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": 7.760603841246003e+17,
+    "train_loss": 0.3755328197479248,
+    "train_runtime": 13172.2209,
+    "train_samples_per_second": 29.138,
+    "train_steps_per_second": 0.057
+}

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:f7a2849c10de0bef3518883431e52401677ee6d4bce0997c8fd5bc95ec45844b
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e318dfbac30fcfef5610ffa9cddae0c6dd7de19ac255a30ca2f6bd3f704482c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b8c8cfd631f875175c5d9bf7b25523ba5a08f0d7bccb029e1f731864dadc4f
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca632ef1b95d88b3583611bd6dd74c918200073ee2f5e27391e6c5f3162385ba
+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": 7.760603841246003e+17,
+    "train_loss": 0.3755328197479248,
+    "train_runtime": 13172.2209,
+    "train_samples_per_second": 29.138,
+    "train_steps_per_second": 0.057
+}

trainer_log.jsonl

@@ -0,0 +1,76 @@
+{"current_steps": 10, "total_steps": 750, "loss": 0.4323, "lr": 6.000000000000001e-07, "epoch": 0.026680006670001668, "percentage": 1.33, "elapsed_time": "0:03:39", "remaining_time": "4:30:22"}
+{"current_steps": 20, "total_steps": 750, "loss": 0.4129, "lr": 1.2666666666666669e-06, "epoch": 0.053360013340003336, "percentage": 2.67, "elapsed_time": "0:06:31", "remaining_time": "3:58:05"}
+{"current_steps": 30, "total_steps": 750, "loss": 0.4053, "lr": 1.9333333333333336e-06, "epoch": 0.080040020010005, "percentage": 4.0, "elapsed_time": "0:09:21", "remaining_time": "3:44:39"}
+{"current_steps": 40, "total_steps": 750, "loss": 0.4119, "lr": 2.6e-06, "epoch": 0.10672002668000667, "percentage": 5.33, "elapsed_time": "0:12:13", "remaining_time": "3:36:57"}
+{"current_steps": 50, "total_steps": 750, "loss": 0.4049, "lr": 3.266666666666667e-06, "epoch": 0.13340003335000833, "percentage": 6.67, "elapsed_time": "0:15:07", "remaining_time": "3:31:49"}
+{"current_steps": 60, "total_steps": 750, "loss": 0.3997, "lr": 3.9333333333333335e-06, "epoch": 0.16008004002001, "percentage": 8.0, "elapsed_time": "0:17:58", "remaining_time": "3:26:47"}
+{"current_steps": 70, "total_steps": 750, "loss": 0.4041, "lr": 4.600000000000001e-06, "epoch": 0.18676004669001167, "percentage": 9.33, "elapsed_time": "0:20:55", "remaining_time": "3:23:20"}
+{"current_steps": 80, "total_steps": 750, "loss": 0.3989, "lr": 4.99956677884892e-06, "epoch": 0.21344005336001334, "percentage": 10.67, "elapsed_time": "0:23:50", "remaining_time": "3:19:44"}
+{"current_steps": 90, "total_steps": 750, "loss": 0.391, "lr": 4.994694765050121e-06, "epoch": 0.24012006003001501, "percentage": 12.0, "elapsed_time": "0:26:43", "remaining_time": "3:15:55"}
+{"current_steps": 100, "total_steps": 750, "loss": 0.3876, "lr": 4.984419797901491e-06, "epoch": 0.26680006670001666, "percentage": 13.33, "elapsed_time": "0:29:38", "remaining_time": "3:12:37"}
+{"current_steps": 110, "total_steps": 750, "loss": 0.3934, "lr": 4.9687641306938766e-06, "epoch": 0.29348007337001836, "percentage": 14.67, "elapsed_time": "0:32:33", "remaining_time": "3:09:22"}
+{"current_steps": 120, "total_steps": 750, "loss": 0.3924, "lr": 4.94776167011629e-06, "epoch": 0.32016008004002, "percentage": 16.0, "elapsed_time": "0:35:24", "remaining_time": "3:05:52"}
+{"current_steps": 130, "total_steps": 750, "loss": 0.3899, "lr": 4.921457902821578e-06, "epoch": 0.3468400867100217, "percentage": 17.33, "elapsed_time": "0:38:17", "remaining_time": "3:02:36"}
+{"current_steps": 140, "total_steps": 750, "loss": 0.3949, "lr": 4.889909796912454e-06, "epoch": 0.37352009338002334, "percentage": 18.67, "elapsed_time": "0:41:10", "remaining_time": "2:59:24"}
