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

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": 7.869097163274322e+17,
+    "train_loss": 0.5555472550983716,
+    "train_runtime": 14309.8006,
+    "train_samples_per_second": 19.012,
+    "train_steps_per_second": 0.037
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- '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 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 +1,29 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad0687cc8386dada059bcedb7ba2660d0968c8fb621f7e4362d608c5fc58dd4
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9d51504866dfe38f4e56479e59bde6ce568aaa03ec007c580c9e3b963f5e5a
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94188af9530a9473ce9b412540e8d98c9eb60df0f1b60220814e302f34352a9c
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee165e24895ab934391f9f65c5d44f622b92150c316c6f2358f71e1e75d04498
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "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": "<|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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 7.869097163274322e+17,
+    "train_loss": 0.5555472550983716,
+    "train_runtime": 14309.8006,
+    "train_samples_per_second": 19.012,
+    "train_steps_per_second": 0.037
+}

trainer_log.jsonl

@@ -0,0 +1,54 @@
+{"current_steps": 10, "total_steps": 532, "loss": 0.5923, "lr": 8.333333333333333e-07, "epoch": 0.037638202775817454, "percentage": 1.88, "elapsed_time": "0:04:58", "remaining_time": "4:19:42"}
+{"current_steps": 20, "total_steps": 532, "loss": 0.5849, "lr": 1.7592592592592594e-06, "epoch": 0.07527640555163491, "percentage": 3.76, "elapsed_time": "0:09:20", "remaining_time": "3:59:15"}
+{"current_steps": 30, "total_steps": 532, "loss": 0.5754, "lr": 2.6851851851851856e-06, "epoch": 0.11291460832745237, "percentage": 5.64, "elapsed_time": "0:13:47", "remaining_time": "3:50:47"}
+{"current_steps": 40, "total_steps": 532, "loss": 0.5628, "lr": 3.6111111111111115e-06, "epoch": 0.15055281110326982, "percentage": 7.52, "elapsed_time": "0:18:15", "remaining_time": "3:44:34"}
+{"current_steps": 50, "total_steps": 532, "loss": 0.5897, "lr": 4.537037037037038e-06, "epoch": 0.18819101387908727, "percentage": 9.4, "elapsed_time": "0:22:52", "remaining_time": "3:40:29"}
+{"current_steps": 60, "total_steps": 532, "loss": 0.5834, "lr": 4.998650245168965e-06, "epoch": 0.22582921665490474, "percentage": 11.28, "elapsed_time": "0:27:34", "remaining_time": "3:36:52"}
+{"current_steps": 70, "total_steps": 532, "loss": 0.58, "lr": 4.987860949769804e-06, "epoch": 0.26346741943072216, "percentage": 13.16, "elapsed_time": "0:32:00", "remaining_time": "3:31:17"}
+{"current_steps": 80, "total_steps": 532, "loss": 0.5686, "lr": 4.9663289476829e-06, "epoch": 0.30110562220653964, "percentage": 15.04, "elapsed_time": "0:36:34", "remaining_time": "3:26:38"}
+{"current_steps": 90, "total_steps": 532, "loss": 0.5584, "lr": 4.934147215158732e-06, "epoch": 0.3387438249823571, "percentage": 16.92, "elapsed_time": "0:40:55", "remaining_time": "3:20:59"}
+{"current_steps": 100, "total_steps": 532, "loss": 0.5994, "lr": 4.891454714510784e-06, "epoch": 0.37638202775817453, "percentage": 18.8, "elapsed_time": "0:45:27", "remaining_time": "3:16:23"}
+{"current_steps": 110, "total_steps": 532, "loss": 0.5661, "lr": 4.838435794069406e-06, "epoch": 0.414020230533992, "percentage": 20.68, "elapsed_time": "0:49:53", "remaining_time": "3:11:22"}
+{"current_steps": 120, "total_steps": 532, "loss": 0.589, "lr": 4.775319392156593e-06, "epoch": 0.4516584333098095, "percentage": 22.56, "elapsed_time": "0:54:21", "remaining_time": "3:06:39"}
