": "5:21:38"}
+{"current_steps": 130, "total_steps": 974, "loss": 0.1032, "lr": 9.573394379793557e-06, "epoch": 0.26700898587933247, "percentage": 13.35, "elapsed_time": "0:48:57", "remaining_time": "5:17:52"}
+{"current_steps": 140, "total_steps": 974, "loss": 0.1063, "lr": 9.505843484280783e-06, "epoch": 0.28754813863928114, "percentage": 14.37, "elapsed_time": "0:52:43", "remaining_time": "5:14:05"}
+{"current_steps": 150, "total_steps": 974, "loss": 0.1027, "lr": 9.433605315414967e-06, "epoch": 0.3080872913992298, "percentage": 15.4, "elapsed_time": "0:56:27", "remaining_time": "5:10:09"}
+{"current_steps": 160, "total_steps": 974, "loss": 0.0995, "lr": 9.356755020068201e-06, "epoch": 0.3286264441591784, "percentage": 16.43, "elapsed_time": "1:00:14", "remaining_time": "5:06:29"}
+{"current_steps": 170, "total_steps": 974, "loss": 0.1017, "lr": 9.275372542948466e-06, "epoch": 0.3491655969191271, "percentage": 17.45, "elapsed_time": "1:04:01", "remaining_time": "5:02:47"}
+{"current_steps": 180, "total_steps": 974, "loss": 0.1015, "lr": 9.189542543435909e-06, "epoch": 0.36970474967907574, "percentage": 18.48, "elapsed_time": "1:07:47", "remaining_time": "4:59:02"}
+{"current_steps": 190, "total_steps": 974, "loss": 0.099, "lr": 9.099354307514607e-06, "epoch": 0.3902439024390244, "percentage": 19.51, "elapsed_time": "1:11:34", "remaining_time": "4:55:19"}
+{"current_steps": 200, "total_steps": 974, "loss": 0.0989, "lr": 9.004901654891453e-06, "epoch": 0.41078305519897307, "percentage": 20.53, "elapsed_time": "1:15:21", "remaining_time": "4:51:36"}
+{"current_steps": 210, "total_steps": 974, "loss": 0.096, "lr": 8.906282841398747e-06, "epoch": 0.4313222079589217, "percentage": 21.56, "elapsed_time": "1:19:04", "remaining_time": "4:47:41"}
+{"current_steps": 220, "total_steps": 974, "loss": 0.0957, "lr": 8.803600456782053e-06, "epoch": 0.45186136071887034, "percentage": 22.59, "elapsed_time": "1:22:50", "remaining_time": "4:43:55"}
+{"current_steps": 230, "total_steps": 974, "loss": 0.0959, "lr": 8.696961317979622e-06, "epoch": 0.472400513478819, "percentage": 23.61, "elapsed_time": "1:26:37", "remaining_time": "4:40:11"}
+{"current_steps": 240, "total_steps": 974, "loss": 0.0954, "lr": 8.586476358004427e-06, "epoch": 0.49293966623876767, "percentage": 24.64, "elapsed_time": "1:30:22", "remaining_time": "4:36:22"}
+{"current_steps": 250, "total_steps": 974, "loss": 0.0958, "lr": 8.472260510544383e-06, "epoch": 0.5134788189987163, "percentage": 25.67, "elapsed_time": "1:34:07", "remaining_time": "4:32:35"}
+{"current_steps": 260, "total_steps": 974, "loss": 0.0934, "lr": 8.354432590400792e-06, "epoch": 0.5340179717586649, "percentage": 26.69, "elapsed_time": "1:37:52", "remaining_time": "4:28:46"}
+{"current_steps": 270, "total_steps": 974, "loss": 0.0964, "lr": 8.23311516988942e-06, "epoch": 0.5545571245186136, "percentage": 27.72, "elapsed_time": "1:41:37", "remaining_time": "4:24:59"}
+{"current_steps": 280, "total_steps": 974, "loss": 0.094, "lr": 8.10843445133274e-06, "epoch": 0.5750962772785623, "percentage": 28.75, "elapsed_time": "1:45:24", "remaining_time": "4:21:15"}
+{"current_steps": 290, "total_steps": 974, "loss": 0.0908, "lr": 7.980520135776023e-06, "epoch": 0.5956354300385109, "percentage": 29.77, "elapsed_time": "1:49:10", "remaining_time": "4:17:29"}
+{"current_steps": 300, "total_steps": 974, "loss": 0.092, "lr": 7.849505288063808e-06, "epoch": 0.6161745827984596, "percentage": 30.8, "elapsed_time": "1:52:56", "remaining_time": "4:13:43"}
+{"current_steps": 310, "total_steps": 974, "loss": 0.0889, "lr": 7.71552619841716e-06, "epoch": 0.6367137355584083, "percentage": 31.83, "elapsed_time": "1:56:43", "remaining_time": "4:10:00"}
+{"current_steps": 320, "total_steps": 974, "loss": 0.0914, "lr": 7.578722240655645e-06, "epoch": 0.6572528883183568, "percentage": 32.85, "elapsed_time": "2:00:28", "remaining_time": "4:06:12"}
+{"current_steps": 330, "total_steps": 974, "loss": 0.0885, "lr": 7.43923572721156e-06, "epoch": 0.6777920410783055, "percentage": 33.88, "elapsed_time": "2:04:15", "remaining_time": "4:02:28"}
+{"current_steps": 340, "total_steps": 974, "loss": 0.0918, "lr": 7.297211761087229e-06, "epoch": 0.6983311938382541, "percentage": 34.91, "elapsed_time": "2:08:01", "remaining_time": "3:58:44"}