+{"current_steps": 150, "total_steps": 750, "loss": 0.3921, "lr": 4.85318567856128e-06, "epoch": 0.400200100050025, "percentage": 20.0, "elapsed_time": "0:44:03", "remaining_time": "2:56:13"}
+{"current_steps": 160, "total_steps": 750, "loss": 0.3864, "lr": 4.811365084030784e-06, "epoch": 0.4268801067200267, "percentage": 21.33, "elapsed_time": "0:47:22", "remaining_time": "2:54:42"}
+{"current_steps": 170, "total_steps": 750, "loss": 0.398, "lr": 4.764538587416233e-06, "epoch": 0.45356011339002833, "percentage": 22.67, "elapsed_time": "0:50:14", "remaining_time": "2:51:25"}
+{"current_steps": 180, "total_steps": 750, "loss": 0.3884, "lr": 4.712807604482108e-06, "epoch": 0.48024012006003003, "percentage": 24.0, "elapsed_time": "0:53:12", "remaining_time": "2:48:28"}
+{"current_steps": 190, "total_steps": 750, "loss": 0.3963, "lr": 4.656284173018144e-06, "epoch": 0.5069201267300317, "percentage": 25.33, "elapsed_time": "0:56:08", "remaining_time": "2:45:27"}
+{"current_steps": 200, "total_steps": 750, "loss": 0.3884, "lr": 4.595090710190419e-06, "epoch": 0.5336001334000333, "percentage": 26.67, "elapsed_time": "0:59:06", "remaining_time": "2:42:32"}
+{"current_steps": 210, "total_steps": 750, "loss": 0.3878, "lr": 4.529359747413038e-06, "epoch": 0.560280140070035, "percentage": 28.0, "elapsed_time": "1:01:59", "remaining_time": "2:39:25"}
+{"current_steps": 220, "total_steps": 750, "loss": 0.3967, "lr": 4.4592336433146e-06, "epoch": 0.5869601467400367, "percentage": 29.33, "elapsed_time": "1:04:51", "remaining_time": "2:36:15"}
+{"current_steps": 230, "total_steps": 750, "loss": 0.389, "lr": 4.384864275421109e-06, "epoch": 0.6136401534100383, "percentage": 30.67, "elapsed_time": "1:07:42", "remaining_time": "2:33:04"}
+{"current_steps": 240, "total_steps": 750, "loss": 0.4003, "lr": 4.30641271122307e-06, "epoch": 0.64032016008004, "percentage": 32.0, "elapsed_time": "1:10:36", "remaining_time": "2:30:02"}
+{"current_steps": 250, "total_steps": 750, "loss": 0.3947, "lr": 4.224048859339175e-06, "epoch": 0.6670001667500417, "percentage": 33.33, "elapsed_time": "1:13:27", "remaining_time": "2:26:55"}
+{"current_steps": 260, "total_steps": 750, "loss": 0.3867, "lr": 4.1379511015320625e-06, "epoch": 0.6936801734200434, "percentage": 34.67, "elapsed_time": "1:16:19", "remaining_time": "2:23:51"}
+{"current_steps": 270, "total_steps": 750, "loss": 0.3895, "lr": 4.048305906373151e-06, "epoch": 0.720360180090045, "percentage": 36.0, "elapsed_time": "1:19:11", "remaining_time": "2:20:47"}
+{"current_steps": 280, "total_steps": 750, "loss": 0.394, "lr": 3.955307425393224e-06, "epoch": 0.7470401867600467, "percentage": 37.33, "elapsed_time": "1:22:04", "remaining_time": "2:17:46"}
+{"current_steps": 290, "total_steps": 750, "loss": 0.3794, "lr": 3.859157072593459e-06, "epoch": 0.7737201934300484, "percentage": 38.67, "elapsed_time": "1:24:59", "remaining_time": "2:14:48"}
+{"current_steps": 300, "total_steps": 750, "loss": 0.3855, "lr": 3.760063088227542e-06, "epoch": 0.80040020010005, "percentage": 40.0, "elapsed_time": "1:27:55", "remaining_time": "2:11:53"}
+{"current_steps": 310, "total_steps": 750, "loss": 0.3871, "lr": 3.658240087799655e-06, "epoch": 0.8270802067700517, "percentage": 41.33, "elapsed_time": "1:31:13", "remaining_time": "2:09:29"}
+{"current_steps": 320, "total_steps": 750, "loss": 0.3927, "lr": 3.5539085972550786e-06, "epoch": 0.8537602134400534, "percentage": 42.67, "elapsed_time": "1:34:06", "remaining_time": "2:06:27"}
+{"current_steps": 330, "total_steps": 750, "loss": 0.3777, "lr": 3.4472945753701038e-06, "epoch": 0.8804402201100551, "percentage": 44.0, "elapsed_time": "1:36:58", "remaining_time": "2:03:25"}
