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 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6847133040428162,
+    "eval_runtime": 113.6409,
+    "eval_samples_per_second": 66.323,
+    "eval_steps_per_second": 2.077,
+    "total_flos": 1.7575386520355865e+19,
+    "train_loss": 0.5721450322828953,
+    "train_runtime": 14690.2311,
+    "train_samples_per_second": 13.852,
+    "train_steps_per_second": 0.216
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6847133040428162,
+    "eval_runtime": 113.6409,
+    "eval_samples_per_second": 66.323,
+    "eval_steps_per_second": 2.077
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707f9b1965750f43ea7379f9bf29914c9d91d2b67e439251d5e2167bd0eefa0a
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94947f4555df6d933a3354a8b9b7829df5fac6bd8820fcfe5e480e0a9130341
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ad3196597e8d4fdf1e4949938ffd090dd3db7538f63d201b70d91be782cb9c
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00f001e380558837a3278a7b032e3289b0705f59119e0239537316e6bcfa618a
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.7575386520355865e+19,
+    "train_loss": 0.5721450322828953,
+    "train_runtime": 14690.2311,
+    "train_samples_per_second": 13.852,
+    "train_steps_per_second": 0.216
+}

trainer_log.jsonl

@@ -0,0 +1,67 @@
+{"current_steps": 50, "total_steps": 3180, "loss": 0.7831, "lr": 2.0545073375262055e-06, "epoch": 0.047175374454534735, "percentage": 1.57, "elapsed_time": "0:03:43", "remaining_time": "3:52:52"}
+{"current_steps": 100, "total_steps": 3180, "loss": 0.6891, "lr": 4.150943396226416e-06, "epoch": 0.09435074890906947, "percentage": 3.14, "elapsed_time": "0:07:24", "remaining_time": "3:48:01"}
+{"current_steps": 150, "total_steps": 3180, "loss": 0.6727, "lr": 6.247379454926625e-06, "epoch": 0.1415261233636042, "percentage": 4.72, "elapsed_time": "0:11:06", "remaining_time": "3:44:32"}
+{"current_steps": 200, "total_steps": 3180, "loss": 0.6608, "lr": 8.343815513626834e-06, "epoch": 0.18870149781813894, "percentage": 6.29, "elapsed_time": "0:14:48", "remaining_time": "3:40:44"}
+{"current_steps": 250, "total_steps": 3180, "loss": 0.6656, "lr": 1.0440251572327045e-05, "epoch": 0.23587687227267368, "percentage": 7.86, "elapsed_time": "0:18:33", "remaining_time": "3:37:24"}
+{"current_steps": 300, "total_steps": 3180, "loss": 0.6613, "lr": 1.2536687631027256e-05, "epoch": 0.2830522467272084, "percentage": 9.43, "elapsed_time": "0:22:15", "remaining_time": "3:33:41"}
+{"current_steps": 350, "total_steps": 3180, "loss": 0.6612, "lr": 1.4633123689727464e-05, "epoch": 0.33022762118174315, "percentage": 11.01, "elapsed_time": "0:25:56", "remaining_time": "3:29:47"}
+{"current_steps": 400, "total_steps": 3180, "loss": 0.6587, "lr": 1.6729559748427675e-05, "epoch": 0.3774029956362779, "percentage": 12.58, "elapsed_time": "0:29:39", "remaining_time": "3:26:04"}
+{"current_steps": 450, "total_steps": 3180, "loss": 0.6613, "lr": 1.8825995807127882e-05, "epoch": 0.4245783700908126, "percentage": 14.15, "elapsed_time": "0:33:20", "remaining_time": "3:22:14"}
+{"current_steps": 500, "total_steps": 3180, "loss": 0.6615, "lr": 1.9996731117142877e-05, "epoch": 0.47175374454534735, "percentage": 15.72, "elapsed_time": "0:37:01", "remaining_time": "3:18:27"}