+{"current_steps": 130, "total_steps": 532, "loss": 0.5423, "lr": 4.70237804851899e-06, "epoch": 0.4892966360856269, "percentage": 24.44, "elapsed_time": "0:58:33", "remaining_time": "3:01:05"}
+{"current_steps": 140, "total_steps": 532, "loss": 0.5741, "lr": 4.619926727487774e-06, "epoch": 0.5269348388614443, "percentage": 26.32, "elapsed_time": "1:03:00", "remaining_time": "2:56:25"}
+{"current_steps": 150, "total_steps": 532, "loss": 0.5942, "lr": 4.528321457947091e-06, "epoch": 0.5645730416372619, "percentage": 28.2, "elapsed_time": "1:07:33", "remaining_time": "2:52:03"}
+{"current_steps": 160, "total_steps": 532, "loss": 0.5735, "lr": 4.427957795983715e-06, "epoch": 0.6022112444130793, "percentage": 30.08, "elapsed_time": "1:11:59", "remaining_time": "2:47:22"}
+{"current_steps": 170, "total_steps": 532, "loss": 0.5667, "lr": 4.319269116856291e-06, "epoch": 0.6398494471888967, "percentage": 31.95, "elapsed_time": "1:16:35", "remaining_time": "2:43:05"}
+{"current_steps": 180, "total_steps": 532, "loss": 0.5578, "lr": 4.2027247436595245e-06, "epoch": 0.6774876499647142, "percentage": 33.83, "elapsed_time": "1:21:07", "remaining_time": "2:38:38"}
+{"current_steps": 190, "total_steps": 532, "loss": 0.5784, "lr": 4.078827920763835e-06, "epoch": 0.7151258527405316, "percentage": 35.71, "elapsed_time": "1:25:33", "remaining_time": "2:33:59"}
+{"current_steps": 200, "total_steps": 532, "loss": 0.571, "lr": 3.948113640781265e-06, "epoch": 0.7527640555163491, "percentage": 37.59, "elapsed_time": "1:30:00", "remaining_time": "2:29:25"}
+{"current_steps": 210, "total_steps": 532, "loss": 0.56, "lr": 3.8111463344409026e-06, "epoch": 0.7904022582921666, "percentage": 39.47, "elapsed_time": "1:34:18", "remaining_time": "2:24:37"}
+{"current_steps": 220, "total_steps": 532, "loss": 0.5752, "lr": 3.668517433349069e-06, "epoch": 0.828040461067984, "percentage": 41.35, "elapsed_time": "1:38:47", "remaining_time": "2:20:06"}
+{"current_steps": 230, "total_steps": 532, "loss": 0.5845, "lr": 3.520842816158374e-06, "epoch": 0.8656786638438014, "percentage": 43.23, "elapsed_time": "1:43:18", "remaining_time": "2:15:39"}
+{"current_steps": 240, "total_steps": 532, "loss": 0.5928, "lr": 3.368760149173219e-06, "epoch": 0.903316866619619, "percentage": 45.11, "elapsed_time": "1:47:57", "remaining_time": "2:11:20"}
+{"current_steps": 250, "total_steps": 532, "loss": 0.5614, "lr": 3.212926132875141e-06, "epoch": 0.9409550693954364, "percentage": 46.99, "elapsed_time": "1:52:22", "remaining_time": "2:06:45"}
+{"current_steps": 260, "total_steps": 532, "loss": 0.58, "lr": 3.054013666257638e-06, "epoch": 0.9785932721712538, "percentage": 48.87, "elapsed_time": "1:57:00", "remaining_time": "2:02:24"}
+{"current_steps": 270, "total_steps": 532, "loss": 0.5852, "lr": 2.8927089412150176e-06, "epoch": 1.015055281110327, "percentage": 50.75, "elapsed_time": "2:01:27", "remaining_time": "1:57:51"}
+{"current_steps": 280, "total_steps": 532, "loss": 0.532, "lr": 2.729708479531844e-06, "epoch": 1.0526934838861444, "percentage": 52.63, "elapsed_time": "2:06:06", "remaining_time": "1:53:30"}
+{"current_steps": 290, "total_steps": 532, "loss": 0.5312, "lr": 2.5657161252674047e-06, "epoch": 1.090331686661962, "percentage": 54.51, "elapsed_time": "2:10:36", "remaining_time": "1:48:59"}
+{"current_steps": 300, "total_steps": 532, "loss": 0.5181, "lr": 2.4014400055222337e-06, "epoch": 1.1279698894377794, "percentage": 56.39, "elapsed_time": "2:15:05", "remaining_time": "1:44:28"}
+{"current_steps": 310, "total_steps": 532, "loss": 0.5504, "lr": 2.2375894727102552e-06, "epoch": 1.1656080922135967, "percentage": 58.27, "elapsed_time": "2:19:32", "remaining_time": "1:39:55"}