+{"current_steps": 340, "total_steps": 750, "loss": 0.3926, "lr": 3.338628924375638e-06, "epoch": 0.9071202267800567, "percentage": 45.33, "elapsed_time": "1:39:50", "remaining_time": "2:00:24"}
+{"current_steps": 350, "total_steps": 750, "loss": 0.3919, "lr": 3.228146989874389e-06, "epoch": 0.9338002334500584, "percentage": 46.67, "elapsed_time": "1:42:43", "remaining_time": "1:57:24"}
+{"current_steps": 360, "total_steps": 750, "loss": 0.3975, "lr": 3.116088051134695e-06, "epoch": 0.9604802401200601, "percentage": 48.0, "elapsed_time": "1:45:39", "remaining_time": "1:54:27"}
+{"current_steps": 370, "total_steps": 750, "loss": 0.3869, "lr": 3.002694802864912e-06, "epoch": 0.9871602467900616, "percentage": 49.33, "elapsed_time": "1:48:32", "remaining_time": "1:51:28"}
+{"current_steps": 380, "total_steps": 750, "loss": 0.3735, "lr": 2.888212829590719e-06, "epoch": 1.0133400033350008, "percentage": 50.67, "elapsed_time": "1:51:23", "remaining_time": "1:48:28"}
+{"current_steps": 390, "total_steps": 750, "loss": 0.3597, "lr": 2.77289007377372e-06, "epoch": 1.0400200100050025, "percentage": 52.0, "elapsed_time": "1:54:16", "remaining_time": "1:45:29"}
+{"current_steps": 400, "total_steps": 750, "loss": 0.3569, "lr": 2.6569762988232838e-06, "epoch": 1.0667000166750042, "percentage": 53.33, "elapsed_time": "1:57:08", "remaining_time": "1:42:30"}
+{"current_steps": 410, "total_steps": 750, "loss": 0.3498, "lr": 2.5407225481646146e-06, "epoch": 1.0933800233450057, "percentage": 54.67, "elapsed_time": "2:00:02", "remaining_time": "1:39:33"}
+{"current_steps": 420, "total_steps": 750, "loss": 0.3523, "lr": 2.4243806015345988e-06, "epoch": 1.1200600300150074, "percentage": 56.0, "elapsed_time": "2:02:58", "remaining_time": "1:36:37"}
+{"current_steps": 430, "total_steps": 750, "loss": 0.356, "lr": 2.3082024296829538e-06, "epoch": 1.1467400366850091, "percentage": 57.33, "elapsed_time": "2:05:53", "remaining_time": "1:33:40"}
+{"current_steps": 440, "total_steps": 750, "loss": 0.3576, "lr": 2.192439648659699e-06, "epoch": 1.1734200433550108, "percentage": 58.67, "elapsed_time": "2:08:43", "remaining_time": "1:30:41"}
+{"current_steps": 450, "total_steps": 750, "loss": 0.3557, "lr": 2.0773429748708153e-06, "epoch": 1.2001000500250125, "percentage": 60.0, "elapsed_time": "2:11:39", "remaining_time": "1:27:46"}
+{"current_steps": 460, "total_steps": 750, "loss": 0.3522, "lr": 1.963161682082342e-06, "epoch": 1.2267800566950142, "percentage": 61.33, "elapsed_time": "2:14:55", "remaining_time": "1:25:03"}
+{"current_steps": 470, "total_steps": 750, "loss": 0.3525, "lr": 1.850143061548907e-06, "epoch": 1.253460063365016, "percentage": 62.67, "elapsed_time": "2:17:47", "remaining_time": "1:22:05"}
+{"current_steps": 480, "total_steps": 750, "loss": 0.3571, "lr": 1.7385318864359304e-06, "epoch": 1.2801400700350176, "percentage": 64.0, "elapsed_time": "2:20:40", "remaining_time": "1:19:07"}
+{"current_steps": 490, "total_steps": 750, "loss": 0.3599, "lr": 1.6285698816954626e-06, "epoch": 1.306820076705019, "percentage": 65.33, "elapsed_time": "2:23:35", "remaining_time": "1:16:11"}
+{"current_steps": 500, "total_steps": 750, "loss": 0.3583, "lr": 1.520495200543754e-06, "epoch": 1.3335000833750208, "percentage": 66.67, "elapsed_time": "2:26:27", "remaining_time": "1:13:13"}
+{"current_steps": 510, "total_steps": 750, "loss": 0.3704, "lr": 1.41454190867443e-06, "epoch": 1.3601800900450225, "percentage": 68.0, "elapsed_time": "2:29:21", "remaining_time": "1:10:17"}
+{"current_steps": 520, "total_steps": 750, "loss": 0.3562, "lr": 1.3109394773243117e-06, "epoch": 1.3868600967150242, "percentage": 69.33, "elapsed_time": "2:32:15", "remaining_time": "1:07:20"}
