Logs at step 15000

Checkpoint step 15000

Samples at step 14000

Logs at step 14000

Checkpoint step 14000

Best model (epoch 3, loss 0.4165)

Best model (epoch 2, loss 0.4191)

Samples at step 13000

Logs at step 13000

Checkpoint step 13000

Best model (epoch 1, loss 0.4259)

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload model.safetensors with huggingface_hub

Samples at step 12000

Logs at step 12000

Checkpoint step 12000

Best model (epoch 9, loss 0.4254)

Samples at step 11000

Logs at step 11000

Checkpoint step 11000

Samples at step 10000

Logs at step 10000

Checkpoint step 10000

Samples at step 9000

Logs at step 9000

Checkpoint step 9000

Samples at step 8000

Logs at step 8000

Checkpoint step 8000

Best model (epoch 6, loss 0.4320)

Samples at step 7000

Logs at step 7000

Checkpoint step 7000

Best model (epoch 5, loss 0.4363)

Samples at step 6000

Logs at step 6000

Checkpoint step 6000

Best model (epoch 4, loss 0.4404)

Samples at step 5000

Logs at step 5000

Checkpoint step 5000

Samples at step 4000

Logs at step 4000

Checkpoint step 4000

Best model (epoch 3, loss 0.4610)

Update inference_colab.py

Update model.py

Update trainer_colab.py

Samples at step 3000