+{"current_steps": 550, "total_steps": 3180, "loss": 0.6598, "lr": 1.996500635384337e-05, "epoch": 0.518929118999882, "percentage": 17.3, "elapsed_time": "0:40:45", "remaining_time": "3:14:52"}
+{"current_steps": 600, "total_steps": 3180, "loss": 0.6586, "lr": 1.9899637947477248e-05, "epoch": 0.5661044934544168, "percentage": 18.87, "elapsed_time": "0:44:27", "remaining_time": "3:11:11"}
+{"current_steps": 650, "total_steps": 3180, "loss": 0.6602, "lr": 1.9800846593471427e-05, "epoch": 0.6132798679089515, "percentage": 20.44, "elapsed_time": "0:48:09", "remaining_time": "3:07:25"}
+{"current_steps": 700, "total_steps": 3180, "loss": 0.6577, "lr": 1.966896582909968e-05, "epoch": 0.6604552423634863, "percentage": 22.01, "elapsed_time": "0:51:54", "remaining_time": "3:03:53"}
+{"current_steps": 750, "total_steps": 3180, "loss": 0.6544, "lr": 1.9504440907401113e-05, "epoch": 0.707630616818021, "percentage": 23.58, "elapsed_time": "0:55:35", "remaining_time": "3:00:07"}
+{"current_steps": 800, "total_steps": 3180, "loss": 0.6577, "lr": 1.9307827293926344e-05, "epoch": 0.7548059912725558, "percentage": 25.16, "elapsed_time": "0:59:20", "remaining_time": "2:56:31"}
+{"current_steps": 850, "total_steps": 3180, "loss": 0.6569, "lr": 1.9079788791386468e-05, "epoch": 0.8019813657270904, "percentage": 26.73, "elapsed_time": "1:03:02", "remaining_time": "2:52:47"}
+{"current_steps": 900, "total_steps": 3180, "loss": 0.6502, "lr": 1.8821095298536435e-05, "epoch": 0.8491567401816252, "percentage": 28.3, "elapsed_time": "1:06:43", "remaining_time": "2:49:02"}
+{"current_steps": 950, "total_steps": 3180, "loss": 0.6559, "lr": 1.853262021085921e-05, "epoch": 0.8963321146361599, "percentage": 29.87, "elapsed_time": "1:10:24", "remaining_time": "2:45:16"}
+{"current_steps": 1000, "total_steps": 3180, "loss": 0.6549, "lr": 1.821533747182645e-05, "epoch": 0.9435074890906947, "percentage": 31.45, "elapsed_time": "1:14:06", "remaining_time": "2:41:33"}
+{"current_steps": 1000, "total_steps": 3180, "eval_loss": 0.6482675671577454, "epoch": 0.9435074890906947, "percentage": 31.45, "elapsed_time": "1:15:59", "remaining_time": "2:45:40"}
+{"current_steps": 1050, "total_steps": 3180, "loss": 0.6477, "lr": 1.787031828469124e-05, "epoch": 0.9906828635452294, "percentage": 33.02, "elapsed_time": "1:20:30", "remaining_time": "2:43:18"}
+{"current_steps": 1100, "total_steps": 3180, "loss": 0.5975, "lr": 1.7498727495914378e-05, "epoch": 1.0377402995636278, "percentage": 34.59, "elapsed_time": "1:24:12", "remaining_time": "2:39:14"}
+{"current_steps": 1150, "total_steps": 3180, "loss": 0.5819, "lr": 1.710181966243447e-05, "epoch": 1.0849156740181625, "percentage": 36.16, "elapsed_time": "1:27:56", "remaining_time": "2:35:13"}
+{"current_steps": 1200, "total_steps": 3180, "loss": 0.5819, "lr": 1.6680934816059403e-05, "epoch": 1.1320910484726974, "percentage": 37.74, "elapsed_time": "1:31:38", "remaining_time": "2:31:13"}
+{"current_steps": 1250, "total_steps": 3180, "loss": 0.5853, "lr": 1.623749393927938e-05, "epoch": 1.179266422927232, "percentage": 39.31, "elapsed_time": "1:35:22", "remaining_time": "2:27:15"}
+{"current_steps": 1300, "total_steps": 3180, "loss": 0.5844, "lr": 1.5772994167775986e-05, "epoch": 1.2264417973817667, "percentage": 40.88, "elapsed_time": "1:39:07", "remaining_time": "2:23:21"}
+{"current_steps": 1350, "total_steps": 3180, "loss": 0.5866, "lr": 1.5289003735824454e-05, "epoch": 1.2736171718363014, "percentage": 42.45, "elapsed_time": "1:42:48", "remaining_time": "2:19:21"}
