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
+tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/tokenizer.json filter=lfs diff=lfs merge=lfs -text

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/chat_template.jinja

@@ -0,0 +1,117 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+            {{- '\n' + message.content | trim + '\n' }}
+        {%- 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<function=' + tool_call.name + '>\n' }}
+            {%- if tool_call.arguments is defined %}
+                {%- for args_name, args_value in tool_call.arguments|items %}
+                    {{- '<parameter=' + args_name + '>\n' }}
+                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                    {{- args_value }}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+            {%- endif %}
+            {{- '</function>\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42071fa79270c34581a4f3efe7abc6c665584ec55a47afdfef22f6033a5a90c
+size 4997184968

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faab5a0cc438312b08fff8737126bf6323a7dfaabdc6944347f3ebd816eaa207
+size 4997741608

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da772eafc553cc5aad740132b4eda49b95539b8f801f410d1ece6c2de5a9dd7
+size 4997742208

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac09e6564051a3d470c3cbada69ebdf3fb747f09ec1da4f3f872e03204720a4
+size 4997743184

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57f31a4e0ddf0564cead28f56e21104188015683f08b0c61571b58716db34a9
+size 4997743184

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c67e2736b77f1002f0e9f0ac1bd89780bf3d9293bf89c0f71c975f90c2cfa82
+size 4997743184

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46586ba6e25b130044a764380e1bb5b5c60695206aa69ed61e1de866722de047
+size 4997743184

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e0482236fa17140accddd2ab40fde7e45397eddfb1e39d33f42cf46cad7214
+size 4997743184

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911275d608d227732cd651000bf653e03c3a082b8fa91626f4f9162cef08e4ad
+size 4997743184

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510e56d133139b8c366282180978a990b2fd4125c3859792ef6dd22feeb09427
+size 4997743184

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982a9d051766d10fa3dcf01ed161e373c9731686fdf361ae288a60f2e0bccd02
+size 4997743184

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72311984fefcc1f23037193f9025a224e91f017afd3fb02a020bfd21cae39fd
+size 4997743184

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132292243eb4f87b1ef2a17f0674a12f80eb9d80e0512d7bf32f7b6915712818
+size 1094220288

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/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
+  }
+}

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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": 1048576,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/trainer_state.json

