finetuned_horror

This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4434

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: 10
• eval_batch_size: 8
• 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	6	3.8377
No log	2.0	12	3.6021
No log	3.0	18	3.4019
No log	4.0	24	3.2140
No log	5.0	30	3.0524
No log	6.0	36	2.9159
No log	7.0	42	2.7962
No log	8.0	48	2.6871
No log	9.0	54	2.5802
No log	10.0	60	2.4840
No log	11.0	66	2.3933
No log	12.0	72	2.3195
No log	13.0	78	2.2517
No log	14.0	84	2.1826
No log	15.0	90	2.1190
No log	16.0	96	2.0643
No log	17.0	102	2.0083
No log	18.0	108	1.9614
No log	19.0	114	1.9132
No log	20.0	120	1.8748
No log	21.0	126	1.8417
No log	22.0	132	1.8027
No log	23.0	138	1.7775
No log	24.0	144	1.7520
No log	25.0	150	1.7265
No log	26.0	156	1.7021
No log	27.0	162	1.6795
No log	28.0	168	1.6613
No log	29.0	174	1.6414
No log	30.0	180	1.6221
No log	31.0	186	1.6019
No log	32.0	192	1.5890
No log	33.0	198	1.5694
No log	34.0	204	1.5511
No log	35.0	210	1.5325
No log	36.0	216	1.5186
No log	37.0	222	1.5097
No log	38.0	228	1.5022
No log	39.0	234	1.4903
No log	40.0	240	1.4815
No log	41.0	246	1.4766
No log	42.0	252	1.4705
No log	43.0	258	1.4653
No log	44.0	264	1.4590
No log	45.0	270	1.4544
No log	46.0	276	1.4511
No log	47.0	282	1.4476
No log	48.0	288	1.4456
No log	49.0	294	1.4440
No log	50.0	300	1.4434

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0