+{"current_steps": 1400, "total_steps": 3180, "loss": 0.5819, "lr": 1.4787156681654358e-05, "epoch": 1.320792546290836, "percentage": 44.03, "elapsed_time": "1:46:31", "remaining_time": "2:15:25"}
+{"current_steps": 1450, "total_steps": 3180, "loss": 0.5849, "lr": 1.426914733064444e-05, "epoch": 1.367967920745371, "percentage": 45.6, "elapsed_time": "1:50:16", "remaining_time": "2:11:33"}
+{"current_steps": 1500, "total_steps": 3180, "loss": 0.5844, "lr": 1.373672457497717e-05, "epoch": 1.4151432951999057, "percentage": 47.17, "elapsed_time": "1:54:00", "remaining_time": "2:07:40"}
+{"current_steps": 1550, "total_steps": 3180, "loss": 0.5846, "lr": 1.3191685969066082e-05, "epoch": 1.4623186696544404, "percentage": 48.74, "elapsed_time": "1:57:41", "remaining_time": "2:03:46"}
+{"current_steps": 1600, "total_steps": 3180, "loss": 0.5829, "lr": 1.2635871660690677e-05, "epoch": 1.5094940441089753, "percentage": 50.31, "elapsed_time": "2:01:24", "remaining_time": "1:59:53"}
+{"current_steps": 1650, "total_steps": 3180, "loss": 0.5854, "lr": 1.2071158178328547e-05, "epoch": 1.55666941856351, "percentage": 51.89, "elapsed_time": "2:05:08", "remaining_time": "1:56:02"}
+{"current_steps": 1700, "total_steps": 3180, "loss": 0.5833, "lr": 1.1499452095659713e-05, "epoch": 1.6038447930180446, "percentage": 53.46, "elapsed_time": "2:08:51", "remaining_time": "1:52:10"}
+{"current_steps": 1750, "total_steps": 3180, "loss": 0.5808, "lr": 1.092268359463302e-05, "epoch": 1.6510201674725793, "percentage": 55.03, "elapsed_time": "2:12:33", "remaining_time": "1:48:19"}
+{"current_steps": 1800, "total_steps": 3180, "loss": 0.5823, "lr": 1.0342799948826788e-05, "epoch": 1.698195541927114, "percentage": 56.6, "elapsed_time": "2:16:14", "remaining_time": "1:44:27"}
+{"current_steps": 1850, "total_steps": 3180, "loss": 0.5824, "lr": 9.761758949105056e-06, "epoch": 1.7453709163816487, "percentage": 58.18, "elapsed_time": "2:19:58", "remaining_time": "1:40:37"}
+{"current_steps": 1900, "total_steps": 3180, "loss": 0.5814, "lr": 9.18152229376561e-06, "epoch": 1.7925462908361836, "percentage": 59.75, "elapsed_time": "2:23:40", "remaining_time": "1:36:47"}
+{"current_steps": 1950, "total_steps": 3180, "loss": 0.5795, "lr": 8.604048965495786e-06, "epoch": 1.8397216652907182, "percentage": 61.32, "elapsed_time": "2:27:20", "remaining_time": "1:32:56"}
+{"current_steps": 2000, "total_steps": 3180, "loss": 0.5796, "lr": 8.031288617496686e-06, "epoch": 1.8868970397452531, "percentage": 62.89, "elapsed_time": "2:31:02", "remaining_time": "1:29:07"}
+{"current_steps": 2000, "total_steps": 3180, "eval_loss": 0.6402788162231445, "epoch": 1.8868970397452531, "percentage": 62.89, "elapsed_time": "2:32:56", "remaining_time": "1:30:14"}
+{"current_steps": 2050, "total_steps": 3180, "loss": 0.5762, "lr": 7.465174991105405e-06, "epoch": 1.9340724141997878, "percentage": 64.47, "elapsed_time": "2:37:27", "remaining_time": "1:26:47"}
+{"current_steps": 2100, "total_steps": 3180, "loss": 0.5747, "lr": 6.90761938713854e-06, "epoch": 1.9812477886543225, "percentage": 66.04, "elapsed_time": "2:41:11", "remaining_time": "1:22:53"}
+{"current_steps": 2150, "total_steps": 3180, "loss": 0.5171, "lr": 6.360504212998903e-06, "epoch": 2.028305224672721, "percentage": 67.61, "elapsed_time": "2:44:53", "remaining_time": "1:18:59"}
