Run summary:
train/epoch 1.0
train/global_step 141
train/learning_rate 0.0002
train/loss 0.9442
train/total_flos 2342567262191616.0
train/train_loss 0.94424
train/train_runtime 894.5304
train/train_samples_per_second 0.63
train/train_steps_per_second 0.158
[141/141 14:37, Epoch 1/1]
Step Training Loss
25 1.142500
50 1.023600
75 0.902600
100 0.805700
125 0.944200