+{"current_steps": 350, "total_steps": 974, "loss": 0.0865, "lr": 7.152798084909365e-06, "epoch": 0.7188703465982028, "percentage": 35.93, "elapsed_time": "2:11:44", "remaining_time": "3:54:53"}
+{"current_steps": 360, "total_steps": 974, "loss": 0.0866, "lr": 7.006144927237505e-06, "epoch": 0.7394094993581515, "percentage": 36.96, "elapsed_time": "2:15:29", "remaining_time": "3:51:05"}
+{"current_steps": 370, "total_steps": 974, "loss": 0.0871, "lr": 6.857404846286444e-06, "epoch": 0.7599486521181001, "percentage": 37.99, "elapsed_time": "2:19:16", "remaining_time": "3:47:21"}
+{"current_steps": 380, "total_steps": 974, "loss": 0.0884, "lr": 6.706732571225183e-06, "epoch": 0.7804878048780488, "percentage": 39.01, "elapsed_time": "2:23:01", "remaining_time": "3:43:34"}
+{"current_steps": 390, "total_steps": 974, "loss": 0.085, "lr": 6.554284841217519e-06, "epoch": 0.8010269576379975, "percentage": 40.04, "elapsed_time": "2:26:48", "remaining_time": "3:39:50"}
+{"current_steps": 400, "total_steps": 974, "loss": 0.0861, "lr": 6.400220242371714e-06, "epoch": 0.8215661103979461, "percentage": 41.07, "elapsed_time": "2:30:33", "remaining_time": "3:36:03"}
+{"current_steps": 410, "total_steps": 974, "loss": 0.0852, "lr": 6.244699042768835e-06, "epoch": 0.8421052631578947, "percentage": 42.09, "elapsed_time": "2:34:19", "remaining_time": "3:32:17"}
+{"current_steps": 420, "total_steps": 974, "loss": 0.0838, "lr": 6.087883025741408e-06, "epoch": 0.8626444159178434, "percentage": 43.12, "elapsed_time": "2:38:06", "remaining_time": "3:28:32"}
+{"current_steps": 430, "total_steps": 974, "loss": 0.0865, "lr": 5.929935321575806e-06, "epoch": 0.883183568677792, "percentage": 44.15, "elapsed_time": "2:41:52", "remaining_time": "3:24:47"}
+{"current_steps": 440, "total_steps": 974, "loss": 0.0837, "lr": 5.771020237813448e-06, "epoch": 0.9037227214377407, "percentage": 45.17, "elapsed_time": "2:45:37", "remaining_time": "3:21:00"}
+{"current_steps": 450, "total_steps": 974, "loss": 0.0879, "lr": 5.611303088327331e-06, "epoch": 0.9242618741976893, "percentage": 46.2, "elapsed_time": "2:49:24", "remaining_time": "3:17:16"}
+{"current_steps": 460, "total_steps": 974, "loss": 0.0876, "lr": 5.450950021351725e-06, "epoch": 0.944801026957638, "percentage": 47.23, "elapsed_time": "2:53:10", "remaining_time": "3:13:30"}
+{"current_steps": 470, "total_steps": 974, "loss": 0.0851, "lr": 5.290127846643903e-06, "epoch": 0.9653401797175867, "percentage": 48.25, "elapsed_time": "2:56:56", "remaining_time": "3:09:44"}
+{"current_steps": 480, "total_steps": 974, "loss": 0.0827, "lr": 5.129003861957706e-06, "epoch": 0.9858793324775353, "percentage": 49.28, "elapsed_time": "3:00:43", "remaining_time": "3:05:59"}
+{"current_steps": 490, "total_steps": 974, "loss": 0.0749, "lr": 4.967745679009474e-06, "epoch": 1.0061617458279846, "percentage": 50.31, "elapsed_time": "3:04:26", "remaining_time": "3:02:11"}
+{"current_steps": 500, "total_steps": 974, "loss": 0.0626, "lr": 4.806521049117363e-06, "epoch": 1.0267008985879333, "percentage": 51.33, "elapsed_time": "3:08:13", "remaining_time": "2:58:26"}
+{"current_steps": 510, "total_steps": 974, "loss": 0.0621, "lr": 4.645497688695444e-06, "epoch": 1.047240051347882, "percentage": 52.36, "elapsed_time": "3:11:58", "remaining_time": "2:54:39"}
+{"current_steps": 520, "total_steps": 974, "loss": 0.0626, "lr": 4.484843104784106e-06, "epoch": 1.0677792041078304, "percentage": 53.39, "elapsed_time": "3:15:46", "remaining_time": "2:50:55"}
+{"current_steps": 530, "total_steps": 974, "loss": 0.0608, "lr": 4.32472442079828e-06, "epoch": 1.0883183568677792, "percentage": 54.41, "elapsed_time": "3:19:31", "remaining_time": "2:47:09"}
+{"current_steps": 540, "total_steps": 974, "loss": 0.0626, "lr": 4.165308202674704e-06, "epoch": 1.1088575096277278, "percentage": 55.44, "elapsed_time": "3:23:18", "remaining_time": "2:43:24"}
+{"current_steps": 550, "total_steps": 974, "loss": 0.0594, "lr": 4.006760285599146e-06, "epoch": 1.1293966623876766, "percentage": 56.47, "elapsed_time": "3:27:03", "remaining_time": "2:39:37"}
+{"current_steps": 560, "total_steps": 974, "loss": 0.0563, "lr": 3.849245601493784e-06, "epoch": 1.149935815147625, "percentage": 57.49, "elapsed_time": "3:30:45", "remaining_time": "2:35:48"}
+{"current_steps": 570, "total_steps": 974, "loss": 0.0589, "lr": 3.69292800744422e-06, "epoch": 1.1704749679075739, "percentage": 58.52, "elapsed_time": "3:34:28", "remaining_time": "2:32:00"}