+{"current_steps": 320, "total_steps": 532, "loss": 0.5295, "lr": 2.0748720415399542e-06, "epoch": 1.2032462949894143, "percentage": 60.15, "elapsed_time": "2:23:49", "remaining_time": "1:35:16"}
+{"current_steps": 330, "total_steps": 532, "loss": 0.5276, "lr": 1.913990333930858e-06, "epoch": 1.2408844977652318, "percentage": 62.03, "elapsed_time": "2:28:18", "remaining_time": "1:30:46"}
+{"current_steps": 340, "total_steps": 532, "loss": 0.5329, "lr": 1.7556390450573213e-06, "epoch": 1.278522700541049, "percentage": 63.91, "elapsed_time": "2:32:49", "remaining_time": "1:26:18"}
+{"current_steps": 350, "total_steps": 532, "loss": 0.5282, "lr": 1.600501943620384e-06, "epoch": 1.3161609033168666, "percentage": 65.79, "elapsed_time": "2:37:27", "remaining_time": "1:21:52"}
+{"current_steps": 360, "total_steps": 532, "loss": 0.5233, "lr": 1.4492489193006884e-06, "epoch": 1.353799106092684, "percentage": 67.67, "elapsed_time": "2:41:52", "remaining_time": "1:17:20"}
+{"current_steps": 370, "total_steps": 532, "loss": 0.5148, "lr": 1.302533090141689e-06, "epoch": 1.3914373088685015, "percentage": 69.55, "elapsed_time": "2:46:16", "remaining_time": "1:12:48"}
+{"current_steps": 380, "total_steps": 532, "loss": 0.5369, "lr": 1.1609879823536233e-06, "epoch": 1.429075511644319, "percentage": 71.43, "elapsed_time": "2:50:42", "remaining_time": "1:08:16"}
+{"current_steps": 390, "total_steps": 532, "loss": 0.5451, "lr": 1.0252247947159846e-06, "epoch": 1.4667137144201363, "percentage": 73.31, "elapsed_time": "2:55:08", "remaining_time": "1:03:46"}
+{"current_steps": 400, "total_steps": 532, "loss": 0.5418, "lr": 8.95829759390954e-07, "epoch": 1.5043519171959538, "percentage": 75.19, "elapsed_time": "2:59:37", "remaining_time": "0:59:16"}
+{"current_steps": 410, "total_steps": 532, "loss": 0.5178, "lr": 7.733616105439077e-07, "epoch": 1.5419901199717714, "percentage": 77.07, "elapsed_time": "3:04:08", "remaining_time": "0:54:47"}
+{"current_steps": 420, "total_steps": 532, "loss": 0.5241, "lr": 6.58349171701651e-07, "epoch": 1.5796283227475887, "percentage": 78.95, "elapsed_time": "3:08:31", "remaining_time": "0:50:16"}
+{"current_steps": 430, "total_steps": 532, "loss": 0.5551, "lr": 5.51289072266255e-07, "epoch": 1.6172665255234062, "percentage": 80.83, "elapsed_time": "3:13:10", "remaining_time": "0:45:49"}
+{"current_steps": 440, "total_steps": 532, "loss": 0.5557, "lr": 4.5264360304473065e-07, "epoch": 1.6549047282992237, "percentage": 82.71, "elapsed_time": "3:17:44", "remaining_time": "0:41:20"}
+{"current_steps": 450, "total_steps": 532, "loss": 0.5268, "lr": 3.6283872005444087e-07, "epoch": 1.692542931075041, "percentage": 84.59, "elapsed_time": "3:22:03", "remaining_time": "0:36:49"}
+{"current_steps": 460, "total_steps": 532, "loss": 0.5353, "lr": 2.8226220522394735e-07, "epoch": 1.7301811338508586, "percentage": 86.47, "elapsed_time": "3:26:31", "remaining_time": "0:32:19"}
+{"current_steps": 470, "total_steps": 532, "loss": 0.5543, "lr": 2.1126199193144904e-07, "epoch": 1.7678193366266761, "percentage": 88.35, "elapsed_time": "3:30:56", "remaining_time": "0:27:49"}
+{"current_steps": 480, "total_steps": 532, "loss": 0.5107, "lr": 1.5014466261124128e-07, "epoch": 1.8054575394024934, "percentage": 90.23, "elapsed_time": "3:35:19", "remaining_time": "0:23:19"}
+{"current_steps": 490, "total_steps": 532, "loss": 0.5371, "lr": 9.917412491559337e-08, "epoch": 1.843095742178311, "percentage": 92.11, "elapsed_time": "3:39:49", "remaining_time": "0:18:50"}
