Model save

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+base_model: Qwen/Qwen2.5-0.5B
 library_name: transformers
 model_name: Qwen-2.5-7B-Simple-RL
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for Qwen-2.5-7B-Simple-RL
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -35,7 +35,7 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
 ### Framework versions
 
 - TRL: 0.16.0.dev0
-- Transformers: 4.49.0
+- Transformers: 4.47.1
 - Pytorch: 2.5.1
 - Datasets: 3.3.0
 - Tokenizers: 0.21.0

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 49.2958,
+    "train_runtime": 29.2169,
     "train_samples": 7500,
-    "train_samples_per_second": 0.325,
-    "train_steps_per_second": 0.02
+    "train_samples_per_second": 0.548,
+    "train_steps_per_second": 0.034
 }

config.json

@@ -1,6 +1,5 @@
 {
-  "_attn_implementation_autoset": true,
-  "_name_or_path": "Qwen/Qwen2.5-Math-7B",
+  "_name_or_path": "Qwen/Qwen2.5-0.5B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -8,24 +7,24 @@
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "hidden_act": "silu",
-  "hidden_size": 3584,
+  "hidden_size": 896,
   "initializer_range": 0.02,
-  "intermediate_size": 18944,
-  "max_position_embeddings": 4096,
-  "max_window_layers": 28,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
   "model_type": "qwen2",
-  "num_attention_heads": 28,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 4,
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000,
-  "sliding_window": 4096,
-  "tie_word_embeddings": false,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0",
-  "use_cache": true,
+  "transformers_version": "4.47.1",
+  "use_cache": false,
   "use_mrope": false,
   "use_sliding_window": false,
-  "vocab_size": 152064
+  "vocab_size": 151936
 }

generation_config.json

@@ -2,5 +2,5 @@
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "max_new_tokens": 2048,
-  "transformers_version": "4.49.0"
+  "transformers_version": "4.47.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:544472637a7b59b3256215f56e4da8920314f3bac08e3d129fc694c1dece31d5
-size 1260367448
+oid sha256:88c142557820ccad55bb59756bfcfcf891de9cc6202816bd346445188a0ed342
+size 988097824

special_tokens_map.json

@@ -1,20 +1,28 @@
 {
-  "bos_token": {
-    "content": "<｜begin▁of▁sentence｜>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": 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|>"
+  ],
   "eos_token": {
-    "content": "<｜end▁of▁sentence｜>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<｜end▁of▁sentence｜>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4256422650d141f228fe954acee98679da412984c29a569877eefd3af69315a
-size 11422959
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -1,10 +1,9 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
+  "add_bos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "151643": {
-      "content": "<｜end▁of▁sentence｜>",
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -12,23 +11,23 @@
       "special": true
     },
     "151644": {
-      "content": "<｜User｜>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "151645": {
-      "content": "<｜Assistant｜>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "151646": {
-      "content": "<｜begin▁of▁sentence｜>",
+      "content": "<|object_ref_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -36,28 +35,28 @@
       "special": true
     },
     "151647": {
-      "content": "<|EOT|>",
+      "content": "<|object_ref_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "151648": {
-      "content": "<think>",
+      "content": "<|box_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "151649": {
-      "content": "</think>",
+      "content": "<|box_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "151650": {
       "content": "<|quad_start|>",
@@ -180,16 +179,30 @@
       "special": false
     }
   },
-  "bos_token": "<｜begin▁of▁sentence｜>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<｜end▁of▁sentence｜>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "legacy": true,
-  "model_max_length": 16384,
-  "pad_token": "<｜end▁of▁sentence｜>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizerFast",
-  "unk_token": null,
-  "use_default_system_prompt": false
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 49.2958,
+    "train_runtime": 29.2169,
     "train_samples": 7500,
-    "train_samples_per_second": 0.325,
-    "train_steps_per_second": 0.02
+    "train_samples_per_second": 0.548,
+    "train_steps_per_second": 0.034
 }

trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "clip_ratio": 0.0,
-      "completion_length": 256.0,
+      "completion_length": 242.3125,
       "epoch": 0.0010666666666666667,
       "grad_norm": 0.0,
       "kl": 0.0,
@@ -27,9 +27,9 @@
       "step": 1,
       "total_flos": 0.0,
       "train_loss": 0.0,
-      "train_runtime": 49.2958,
-      "train_samples_per_second": 0.325,
-      "train_steps_per_second": 0.02
+      "train_runtime": 29.2169,
+      "train_samples_per_second": 0.548,
+      "train_steps_per_second": 0.034
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a583b94977bd994f0e18110bd26ee8dce871621ac897bf26644714c54342d23
+oid sha256:b22a4ab5c171170644575774d43badfbd904431c614da51d0bc7170607b4d447
 size 6520