ckt1

This model is a fine-tuned version of distilbert/distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9517

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	1.9943
No log	2.0	2	1.9329
No log	3.0	3	1.8768
No log	4.0	4	1.8236
No log	5.0	5	1.7748
No log	6.0	6	1.7300
No log	7.0	7	1.6890
No log	8.0	8	1.6514
No log	9.0	9	1.6152
No log	10.0	10	1.5820
No log	11.0	11	1.5501
No log	12.0	12	1.5189
No log	13.0	13	1.4888
No log	14.0	14	1.4590
No log	15.0	15	1.4322
No log	16.0	16	1.4058
No log	17.0	17	1.3810
No log	18.0	18	1.3556
No log	19.0	19	1.3308
No log	20.0	20	1.3066
No log	21.0	21	1.2823
No log	22.0	22	1.2586
No log	23.0	23	1.2353
No log	24.0	24	1.2135
No log	25.0	25	1.1919
No log	26.0	26	1.1719
No log	27.0	27	1.1529
No log	28.0	28	1.1349
No log	29.0	29	1.1180
No log	30.0	30	1.1012
No log	31.0	31	1.0854
No log	32.0	32	1.0700
No log	33.0	33	1.0561
No log	34.0	34	1.0429
No log	35.0	35	1.0313
No log	36.0	36	1.0208
No log	37.0	37	1.0112
No log	38.0	38	1.0024
No log	39.0	39	0.9942
No log	40.0	40	0.9869
No log	41.0	41	0.9804
No log	42.0	42	0.9745
No log	43.0	43	0.9694
No log	44.0	44	0.9649
No log	45.0	45	0.9611
No log	46.0	46	0.9580
No log	47.0	47	0.9555
No log	48.0	48	0.9536
No log	49.0	49	0.9523
No log	50.0	50	0.9517

Framework versions

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