Skip to main content
upup-ashton-wang-usc
Projects
Tina
Run groups
Tina-OpenR1
Logs
Overview
Workspace
Runs
Logs
Files
Artifacts

Upup-ashton-wang's group workspace

Timestamps visible
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:34:59
Failed to parse gold solution:  Answer: 9
2025-04-03 08:35:24
{'loss': 0.0123, 'grad_norm': 0.8202553391456604, 'learning_rate': 7.776173035551165e-07, 'rewards/accuracy_reward': 0.078125, 'rewards/format_reward': 0.875, 'rewards/tag_count_reward': 0.9296875, 'rewards/len_reward': -0.005438145250082016, 'rewards/reasoning_steps_reward': 0.7604166716337204, 'rewards/cosine_scaled_reward': 0.0873645693063736, 'rewards/repetition_penalty_reward': -0.146163672208786, 'reward': 2.5789918899536133, 'reward_std': 0.7456816211342812, 'completion_length': 1755.28125, 'kl': 0.306884765625, 'epoch': 0.34}