+{"current_steps": 530, "total_steps": 750, "loss": 0.3443, "lr": 1.2099122862898214e-06, "epoch": 1.413540103385026, "percentage": 70.67, "elapsed_time": "2:35:06", "remaining_time": "1:04:22"}
+{"current_steps": 540, "total_steps": 750, "loss": 0.355, "lr": 1.1116791379703032e-06, "epoch": 1.4402201100550276, "percentage": 72.0, "elapsed_time": "2:37:59", "remaining_time": "1:01:26"}
+{"current_steps": 550, "total_steps": 750, "loss": 0.3584, "lr": 1.0164527834907468e-06, "epoch": 1.466900116725029, "percentage": 73.33, "elapsed_time": "2:40:50", "remaining_time": "0:58:29"}
+{"current_steps": 560, "total_steps": 750, "loss": 0.3571, "lr": 9.244394619302338e-07, "epoch": 1.4935801233950308, "percentage": 74.67, "elapsed_time": "2:43:43", "remaining_time": "0:55:32"}
+{"current_steps": 570, "total_steps": 750, "loss": 0.363, "lr": 8.35838453654009e-07, "epoch": 1.5202601300650325, "percentage": 76.0, "elapsed_time": "2:46:35", "remaining_time": "0:52:36"}
+{"current_steps": 580, "total_steps": 750, "loss": 0.3641, "lr": 7.508416487165862e-07, "epoch": 1.5469401367350342, "percentage": 77.33, "elapsed_time": "2:49:27", "remaining_time": "0:49:40"}
+{"current_steps": 590, "total_steps": 750, "loss": 0.3571, "lr": 6.696331312706245e-07, "epoch": 1.5736201434050359, "percentage": 78.67, "elapsed_time": "2:52:20", "remaining_time": "0:46:44"}
+{"current_steps": 600, "total_steps": 750, "loss": 0.3586, "lr": 5.923887808816373e-07, "epoch": 1.6003001500750376, "percentage": 80.0, "elapsed_time": "2:55:17", "remaining_time": "0:43:49"}
+{"current_steps": 610, "total_steps": 750, "loss": 0.3617, "lr": 5.192758916120236e-07, "epoch": 1.6269801567450393, "percentage": 81.33, "elapsed_time": "2:58:39", "remaining_time": "0:41:00"}
+{"current_steps": 620, "total_steps": 750, "loss": 0.3601, "lr": 4.5045280969937847e-07, "epoch": 1.653660163415041, "percentage": 82.67, "elapsed_time": "3:01:34", "remaining_time": "0:38:04"}
+{"current_steps": 630, "total_steps": 750, "loss": 0.3511, "lr": 3.86068590613804e-07, "epoch": 1.6803401700850427, "percentage": 84.0, "elapsed_time": "3:04:29", "remaining_time": "0:35:08"}
+{"current_steps": 640, "total_steps": 750, "loss": 0.3545, "lr": 3.262626762369525e-07, "epoch": 1.7070201767550441, "percentage": 85.33, "elapsed_time": "3:07:23", "remaining_time": "0:32:12"}
+{"current_steps": 650, "total_steps": 750, "loss": 0.3549, "lr": 2.7116459286195887e-07, "epoch": 1.7337001834250458, "percentage": 86.67, "elapsed_time": "3:10:22", "remaining_time": "0:29:17"}
+{"current_steps": 660, "total_steps": 750, "loss": 0.353, "lr": 2.208936706683351e-07, "epoch": 1.7603801900950475, "percentage": 88.0, "elapsed_time": "3:13:14", "remaining_time": "0:26:21"}
+{"current_steps": 670, "total_steps": 750, "loss": 0.3605, "lr": 1.7555878527937164e-07, "epoch": 1.7870601967650492, "percentage": 89.33, "elapsed_time": "3:16:09", "remaining_time": "0:23:25"}
+{"current_steps": 680, "total_steps": 750, "loss": 0.3512, "lr": 1.352581219617824e-07, "epoch": 1.8137402034350507, "percentage": 90.67, "elapsed_time": "3:19:03", "remaining_time": "0:20:29"}
+{"current_steps": 690, "total_steps": 750, "loss": 0.3529, "lr": 1.0007896297828113e-07, "epoch": 1.8404202101050524, "percentage": 92.0, "elapsed_time": "3:21:56", "remaining_time": "0:17:33"}
+{"current_steps": 700, "total_steps": 750, "loss": 0.3495, "lr": 7.009749855363457e-08, "epoch": 1.8671002167750541, "percentage": 93.33, "elapsed_time": "3:24:45", "remaining_time": "0:14:37"}
+{"current_steps": 710, "total_steps": 750, "loss": 0.3564, "lr": 4.537866186360207e-08, "epoch": 1.8937802234450558, "percentage": 94.67, "elapsed_time": "3:27:40", "remaining_time": "0:11:41"}
