tenacioustommy commited on
Commit
f26a265
·
verified ·
1 Parent(s): 47b5143

End of training

Browse files
Files changed (4) hide show
  1. README.md +3 -1
  2. all_results.json +5 -0
  3. config.json +1 -1
  4. eval_results.json +7 -0
README.md CHANGED
@@ -1,8 +1,10 @@
1
  ---
 
2
  library_name: transformers
3
  model_name: Qwen2.5-3B-Open-R1-Distill
4
  tags:
5
  - generated_from_trainer
 
6
  - trl
7
  - sft
8
  licence: license
@@ -10,7 +12,7 @@ licence: license
10
 
11
  # Model Card for Qwen2.5-3B-Open-R1-Distill
12
 
13
- This model is a fine-tuned version of [None](https://huggingface.co/None).
14
  It has been trained using [TRL](https://github.com/huggingface/trl).
15
 
16
  ## Quick start
 
1
  ---
2
+ datasets: HuggingFaceH4/Bespoke-Stratos-17k
3
  library_name: transformers
4
  model_name: Qwen2.5-3B-Open-R1-Distill
5
  tags:
6
  - generated_from_trainer
7
+ - open-r1
8
  - trl
9
  - sft
10
  licence: license
 
12
 
13
  # Model Card for Qwen2.5-3B-Open-R1-Distill
14
 
15
+ This model is a fine-tuned version of [None](https://huggingface.co/None) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
16
  It has been trained using [TRL](https://github.com/huggingface/trl).
17
 
18
  ## Quick start
all_results.json CHANGED
@@ -1,4 +1,9 @@
1
  {
 
 
 
 
 
2
  "total_flos": 128380330573824.0,
3
  "train_loss": 0.7332075143001489,
4
  "train_runtime": 1234.0886,
 
1
  {
2
+ "eval_loss": 0.7079793214797974,
3
+ "eval_runtime": 3.2531,
4
+ "eval_samples": 100,
5
+ "eval_samples_per_second": 39.654,
6
+ "eval_steps_per_second": 1.537,
7
  "total_flos": 128380330573824.0,
8
  "train_loss": 0.7332075143001489,
9
  "train_runtime": 1234.0886,
config.json CHANGED
@@ -23,7 +23,7 @@
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.49.0.dev0",
26
- "use_cache": false,
27
  "use_sliding_window": false,
28
  "vocab_size": 151936
29
  }
 
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.49.0.dev0",
26
+ "use_cache": true,
27
  "use_sliding_window": false,
28
  "vocab_size": 151936
29
  }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_loss": 0.7079793214797974,
3
+ "eval_runtime": 3.2531,
4
+ "eval_samples": 100,
5
+ "eval_samples_per_second": 39.654,
6
+ "eval_steps_per_second": 1.537
7
+ }