village_model

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0497

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	2	0.8601
No log	2.0	4	0.6303
No log	3.0	6	0.6093
No log	4.0	8	1.1558
No log	5.0	10	1.4105
No log	6.0	12	1.2270
No log	7.0	14	1.0186
No log	8.0	16	0.8103
No log	9.0	18	1.1208
No log	10.0	20	1.2932
No log	11.0	22	1.3319
No log	12.0	24	1.2238
No log	13.0	26	1.1376
No log	14.0	28	1.2790
No log	15.0	30	1.3755
No log	16.0	32	1.3012
No log	17.0	34	1.1688
No log	18.0	36	1.1888
No log	19.0	38	1.2464
No log	20.0	40	1.2791
No log	21.0	42	1.3723
No log	22.0	44	1.3523
No log	23.0	46	1.2353
No log	24.0	48	1.2033
No log	25.0	50	1.2052
No log	26.0	52	1.1590
No log	27.0	54	1.0899
No log	28.0	56	1.0942
No log	29.0	58	1.2419
No log	30.0	60	1.3191
No log	31.0	62	1.3171
No log	32.0	64	1.2407
No log	33.0	66	1.1027
No log	34.0	68	0.9552
No log	35.0	70	0.8614
No log	36.0	72	0.7843
No log	37.0	74	0.7584
No log	38.0	76	0.8167
No log	39.0	78	0.8653
No log	40.0	80	0.9118
No log	41.0	82	0.9450
No log	42.0	84	0.9677
No log	43.0	86	0.9923
No log	44.0	88	1.0085
No log	45.0	90	1.0226
No log	46.0	92	1.0362
No log	47.0	94	1.0430
No log	48.0	96	1.0454
No log	49.0	98	1.0465
No log	50.0	100	1.0497

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0