learning_rate: 0.001
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
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: 100

Training Loss	Epoch	Step	Validation Loss
0.8271	1.0	523	1.5899
0.5972	2.0	1046	1.1333
0.4294	3.0	1569	0.9262
0.3194	4.0	2092	0.7871
0.2746	5.0	2615	0.7179
0.2798	6.0	3138	0.6662
0.2385	7.0	3661	0.6456
0.2246	8.0	4184	0.6130
0.2104	9.0	4707	0.6052
0.2086	10.0	5230	0.5823
0.2237	11.0	5753	0.5626
0.1805	12.0	6276	0.5662
0.1748	13.0	6799	0.5578
0.1779	14.0	7322	0.5472
0.191	15.0	7845	0.5309
0.1615	16.0	8368	0.5256
0.159	17.0	8891	0.5271
0.158	18.0	9414	0.5349

Blend-ai/AMD-bot

AMD-bot:Cutomer support automation