-
Delete rl_latest.zip
-
Delete rl_best.zip
-
Delete checkpoints
-
RL step=3538960 rew=15.060
-
RL step=3538960 rew=15.060
-
RL step=3538960 rew=15.060
-
RL step=3538960 rew=15.060
-
RL step=3538960 rew=15.060
-
RL step=2949136 rew=13.024
-
RL step=2949136 rew=13.024
-
RL step=2949136 rew=13.024
-
RL step=2949136 rew=13.024
-
RL step=2949136 rew=13.024
-
RL step=2359312 rew=-31.418
-
RL step=2359312 rew=-31.418
-
RL step=2359312 rew=-31.418
-
RL step=2359312 rew=-31.418
-
RL step=1769488 rew=-2683.265
-
RL step=1769488 rew=-2683.265
-
RL step=1769488 rew=-2683.265
-
RL step=1769488 rew=-2683.265
-
RL step=1179664 rew=-31.064
-
RL step=1179664 rew=-31.064
-
RL step=1179664 rew=-31.064
-
RL step=1179664 rew=-31.064
-
RL step=1179664 rew=-31.064
-
RL step=589840 rew=-329.545
-
RL step=589840 rew=-329.545
-
RL step=589840 rew=-329.545
-
RL step=589840 rew=-329.545
-
RL step=589840 rew=-329.545
-
Rename checkpoint_latest.pt to checkpoint_best.pt
-
Upload training.log with huggingface_hub
-
step=204000 loss=0.0000
-
step=204000 loss=0.0000
-
Upload README.md with huggingface_hub
-
Upload training.log with huggingface_hub
-
step=185584 loss=3.2247
-
step=185584 loss=3.2247
-
Upload training.log with huggingface_hub
-
step=167000 loss=0.0000
-
step=167000 loss=0.0000
-
Upload training.log with huggingface_hub
-
step=148424 loss=2.1527
-
step=148424 loss=2.1527
-
Upload training.log with huggingface_hub
-
step=129926 loss=2.1376
-
step=129926 loss=2.1376
-
Upload training.log with huggingface_hub
-
step=111336 loss=2.0800