+{"current_steps": 580, "total_steps": 974, "loss": 0.0602, "lr": 3.5379701152446184e-06, "epoch": 1.1910141206675224, "percentage": 59.55, "elapsed_time": "3:38:14", "remaining_time": "2:28:15"}
+{"current_steps": 590, "total_steps": 974, "loss": 0.0572, "lr": 3.384533122238267e-06, "epoch": 1.2115532734274712, "percentage": 60.57, "elapsed_time": "3:42:00", "remaining_time": "2:24:29"}
+{"current_steps": 600, "total_steps": 974, "loss": 0.0601, "lr": 3.2327766436295618e-06, "epoch": 1.2320924261874198, "percentage": 61.6, "elapsed_time": "3:45:47", "remaining_time": "2:20:44"}
+{"current_steps": 610, "total_steps": 974, "loss": 0.0605, "lr": 3.0828585464418013e-06, "epoch": 1.2526315789473683, "percentage": 62.63, "elapsed_time": "3:49:34", "remaining_time": "2:16:59"}
+{"current_steps": 620, "total_steps": 974, "loss": 0.0597, "lr": 2.934934785293593e-06, "epoch": 1.273170731707317, "percentage": 63.66, "elapsed_time": "3:53:20", "remaining_time": "2:13:13"}
+{"current_steps": 630, "total_steps": 974, "loss": 0.058, "lr": 2.7891592401646406e-06, "epoch": 1.2937098844672656, "percentage": 64.68, "elapsed_time": "3:57:06", "remaining_time": "2:09:28"}
+{"current_steps": 640, "total_steps": 974, "loss": 0.0574, "lr": 2.6456835563197194e-06, "epoch": 1.3142490372272144, "percentage": 65.71, "elapsed_time": "4:00:52", "remaining_time": "2:05:42"}
+{"current_steps": 650, "total_steps": 974, "loss": 0.0591, "lr": 2.504656986557342e-06, "epoch": 1.334788189987163, "percentage": 66.74, "elapsed_time": "4:04:39", "remaining_time": "2:01:57"}
+{"current_steps": 660, "total_steps": 974, "loss": 0.0587, "lr": 2.3662262359472326e-06, "epoch": 1.3553273427471118, "percentage": 67.76, "elapsed_time": "4:08:25", "remaining_time": "1:58:11"}
+{"current_steps": 670, "total_steps": 974, "loss": 0.0592, "lr": 2.2305353092181014e-06, "epoch": 1.3758664955070603, "percentage": 68.79, "elapsed_time": "4:12:11", "remaining_time": "1:54:25"}
+{"current_steps": 680, "total_steps": 974, "loss": 0.0588, "lr": 2.09772536095451e-06, "epoch": 1.396405648267009, "percentage": 69.82, "elapsed_time": "4:15:58", "remaining_time": "1:50:40"}
+{"current_steps": 690, "total_steps": 974, "loss": 0.0588, "lr": 1.967934548758621e-06, "epoch": 1.4169448010269576, "percentage": 70.84, "elapsed_time": "4:19:45", "remaining_time": "1:46:54"}
+{"current_steps": 700, "total_steps": 974, "loss": 0.0555, "lr": 1.8412978895296223e-06, "epoch": 1.4374839537869062, "percentage": 71.87, "elapsed_time": "4:23:29", "remaining_time": "1:43:08"}
+{"current_steps": 710, "total_steps": 974, "loss": 0.0568, "lr": 1.7179471190103103e-06, "epoch": 1.458023106546855, "percentage": 72.9, "elapsed_time": "4:27:14", "remaining_time": "1:39:21"}
+{"current_steps": 720, "total_steps": 974, "loss": 0.0584, "lr": 1.5980105547469443e-06, "epoch": 1.4785622593068035, "percentage": 73.92, "elapsed_time": "4:31:00", "remaining_time": "1:35:36"}
+{"current_steps": 730, "total_steps": 974, "loss": 0.0578, "lr": 1.4816129626049365e-06, "epoch": 1.4991014120667523, "percentage": 74.95, "elapsed_time": "4:34:47", "remaining_time": "1:31:50"}
+{"current_steps": 740, "total_steps": 974, "loss": 0.0579, "lr": 1.3688754269792297e-06, "epoch": 1.5196405648267008, "percentage": 75.98, "elapsed_time": "4:38:34", "remaining_time": "1:28:05"}
+{"current_steps": 750, "total_steps": 974, "loss": 0.0567, "lr": 1.2599152248343848e-06, "epoch": 1.5401797175866494, "percentage": 77.0, "elapsed_time": "4:42:19", "remaining_time": "1:24:19"}
+{"current_steps": 760, "total_steps": 974, "loss": 0.0581, "lr": 1.1548457037054089e-06, "epoch": 1.5607188703465982, "percentage": 78.03, "elapsed_time": "4:46:06", "remaining_time": "1:20:33"}
+{"current_steps": 770, "total_steps": 974, "loss": 0.0563, "lr": 1.0537761637862198e-06, "epoch": 1.581258023106547, "percentage": 79.06, "elapsed_time": "4:49:52", "remaining_time": "1:16:47"}
+{"current_steps": 780, "total_steps": 974, "loss": 0.0556, "lr": 9.568117442284375e-07, "epoch": 1.6017971758664955, "percentage": 80.08, "elapsed_time": "4:53:37", "remaining_time": "1:13:01"}
+{"current_steps": 790, "total_steps": 974, "loss": 0.0556, "lr": 8.640533137687523e-07, "epoch": 1.622336328626444, "percentage": 81.11, "elapsed_time": "4:57:24", "remaining_time": "1:09:16"}
