Hugging Face's logo

imliiny1
/
Qwen2.5-1.5B-Open-R1-Distill

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
Generated from Trainer
open-r1
trl
sft
conversational
text-generation-inference
Model card Files
xet
Metrics Community
imliiny1 commited on
Commit
b3e8f7d
·
verified ·
1 Parent(s): f3338ac

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
@@ -26,7 +26,7 @@ print(output["generated_text"])
26
 
27
  ## Training procedure
28
 
29
- [<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/R1-liiny1/huggingface/runs/69rqk77e)
30
 
31
 
32
  This model was trained with SFT.
 
26
 
27
  ## Training procedure
28
 
29
+ [<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/R1-liiny1/huggingface/runs/hknm9nzd)
30
 
31
 
32
  This model was trained with SFT.
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 77507944513536.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 1.7195,
5
  "train_samples": 16710,
6
- "train_samples_per_second": 12658.374,
7
- "train_steps_per_second": 3164.884
8
  }
 
1
  {
2
  "total_flos": 77507944513536.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 1.7307,
5
  "train_samples": 16710,
6
+ "train_samples_per_second": 12576.308,
7
+ "train_steps_per_second": 3144.366
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 77507944513536.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 1.7195,
5
  "train_samples": 16710,
6
- "train_samples_per_second": 12658.374,
7
- "train_steps_per_second": 3164.884
8
  }
 
1
  {
2
  "total_flos": 77507944513536.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 1.7307,
5
  "train_samples": 16710,
6
+ "train_samples_per_second": 12576.308,
7
+ "train_steps_per_second": 3144.366
8
  }
trainer_state.json CHANGED
@@ -8717,9 +8717,9 @@
8717
  "step": 5442,
8718
  "total_flos": 77507944513536.0,
8719
  "train_loss": 0.0,
8720
- "train_runtime": 1.7195,
8721
- "train_samples_per_second": 12658.374,
8722
- "train_steps_per_second": 3164.884
8723
  }
8724
  ],
8725
  "logging_steps": 5,
 
8717
  "step": 5442,
8718
  "total_flos": 77507944513536.0,
8719
  "train_loss": 0.0,
8720
+ "train_runtime": 1.7307,
8721
+ "train_samples_per_second": 12576.308,
8722
+ "train_steps_per_second": 3144.366
8723
  }
8724
  ],
8725
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b1818adc56ab5fce8089593fb4582a6dc05d14b668bca26d27ef90584752a5c
3
  size 7480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c671f6fe03973674062c7d9c561611a63cfb672bb1de26bd353d1a79682a52fe
3
  size 7480