+{"current_steps": 720, "total_steps": 750, "loss": 0.3613, "lr": 2.59759884041369e-08, "epoch": 1.9204602301150575, "percentage": 96.0, "elapsed_time": "3:30:31", "remaining_time": "0:08:46"}
+{"current_steps": 730, "total_steps": 750, "loss": 0.3563, "lr": 1.193150004542204e-08, "epoch": 1.9471402367850592, "percentage": 97.33, "elapsed_time": "3:33:25", "remaining_time": "0:05:50"}
+{"current_steps": 740, "total_steps": 750, "loss": 0.3648, "lr": 3.275614021857609e-09, "epoch": 1.973820243455061, "percentage": 98.67, "elapsed_time": "3:36:20", "remaining_time": "0:02:55"}
+{"current_steps": 750, "total_steps": 750, "loss": 0.3516, "lr": 2.7077055103075233e-11, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:39:08", "remaining_time": "0:00:00"}
+{"current_steps": 750, "total_steps": 750, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:39:32", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,568 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.026680006670001668,
+      "grad_norm": 15.408050169663637,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.4323,
+      "step": 10
+    },
+    {
+      "epoch": 0.053360013340003336,
+      "grad_norm": 1.189430364372762,
+      "learning_rate": 1.2666666666666669e-06,
+      "loss": 0.4129,
+      "step": 20
+    },
+    {
+      "epoch": 0.080040020010005,
+      "grad_norm": 0.7970860805702856,
+      "learning_rate": 1.9333333333333336e-06,
+      "loss": 0.4053,
+      "step": 30
+    },
+    {
+      "epoch": 0.10672002668000667,
+      "grad_norm": 0.7345760839053289,
+      "learning_rate": 2.6e-06,
+      "loss": 0.4119,
+      "step": 40
+    },
+    {
+      "epoch": 0.13340003335000833,
+      "grad_norm": 0.7663068974737514,
+      "learning_rate": 3.266666666666667e-06,
+      "loss": 0.4049,
+      "step": 50
+    },
+    {
+      "epoch": 0.16008004002001,
+      "grad_norm": 0.7780217786536092,
+      "learning_rate": 3.9333333333333335e-06,
+      "loss": 0.3997,
+      "step": 60
+    },
+    {
+      "epoch": 0.18676004669001167,
+      "grad_norm": 0.770900330729544,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.4041,
+      "step": 70
+    },
+    {
+      "epoch": 0.21344005336001334,
+      "grad_norm": 0.7609606894845664,
+      "learning_rate": 4.99956677884892e-06,
+      "loss": 0.3989,
+      "step": 80
+    },
+    {
+      "epoch": 0.24012006003001501,
+      "grad_norm": 0.627045791653071,
+      "learning_rate": 4.994694765050121e-06,
+      "loss": 0.391,
+      "step": 90
+    },
+    {
+      "epoch": 0.26680006670001666,
+      "grad_norm": 0.5547021099708215,
+      "learning_rate": 4.984419797901491e-06,
+      "loss": 0.3876,
+      "step": 100
+    },
+    {
+      "epoch": 0.29348007337001836,
+      "grad_norm": 0.49095795320167634,
+      "learning_rate": 4.9687641306938766e-06,
+      "loss": 0.3934,
+      "step": 110
+    },
+    {
+      "epoch": 0.32016008004002,
+      "grad_norm": 0.4888533119128345,
+      "learning_rate": 4.94776167011629e-06,
+      "loss": 0.3924,
+      "step": 120
+    },
+    {
+      "epoch": 0.3468400867100217,
+      "grad_norm": 0.48920665825286863,
+      "learning_rate": 4.921457902821578e-06,
+      "loss": 0.3899,
+      "step": 130
+    },
+    {
+      "epoch": 0.37352009338002334,
+      "grad_norm": 0.4252398206886706,
+      "learning_rate": 4.889909796912454e-06,
+      "loss": 0.3949,
+      "step": 140
+    },
+    {
+      "epoch": 0.400200100050025,
+      "grad_norm": 0.5021822205282466,
+      "learning_rate": 4.85318567856128e-06,
+      "loss": 0.3921,
+      "step": 150
+    },
+    {
+      "epoch": 0.4268801067200267,
+      "grad_norm": 0.47519317579474546,
+      "learning_rate": 4.811365084030784e-06,
