learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Cer
5.4668	0.5021	300	1.0444	0.2297
1.7381	1.0033	600	0.9856	0.2355
1.2914	1.5054	900	0.8753	0.2055
1.0549	2.0067	1200	0.9217	0.1924
0.7774	2.5088	1500	0.9469	0.1940
0.6229	3.0100	1800	1.0222	0.1919
0.4280	3.5121	2100	1.0945	0.1952
0.3410	4.0134	2400	1.1561	0.1967
0.2191	4.5155	2700	1.3199	0.1977
0.1739	5.0167	3000	1.4493	0.1956
0.1106	5.5188	3300	1.4783	0.1950
0.0941	6.0201	3600	1.6971	0.1938
0.0602	6.5222	3900	1.7262	0.1969
0.0489	7.0234	4200	1.9145	0.1934
0.0314	7.5255	4500	1.8897	0.1925
0.0238	8.0268	4800	2.0750	0.1915
0.0142	8.5289	5100	2.0837	0.1914
0.0090	9.0301	5400	2.1940	0.1906
0.0052	9.5322	5700	2.2516	0.1901

dhasmana/Angika-Chhattisgarhi-Kumaoni-Magadhi-Garhwali-Bhojpuri-w2v-bert-2.0

Angika-Chhattisgarhi-Kumaoni-Magadhi-Garhwali-Bhojpuri-w2v-bert-2.0