@@ -0,0 +1,517 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04357298474945534,
+      "grad_norm": 0.4522840399548457,
+      "learning_rate": 1.9999576858841395e-05,
+      "loss": 0.2493,
+      "step": 10
+    },
+    {
+      "epoch": 0.08714596949891068,
+      "grad_norm": 0.31348343047347144,
+      "learning_rate": 1.9984770677968e-05,
+      "loss": 0.1812,
+      "step": 20
+    },
+    {
+      "epoch": 0.13071895424836602,
+      "grad_norm": 0.8766949036476201,
+      "learning_rate": 1.9948843235232534e-05,
+      "loss": 0.1639,
+      "step": 30
+    },
+    {
+      "epoch": 0.17429193899782136,
+      "grad_norm": 0.3632838517168123,
+      "learning_rate": 1.989187052966899e-05,
+      "loss": 0.1609,
+      "step": 40
+    },
+    {
+      "epoch": 0.2178649237472767,
+      "grad_norm": 0.32973551701927994,
+      "learning_rate": 1.9813973078360024e-05,
+      "loss": 0.1566,
+      "step": 50
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.27091995274763747,
+      "learning_rate": 1.9715315661501454e-05,
+      "loss": 0.1463,
+      "step": 60
+    },
+    {
+      "epoch": 0.30501089324618735,
+      "grad_norm": 0.45720610991030536,
+      "learning_rate": 1.9596106973834833e-05,
+      "loss": 0.1495,
+      "step": 70
+    },
+    {
+      "epoch": 0.3485838779956427,
+      "grad_norm": 0.26457788075285904,
+      "learning_rate": 1.9456599183185508e-05,
+      "loss": 0.1444,
+      "step": 80
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.3448114843828686,
+      "learning_rate": 1.9297087397039985e-05,
+      "loss": 0.1572,
+      "step": 90
+    },
+    {
+      "epoch": 0.4357298474945534,
+      "grad_norm": 1.0941637231338552,
+      "learning_rate": 1.9117909038290975e-05,
+      "loss": 0.1413,
+      "step": 100
+    },
+    {
+      "epoch": 0.4793028322440087,
+      "grad_norm": 0.289830295894563,
+      "learning_rate": 1.891944313147066e-05,
+      "loss": 0.155,
+      "step": 110
+    },
+    {
+      "epoch": 0.5228758169934641,
+      "grad_norm": 0.5591093067329476,
+      "learning_rate": 1.870210950098201e-05,
+      "loss": 0.1597,
+      "step": 120
+    },
+    {
+      "epoch": 0.5664488017429193,
+      "grad_norm": 0.23940605559209358,
+      "learning_rate": 1.8466367883024187e-05,
+      "loss": 0.146,
+      "step": 130
+    },
+    {
+      "epoch": 0.6100217864923747,
+      "grad_norm": 0.2794052204310604,
+      "learning_rate": 1.8212716953090627e-05,
+      "loss": 0.1385,
+      "step": 140
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 0.2804030374661795,
+      "learning_rate": 1.7941693271096966e-05,
+      "loss": 0.1326,
+      "step": 150
+    },
+    {
+      "epoch": 0.6971677559912854,
+      "grad_norm": 0.22120226387823702,
+      "learning_rate": 1.765387014637027e-05,
+      "loss": 0.1457,
+      "step": 160
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.2547349852942046,
+      "learning_rate": 1.734985642490043e-05,
+      "loss": 0.1395,
+      "step": 170
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.21471333351383282,
+      "learning_rate": 1.703029520141921e-05,
+      "loss": 0.145,
+      "step": 180
+    },
+    {
+      "epoch": 0.8278867102396514,
+      "grad_norm": 0.28985151300975615,
+      "learning_rate": 1.669586245903125e-05,
+      "loss": 0.1385,
+      "step": 190
+    },
+    {
+      "epoch": 0.8714596949891068,
+      "grad_norm": 0.43244627797081386,
+      "learning_rate": 1.634726563927478e-05,
+      "loss": 0.1397,
+      "step": 200
+    },
+    {
+      "epoch": 0.9150326797385621,
+      "grad_norm": 0.24233023411435914,
+      "learning_rate": 1.5985242145636753e-05,
+      "loss": 0.1358,
+      "step": 210
+    },
+    {
+      "epoch": 0.9586056644880174,
+      "grad_norm": 0.24312594283184605,
+      "learning_rate": 1.561055778368807e-05,
+      "loss": 0.1276,
+      "step": 220
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5332025099253912,
+      "learning_rate": 1.5224005141138509e-05,
+      "loss": 0.1308,
+      "step": 230
+    },
+    {
+      "epoch": 1.0435729847494553,
+      "grad_norm": 0.3200924282076549,
+      "learning_rate": 1.4826401911238131e-05,
