learning_rate: 5e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
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
lr_scheduler_warmup_steps: 20
num_epochs: 50
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.6259	1.0	141	0.6782
0.487	2.0	282	0.6630
0.4701	3.0	423	0.6503
0.4628	4.0	564	0.6622
0.4566	5.0	705	0.6497
0.4508	6.0	846	0.6425
0.4442	7.0	987	0.6440
0.4402	8.0	1128	0.6381
0.4397	9.0	1269	0.6373
0.4354	10.0	1410	0.6350
0.4315	11.0	1551	0.6377
0.4328	12.0	1692	0.6315
0.4271	13.0	1833	0.6398
0.4233	14.0	1974	0.6403
0.4209	15.0	2115	0.6331
0.4205	16.0	2256	0.6315
0.4193	17.0	2397	0.6333
0.4174	18.0	2538	0.6372
0.4146	19.0	2679	0.6354
0.4129	20.0	2820	0.6328
0.4107	21.0	2961	0.6346
0.4108	22.0	3102	0.6307
0.4079	23.0	3243	0.6383
0.4055	24.0	3384	0.6320
0.4066	25.0	3525	0.6292
0.4035	26.0	3666	0.6317
0.4035	27.0	3807	0.6327
0.4027	28.0	3948	0.6300
0.4	29.0	4089	0.6293
0.3985	30.0	4230	0.6316
0.3984	31.0	4371	0.6313
0.3972	32.0	4512	0.6343
0.3961	33.0	4653	0.6312
0.395	34.0	4794	0.6354
0.3939	35.0	4935	0.6320
0.3926	36.0	5076	0.6311
0.3925	37.0	5217	0.6335
0.3915	38.0	5358	0.6301
0.3895	39.0	5499	0.6363
0.3888	40.0	5640	0.6373
0.3881	41.0	5781	0.6377
0.386	42.0	5922	0.6357
0.3852	43.0	6063	0.6310
0.3862	44.0	6204	0.6339
0.385	45.0	6345	0.6285
0.3851	46.0	6486	0.6309
0.3842	47.0	6627	0.6344
0.3826	48.0	6768	0.6325
0.3818	49.0	6909	0.6315
0.3836	49.6471	7000	0.6316

kavinda123321/sinhala_check5

sinhala_check5