+{"current_steps": 2200, "total_steps": 3180, "loss": 0.471, "lr": 5.825676627331614e-06, "epoch": 2.0754805991272556, "percentage": 69.18, "elapsed_time": "2:48:34", "remaining_time": "1:15:05"}
+{"current_steps": 2250, "total_steps": 3180, "loss": 0.4737, "lr": 5.304942303686238e-06, "epoch": 2.1226559735817903, "percentage": 70.75, "elapsed_time": "2:52:19", "remaining_time": "1:11:13"}
+{"current_steps": 2300, "total_steps": 3180, "loss": 0.4734, "lr": 4.800059334240049e-06, "epoch": 2.169831348036325, "percentage": 72.33, "elapsed_time": "2:55:59", "remaining_time": "1:07:20"}
+{"current_steps": 2350, "total_steps": 3180, "loss": 0.4713, "lr": 4.3127322941645385e-06, "epoch": 2.2170067224908596, "percentage": 73.9, "elapsed_time": "2:59:40", "remaining_time": "1:03:27"}
+{"current_steps": 2400, "total_steps": 3180, "loss": 0.4715, "lr": 3.844606486674862e-06, "epoch": 2.2641820969453947, "percentage": 75.47, "elapsed_time": "3:03:23", "remaining_time": "0:59:36"}
+{"current_steps": 2450, "total_steps": 3180, "loss": 0.47, "lr": 3.3972623881920296e-06, "epoch": 2.3113574713999294, "percentage": 77.04, "elapsed_time": "3:07:07", "remaining_time": "0:55:45"}
+{"current_steps": 2500, "total_steps": 3180, "loss": 0.4661, "lr": 2.9722103123719324e-06, "epoch": 2.358532845854464, "percentage": 78.62, "elapsed_time": "3:10:49", "remaining_time": "0:51:54"}
+{"current_steps": 2550, "total_steps": 3180, "loss": 0.4686, "lr": 2.5708853110164346e-06, "epoch": 2.405708220308999, "percentage": 80.19, "elapsed_time": "3:14:34", "remaining_time": "0:48:04"}
+{"current_steps": 2600, "total_steps": 3180, "loss": 0.4673, "lr": 2.194642329081902e-06, "epoch": 2.4528835947635335, "percentage": 81.76, "elapsed_time": "3:18:17", "remaining_time": "0:44:14"}
+{"current_steps": 2650, "total_steps": 3180, "loss": 0.4664, "lr": 1.844751630142797e-06, "epoch": 2.500058969218068, "percentage": 83.33, "elapsed_time": "3:22:01", "remaining_time": "0:40:24"}
+{"current_steps": 2700, "total_steps": 3180, "loss": 0.4686, "lr": 1.5223945077547253e-06, "epoch": 2.547234343672603, "percentage": 84.91, "elapsed_time": "3:25:44", "remaining_time": "0:36:34"}
+{"current_steps": 2750, "total_steps": 3180, "loss": 0.4676, "lr": 1.2286592971962152e-06, "epoch": 2.5944097181271375, "percentage": 86.48, "elapsed_time": "3:29:27", "remaining_time": "0:32:45"}
+{"current_steps": 2800, "total_steps": 3180, "loss": 0.4684, "lr": 9.645377010542212e-07, "epoch": 2.641585092581672, "percentage": 88.05, "elapsed_time": "3:33:08", "remaining_time": "0:28:55"}
+{"current_steps": 2850, "total_steps": 3180, "loss": 0.4632, "lr": 7.309214410588927e-07, "epoch": 2.6887604670362073, "percentage": 89.62, "elapsed_time": "3:36:50", "remaining_time": "0:25:06"}
+{"current_steps": 2900, "total_steps": 3180, "loss": 0.4643, "lr": 5.285992474715796e-07, "epoch": 2.735935841490742, "percentage": 91.19, "elapsed_time": "3:40:32", "remaining_time": "0:21:17"}
+{"current_steps": 2950, "total_steps": 3180, "loss": 0.465, "lr": 3.5825419619046176e-07, "epoch": 2.7831112159452767, "percentage": 92.77, "elapsed_time": "3:44:14", "remaining_time": "0:17:29"}
+{"current_steps": 3000, "total_steps": 3180, "loss": 0.4646, "lr": 2.2046140256418713e-07, "epoch": 2.8302865903998113, "percentage": 94.34, "elapsed_time": "3:47:57", "remaining_time": "0:13:40"}
