Toflamus/GPT-2_3M_finetuned2

Output

This model is a fine-tuned version of Toflamus/GPT-2_para3M on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 5.9785

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
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
7.6797	0.27	100	7.0355
6.9842	0.55	200	6.6754
6.7517	0.82	300	6.5074
6.6145	1.09	400	6.3942
6.5294	1.37	500	6.3043
6.4228	1.64	600	6.2332
6.3582	1.91	700	6.1772
6.3	2.19	800	6.1279
6.2841	2.46	900	6.0878
6.2103	2.73	1000	6.0572
6.1908	3.01	1100	6.0325
6.1733	3.28	1200	6.0132
6.1383	3.55	1300	5.9991
6.149	3.83	1400	5.9901
6.1383	4.1	1500	5.9836
6.1155	4.37	1600	5.9800
6.1275	4.65	1700	5.9788
6.1257	4.92	1800	5.9785

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.2