Hugging Face's logo

qgallouedec
/
Qwen2-0.5B-Reward

Token Classification
Transformers
Safetensors
qwen2
Generated from Trainer
trl
stepwise-reward-trainer
text-generation-inference
Inference Endpoints
Model card Files Community
qgallouedec HF staff commited on
Commit
b060d14
•
1 Parent(s): cdf2aec

Model save

Browse files
Files changed (2) hide show
  1. all_results.json +5 -5
  2. eval_results.json +5 -5
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_accuracy": 0.9982057358005328,
4
- "eval_loss": 0.02584557794034481,
5
- "eval_runtime": 10.5668,
6
- "eval_samples_per_second": 349.682,
7
- "eval_steps_per_second": 5.489
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_accuracy": 0.9902498704209937,
4
+ "eval_loss": 0.0218771081417799,
5
+ "eval_runtime": 10.6397,
6
+ "eval_samples_per_second": 347.286,
7
+ "eval_steps_per_second": 5.451
8
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_accuracy": 0.9982057358005328,
4
- "eval_loss": 0.02584557794034481,
5
- "eval_runtime": 10.5668,
6
- "eval_samples_per_second": 349.682,
7
- "eval_steps_per_second": 5.489
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_accuracy": 0.9902498704209937,
4
+ "eval_loss": 0.0218771081417799,
5
+ "eval_runtime": 10.6397,
6
+ "eval_samples_per_second": 347.286,
7
+ "eval_steps_per_second": 5.451
8
  }