Hugging Face's logo

bluuluu
/
Qwen2.5-1.5B-Open-R1-Distill

Transformers
PyTorch
Safetensors
mamba
Generated from Trainer
open-r1
text-generation-inference
Model card Files
xet
Community
bluuluu commited on
Commit
680a22e
·
verified ·
1 Parent(s): f6d76d0

Model save

Browse files
Files changed (6) hide show
  1. README.md +3 -3
  2. all_results.json +4 -4
  3. pytorch_model.bin +2 -2
  4. train_results.json +4 -4
  5. trainer_state.json +0 -0
  6. training_args.bin +2 -2
README.md CHANGED
@@ -24,7 +24,7 @@ print(output["generated_text"])
24
 
25
  ## Training procedure
26
 
27
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/2741919970-hustvl/huggingface/runs/4c8t09gs)
28
 
29
 
30
  This model was trained with SFT.
@@ -32,9 +32,9 @@ This model was trained with SFT.
32
  ### Framework versions
33
 
34
  - TRL: 0.16.0.dev0
35
- - Transformers: 4.49.0.dev0
36
  - Pytorch: 2.5.1
37
- - Datasets: 3.3.0
38
  - Tokenizers: 0.21.0
39
 
40
  ## Citations
 
24
 
25
  ## Training procedure
26
 
27
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/2741919970-hustvl/huggingface/runs/8d6xpsju)
28
 
29
 
30
  This model was trained with SFT.
 
32
  ### Framework versions
33
 
34
  - TRL: 0.16.0.dev0
35
+ - Transformers: 4.50.0.dev0
36
  - Pytorch: 2.5.1
37
+ - Datasets: 3.3.1
38
  - Tokenizers: 0.21.0
39
 
40
  ## Citations
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 0.9694986148756377,
4
- "train_runtime": 60321.7593,
5
  "train_samples": 16610,
6
- "train_samples_per_second": 1.456,
7
- "train_steps_per_second": 0.023
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.9815138741495063,
4
+ "train_runtime": 13832.1557,
5
  "train_samples": 16610,
6
+ "train_samples_per_second": 2.402,
7
+ "train_steps_per_second": 0.15
8
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c804c21eeaa4c26cb165eb7209004d569ded8498b9c81e8eceea42fdbce2fe0a
3
- size 5405377370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a6070621e5611568510334c5f43acb28fdba0d123da3e78b505258dee64316
3
+ size 2687651730
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 0.9694986148756377,
4
- "train_runtime": 60321.7593,
5
  "train_samples": 16610,
6
- "train_samples_per_second": 1.456,
7
- "train_steps_per_second": 0.023
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.9815138741495063,
4
+ "train_runtime": 13832.1557,
5
  "train_samples": 16610,
6
+ "train_samples_per_second": 2.402,
7
+ "train_steps_per_second": 0.15
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37d2ff69a21f3783ee3eacd1fa2d3fdb42571b639bc8e26c0774c870aff0ac89
3
- size 8376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdd831cea05fdcc5520eecfb7adc86659d142ec77ebe9d596677e3f6183ba13
3
+ size 8568