+{"current_steps": 500, "total_steps": 532, "loss": 0.5313, "lr": 5.8570472148445633e-08, "epoch": 1.8807339449541285, "percentage": 93.98, "elapsed_time": "3:44:14", "remaining_time": "0:14:21"}
+{"current_steps": 510, "total_steps": 532, "loss": 0.5378, "lr": 2.8509032891635146e-08, "epoch": 1.9183721477299458, "percentage": 95.86, "elapsed_time": "3:48:46", "remaining_time": "0:09:52"}
+{"current_steps": 520, "total_steps": 532, "loss": 0.5291, "lr": 9.119613927399684e-09, "epoch": 1.9560103505057633, "percentage": 97.74, "elapsed_time": "3:53:15", "remaining_time": "0:05:22"}
+{"current_steps": 530, "total_steps": 532, "loss": 0.5559, "lr": 4.859397262726995e-10, "epoch": 1.9936485532815809, "percentage": 99.62, "elapsed_time": "3:57:43", "remaining_time": "0:00:53"}
+{"current_steps": 532, "total_steps": 532, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:58:29", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,414 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 532,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.037638202775817454,
+      "grad_norm": 20.371968284259324,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.5923,
+      "step": 10
+    },
+    {
+      "epoch": 0.07527640555163491,
+      "grad_norm": 0.8786546808697457,
+      "learning_rate": 1.7592592592592594e-06,
+      "loss": 0.5849,
+      "step": 20
+    },
+    {
+      "epoch": 0.11291460832745237,
+      "grad_norm": 0.6200515032845644,
+      "learning_rate": 2.6851851851851856e-06,
+      "loss": 0.5754,
+      "step": 30
+    },
+    {
+      "epoch": 0.15055281110326982,
+      "grad_norm": 0.604344938574343,
+      "learning_rate": 3.6111111111111115e-06,
+      "loss": 0.5628,
+      "step": 40
+    },
+    {
+      "epoch": 0.18819101387908727,
+      "grad_norm": 8.233110803533657,
+      "learning_rate": 4.537037037037038e-06,
+      "loss": 0.5897,
+      "step": 50
+    },
+    {
+      "epoch": 0.22582921665490474,
+      "grad_norm": 0.5824369986909103,
+      "learning_rate": 4.998650245168965e-06,
+      "loss": 0.5834,
+      "step": 60
+    },
+    {
+      "epoch": 0.26346741943072216,
+      "grad_norm": 0.5709451199777168,
+      "learning_rate": 4.987860949769804e-06,
+      "loss": 0.58,
+      "step": 70
+    },
+    {
+      "epoch": 0.30110562220653964,
+      "grad_norm": 0.557443125157301,
+      "learning_rate": 4.9663289476829e-06,
+      "loss": 0.5686,
+      "step": 80
+    },
+    {
+      "epoch": 0.3387438249823571,
+      "grad_norm": 0.49885715553958243,
+      "learning_rate": 4.934147215158732e-06,
+      "loss": 0.5584,
+      "step": 90
+    },
+    {
+      "epoch": 0.37638202775817453,
+      "grad_norm": 0.41661708295752625,
+      "learning_rate": 4.891454714510784e-06,
+      "loss": 0.5994,
+      "step": 100
+    },
+    {
+      "epoch": 0.414020230533992,
+      "grad_norm": 0.41407258641803263,
+      "learning_rate": 4.838435794069406e-06,
+      "loss": 0.5661,
+      "step": 110
+    },
+    {
+      "epoch": 0.4516584333098095,
+      "grad_norm": 0.43186345082298655,
+      "learning_rate": 4.775319392156593e-06,
+      "loss": 0.589,
+      "step": 120
+    },
+    {
+      "epoch": 0.4892966360856269,
+      "grad_norm": 0.4096882144739654,
+      "learning_rate": 4.70237804851899e-06,
+      "loss": 0.5423,
+      "step": 130
+    },
+    {
+      "epoch": 0.5269348388614443,
+      "grad_norm": 0.3998323798211624,
+      "learning_rate": 4.619926727487774e-06,
+      "loss": 0.5741,
+      "step": 140
+    },
+    {
+      "epoch": 0.5645730416372619,
+      "grad_norm": 0.42564571493679665,
+      "learning_rate": 4.528321457947091e-06,
+      "loss": 0.5942,
+      "step": 150
+    },
+    {
+      "epoch": 0.6022112444130793,
