results_2

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.5776

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	5.3982
No log	2.0	2	4.8609
No log	3.0	3	4.7142
No log	4.0	4	4.6615
No log	5.0	5	4.6245
No log	6.0	6	4.5932
No log	7.0	7	4.5661
No log	8.0	8	4.5424
No log	9.0	9	4.5194
No log	10.0	10	4.4968
No log	11.0	11	4.4755
No log	12.0	12	4.4542
No log	13.0	13	4.4360
No log	14.0	14	4.4160
No log	15.0	15	4.3955
No log	16.0	16	4.3757
No log	17.0	17	4.3547
No log	18.0	18	4.3332
No log	19.0	19	4.3108
No log	20.0	20	4.2878
No log	21.0	21	4.2635
No log	22.0	22	4.2386
No log	23.0	23	4.2121
No log	24.0	24	4.1849
No log	25.0	25	4.1581
No log	26.0	26	4.1309
No log	27.0	27	4.1021
No log	28.0	28	4.0720
No log	29.0	29	4.0414
No log	30.0	30	4.0136
No log	31.0	31	3.9845
No log	32.0	32	3.9580
No log	33.0	33	3.9301
No log	34.0	34	3.9012
No log	35.0	35	3.8716
No log	36.0	36	3.8444
No log	37.0	37	3.8159
No log	38.0	38	3.7859
No log	39.0	39	3.7543
No log	40.0	40	3.7212
No log	41.0	41	3.6875
No log	42.0	42	3.6533
No log	43.0	43	3.6191
No log	44.0	44	3.5842
No log	45.0	45	3.5481
No log	46.0	46	3.5108
No log	47.0	47	3.4728
No log	48.0	48	3.4346
No log	49.0	49	3.4008
No log	50.0	50	3.3707
No log	51.0	51	3.3395
No log	52.0	52	3.3093
No log	53.0	53	3.2779
No log	54.0	54	3.2470
No log	55.0	55	3.2158
No log	56.0	56	3.1847
No log	57.0	57	3.1528
No log	58.0	58	3.1244
No log	59.0	59	3.0970
No log	60.0	60	3.0729
No log	61.0	61	3.0486
No log	62.0	62	3.0261
No log	63.0	63	3.0033
No log	64.0	64	2.9807
No log	65.0	65	2.9575
No log	66.0	66	2.9348
No log	67.0	67	2.9117
No log	68.0	68	2.8894
No log	69.0	69	2.8685
No log	70.0	70	2.8501
No log	71.0	71	2.8357
No log	72.0	72	2.8204
No log	73.0	73	2.8070
No log	74.0	74	2.7933
No log	75.0	75	2.7819
No log	76.0	76	2.7697
No log	77.0	77	2.7569
No log	78.0	78	2.7427
No log	79.0	79	2.7304
No log	80.0	80	2.7188
No log	81.0	81	2.7096
No log	82.0	82	2.6990
No log	83.0	83	2.6880
No log	84.0	84	2.6766
No log	85.0	85	2.6658
No log	86.0	86	2.6550
No log	87.0	87	2.6444
No log	88.0	88	2.6353
No log	89.0	89	2.6272
No log	90.0	90	2.6194
No log	91.0	91	2.6118
No log	92.0	92	2.6052
No log	93.0	93	2.5996
No log	94.0	94	2.5947
No log	95.0	95	2.5901
No log	96.0	96	2.5860
No log	97.0	97	2.5828
No log	98.0	98	2.5803
No log	99.0	99	2.5785
No log	100.0	100	2.5776

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2