You can deploy this model and start earning money today!

khier12/
mms-1b-algerian-east-v2

Name: mms-1b-algerian-east-v2
Availability: InStock

Views

No views yet

mms-1b-algerian-east-v2

This model is a fine-tuned version of khier12/800min_mms-1b_Full_FT_Algerian_Dialect on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_BNB 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: 150
num_epochs: 12
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
134.4558	0.3656	100	1.6486	0.7299
102.5500	0.7312	200	1.2094	0.6529
33.0515	1.0951	300	1.0335	0.6089
33.1589	1.4606	400	0.9232	0.5719
31.2878	1.8262	500	0.8515	0.5467
29.0004	2.1901	600	0.8176	0.5312
27.0669	2.5557	700	0.7933	0.5148
26.3714	2.9213	800	0.7740	0.5059
27.1695	3.2852	900	0.7244	0.4826
27.6370	3.6507	1000	0.7020	0.4809
29.3353	4.0146	1100	0.7638	0.4757
26.7547	4.3802	1200	0.7195	0.4648
21.4594	4.7458	1300	0.6774	0.4547
29.6335	5.1097	1400	0.6554	0.4460
33.3210	5.4753	1500	0.6493	0.4443
25.4002	5.8409	1600	0.6405	0.4310
22.3004	6.2047	1700	0.6523	0.4296
28.1907	6.5703	1800	0.6510	0.4242
25.3794	6.9359	1900	0.6273	0.4216
23.8162	7.2998	2000	0.6147	0.4200
27.0182	7.6654	2100	0.6142	0.4156
20.3677	8.0292	2200	0.6578	0.4173
24.0046	8.3948	2300	0.6234	0.4104
18.2346	8.7604	2400	0.6196	0.4072
24.7345	9.1243	2500	0.6020	0.4085
20.5054	9.4899	2600	0.6006	0.4051
29.3066	9.8555	2700	0.5983	0.4029
16.9787	10.2194	2800	0.6045	0.4016
21.4099	10.5849	2900	0.5998	0.4029
15.6921	10.9505	3000	0.5976	0.4005
20.4868	11.3144	3100	0.5975	0.3997
27.2156	11.6800	3200	0.5946	0.4015