+      "grad_norm": 0.3912736147474385,
+      "learning_rate": 4.427957795983715e-06,
+      "loss": 0.5735,
+      "step": 160
+    },
+    {
+      "epoch": 0.6398494471888967,
+      "grad_norm": 0.40658685656666593,
+      "learning_rate": 4.319269116856291e-06,
+      "loss": 0.5667,
+      "step": 170
+    },
+    {
+      "epoch": 0.6774876499647142,
+      "grad_norm": 0.408062593581521,
+      "learning_rate": 4.2027247436595245e-06,
+      "loss": 0.5578,
+      "step": 180
+    },
+    {
+      "epoch": 0.7151258527405316,
+      "grad_norm": 0.47342188328224316,
+      "learning_rate": 4.078827920763835e-06,
+      "loss": 0.5784,
+      "step": 190
+    },
+    {
+      "epoch": 0.7527640555163491,
+      "grad_norm": 0.3807306896086036,
+      "learning_rate": 3.948113640781265e-06,
+      "loss": 0.571,
+      "step": 200
+    },
+    {
+      "epoch": 0.7904022582921666,
+      "grad_norm": 0.40139763329295447,
+      "learning_rate": 3.8111463344409026e-06,
+      "loss": 0.56,
+      "step": 210
+    },
+    {
+      "epoch": 0.828040461067984,
+      "grad_norm": 0.46636837900138484,
+      "learning_rate": 3.668517433349069e-06,
+      "loss": 0.5752,
+      "step": 220
+    },
+    {
+      "epoch": 0.8656786638438014,
+      "grad_norm": 0.4250007472811382,
+      "learning_rate": 3.520842816158374e-06,
+      "loss": 0.5845,
+      "step": 230
+    },
+    {
+      "epoch": 0.903316866619619,
+      "grad_norm": 0.41635021722275656,
+      "learning_rate": 3.368760149173219e-06,
+      "loss": 0.5928,
+      "step": 240
+    },
+    {
+      "epoch": 0.9409550693954364,
+      "grad_norm": 0.43894853146688345,
+      "learning_rate": 3.212926132875141e-06,
+      "loss": 0.5614,
+      "step": 250
+    },
+    {
+      "epoch": 0.9785932721712538,
+      "grad_norm": 0.42161850151896035,
+      "learning_rate": 3.054013666257638e-06,
+      "loss": 0.58,
+      "step": 260
+    },
+    {
+      "epoch": 1.015055281110327,
+      "grad_norm": 0.45211808401795345,
+      "learning_rate": 2.8927089412150176e-06,
+      "loss": 0.5852,
+      "step": 270
+    },
+    {
+      "epoch": 1.0526934838861444,
+      "grad_norm": 0.40722510696568537,
+      "learning_rate": 2.729708479531844e-06,
+      "loss": 0.532,
+      "step": 280
+    },
+    {
+      "epoch": 1.090331686661962,
+      "grad_norm": 0.3964696274251261,
+      "learning_rate": 2.5657161252674047e-06,
+      "loss": 0.5312,
+      "step": 290
+    },
+    {
+      "epoch": 1.1279698894377794,
+      "grad_norm": 0.3941081603173965,
+      "learning_rate": 2.4014400055222337e-06,
+      "loss": 0.5181,
+      "step": 300
+    },
+    {
+      "epoch": 1.1656080922135967,
+      "grad_norm": 0.43576234646890405,
+      "learning_rate": 2.2375894727102552e-06,
+      "loss": 0.5504,
+      "step": 310
+    },
+    {
+      "epoch": 1.2032462949894143,
+      "grad_norm": 0.39797299710552336,
+      "learning_rate": 2.0748720415399542e-06,
+      "loss": 0.5295,
+      "step": 320
+    },
+    {
+      "epoch": 1.2408844977652318,
+      "grad_norm": 0.3685397052283085,
+      "learning_rate": 1.913990333930858e-06,
+      "loss": 0.5276,
+      "step": 330
+    },
+    {
+      "epoch": 1.278522700541049,
+      "grad_norm": 0.385020492453289,
+      "learning_rate": 1.7556390450573213e-06,
+      "loss": 0.5329,
+      "step": 340
+    },
+    {
+      "epoch": 1.3161609033168666,
+      "grad_norm": 0.358339166503952,
+      "learning_rate": 1.600501943620384e-06,
+      "loss": 0.5282,
+      "step": 350
+    },
+    {
+      "epoch": 1.353799106092684,
+      "grad_norm": 0.3959823586817411,
