final-iteration / run-output /plots /training_log.csv
vaibhavkhandare's picture
Upload folder using huggingface_hub
ad5d3b3 verified
raw
history blame
288 Bytes
round,avg_episode_reward,max_episode_reward,min_episode_reward,avg_grader,max_grader,n_training_samples,train_loss
1,3.463,4.232,2.793,0.3947,0.6341,44,2.4064
2,3.072,3.802,2.25,0.2737,0.5068,48,2.434
3,3.469,3.956,2.979,0.3738,0.574,41,2.4042
4,3.316,3.517,3.073,0.3453,0.4575,47,2.4202