+{"current_steps": 3000, "total_steps": 3180, "eval_loss": 0.6850141286849976, "epoch": 2.8302865903998113, "percentage": 94.34, "elapsed_time": "3:49:50", "remaining_time": "0:13:47"}
+{"current_steps": 3050, "total_steps": 3180, "loss": 0.4644, "lr": 1.1568607969963175e-07, "epoch": 2.877461964854346, "percentage": 95.91, "elapsed_time": "3:54:22", "remaining_time": "0:09:59"}
+{"current_steps": 3100, "total_steps": 3180, "loss": 0.4691, "lr": 4.42819678192774e-08, "epoch": 2.9246373393088807, "percentage": 97.48, "elapsed_time": "3:58:05", "remaining_time": "0:06:08"}
+{"current_steps": 3150, "total_steps": 3180, "loss": 0.4661, "lr": 6.490139970976029e-09, "epoch": 2.9718127137634154, "percentage": 99.06, "elapsed_time": "4:01:46", "remaining_time": "0:02:18"}
+{"current_steps": 3180, "total_steps": 3180, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:04:50", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,508 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 1000,
+  "global_step": 3180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.047175374454534735,
+      "grad_norm": 0.6658920049667358,
+      "learning_rate": 2.0545073375262055e-06,
+      "loss": 0.7831,
+      "step": 50
+    },
+    {
+      "epoch": 0.09435074890906947,
+      "grad_norm": 0.6541114449501038,
+      "learning_rate": 4.150943396226416e-06,
+      "loss": 0.6891,
+      "step": 100
+    },
+    {
+      "epoch": 0.1415261233636042,
+      "grad_norm": 0.64142906665802,
+      "learning_rate": 6.247379454926625e-06,
+      "loss": 0.6727,
+      "step": 150
+    },
+    {
+      "epoch": 0.18870149781813894,
+      "grad_norm": 0.645492434501648,
+      "learning_rate": 8.343815513626834e-06,
+      "loss": 0.6608,
+      "step": 200
+    },
+    {
+      "epoch": 0.23587687227267368,
+      "grad_norm": 0.6750236749649048,
+      "learning_rate": 1.0440251572327045e-05,
+      "loss": 0.6656,
+      "step": 250
+    },
+    {
+      "epoch": 0.2830522467272084,
+      "grad_norm": 0.6192681789398193,
+      "learning_rate": 1.2536687631027256e-05,
+      "loss": 0.6613,
+      "step": 300
+    },
+    {
+      "epoch": 0.33022762118174315,
+      "grad_norm": 0.6124400496482849,
+      "learning_rate": 1.4633123689727464e-05,
+      "loss": 0.6612,
+      "step": 350
+    },
+    {
+      "epoch": 0.3774029956362779,
+      "grad_norm": 0.5999819040298462,
+      "learning_rate": 1.6729559748427675e-05,
+      "loss": 0.6587,
+      "step": 400
+    },
+    {
+      "epoch": 0.4245783700908126,
+      "grad_norm": 0.6131274104118347,
+      "learning_rate": 1.8825995807127882e-05,
+      "loss": 0.6613,
+      "step": 450
+    },
+    {
+      "epoch": 0.47175374454534735,
+      "grad_norm": 0.5893041491508484,
+      "learning_rate": 1.9996731117142877e-05,
+      "loss": 0.6615,
+      "step": 500
+    },
+    {
+      "epoch": 0.518929118999882,
+      "grad_norm": 0.546073853969574,
+      "learning_rate": 1.996500635384337e-05,
+      "loss": 0.6598,
+      "step": 550
+    },
+    {
+      "epoch": 0.5661044934544168,
+      "grad_norm": 0.5713281035423279,
+      "learning_rate": 1.9899637947477248e-05,
+      "loss": 0.6586,
+      "step": 600
+    },
+    {
+      "epoch": 0.6132798679089515,
+      "grad_norm": 0.5555443167686462,
+      "learning_rate": 1.9800846593471427e-05,
+      "loss": 0.6602,
+      "step": 650
+    },
