Hugging Face's logo

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

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
sft
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
shuheikurita commited on
Commit
75eec35
·
verified ·
1 Parent(s): 6bf4a25

Model save

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. all_results.json +3 -3
  3. train_results.json +3 -3
  4. trainer_state.json +3 -3
  5. training_args.bin +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<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/shuheikurita/huggingface/runs/qdr8f4ug)
31
 
32
 
33
  This model was trained with SFT.
 
27
 
28
  ## Training procedure
29
 
30
+ [<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/shuheikurita/huggingface/runs/v73vl428)
31
 
32
 
33
  This model was trained with SFT.
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 76774385909760.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 1.2564,
5
  "train_samples": 16610,
6
- "train_samples_per_second": 17209.763,
7
- "train_steps_per_second": 268.219
8
  }
 
1
  {
2
  "total_flos": 76774385909760.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 1.3263,
5
  "train_samples": 16610,
6
+ "train_samples_per_second": 16303.078,
7
+ "train_steps_per_second": 254.088
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 76774385909760.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 1.2564,
5
  "train_samples": 16610,
6
- "train_samples_per_second": 17209.763,
7
- "train_steps_per_second": 268.219
8
  }
 
1
  {
2
  "total_flos": 76774385909760.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 1.3263,
5
  "train_samples": 16610,
6
+ "train_samples_per_second": 16303.078,
7
+ "train_steps_per_second": 254.088
8
  }
trainer_state.json CHANGED
@@ -13,9 +13,9 @@
13
  "step": 337,
14
  "total_flos": 76774385909760.0,
15
  "train_loss": 0.0,
16
- "train_runtime": 1.2564,
17
- "train_samples_per_second": 17209.763,
18
- "train_steps_per_second": 268.219
19
  }
20
  ],
21
  "logging_steps": 500,
 
13
  "step": 337,
14
  "total_flos": 76774385909760.0,
15
  "train_loss": 0.0,
16
+ "train_runtime": 1.3263,
17
+ "train_samples_per_second": 16303.078,
18
+ "train_steps_per_second": 254.088
19
  }
20
  ],
21
  "logging_steps": 500,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d33395b009127ad5ce88ef107a3c0a4caabdbeb5b1ad109ac6c2f401a009ea5
3
  size 7416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b10f82357d6aa2b783865dc3ff3eb73628da72db3bbc5390cc9a9398b335fd2b
3
  size 7416