Hugging Face's logo

chenggong1995
/
OLMoE-1B-7B-0125-Instruct-grpo-E6-D100

Text Generation
Transformers
Safetensors
olmoe
Generated from Trainer
open-r1
trl
grpo
conversational
Inference Endpoints
Model card Files Community
chenggong1995 commited on
Commit
44e74b1
·
verified ·
1 Parent(s): d3a673c

End of training

Browse files
Files changed (5) hide show
  1. README.md +3 -1
  2. all_results.json +4 -4
  3. config.json +1 -1
  4. eval_results.json +4 -4
  5. tokenizer.json +8 -1
README.md CHANGED
@@ -1,9 +1,11 @@
1
  ---
2
  base_model: allenai/OLMoE-1B-7B-0125-Instruct
 
3
  library_name: transformers
4
  model_name: OLMoE-1B-7B-0125-Instruct-grpo-E6-D100
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
  - grpo
9
  licence: license
@@ -11,7 +13,7 @@ licence: license
11
 
12
  # Model Card for OLMoE-1B-7B-0125-Instruct-grpo-E6-D100
13
 
14
- This model is a fine-tuned version of [allenai/OLMoE-1B-7B-0125-Instruct](https://huggingface.co/allenai/OLMoE-1B-7B-0125-Instruct).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
1
  ---
2
  base_model: allenai/OLMoE-1B-7B-0125-Instruct
3
+ datasets: chenggong1995/NuminaMath-TIR-100
4
  library_name: transformers
5
  model_name: OLMoE-1B-7B-0125-Instruct-grpo-E6-D100
6
  tags:
7
  - generated_from_trainer
8
+ - open-r1
9
  - trl
10
  - grpo
11
  licence: license
 
13
 
14
  # Model Card for OLMoE-1B-7B-0125-Instruct-grpo-E6-D100
15
 
16
+ This model is a fine-tuned version of [allenai/OLMoE-1B-7B-0125-Instruct](https://huggingface.co/allenai/OLMoE-1B-7B-0125-Instruct) on the [chenggong1995/NuminaMath-TIR-100](https://huggingface.co/datasets/chenggong1995/NuminaMath-TIR-100) dataset.
17
  It has been trained using [TRL](https://github.com/huggingface/trl).
18
 
19
  ## Quick start
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "eval_loss": 0.0047706114128232,
3
- "eval_runtime": 88.6672,
4
  "eval_samples": 99,
5
- "eval_samples_per_second": 1.117,
6
- "eval_steps_per_second": 0.079,
7
  "total_flos": 0.0,
8
  "train_loss": 0.0,
9
  "train_runtime": 1.7279,
 
1
  {
2
+ "eval_loss": 0.0061603132635355,
3
+ "eval_runtime": 143.0561,
4
  "eval_samples": 99,
5
+ "eval_samples_per_second": 0.692,
6
+ "eval_steps_per_second": 0.049,
7
  "total_flos": 0.0,
8
  "train_loss": 0.0,
9
  "train_runtime": 1.7279,
config.json CHANGED
@@ -28,6 +28,6 @@
28
  "tie_word_embeddings": false,
29
  "torch_dtype": "bfloat16",
30
  "transformers_version": "4.49.0",
31
- "use_cache": false,
32
  "vocab_size": 50304
33
  }
 
28
  "tie_word_embeddings": false,
29
  "torch_dtype": "bfloat16",
30
  "transformers_version": "4.49.0",
31
+ "use_cache": true,
32
  "vocab_size": 50304
33
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "eval_loss": 0.0047706114128232,
3
- "eval_runtime": 88.6672,
4
  "eval_samples": 99,
5
- "eval_samples_per_second": 1.117,
6
- "eval_steps_per_second": 0.079
7
  }
 
1
  {
2
+ "eval_loss": 0.0061603132635355,
3
+ "eval_runtime": 143.0561,
4
  "eval_samples": 99,
5
+ "eval_samples_per_second": 0.692,
6
+ "eval_steps_per_second": 0.049
7
  }
tokenizer.json CHANGED
@@ -1,7 +1,14 @@
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
+ "padding": {
5
+ "strategy": "BatchLongest",
6
+ "direction": "Left",
7
+ "pad_to_multiple_of": null,
8
+ "pad_id": 50280,
9
+ "pad_type_id": 0,
10
+ "pad_token": "<pad>"
11
+ },
12
  "added_tokens": [
13
  {
14
  "id": 0,