learning_rate: 0.001
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Bertscore Precision	Bertscore Recall	Bertscore F1
No log	1.0	175	5.9907	0.7932	0.8231	0.8076
No log	2.0	350	5.7637	0.8333	0.8347	0.8338
4.9374	3.0	525	5.6588	0.8427	0.8399	0.8411
4.9374	4.0	700	5.6527	0.8373	0.8378	0.8373
4.9374	5.0	875	5.6739	0.8400	0.8384	0.8390
3.9529	6.0	1050	5.6938	0.8390	0.8398	0.8392
3.9529	7.0	1225	5.7255	0.8431	0.8418	0.8422
3.9529	8.0	1400	5.7639	0.8403	0.8416	0.8408
3.5438	9.0	1575	5.7559	0.8440	0.8419	0.8427
3.5438	10.0	1750	5.7626	0.8417	0.8420	0.8417

DipanjanSanyal/cefr_a1_tiny_lm

cefr_a1_tiny_lm