+{"current_steps": 800, "total_steps": 974, "loss": 0.0571, "lr": 7.755973657986648e-07, "epoch": 1.6428754813863928, "percentage": 82.14, "elapsed_time": "5:01:10", "remaining_time": "1:05:30"}
+{"current_steps": 810, "total_steps": 974, "loss": 0.0555, "lr": 6.91535917985739e-07, "epoch": 1.6634146341463416, "percentage": 83.16, "elapsed_time": "5:04:56", "remaining_time": "1:01:44"}
+{"current_steps": 820, "total_steps": 974, "loss": 0.0553, "lr": 6.119564165508057e-07, "epoch": 1.6839537869062902, "percentage": 84.19, "elapsed_time": "5:08:42", "remaining_time": "0:57:58"}
+{"current_steps": 830, "total_steps": 974, "loss": 0.0575, "lr": 5.369416453006764e-07, "epoch": 1.7044929396662387, "percentage": 85.22, "elapsed_time": "5:12:28", "remaining_time": "0:54:12"}
+{"current_steps": 840, "total_steps": 974, "loss": 0.054, "lr": 4.665696395110081e-07, "epoch": 1.7250320924261873, "percentage": 86.24, "elapsed_time": "5:16:15", "remaining_time": "0:50:27"}
+{"current_steps": 850, "total_steps": 974, "loss": 0.0563, "lr": 4.009136047489026e-07, "epoch": 1.745571245186136, "percentage": 87.27, "elapsed_time": "5:20:01", "remaining_time": "0:46:41"}
+{"current_steps": 860, "total_steps": 974, "loss": 0.054, "lr": 3.400418407196826e-07, "epoch": 1.7661103979460848, "percentage": 88.3, "elapsed_time": "5:23:46", "remaining_time": "0:42:55"}
+{"current_steps": 870, "total_steps": 974, "loss": 0.054, "lr": 2.840176702170683e-07, "epoch": 1.7866495507060334, "percentage": 89.32, "elapsed_time": "5:27:30", "remaining_time": "0:39:09"}
+{"current_steps": 880, "total_steps": 974, "loss": 0.0566, "lr": 2.3289937325065902e-07, "epoch": 1.807188703465982, "percentage": 90.35, "elapsed_time": "5:31:16", "remaining_time": "0:35:23"}
+{"current_steps": 890, "total_steps": 974, "loss": 0.0543, "lr": 1.8674012641925642e-07, "epoch": 1.8277278562259307, "percentage": 91.38, "elapsed_time": "5:35:01", "remaining_time": "0:31:37"}
+{"current_steps": 900, "total_steps": 974, "loss": 0.057, "lr": 1.455879475930827e-07, "epoch": 1.8482670089858795, "percentage": 92.4, "elapsed_time": "5:38:47", "remaining_time": "0:27:51"}
+{"current_steps": 910, "total_steps": 974, "loss": 0.0572, "lr": 1.0948564596244937e-07, "epoch": 1.868806161745828, "percentage": 93.43, "elapsed_time": "5:42:33", "remaining_time": "0:24:05"}
+{"current_steps": 920, "total_steps": 974, "loss": 0.0553, "lr": 7.847077750483489e-08, "epoch": 1.8893453145057766, "percentage": 94.46, "elapsed_time": "5:46:18", "remaining_time": "0:20:19"}
+{"current_steps": 930, "total_steps": 974, "loss": 0.0546, "lr": 5.257560591669764e-08, "epoch": 1.9098844672657251, "percentage": 95.48, "elapsed_time": "5:50:04", "remaining_time": "0:16:33"}
+{"current_steps": 940, "total_steps": 974, "loss": 0.0571, "lr": 3.182706905067001e-08, "epoch": 1.930423620025674, "percentage": 96.51, "elapsed_time": "5:53:50", "remaining_time": "0:12:47"}
+{"current_steps": 950, "total_steps": 974, "loss": 0.0559, "lr": 1.624675089303529e-08, "epoch": 1.9509627727856227, "percentage": 97.54, "elapsed_time": "5:57:36", "remaining_time": "0:09:02"}
+{"current_steps": 960, "total_steps": 974, "loss": 0.0572, "lr": 5.850859110658191e-09, "epoch": 1.9715019255455712, "percentage": 98.56, "elapsed_time": "6:01:19", "remaining_time": "0:05:16"}
+{"current_steps": 970, "total_steps": 974, "loss": 0.0544, "lr": 6.502081907039381e-10, "epoch": 1.9920410783055198, "percentage": 99.59, "elapsed_time": "6:05:06", "remaining_time": "0:01:30"}
+{"current_steps": 974, "total_steps": 974, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "6:08:07", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,722 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 974,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02053915275994865,
+      "grad_norm": 0.6241949796676636,
+      "learning_rate": 9.99789342773948e-06,
+      "loss": 0.1517,
+      "step": 10
+    },
+    {
+      "epoch": 0.0410783055198973,
+      "grad_norm": 0.3109052777290344,
+      "learning_rate": 9.99061372843304e-06,
+      "loss": 0.1347,
+      "step": 20
+    },
+    {
+      "epoch": 0.06161745827984596,
+      "grad_norm": 0.28893721103668213,
+      "learning_rate": 9.978142466031648e-06,
+      "loss": 0.12,
+      "step": 30
+    },
+    {
