learning_rate: 0.001
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
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_ratio: 0.03
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
3.7908	0.5857	1000	3.7377	6.18	16.2781
3.5926	1.1716	2000	3.3270	8.0493	16.4099
3.2234	1.7572	3000	3.0900	9.7393	15.2034
2.9178	2.3432	4000	2.8567	9.8133	17.6295
2.7302	2.9288	5000	2.6926	15.7344	12.8374
2.4324	3.5148	6000	2.5841	16.7132	12.9787
2.3135	4.1007	7000	2.4542	17.5718	13.288
2.0808	4.6864	8000	2.3554	18.0186	13.6381
1.9353	5.2723	9000	2.3031	20.0612	12.8465
1.8244	5.8580	10000	2.1954	19.1501	14.0303
1.6091	6.4439	11000	2.2027	23.3063	12.3297
1.5548	7.0299	12000	2.1910	23.6853	12.4534
1.325	7.6155	13000	2.1362	27.8799	11.4823
1.2595	8.2015	14000	2.1696	25.782	12.1096
1.1253	8.7871	15000	2.1173	27.8543	11.8945
0.9858	9.3731	16000	2.1696	29.3317	11.7985
0.938	9.9587	17000	2.1540	29.991	11.75

abdeljalilELmajjodi/Motarjem-v0.1

Motarjem-v0.1