初始化项目，由ModelHub XC社区提供模型

Model: edbeeching/Qwen3-0.6B-SFT-Eval-Smoke Source: Original Platform
2026-07-12 04:04:09 +08:00
commit 7facb2f25e
13 changed files with 365 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,59 @@
+---
+base_model: Qwen/Qwen3-0.6B
+library_name: transformers
+model_name: Qwen3-0.6B-SFT-Eval-Smoke
+tags:
+- generated_from_trainer
+- trl
+- sft
+- trl-internal
+licence: license
+---
+
+# Model Card for Qwen3-0.6B-SFT-Eval-Smoke
+
+This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="edbeeching/Qwen3-0.6B-SFT-Eval-Smoke", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 1.7.0.dev0
+- Transformers: 5.5.4
+- Pytorch: 2.10.0
+- Datasets: 5.0.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```
--- a/all_results.json
+++ b/all_results.json
@@ -0,0 +1,9 @@
+{
+    "epoch": 0.008849557522123894,
+    "total_flos": 21649856397312.0,
+    "train_loss": 1.0641121864318848,
+    "train_runtime": 10.9027,
+    "train_samples": 900,
+    "train_samples_per_second": 0.734,
+    "train_steps_per_second": 0.092
+}
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.5.4"
+}
--- a/inspect_eval_jobs.jsonl
+++ b/inspect_eval_jobs.jsonl
@@ -0,0 +1 @@
+{"benchmark": "gsm8k_128", "benchmark_config": {"limit": 128, "max_connections": 128, "max_tokens": 30000, "model_args": ["data_parallel_size=8", "tensor_parallel_size=1", "max_model_len=32768"], "task": "inspect_evals/gsm8k"}, "command": ["sbatch", "--parsable", "--job-name", "inspect-gsm8k_128-edbeeching-Qwen3-0.6B-SFT-Eval-Smoke-qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "--chdir", "/fsx/edward/work/carbon-meta/trl-internal-pr167", "--output", "/scratch/edward/22269378/output/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256/inspect-evals/gsm8k_128/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001/slurm-%j.out", "--error", "/scratch/edward/22269378/output/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256/inspect-evals/gsm8k_128/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001/slurm-%j.err", "/fsx/edward/work/carbon-meta/trl-internal-pr167/dev/slurm/eval_inspect.slurm", "--task", "inspect_evals/gsm8k", "--model", "edbeeching/Qwen3-0.6B-SFT-Eval-Smoke", "--log-dir", "hf://buckets/edbeeching/inspect-bucket/trl-internal/inspect-evals/qwen3-0.6b-smoke/reasoning-parser/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256/gsm8k_128/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "--limit", "128", "--max-connections", "128", "--max-tokens", "30000", "--model-arg", "data_parallel_size=8", "--model-arg", "tensor_parallel_size=1", "--model-arg", "max_model_len=32768", "--model-arg", "revision=qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "--model-arg", "reasoning_parser=qwen3"], "created_at": "2026-06-18T07:35:54.554218+00:00", "job_id": "22269380", "log_dir": "hf://buckets/edbeeching/inspect-bucket/trl-internal/inspect-evals/qwen3-0.6b-smoke/reasoning-parser/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256/gsm8k_128/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "model": "edbeeching/Qwen3-0.6B-SFT-Eval-Smoke", "model_revision": "qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "reasoning_parser": "qwen3", "slurm_log_dir": "/scratch/edward/22269378/output/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256/inspect-evals/gsm8k_128/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "status": "submitted", "stderr": "", "stdout": "22269380", "task": "inspect_evals/gsm8k"}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c6471fedf92223e6bd28ac296e720f1ab91cecb531bc91c7cfe03b52daff98
+size 1192135096
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,9 @@
+{
+    "epoch": 0.008849557522123894,
+    "total_flos": 21649856397312.0,
+    "train_loss": 1.0641121864318848,
+    "train_runtime": 10.9027,
+    "train_samples": 900,
+    "train_samples_per_second": 0.734,
+    "train_steps_per_second": 0.092
+}
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,52 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.008849557522123894,
+  "eval_steps": 10,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008849557522123894,
+      "grad_norm": 8.375,
+      "learning_rate": 0.0,
+      "loss": 1.0641121864318848,
+      "mean_token_accuracy": 0.730694055557251,
+      "num_tokens": 8192.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.008849557522123894,
+      "step": 1,
+      "total_flos": 21649856397312.0,
+      "train_loss": 1.0641121864318848,
+      "train_runtime": 10.9027,
+      "train_samples_per_second": 0.734,
+      "train_steps_per_second": 0.092
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 21649856397312.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8c07d583399a249350892b1e7bdc4638224e67ddd4d541eb91c23cbc2708d7
+size 10769
				`@@ -0,0 +1 @@`
				{"benchmark": "gsm8k_128", "benchmark_config": {"limit": 128, "max_connections": 128, "max_tokens": 30000, "model_args": ["data_parallel_size=8", "tensor_parallel_size=1", "max_model_len=32768"], "task": "inspect_evals/gsm8k"}, "command": ["sbatch", "--parsable", "--job-name", "inspect-gsm8k_128-edbeeching-Qwen3-0.6B-SFT-Eval-Smoke-qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "--chdir", "/fsx/edward/work/carbon-meta/trl-internal-pr167", "--output", "/scratch/edward/22269378/output/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256/inspect-evals/gsm8k_128/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001/slurm-%j.out", "--error", "/scratch/edward/22269378/output/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256/inspect-evals/gsm8k_128/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001/slurm-%j.err", "/fsx/edward/work/carbon-meta/trl-internal-pr167/dev/slurm/eval_inspect.slurm", "--task", "inspect_evals/gsm8k", "--model", "edbeeching/Qwen3-0.6B-SFT-Eval-Smoke", "--log-dir", "hf://buckets/edbeeching/inspect-bucket/trl-internal/inspect-evals/qwen3-0.6b-smoke/reasoning-parser/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256/gsm8k_128/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "--limit", "128", "--max-connections", "128", "--max-tokens", "30000", "--model-arg", "data_parallel_size=8", "--model-arg", "tensor_parallel_size=1", "--model-arg", "max_model_len=32768", "--model-arg", "revision=qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "--model-arg", "reasoning_parser=qwen3"], "created_at": "2026-06-18T07:35:54.554218+00:00", "job_id": "22269380", "log_dir": "hf://buckets/edbeeching/inspect-bucket/trl-internal/inspect-evals/qwen3-0.6b-smoke/reasoning-parser/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256/gsm8k_128/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "model": "edbeeching/Qwen3-0.6B-SFT-Eval-Smoke", "model_revision": "qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "reasoning_parser": "qwen3", "slurm_log_dir": "/scratch/edward/22269378/output/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256/inspect-evals/gsm8k_128/qwen3-0_6b-sft-reasoning-parser-smoke-20260618-073256-step-000000001", "status": "submitted", "stderr": "", "stdout": "22269380", "task": "inspect_evals/gsm8k"}