+      "epoch": 0.0821566110397946,
+      "grad_norm": 0.2942233979701996,
+      "learning_rate": 9.960492613958845e-06,
+      "loss": 0.1187,
+      "step": 40
+    },
+    {
+      "epoch": 0.10269576379974327,
+      "grad_norm": 0.26697084307670593,
+      "learning_rate": 9.937682532746152e-06,
+      "loss": 0.1146,
+      "step": 50
+    },
+    {
+      "epoch": 0.12323491655969192,
+      "grad_norm": 0.26033908128738403,
+      "learning_rate": 9.90973595093323e-06,
+      "loss": 0.1111,
+      "step": 60
+    },
+    {
+      "epoch": 0.14377406931964057,
+      "grad_norm": 0.24977026879787445,
+      "learning_rate": 9.87668194038392e-06,
+      "loss": 0.1073,
+      "step": 70
+    },
+    {
+      "epoch": 0.1643132220795892,
+      "grad_norm": 0.2998938262462616,
+      "learning_rate": 9.838554886043768e-06,
+      "loss": 0.1077,
+      "step": 80
+    },
+    {
+      "epoch": 0.18485237483953787,
+      "grad_norm": 0.30642247200012207,
+      "learning_rate": 9.795394450170566e-06,
+      "loss": 0.1087,
+      "step": 90
+    },
+    {
+      "epoch": 0.20539152759948653,
+      "grad_norm": 0.2964343726634979,
+      "learning_rate": 9.747245531075069e-06,
+      "loss": 0.1052,
+      "step": 100
+    },
+    {
+      "epoch": 0.22593068035943517,
+      "grad_norm": 0.2638753056526184,
+      "learning_rate": 9.694158216414836e-06,
+      "loss": 0.1061,
+      "step": 110
+    },
+    {
+      "epoch": 0.24646983311938384,
+      "grad_norm": 0.2852879464626312,
+      "learning_rate": 9.63618773108977e-06,
+      "loss": 0.1024,
+      "step": 120
+    },
+    {
+      "epoch": 0.26700898587933247,
+      "grad_norm": 0.2863173484802246,
+      "learning_rate": 9.573394379793557e-06,
+      "loss": 0.1032,
+      "step": 130
+    },
+    {
+      "epoch": 0.28754813863928114,
+      "grad_norm": 0.2960529625415802,
+      "learning_rate": 9.505843484280783e-06,
+      "loss": 0.1063,
+      "step": 140
+    },
+    {
+      "epoch": 0.3080872913992298,
+      "grad_norm": 0.28948211669921875,
+      "learning_rate": 9.433605315414967e-06,
+      "loss": 0.1027,
+      "step": 150
+    },
+    {
+      "epoch": 0.3286264441591784,
+      "grad_norm": 0.2555496096611023,
+      "learning_rate": 9.356755020068201e-06,
+      "loss": 0.0995,
+      "step": 160
+    },
+    {
+      "epoch": 0.3491655969191271,
+      "grad_norm": 0.2884163558483124,
+      "learning_rate": 9.275372542948466e-06,
+      "loss": 0.1017,
+      "step": 170
+    },
+    {
+      "epoch": 0.36970474967907574,
+      "grad_norm": 0.2388547658920288,
+      "learning_rate": 9.189542543435909e-06,
+      "loss": 0.1015,
+      "step": 180
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.2760099768638611,
+      "learning_rate": 9.099354307514607e-06,
+      "loss": 0.099,
+      "step": 190
+    },
+    {
+      "epoch": 0.41078305519897307,
+      "grad_norm": 0.29273074865341187,
+      "learning_rate": 9.004901654891453e-06,
+      "loss": 0.0989,
+      "step": 200
+    },
+    {
+      "epoch": 0.4313222079589217,
+      "grad_norm": 0.31362560391426086,
+      "learning_rate": 8.906282841398747e-06,
+      "loss": 0.096,
+      "step": 210
+    },
+    {
+      "epoch": 0.45186136071887034,
+      "grad_norm": 0.27469882369041443,
+      "learning_rate": 8.803600456782053e-06,
+      "loss": 0.0957,
+      "step": 220
+    },
+    {
+      "epoch": 0.472400513478819,
+      "grad_norm": 0.2949489653110504,
+      "learning_rate": 8.696961317979622e-06,
+      "loss": 0.0959,
+      "step": 230
+    },
+    {
+      "epoch": 0.49293966623876767,
+      "grad_norm": 0.2868664264678955,
+      "learning_rate": 8.586476358004427e-06,
+      "loss": 0.0954,
+      "step": 240
+    },
+    {
+      "epoch": 0.5134788189987163,
+      "grad_norm": 0.28068357706069946,
+      "learning_rate": 8.472260510544383e-06,
+      "loss": 0.0958,
+      "step": 250
+    },
+    {
+      "epoch": 0.5340179717586649,
+      "grad_norm": 0.2683391273021698,
+      "learning_rate": 8.354432590400792e-06,
+      "loss": 0.0934,
+      "step": 260
+    },
+    {
+      "epoch": 0.5545571245186136,
+      "grad_norm": 0.26564258337020874,
+      "learning_rate": 8.23311516988942e-06,
+      "loss": 0.0964,
+      "step": 270
+    },
+    {
+      "epoch": 0.5750962772785623,