+      "loss": 0.3864,
+      "step": 160
+    },
+    {
+      "epoch": 0.45356011339002833,
+      "grad_norm": 0.42980959620299375,
+      "learning_rate": 4.764538587416233e-06,
+      "loss": 0.398,
+      "step": 170
+    },
+    {
+      "epoch": 0.48024012006003003,
+      "grad_norm": 0.44471481113511596,
+      "learning_rate": 4.712807604482108e-06,
+      "loss": 0.3884,
+      "step": 180
+    },
+    {
+      "epoch": 0.5069201267300317,
+      "grad_norm": 0.4547322694911199,
+      "learning_rate": 4.656284173018144e-06,
+      "loss": 0.3963,
+      "step": 190
+    },
+    {
+      "epoch": 0.5336001334000333,
+      "grad_norm": 0.4100846072759138,
+      "learning_rate": 4.595090710190419e-06,
+      "loss": 0.3884,
+      "step": 200
+    },
+    {
+      "epoch": 0.560280140070035,
+      "grad_norm": 0.447074949695232,
+      "learning_rate": 4.529359747413038e-06,
+      "loss": 0.3878,
+      "step": 210
+    },
+    {
+      "epoch": 0.5869601467400367,
+      "grad_norm": 0.41962285635797336,
+      "learning_rate": 4.4592336433146e-06,
+      "loss": 0.3967,
+      "step": 220
+    },
+    {
+      "epoch": 0.6136401534100383,
+      "grad_norm": 0.46197276332118054,
+      "learning_rate": 4.384864275421109e-06,
+      "loss": 0.389,
+      "step": 230
+    },
+    {
+      "epoch": 0.64032016008004,
+      "grad_norm": 0.45490395624637364,
+      "learning_rate": 4.30641271122307e-06,
+      "loss": 0.4003,
+      "step": 240
+    },
+    {
+      "epoch": 0.6670001667500417,
+      "grad_norm": 0.47095244703700173,
+      "learning_rate": 4.224048859339175e-06,
+      "loss": 0.3947,
+      "step": 250
+    },
+    {
+      "epoch": 0.6936801734200434,
+      "grad_norm": 0.40664417599044195,
+      "learning_rate": 4.1379511015320625e-06,
+      "loss": 0.3867,
+      "step": 260
+    },
+    {
+      "epoch": 0.720360180090045,
+      "grad_norm": 0.40359453605714496,
+      "learning_rate": 4.048305906373151e-06,
+      "loss": 0.3895,
+      "step": 270
+    },
+    {
+      "epoch": 0.7470401867600467,
+      "grad_norm": 0.4327117282017482,
+      "learning_rate": 3.955307425393224e-06,
+      "loss": 0.394,
+      "step": 280
+    },
+    {
+      "epoch": 0.7737201934300484,
+      "grad_norm": 0.40475698383803405,
+      "learning_rate": 3.859157072593459e-06,
+      "loss": 0.3794,
+      "step": 290
+    },
+    {
+      "epoch": 0.80040020010005,
+      "grad_norm": 0.3948002934304265,
+      "learning_rate": 3.760063088227542e-06,
+      "loss": 0.3855,
+      "step": 300
+    },
+    {
+      "epoch": 0.8270802067700517,
+      "grad_norm": 0.43404680043745014,
+      "learning_rate": 3.658240087799655e-06,
+      "loss": 0.3871,
+      "step": 310
+    },
+    {
+      "epoch": 0.8537602134400534,
+      "grad_norm": 0.41236684855200445,
+      "learning_rate": 3.5539085972550786e-06,
+      "loss": 0.3927,
+      "step": 320
+    },
+    {
+      "epoch": 0.8804402201100551,
+      "grad_norm": 0.4139065377254078,
+      "learning_rate": 3.4472945753701038e-06,
+      "loss": 0.3777,
+      "step": 330
+    },
+    {
+      "epoch": 0.9071202267800567,
+      "grad_norm": 0.4366881293043098,
+      "learning_rate": 3.338628924375638e-06,
+      "loss": 0.3926,
+      "step": 340
+    },
+    {
+      "epoch": 0.9338002334500584,
+      "grad_norm": 0.4465717999429923,
+      "learning_rate": 3.228146989874389e-06,
+      "loss": 0.3919,
+      "step": 350
+    },
+    {
+      "epoch": 0.9604802401200601,
+      "grad_norm": 0.45689893725643393,
+      "learning_rate": 3.116088051134695e-06,
+      "loss": 0.3975,
+      "step": 360
+    },
+    {
+      "epoch": 0.9871602467900616,