+      "loss": 0.1033,
+      "step": 240
+    },
+    {
+      "epoch": 1.0871459694989107,
+      "grad_norm": 0.2279580530320654,
+      "learning_rate": 1.4418589163071721e-05,
+      "loss": 0.1004,
+      "step": 250
+    },
+    {
+      "epoch": 1.130718954248366,
+      "grad_norm": 0.2140301888282749,
+      "learning_rate": 1.4001429562405227e-05,
+      "loss": 0.0943,
+      "step": 260
+    },
+    {
+      "epoch": 1.1742919389978215,
+      "grad_norm": 0.1796537937005776,
+      "learning_rate": 1.35758055468477e-05,
+      "loss": 0.1048,
+      "step": 270
+    },
+    {
+      "epoch": 1.2178649237472767,
+      "grad_norm": 0.3243667837085952,
+      "learning_rate": 1.31426174591889e-05,
+      "loss": 0.0915,
+      "step": 280
+    },
+    {
+      "epoch": 1.261437908496732,
+      "grad_norm": 0.2068443670823198,
+      "learning_rate": 1.2702781642861252e-05,
+      "loss": 0.1009,
+      "step": 290
+    },
+    {
+      "epoch": 1.3050108932461875,
+      "grad_norm": 0.21002724360752945,
+      "learning_rate": 1.2257228503554834e-05,
+      "loss": 0.0948,
+      "step": 300
+    },
+    {
+      "epoch": 1.3485838779956427,
+      "grad_norm": 0.35478604633994054,
+      "learning_rate": 1.180690054108585e-05,
+      "loss": 0.0934,
+      "step": 310
+    },
+    {
+      "epoch": 1.392156862745098,
+      "grad_norm": 0.2476253633920981,
+      "learning_rate": 1.1352750355681771e-05,
+      "loss": 0.0937,
+      "step": 320
+    },
+    {
+      "epoch": 1.4357298474945535,
+      "grad_norm": 0.22101664790660844,
+      "learning_rate": 1.0895738632900637e-05,
+      "loss": 0.094,
+      "step": 330
+    },
+    {
+      "epoch": 1.4793028322440087,
+      "grad_norm": 0.22393084621734768,
+      "learning_rate": 1.0436832111447034e-05,
+      "loss": 0.0974,
+      "step": 340
+    },
+    {
+      "epoch": 1.522875816993464,
+      "grad_norm": 0.24292744689588497,
+      "learning_rate": 9.977001538183615e-06,
+      "loss": 0.091,
+      "step": 350
+    },
+    {
+      "epoch": 1.5664488017429194,
+      "grad_norm": 0.215865488961116,
+      "learning_rate": 9.517219614663896e-06,
+      "loss": 0.0975,
+      "step": 360
+    },
+    {
+      "epoch": 1.6100217864923747,
+      "grad_norm": 0.21826513206075018,
+      "learning_rate": 9.058458939530295e-06,
+      "loss": 0.101,
+      "step": 370
+    },
+    {
+      "epoch": 1.65359477124183,
+      "grad_norm": 0.20812205754913463,
+      "learning_rate": 8.601689951129757e-06,
+      "loss": 0.1017,
+      "step": 380
+    },
+    {
+      "epoch": 1.6971677559912854,
+      "grad_norm": 0.2488567524669264,
+      "learning_rate": 8.147878874699273e-06,
+      "loss": 0.0913,
+      "step": 390
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 0.2263021812475993,
+      "learning_rate": 7.697985678463476e-06,
+      "loss": 0.095,
+      "step": 400
+    },
+    {
+      "epoch": 1.784313725490196,
+      "grad_norm": 0.24714280512146383,
+      "learning_rate": 7.25296204296809e-06,
+      "loss": 0.0995,
+      "step": 410
+    },
+    {
+      "epoch": 1.8278867102396514,
+      "grad_norm": 0.23848952412826824,
+      "learning_rate": 6.813749347944625e-06,
+      "loss": 0.0948,
+      "step": 420
+    },
+    {
+      "epoch": 1.871459694989107,
+      "grad_norm": 0.194495160715168,
+      "learning_rate": 6.381276680964947e-06,
+      "loss": 0.0939,
+      "step": 430
+    },
+    {
+      "epoch": 1.915032679738562,
+      "grad_norm": 0.23061250189724297,
+      "learning_rate": 5.956458872097966e-06,
+      "loss": 0.0959,
+      "step": 440
+    },
+    {
+      "epoch": 1.9586056644880174,
+      "grad_norm": 0.2124542355694748,
+      "learning_rate": 5.540194558725973e-06,
+      "loss": 0.0921,
+      "step": 450
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.25573420774185224,
+      "learning_rate": 5.133364284614077e-06,
+      "loss": 0.0933,
+      "step": 460
+    },
+    {
+      "epoch": 2.0435729847494555,
+      "grad_norm": 0.25085911741930494,
+      "learning_rate": 4.7368286372539775e-06,
+      "loss": 0.0633,
+      "step": 470
+    },
+    {
+      "epoch": 2.0871459694989105,