+      "grad_norm": 0.3143099844455719,
+      "learning_rate": 8.10843445133274e-06,
+      "loss": 0.094,
+      "step": 280
+    },
+    {
+      "epoch": 0.5956354300385109,
+      "grad_norm": 0.25333961844444275,
+      "learning_rate": 7.980520135776023e-06,
+      "loss": 0.0908,
+      "step": 290
+    },
+    {
+      "epoch": 0.6161745827984596,
+      "grad_norm": 0.2577582001686096,
+      "learning_rate": 7.849505288063808e-06,
+      "loss": 0.092,
+      "step": 300
+    },
+    {
+      "epoch": 0.6367137355584083,
+      "grad_norm": 0.2629285752773285,
+      "learning_rate": 7.71552619841716e-06,
+      "loss": 0.0889,
+      "step": 310
+    },
+    {
+      "epoch": 0.6572528883183568,
+      "grad_norm": 0.24951164424419403,
+      "learning_rate": 7.578722240655645e-06,
+      "loss": 0.0914,
+      "step": 320
+    },
+    {
+      "epoch": 0.6777920410783055,
+      "grad_norm": 0.264588862657547,
+      "learning_rate": 7.43923572721156e-06,
+      "loss": 0.0885,
+      "step": 330
+    },
+    {
+      "epoch": 0.6983311938382541,
+      "grad_norm": 0.2667712867259979,
+      "learning_rate": 7.297211761087229e-06,
+      "loss": 0.0918,
+      "step": 340
+    },
+    {
+      "epoch": 0.7188703465982028,
+      "grad_norm": 0.2499169409275055,
+      "learning_rate": 7.152798084909365e-06,
+      "loss": 0.0865,
+      "step": 350
+    },
+    {
+      "epoch": 0.7394094993581515,
+      "grad_norm": 0.27517884969711304,
+      "learning_rate": 7.006144927237505e-06,
+      "loss": 0.0866,
+      "step": 360
+    },
+    {
+      "epoch": 0.7599486521181001,
+      "grad_norm": 0.2483636885881424,
+      "learning_rate": 6.857404846286444e-06,
+      "loss": 0.0871,
+      "step": 370
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 0.30694103240966797,
+      "learning_rate": 6.706732571225183e-06,
+      "loss": 0.0884,
+      "step": 380
+    },
+    {
+      "epoch": 0.8010269576379975,
+      "grad_norm": 0.23266981542110443,
+      "learning_rate": 6.554284841217519e-06,
+      "loss": 0.085,
+      "step": 390
+    },
+    {
+      "epoch": 0.8215661103979461,
+      "grad_norm": 0.27542293071746826,
+      "learning_rate": 6.400220242371714e-06,
+      "loss": 0.0861,
+      "step": 400
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.2664916515350342,
+      "learning_rate": 6.244699042768835e-06,
+      "loss": 0.0852,
+      "step": 410
+    },
+    {
+      "epoch": 0.8626444159178434,
+      "grad_norm": 0.24229811131954193,
+      "learning_rate": 6.087883025741408e-06,
+      "loss": 0.0838,
+      "step": 420
+    },
+    {
+      "epoch": 0.883183568677792,
+      "grad_norm": 0.23243330419063568,
+      "learning_rate": 5.929935321575806e-06,
+      "loss": 0.0865,
+      "step": 430
+    },
+    {
+      "epoch": 0.9037227214377407,
+      "grad_norm": 0.2365313470363617,
+      "learning_rate": 5.771020237813448e-06,
+      "loss": 0.0837,
+      "step": 440
+    },
+    {
+      "epoch": 0.9242618741976893,
+      "grad_norm": 0.24980725347995758,
+      "learning_rate": 5.611303088327331e-06,
+      "loss": 0.0879,
+      "step": 450
+    },
+    {
+      "epoch": 0.944801026957638,
+      "grad_norm": 0.2599492371082306,
+      "learning_rate": 5.450950021351725e-06,
+      "loss": 0.0876,
+      "step": 460
+    },
+    {
+      "epoch": 0.9653401797175867,
+      "grad_norm": 0.27633577585220337,
+      "learning_rate": 5.290127846643903e-06,
+      "loss": 0.0851,
+      "step": 470
+    },
+    {
+      "epoch": 0.9858793324775353,
+      "grad_norm": 0.25800392031669617,
+      "learning_rate": 5.129003861957706e-06,
+      "loss": 0.0827,
+      "step": 480
+    },
+    {
+      "epoch": 1.0061617458279846,
+      "grad_norm": 0.22503100335597992,
+      "learning_rate": 4.967745679009474e-06,
+      "loss": 0.0749,
+      "step": 490
+    },
+    {
+      "epoch": 1.0267008985879333,
+      "grad_norm": 0.23040170967578888,
+      "learning_rate": 4.806521049117363e-06,
+      "loss": 0.0626,
+      "step": 500
+    },
+    {
+      "epoch": 1.047240051347882,
+      "grad_norm": 0.23996306955814362,
+      "learning_rate": 4.645497688695444e-06,
+      "loss": 0.0621,
+      "step": 510
+    },
+    {
+      "epoch": 1.0677792041078304,
+      "grad_norm": 0.2363160401582718,
+      "learning_rate": 4.484843104784106e-06,