+      "learning_rate": 1.4492489193006884e-06,
+      "loss": 0.5233,
+      "step": 360
+    },
+    {
+      "epoch": 1.3914373088685015,
+      "grad_norm": 0.37714168383937835,
+      "learning_rate": 1.302533090141689e-06,
+      "loss": 0.5148,
+      "step": 370
+    },
+    {
+      "epoch": 1.429075511644319,
+      "grad_norm": 0.3839744134040006,
+      "learning_rate": 1.1609879823536233e-06,
+      "loss": 0.5369,
+      "step": 380
+    },
+    {
+      "epoch": 1.4667137144201363,
+      "grad_norm": 0.4084228402216514,
+      "learning_rate": 1.0252247947159846e-06,
+      "loss": 0.5451,
+      "step": 390
+    },
+    {
+      "epoch": 1.5043519171959538,
+      "grad_norm": 0.3722310775666982,
+      "learning_rate": 8.95829759390954e-07,
+      "loss": 0.5418,
+      "step": 400
+    },
+    {
+      "epoch": 1.5419901199717714,
+      "grad_norm": 0.3723091238383956,
+      "learning_rate": 7.733616105439077e-07,
+      "loss": 0.5178,
+      "step": 410
+    },
+    {
+      "epoch": 1.5796283227475887,
+      "grad_norm": 0.36274010086702985,
+      "learning_rate": 6.58349171701651e-07,
+      "loss": 0.5241,
+      "step": 420
+    },
+    {
+      "epoch": 1.6172665255234062,
+      "grad_norm": 0.3827469898084054,
+      "learning_rate": 5.51289072266255e-07,
+      "loss": 0.5551,
+      "step": 430
+    },
+    {
+      "epoch": 1.6549047282992237,
+      "grad_norm": 0.4042469036956372,
+      "learning_rate": 4.5264360304473065e-07,
+      "loss": 0.5557,
+      "step": 440
+    },
+    {
+      "epoch": 1.692542931075041,
+      "grad_norm": 0.36511925658271227,
+      "learning_rate": 3.6283872005444087e-07,
+      "loss": 0.5268,
+      "step": 450
+    },
+    {
+      "epoch": 1.7301811338508586,
+      "grad_norm": 0.4026080916542273,
+      "learning_rate": 2.8226220522394735e-07,
+      "loss": 0.5353,
+      "step": 460
+    },
+    {
+      "epoch": 1.7678193366266761,
+      "grad_norm": 0.3791323800107557,
+      "learning_rate": 2.1126199193144904e-07,
+      "loss": 0.5543,
+      "step": 470
+    },
+    {
+      "epoch": 1.8054575394024934,
+      "grad_norm": 0.3975590953752723,
+      "learning_rate": 1.5014466261124128e-07,
+      "loss": 0.5107,
+      "step": 480
+    },
+    {
+      "epoch": 1.843095742178311,
+      "grad_norm": 0.3845716392065491,
+      "learning_rate": 9.917412491559337e-08,
+      "loss": 0.5371,
+      "step": 490
+    },
+    {
+      "epoch": 1.8807339449541285,
+      "grad_norm": 0.351629905127873,
+      "learning_rate": 5.8570472148445633e-08,
+      "loss": 0.5313,
+      "step": 500
+    },
+    {
+      "epoch": 1.9183721477299458,
+      "grad_norm": 0.3890690665902021,
+      "learning_rate": 2.8509032891635146e-08,
+      "loss": 0.5378,
+      "step": 510
+    },
+    {
+      "epoch": 1.9560103505057633,
+      "grad_norm": 0.38113169843995587,
+      "learning_rate": 9.119613927399684e-09,
+      "loss": 0.5291,
+      "step": 520
+    },
+    {
+      "epoch": 1.9936485532815809,
+      "grad_norm": 0.35623501505342836,
+      "learning_rate": 4.859397262726995e-10,
+      "loss": 0.5559,
+      "step": 530
+    },
+    {
+      "epoch": 2.0,
+      "step": 532,
+      "total_flos": 7.869097163274322e+17,
+      "train_loss": 0.5555472550983716,
+      "train_runtime": 14309.8006,
+      "train_samples_per_second": 19.012,
+      "train_steps_per_second": 0.037
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 532,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.869097163274322e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce527e95501bd56a40b8c5c07313381d56028a1df5f16007289340211929dd7e
+size 8017