+      "grad_norm": 0.2216539856845599,
+      "learning_rate": 4.351426427422165e-06,
+      "loss": 0.065,
+      "step": 480
+    },
+    {
+      "epoch": 2.130718954248366,
+      "grad_norm": 0.2381697113244057,
+      "learning_rate": 3.977972914803487e-06,
+      "loss": 0.0688,
+      "step": 490
+    },
+    {
+      "epoch": 2.1742919389978215,
+      "grad_norm": 0.21829646940986236,
+      "learning_rate": 3.617258083433396e-06,
+      "loss": 0.0605,
+      "step": 500
+    },
+    {
+      "epoch": 2.2178649237472765,
+      "grad_norm": 0.21760172588593787,
+      "learning_rate": 3.2700449706070536e-06,
+      "loss": 0.0615,
+      "step": 510
+    },
+    {
+      "epoch": 2.261437908496732,
+      "grad_norm": 0.25853702388486266,
+      "learning_rate": 2.937068052790112e-06,
+      "loss": 0.0585,
+      "step": 520
+    },
+    {
+      "epoch": 2.3050108932461875,
+      "grad_norm": 0.19396514478592783,
+      "learning_rate": 2.6190316919456184e-06,
+      "loss": 0.0591,
+      "step": 530
+    },
+    {
+      "epoch": 2.348583877995643,
+      "grad_norm": 0.2809981133346923,
+      "learning_rate": 2.3166086455635216e-06,
+      "loss": 0.0637,
+      "step": 540
+    },
+    {
+      "epoch": 2.392156862745098,
+      "grad_norm": 0.18574598022490096,
+      "learning_rate": 2.030438643544663e-06,
+      "loss": 0.0593,
+      "step": 550
+    },
+    {
+      "epoch": 2.4357298474945535,
+      "grad_norm": 0.19530609934506238,
+      "learning_rate": 1.7611270349495923e-06,
+      "loss": 0.0579,
+      "step": 560
+    },
+    {
+      "epoch": 2.4793028322440085,
+      "grad_norm": 0.2015667518618375,
+      "learning_rate": 1.5092435074748145e-06,
+      "loss": 0.0572,
+      "step": 570
+    },
+    {
+      "epoch": 2.522875816993464,
+      "grad_norm": 0.17466640899508173,
+      "learning_rate": 1.2753208823652142e-06,
+      "loss": 0.0567,
+      "step": 580
+    },
+    {
+      "epoch": 2.5664488017429194,
+      "grad_norm": 0.2409392834540486,
+      "learning_rate": 1.0598539873118552e-06,
+      "loss": 0.0647,
+      "step": 590
+    },
+    {
+      "epoch": 2.610021786492375,
+      "grad_norm": 0.20914710167564862,
+      "learning_rate": 8.632986097193574e-07,
+      "loss": 0.0619,
+      "step": 600
+    },
+    {
+      "epoch": 2.65359477124183,
+      "grad_norm": 0.22375308170452685,
+      "learning_rate": 6.860705325570493e-07,
+      "loss": 0.06,
+      "step": 610
+    },
+    {
+      "epoch": 2.6971677559912854,
+      "grad_norm": 0.23707517838111952,
+      "learning_rate": 5.285446548334072e-07,
+      "loss": 0.0622,
+      "step": 620
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "grad_norm": 0.18457475424451614,
+      "learning_rate": 3.9105419855430146e-07,
+      "loss": 0.062,
+      "step": 630
+    },
+    {
+      "epoch": 2.784313725490196,
+      "grad_norm": 0.21944929540405267,
+      "learning_rate": 2.738900038425796e-07,
+      "loss": 0.0597,
+      "step": 640
+    },
+    {
+      "epoch": 2.8278867102396514,
+      "grad_norm": 0.1961364495316805,
+      "learning_rate": 1.7729991371008504e-07,
+      "loss": 0.0567,
+      "step": 650
+    },
+    {
+      "epoch": 2.871459694989107,
+      "grad_norm": 0.23872305881225686,
+      "learning_rate": 1.0148824978349791e-07,
+      "loss": 0.066,
+      "step": 660
+    },
+    {
+      "epoch": 2.915032679738562,
+      "grad_norm": 0.2071017854751512,
+      "learning_rate": 4.6615380093055774e-08,
+      "loss": 0.0674,
+      "step": 670
+    },
+    {
+      "epoch": 2.9586056644880174,
+      "grad_norm": 0.2407437007471865,
+      "learning_rate": 1.2797379838402901e-08,
+      "loss": 0.0601,
+      "step": 680
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.34886410381128535,
+      "learning_rate": 1.0578584918374824e-10,
+      "loss": 0.0666,
+      "step": 690
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.613058851201352e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

tmp/bytedance/qwen3_coder_30b_a3b-sft-step690/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc386d136ddc2deaac86cb8533aa529ca4933fc26556ae5d3671fd510fe1aa83
+size 8273