+    {
+      "epoch": 0.6604552423634863,
+      "grad_norm": 0.5415436625480652,
+      "learning_rate": 1.966896582909968e-05,
+      "loss": 0.6577,
+      "step": 700
+    },
+    {
+      "epoch": 0.707630616818021,
+      "grad_norm": 0.5836868286132812,
+      "learning_rate": 1.9504440907401113e-05,
+      "loss": 0.6544,
+      "step": 750
+    },
+    {
+      "epoch": 0.7548059912725558,
+      "grad_norm": 0.539230465888977,
+      "learning_rate": 1.9307827293926344e-05,
+      "loss": 0.6577,
+      "step": 800
+    },
+    {
+      "epoch": 0.8019813657270904,
+      "grad_norm": 0.5532299280166626,
+      "learning_rate": 1.9079788791386468e-05,
+      "loss": 0.6569,
+      "step": 850
+    },
+    {
+      "epoch": 0.8491567401816252,
+      "grad_norm": 0.5102491974830627,
+      "learning_rate": 1.8821095298536435e-05,
+      "loss": 0.6502,
+      "step": 900
+    },
+    {
+      "epoch": 0.8963321146361599,
+      "grad_norm": 0.5178349614143372,
+      "learning_rate": 1.853262021085921e-05,
+      "loss": 0.6559,
+      "step": 950
+    },
+    {
+      "epoch": 0.9435074890906947,
+      "grad_norm": 0.5248669385910034,
+      "learning_rate": 1.821533747182645e-05,
+      "loss": 0.6549,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9435074890906947,
+      "eval_loss": 0.6482675671577454,
+      "eval_runtime": 113.518,
+      "eval_samples_per_second": 66.395,
+      "eval_steps_per_second": 2.079,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9906828635452294,
+      "grad_norm": 0.5705227255821228,
+      "learning_rate": 1.787031828469124e-05,
+      "loss": 0.6477,
+      "step": 1050
+    },
+    {
+      "epoch": 1.0377402995636278,
+      "grad_norm": 0.5323419570922852,
+      "learning_rate": 1.7498727495914378e-05,
+      "loss": 0.5975,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0849156740181625,
+      "grad_norm": 0.5340594053268433,
+      "learning_rate": 1.710181966243447e-05,
+      "loss": 0.5819,
+      "step": 1150
+    },
+    {
+      "epoch": 1.1320910484726974,
+      "grad_norm": 0.49585267901420593,
+      "learning_rate": 1.6680934816059403e-05,
+      "loss": 0.5819,
+      "step": 1200
+    },
+    {
+      "epoch": 1.179266422927232,
+      "grad_norm": 0.500704824924469,
+      "learning_rate": 1.623749393927938e-05,
+      "loss": 0.5853,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2264417973817667,
+      "grad_norm": 0.49850329756736755,
+      "learning_rate": 1.5772994167775986e-05,
+      "loss": 0.5844,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2736171718363014,
+      "grad_norm": 0.5016334652900696,
+      "learning_rate": 1.5289003735824454e-05,
+      "loss": 0.5866,
+      "step": 1350
+    },
+    {
+      "epoch": 1.320792546290836,
+      "grad_norm": 0.5468031764030457,
+      "learning_rate": 1.4787156681654358e-05,
+      "loss": 0.5819,
+      "step": 1400
+    },
+    {
+      "epoch": 1.367967920745371,
+      "grad_norm": 0.5233626961708069,
+      "learning_rate": 1.426914733064444e-05,
+      "loss": 0.5849,
+      "step": 1450
+    },
+    {
+      "epoch": 1.4151432951999057,
+      "grad_norm": 0.5027523040771484,
+      "learning_rate": 1.373672457497717e-05,
+      "loss": 0.5844,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4623186696544404,
+      "grad_norm": 0.5051872730255127,