+      "grad_norm": 0.414287916205558,
+      "learning_rate": 3.002694802864912e-06,
+      "loss": 0.3869,
+      "step": 370
+    },
+    {
+      "epoch": 1.0133400033350008,
+      "grad_norm": 0.5346052059521279,
+      "learning_rate": 2.888212829590719e-06,
+      "loss": 0.3735,
+      "step": 380
+    },
+    {
+      "epoch": 1.0400200100050025,
+      "grad_norm": 0.4614875637020273,
+      "learning_rate": 2.77289007377372e-06,
+      "loss": 0.3597,
+      "step": 390
+    },
+    {
+      "epoch": 1.0667000166750042,
+      "grad_norm": 0.46282269510496155,
+      "learning_rate": 2.6569762988232838e-06,
+      "loss": 0.3569,
+      "step": 400
+    },
+    {
+      "epoch": 1.0933800233450057,
+      "grad_norm": 0.39947059398821255,
+      "learning_rate": 2.5407225481646146e-06,
+      "loss": 0.3498,
+      "step": 410
+    },
+    {
+      "epoch": 1.1200600300150074,
+      "grad_norm": 0.4197635665122133,
+      "learning_rate": 2.4243806015345988e-06,
+      "loss": 0.3523,
+      "step": 420
+    },
+    {
+      "epoch": 1.1467400366850091,
+      "grad_norm": 0.42969271752133337,
+      "learning_rate": 2.3082024296829538e-06,
+      "loss": 0.356,
+      "step": 430
+    },
+    {
+      "epoch": 1.1734200433550108,
+      "grad_norm": 0.4529532051275227,
+      "learning_rate": 2.192439648659699e-06,
+      "loss": 0.3576,
+      "step": 440
+    },
+    {
+      "epoch": 1.2001000500250125,
+      "grad_norm": 0.4580509816834029,
+      "learning_rate": 2.0773429748708153e-06,
+      "loss": 0.3557,
+      "step": 450
+    },
+    {
+      "epoch": 1.2267800566950142,
+      "grad_norm": 0.4507174040351447,
+      "learning_rate": 1.963161682082342e-06,
+      "loss": 0.3522,
+      "step": 460
+    },
+    {
+      "epoch": 1.253460063365016,
+      "grad_norm": 0.41339122469566425,
+      "learning_rate": 1.850143061548907e-06,
+      "loss": 0.3525,
+      "step": 470
+    },
+    {
+      "epoch": 1.2801400700350176,
+      "grad_norm": 0.47118328744782373,
+      "learning_rate": 1.7385318864359304e-06,
+      "loss": 0.3571,
+      "step": 480
+    },
+    {
+      "epoch": 1.306820076705019,
+      "grad_norm": 0.4195648791970041,
+      "learning_rate": 1.6285698816954626e-06,
+      "loss": 0.3599,
+      "step": 490
+    },
+    {
+      "epoch": 1.3335000833750208,
+      "grad_norm": 0.4280765329620157,
+      "learning_rate": 1.520495200543754e-06,
+      "loss": 0.3583,
+      "step": 500
+    },
+    {
+      "epoch": 1.3601800900450225,
+      "grad_norm": 0.4641035391900657,
+      "learning_rate": 1.41454190867443e-06,
+      "loss": 0.3704,
+      "step": 510
+    },
+    {
+      "epoch": 1.3868600967150242,
+      "grad_norm": 0.43448940467496644,
+      "learning_rate": 1.3109394773243117e-06,
+      "loss": 0.3562,
+      "step": 520
+    },
+    {
+      "epoch": 1.413540103385026,
+      "grad_norm": 0.4230125610310456,
+      "learning_rate": 1.2099122862898214e-06,
+      "loss": 0.3443,
+      "step": 530
+    },
+    {
+      "epoch": 1.4402201100550276,
+      "grad_norm": 0.4336042974608652,
+      "learning_rate": 1.1116791379703032e-06,
+      "loss": 0.355,
+      "step": 540
+    },
+    {
+      "epoch": 1.466900116725029,
+      "grad_norm": 0.37891687734230883,
+      "learning_rate": 1.0164527834907468e-06,
+      "loss": 0.3584,
+      "step": 550
+    },
+    {
+      "epoch": 1.4935801233950308,
+      "grad_norm": 0.41541208277911973,
+      "learning_rate": 9.244394619302338e-07,
+      "loss": 0.3571,
+      "step": 560
+    },
+    {
+      "epoch": 1.5202601300650325,
+      "grad_norm": 0.3864007083807614,
+      "learning_rate": 8.35838453654009e-07,
+      "loss": 0.363,
