learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use 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: 200
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss
8.5841	0.4728	100	2.6105
1.9725	0.9456	200	1.6720
1.535	1.4161	300	1.5957
1.4496	1.8889	400	1.5590
1.3806	2.3593	500	1.4973
1.3533	2.8322	600	1.4804
1.3	3.3026	700	1.4363
1.3135	3.7754	800	1.4593
1.2523	4.2459	900	1.4570
1.255	4.7187	1000	1.4659
1.2291	5.1891	1100	1.4127
1.2041	5.6619	1200	1.4866
1.1898	6.1324	1300	1.4525
1.1729	6.6052	1400	1.4438
1.1742	7.0757	1500	1.4242
1.1645	7.5485	1600	1.4479
1.1165	8.0189	1700	1.4881
1.1283	8.4917	1800	1.4369
1.1334	8.9645	1900	1.4631
1.1081	9.4350	2000	1.4551
1.1344	9.9078	2100	1.4553

Addaci/bert-base-multilingual-cased-finetuned-yiddish-experiment-4

bert-base-multilingual-cased-finetuned-yiddish-experiment-4