+      "learning_rate": 1.3191685969066082e-05,
+      "loss": 0.5846,
+      "step": 1550
+    },
+    {
+      "epoch": 1.5094940441089753,
+      "grad_norm": 0.5215147733688354,
+      "learning_rate": 1.2635871660690677e-05,
+      "loss": 0.5829,
+      "step": 1600
+    },
+    {
+      "epoch": 1.55666941856351,
+      "grad_norm": 0.5042491555213928,
+      "learning_rate": 1.2071158178328547e-05,
+      "loss": 0.5854,
+      "step": 1650
+    },
+    {
+      "epoch": 1.6038447930180446,
+      "grad_norm": 0.5223520994186401,
+      "learning_rate": 1.1499452095659713e-05,
+      "loss": 0.5833,
+      "step": 1700
+    },
+    {
+      "epoch": 1.6510201674725793,
+      "grad_norm": 0.4980650246143341,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 0.5808,
+      "step": 1750
+    },
+    {
+      "epoch": 1.698195541927114,
+      "grad_norm": 0.5121437907218933,
+      "learning_rate": 1.0342799948826788e-05,
+      "loss": 0.5823,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7453709163816487,
+      "grad_norm": 0.4902792274951935,
+      "learning_rate": 9.761758949105056e-06,
+      "loss": 0.5824,
+      "step": 1850
+    },
+    {
+      "epoch": 1.7925462908361836,
+      "grad_norm": 0.4946081042289734,
+      "learning_rate": 9.18152229376561e-06,
+      "loss": 0.5814,
+      "step": 1900
+    },
+    {
+      "epoch": 1.8397216652907182,
+      "grad_norm": 0.5029374361038208,
+      "learning_rate": 8.604048965495786e-06,
+      "loss": 0.5795,
+      "step": 1950
+    },
+    {
+      "epoch": 1.8868970397452531,
+      "grad_norm": 0.47936609387397766,
+      "learning_rate": 8.031288617496686e-06,
+      "loss": 0.5796,
+      "step": 2000
+    },
+    {
+      "epoch": 1.8868970397452531,
+      "eval_loss": 0.6402788162231445,
+      "eval_runtime": 113.5077,
+      "eval_samples_per_second": 66.401,
+      "eval_steps_per_second": 2.079,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9340724141997878,
+      "grad_norm": 0.5165300369262695,
+      "learning_rate": 7.465174991105405e-06,
+      "loss": 0.5762,
+      "step": 2050
+    },
+    {
+      "epoch": 1.9812477886543225,
+      "grad_norm": 0.49469050765037537,
+      "learning_rate": 6.90761938713854e-06,
+      "loss": 0.5747,
+      "step": 2100
+    },
+    {
+      "epoch": 2.028305224672721,
+      "grad_norm": 0.5297324061393738,
+      "learning_rate": 6.360504212998903e-06,
+      "loss": 0.5171,
+      "step": 2150
+    },
+    {
+      "epoch": 2.0754805991272556,
+      "grad_norm": 0.5692960023880005,
+      "learning_rate": 5.825676627331614e-06,
+      "loss": 0.471,
+      "step": 2200
+    },
+    {
+      "epoch": 2.1226559735817903,
+      "grad_norm": 0.5705838799476624,
+      "learning_rate": 5.304942303686238e-06,
+      "loss": 0.4737,
+      "step": 2250
+    },
+    {
+      "epoch": 2.169831348036325,
+      "grad_norm": 0.5800350308418274,
+      "learning_rate": 4.800059334240049e-06,
+      "loss": 0.4734,
+      "step": 2300
+    },
+    {
+      "epoch": 2.2170067224908596,
+      "grad_norm": 0.5653440952301025,
+      "learning_rate": 4.3127322941645385e-06,
+      "loss": 0.4713,
+      "step": 2350
+    },
+    {
+      "epoch": 2.2641820969453947,
+      "grad_norm": 0.5822903513908386,
+      "learning_rate": 3.844606486674862e-06,
+      "loss": 0.4715,
+      "step": 2400
+    },