+      "loss": 0.0626,
+      "step": 520
+    },
+    {
+      "epoch": 1.0883183568677792,
+      "grad_norm": 0.24278973042964935,
+      "learning_rate": 4.32472442079828e-06,
+      "loss": 0.0608,
+      "step": 530
+    },
+    {
+      "epoch": 1.1088575096277278,
+      "grad_norm": 0.2526680827140808,
+      "learning_rate": 4.165308202674704e-06,
+      "loss": 0.0626,
+      "step": 540
+    },
+    {
+      "epoch": 1.1293966623876766,
+      "grad_norm": 0.260307639837265,
+      "learning_rate": 4.006760285599146e-06,
+      "loss": 0.0594,
+      "step": 550
+    },
+    {
+      "epoch": 1.149935815147625,
+      "grad_norm": 0.2719564139842987,
+      "learning_rate": 3.849245601493784e-06,
+      "loss": 0.0563,
+      "step": 560
+    },
+    {
+      "epoch": 1.1704749679075739,
+      "grad_norm": 0.23317693173885345,
+      "learning_rate": 3.69292800744422e-06,
+      "loss": 0.0589,
+      "step": 570
+    },
+    {
+      "epoch": 1.1910141206675224,
+      "grad_norm": 0.23016999661922455,
+      "learning_rate": 3.5379701152446184e-06,
+      "loss": 0.0602,
+      "step": 580
+    },
+    {
+      "epoch": 1.2115532734274712,
+      "grad_norm": 0.21775227785110474,
+      "learning_rate": 3.384533122238267e-06,
+      "loss": 0.0572,
+      "step": 590
+    },
+    {
+      "epoch": 1.2320924261874198,
+      "grad_norm": 0.247865229845047,
+      "learning_rate": 3.2327766436295618e-06,
+      "loss": 0.0601,
+      "step": 600
+    },
+    {
+      "epoch": 1.2526315789473683,
+      "grad_norm": 0.23535579442977905,
+      "learning_rate": 3.0828585464418013e-06,
+      "loss": 0.0605,
+      "step": 610
+    },
+    {
+      "epoch": 1.273170731707317,
+      "grad_norm": 0.2479717880487442,
+      "learning_rate": 2.934934785293593e-06,
+      "loss": 0.0597,
+      "step": 620
+    },
+    {
+      "epoch": 1.2937098844672656,
+      "grad_norm": 0.24478904902935028,
+      "learning_rate": 2.7891592401646406e-06,
+      "loss": 0.058,
+      "step": 630
+    },
+    {
+      "epoch": 1.3142490372272144,
+      "grad_norm": 0.24038828909397125,
+      "learning_rate": 2.6456835563197194e-06,
+      "loss": 0.0574,
+      "step": 640
+    },
+    {
+      "epoch": 1.334788189987163,
+      "grad_norm": 0.24659165740013123,
+      "learning_rate": 2.504656986557342e-06,
+      "loss": 0.0591,
+      "step": 650
+    },
+    {
+      "epoch": 1.3553273427471118,
+      "grad_norm": 0.23365946114063263,
+      "learning_rate": 2.3662262359472326e-06,
+      "loss": 0.0587,
+      "step": 660
+    },
+    {
+      "epoch": 1.3758664955070603,
+      "grad_norm": 0.2665676772594452,
+      "learning_rate": 2.2305353092181014e-06,
+      "loss": 0.0592,
+      "step": 670
+    },
+    {
+      "epoch": 1.396405648267009,
+      "grad_norm": 0.24800005555152893,
+      "learning_rate": 2.09772536095451e-06,
+      "loss": 0.0588,
+      "step": 680
+    },
+    {
+      "epoch": 1.4169448010269576,
+      "grad_norm": 0.2330596148967743,
+      "learning_rate": 1.967934548758621e-06,
+      "loss": 0.0588,
+      "step": 690
+    },
+    {
+      "epoch": 1.4374839537869062,
+      "grad_norm": 0.2489139586687088,
+      "learning_rate": 1.8412978895296223e-06,
+      "loss": 0.0555,
+      "step": 700
+    },
+    {
+      "epoch": 1.458023106546855,
+      "grad_norm": 0.2403998076915741,
+      "learning_rate": 1.7179471190103103e-06,
+      "loss": 0.0568,
+      "step": 710
+    },
+    {
+      "epoch": 1.4785622593068035,
+      "grad_norm": 0.23150111734867096,
+      "learning_rate": 1.5980105547469443e-06,
+      "loss": 0.0584,
+      "step": 720
+    },
+    {
+      "epoch": 1.4991014120667523,
+      "grad_norm": 0.2429497092962265,
+      "learning_rate": 1.4816129626049365e-06,
+      "loss": 0.0578,
+      "step": 730
+    },
+    {
+      "epoch": 1.5196405648267008,
+      "grad_norm": 0.23500065505504608,
+      "learning_rate": 1.3688754269792297e-06,
+      "loss": 0.0579,
+      "step": 740
+    },
+    {
+      "epoch": 1.5401797175866494,
+      "grad_norm": 0.24009016156196594,
+      "learning_rate": 1.2599152248343848e-06,
+      "loss": 0.0567,
+      "step": 750
+    },
+    {
+      "epoch": 1.5607188703465982,
+      "grad_norm": 0.2493337094783783,
+      "learning_rate": 1.1548457037054089e-06,
