Hugging Face's logo

mamba413
/
Qwen2-0.5B-Reward-DR-SIMU

Text Classification
Transformers
Safetensors
qwen2
Generated from Trainer
trl
reward-trainer
text-embeddings-inference
Model card Files
xet
 Community
mamba413 commited on
Commit
d3bf1ea
·
verified ·
1 Parent(s): 0be2634

Model save

Browse files
Files changed (2) hide show
  1. all_results.json +3 -3
  2. eval_results.json +3 -3
all_results.json CHANGED
@@ -2,7 +2,7 @@
2
  "epoch": 0,
3
  "eval_accuracy": 0.8,
4
  "eval_loss": 0.0,
5
- "eval_runtime": 0.3409,
6
- "eval_samples_per_second": 14.666,
7
- "eval_steps_per_second": 8.8
8
  }
 
2
  "epoch": 0,
3
  "eval_accuracy": 0.8,
4
  "eval_loss": 0.0,
5
+ "eval_runtime": 0.3218,
6
+ "eval_samples_per_second": 15.539,
7
+ "eval_steps_per_second": 9.323
8
  }
eval_results.json CHANGED
@@ -2,7 +2,7 @@
2
  "epoch": 0,
3
  "eval_accuracy": 0.8,
4
  "eval_loss": 0.0,
5
- "eval_runtime": 0.3409,
6
- "eval_samples_per_second": 14.666,
7
- "eval_steps_per_second": 8.8
8
  }
 
2
  "epoch": 0,
3
  "eval_accuracy": 0.8,
4
  "eval_loss": 0.0,
5
+ "eval_runtime": 0.3218,
6
+ "eval_samples_per_second": 15.539,
7
+ "eval_steps_per_second": 9.323
8
  }