ckt3

This model is a fine-tuned version of samhitmantrala/ckt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3129

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: 32
• eval_batch_size: 32
• 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	1	0.6850
No log	2.0	2	0.6271
No log	3.0	3	0.5934
No log	4.0	4	0.5708
No log	5.0	5	0.5513
No log	6.0	6	0.5337
No log	7.0	7	0.5165
No log	8.0	8	0.5004
No log	9.0	9	0.4860
No log	10.0	10	0.4734
No log	11.0	11	0.4634
No log	12.0	12	0.4543
No log	13.0	13	0.4460
No log	14.0	14	0.4381
No log	15.0	15	0.4299
No log	16.0	16	0.4220
No log	17.0	17	0.4141
No log	18.0	18	0.4068
No log	19.0	19	0.4000
No log	20.0	20	0.3933
No log	21.0	21	0.3871
No log	22.0	22	0.3817
No log	23.0	23	0.3766
No log	24.0	24	0.3718
No log	25.0	25	0.3672
No log	26.0	26	0.3625
No log	27.0	27	0.3581
No log	28.0	28	0.3537
No log	29.0	29	0.3493
No log	30.0	30	0.3453
No log	31.0	31	0.3414
No log	32.0	32	0.3380
No log	33.0	33	0.3348
No log	34.0	34	0.3317
No log	35.0	35	0.3288
No log	36.0	36	0.3262
No log	37.0	37	0.3241
No log	38.0	38	0.3221
No log	39.0	39	0.3205
No log	40.0	40	0.3191
No log	41.0	41	0.3179
No log	42.0	42	0.3167
No log	43.0	43	0.3158
No log	44.0	44	0.3150
No log	45.0	45	0.3143
No log	46.0	46	0.3138
No log	47.0	47	0.3134
No log	48.0	48	0.3132
No log	49.0	49	0.3130
No log	50.0	50	0.3129

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2