+      "loss": 0.0581,
+      "step": 760
+    },
+    {
+      "epoch": 1.581258023106547,
+      "grad_norm": 0.25276979804039,
+      "learning_rate": 1.0537761637862198e-06,
+      "loss": 0.0563,
+      "step": 770
+    },
+    {
+      "epoch": 1.6017971758664955,
+      "grad_norm": 0.23559069633483887,
+      "learning_rate": 9.568117442284375e-07,
+      "loss": 0.0556,
+      "step": 780
+    },
+    {
+      "epoch": 1.622336328626444,
+      "grad_norm": 0.22181905806064606,
+      "learning_rate": 8.640533137687523e-07,
+      "loss": 0.0556,
+      "step": 790
+    },
+    {
+      "epoch": 1.6428754813863928,
+      "grad_norm": 0.25861266255378723,
+      "learning_rate": 7.755973657986648e-07,
+      "loss": 0.0571,
+      "step": 800
+    },
+    {
+      "epoch": 1.6634146341463416,
+      "grad_norm": 0.24212630093097687,
+      "learning_rate": 6.91535917985739e-07,
+      "loss": 0.0555,
+      "step": 810
+    },
+    {
+      "epoch": 1.6839537869062902,
+      "grad_norm": 0.23966702818870544,
+      "learning_rate": 6.119564165508057e-07,
+      "loss": 0.0553,
+      "step": 820
+    },
+    {
+      "epoch": 1.7044929396662387,
+      "grad_norm": 0.2524842619895935,
+      "learning_rate": 5.369416453006764e-07,
+      "loss": 0.0575,
+      "step": 830
+    },
+    {
+      "epoch": 1.7250320924261873,
+      "grad_norm": 0.2377074807882309,
+      "learning_rate": 4.665696395110081e-07,
+      "loss": 0.054,
+      "step": 840
+    },
+    {
+      "epoch": 1.745571245186136,
+      "grad_norm": 0.23431187868118286,
+      "learning_rate": 4.009136047489026e-07,
+      "loss": 0.0563,
+      "step": 850
+    },
+    {
+      "epoch": 1.7661103979460848,
+      "grad_norm": 0.2580386698246002,
+      "learning_rate": 3.400418407196826e-07,
+      "loss": 0.054,
+      "step": 860
+    },
+    {
+      "epoch": 1.7866495507060334,
+      "grad_norm": 0.23353375494480133,
+      "learning_rate": 2.840176702170683e-07,
+      "loss": 0.054,
+      "step": 870
+    },
+    {
+      "epoch": 1.807188703465982,
+      "grad_norm": 0.24874167144298553,
+      "learning_rate": 2.3289937325065902e-07,
+      "loss": 0.0566,
+      "step": 880
+    },
+    {
+      "epoch": 1.8277278562259307,
+      "grad_norm": 0.2422235757112503,
+      "learning_rate": 1.8674012641925642e-07,
+      "loss": 0.0543,
+      "step": 890
+    },
+    {
+      "epoch": 1.8482670089858795,
+      "grad_norm": 0.24417363107204437,
+      "learning_rate": 1.455879475930827e-07,
+      "loss": 0.057,
+      "step": 900
+    },
+    {
+      "epoch": 1.868806161745828,
+      "grad_norm": 0.23857787251472473,
+      "learning_rate": 1.0948564596244937e-07,
+      "loss": 0.0572,
+      "step": 910
+    },
+    {
+      "epoch": 1.8893453145057766,
+      "grad_norm": 0.25707000494003296,
+      "learning_rate": 7.847077750483489e-08,
+      "loss": 0.0553,
+      "step": 920
+    },
+    {
+      "epoch": 1.9098844672657251,
+      "grad_norm": 0.2240484207868576,
+      "learning_rate": 5.257560591669764e-08,
+      "loss": 0.0546,
+      "step": 930
+    },
+    {
+      "epoch": 1.930423620025674,
+      "grad_norm": 0.22742733359336853,
+      "learning_rate": 3.182706905067001e-08,
+      "loss": 0.0571,
+      "step": 940
+    },
+    {
+      "epoch": 1.9509627727856227,
+      "grad_norm": 0.24693480134010315,
+      "learning_rate": 1.624675089303529e-08,
+      "loss": 0.0559,
+      "step": 950
+    },
+    {
+      "epoch": 1.9715019255455712,
+      "grad_norm": 0.22910530865192413,
+      "learning_rate": 5.850859110658191e-09,
+      "loss": 0.0572,
+      "step": 960
+    },
+    {
+      "epoch": 1.9920410783055198,
+      "grad_norm": 0.24262285232543945,
+      "learning_rate": 6.502081907039381e-10,
+      "loss": 0.0544,
+      "step": 970
+    },
+    {
+      "epoch": 2.0,
+      "step": 974,
+      "total_flos": 1.635906903930726e+19,
+      "train_loss": 0.07772063925954106,
+      "train_runtime": 22087.4933,
+      "train_samples_per_second": 11.286,
+      "train_steps_per_second": 0.044
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 974,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.635906903930726e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cbda6a7e9c3c5c3c8fd43e37cc7c4833b23554639f23264e2f1c455e71bb27f
+size 8081