final-iteration / run-output /plots /training_log.csv
vaibhavkhandare's picture
Upload folder using huggingface_hub
1d8435e verified
raw
history blame
203 Bytes
round,avg_episode_reward,max_episode_reward,min_episode_reward,avg_grader,max_grader,n_training_samples,train_loss
1,2.511,2.866,2.25,0.1072,0.2462,98,3.0041
2,2.885,3.315,2.383,0.2398,0.4023,100,2.9678