+    {
+      "epoch": 2.3113574713999294,
+      "grad_norm": 0.599399209022522,
+      "learning_rate": 3.3972623881920296e-06,
+      "loss": 0.47,
+      "step": 2450
+    },
+    {
+      "epoch": 2.358532845854464,
+      "grad_norm": 0.5810734033584595,
+      "learning_rate": 2.9722103123719324e-06,
+      "loss": 0.4661,
+      "step": 2500
+    },
+    {
+      "epoch": 2.405708220308999,
+      "grad_norm": 0.5994310975074768,
+      "learning_rate": 2.5708853110164346e-06,
+      "loss": 0.4686,
+      "step": 2550
+    },
+    {
+      "epoch": 2.4528835947635335,
+      "grad_norm": 0.577089786529541,
+      "learning_rate": 2.194642329081902e-06,
+      "loss": 0.4673,
+      "step": 2600
+    },
+    {
+      "epoch": 2.500058969218068,
+      "grad_norm": 0.578800618648529,
+      "learning_rate": 1.844751630142797e-06,
+      "loss": 0.4664,
+      "step": 2650
+    },
+    {
+      "epoch": 2.547234343672603,
+      "grad_norm": 0.5981403589248657,
+      "learning_rate": 1.5223945077547253e-06,
+      "loss": 0.4686,
+      "step": 2700
+    },
+    {
+      "epoch": 2.5944097181271375,
+      "grad_norm": 0.6022927165031433,
+      "learning_rate": 1.2286592971962152e-06,
+      "loss": 0.4676,
+      "step": 2750
+    },
+    {
+      "epoch": 2.641585092581672,
+      "grad_norm": 0.5744144916534424,
+      "learning_rate": 9.645377010542212e-07,
+      "loss": 0.4684,
+      "step": 2800
+    },
+    {
+      "epoch": 2.6887604670362073,
+      "grad_norm": 0.5747597813606262,
+      "learning_rate": 7.309214410588927e-07,
+      "loss": 0.4632,
+      "step": 2850
+    },
+    {
+      "epoch": 2.735935841490742,
+      "grad_norm": 0.5752475261688232,
+      "learning_rate": 5.285992474715796e-07,
+      "loss": 0.4643,
+      "step": 2900
+    },
+    {
+      "epoch": 2.7831112159452767,
+      "grad_norm": 0.5861772894859314,
+      "learning_rate": 3.5825419619046176e-07,
+      "loss": 0.465,
+      "step": 2950
+    },
+    {
+      "epoch": 2.8302865903998113,
+      "grad_norm": 0.5940195918083191,
+      "learning_rate": 2.2046140256418713e-07,
+      "loss": 0.4646,
+      "step": 3000
+    },
+    {
+      "epoch": 2.8302865903998113,
+      "eval_loss": 0.6850141286849976,
+      "eval_runtime": 113.5772,
+      "eval_samples_per_second": 66.36,
+      "eval_steps_per_second": 2.078,
+      "step": 3000
+    },
+    {
+      "epoch": 2.877461964854346,
+      "grad_norm": 0.5916756987571716,
+      "learning_rate": 1.1568607969963175e-07,
+      "loss": 0.4644,
+      "step": 3050
+    },
+    {
+      "epoch": 2.9246373393088807,
+      "grad_norm": 0.5982924103736877,
+      "learning_rate": 4.42819678192774e-08,
+      "loss": 0.4691,
+      "step": 3100
+    },
+    {
+      "epoch": 2.9718127137634154,
+      "grad_norm": 0.5770459175109863,
+      "learning_rate": 6.490139970976029e-09,
+      "loss": 0.4661,
+      "step": 3150
+    },
+    {
+      "epoch": 3.0,
+      "step": 3180,
+      "total_flos": 1.7575386520355865e+19,
+      "train_loss": 0.5721450322828953,
+      "train_runtime": 14690.2311,
+      "train_samples_per_second": 13.852,
+      "train_steps_per_second": 0.216
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7575386520355865e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8343547da8e2788587a7f3cdc36e4b161d7678f66824e6b74ff964d2d82fc7
+size 7544