+      "step": 570
+    },
+    {
+      "epoch": 1.5469401367350342,
+      "grad_norm": 0.4024648189632432,
+      "learning_rate": 7.508416487165862e-07,
+      "loss": 0.3641,
+      "step": 580
+    },
+    {
+      "epoch": 1.5736201434050359,
+      "grad_norm": 0.4004839035782577,
+      "learning_rate": 6.696331312706245e-07,
+      "loss": 0.3571,
+      "step": 590
+    },
+    {
+      "epoch": 1.6003001500750376,
+      "grad_norm": 0.3874058836234485,
+      "learning_rate": 5.923887808816373e-07,
+      "loss": 0.3586,
+      "step": 600
+    },
+    {
+      "epoch": 1.6269801567450393,
+      "grad_norm": 0.38890902653279813,
+      "learning_rate": 5.192758916120236e-07,
+      "loss": 0.3617,
+      "step": 610
+    },
+    {
+      "epoch": 1.653660163415041,
+      "grad_norm": 0.41063912623489557,
+      "learning_rate": 4.5045280969937847e-07,
+      "loss": 0.3601,
+      "step": 620
+    },
+    {
+      "epoch": 1.6803401700850427,
+      "grad_norm": 0.40681835500457375,
+      "learning_rate": 3.86068590613804e-07,
+      "loss": 0.3511,
+      "step": 630
+    },
+    {
+      "epoch": 1.7070201767550441,
+      "grad_norm": 0.39105172522124715,
+      "learning_rate": 3.262626762369525e-07,
+      "loss": 0.3545,
+      "step": 640
+    },
+    {
+      "epoch": 1.7337001834250458,
+      "grad_norm": 0.38073893800603853,
+      "learning_rate": 2.7116459286195887e-07,
+      "loss": 0.3549,
+      "step": 650
+    },
+    {
+      "epoch": 1.7603801900950475,
+      "grad_norm": 0.40771222152079123,
+      "learning_rate": 2.208936706683351e-07,
+      "loss": 0.353,
+      "step": 660
+    },
+    {
+      "epoch": 1.7870601967650492,
+      "grad_norm": 0.41232752076474005,
+      "learning_rate": 1.7555878527937164e-07,
+      "loss": 0.3605,
+      "step": 670
+    },
+    {
+      "epoch": 1.8137402034350507,
+      "grad_norm": 0.413617413753734,
+      "learning_rate": 1.352581219617824e-07,
+      "loss": 0.3512,
+      "step": 680
+    },
+    {
+      "epoch": 1.8404202101050524,
+      "grad_norm": 0.3852997634028503,
+      "learning_rate": 1.0007896297828113e-07,
+      "loss": 0.3529,
+      "step": 690
+    },
+    {
+      "epoch": 1.8671002167750541,
+      "grad_norm": 0.3908416859967314,
+      "learning_rate": 7.009749855363457e-08,
+      "loss": 0.3495,
+      "step": 700
+    },
+    {
+      "epoch": 1.8937802234450558,
+      "grad_norm": 0.4076995635265646,
+      "learning_rate": 4.537866186360207e-08,
+      "loss": 0.3564,
+      "step": 710
+    },
+    {
+      "epoch": 1.9204602301150575,
+      "grad_norm": 0.3683400297611235,
+      "learning_rate": 2.59759884041369e-08,
+      "loss": 0.3613,
+      "step": 720
+    },
+    {
+      "epoch": 1.9471402367850592,
+      "grad_norm": 0.44201742994199583,
+      "learning_rate": 1.193150004542204e-08,
+      "loss": 0.3563,
+      "step": 730
+    },
+    {
+      "epoch": 1.973820243455061,
+      "grad_norm": 0.41657835911706903,
+      "learning_rate": 3.275614021857609e-09,
+      "loss": 0.3648,
+      "step": 740
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.40961365401364447,
+      "learning_rate": 2.7077055103075233e-11,
+      "loss": 0.3516,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "step": 750,
+      "total_flos": 7.760603841246003e+17,
+      "train_loss": 0.3755328197479248,
+      "train_runtime": 13172.2209,
+      "train_samples_per_second": 29.138,
+      "train_steps_per_second": 0.057
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.760603841246003e+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 sha256:5e3363e8e222e21c77ac5f5a3a540532814062d43a7d75506df57a58326dd9d4
+size 8017