230912GPT2_fine_tuned_SP_GPT2_config_ESM_tokenizer_6kSwissProt_20epochs

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1215

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: 0.0005
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• 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: 531
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
4.1505	0.99	41	2.7547
2.6987	2.0	83	2.6860
2.7257	2.99	124	2.6648
2.6391	4.0	166	2.6580
2.6872	4.99	207	2.6411
2.6053	6.0	249	2.6419
2.6612	6.99	290	2.6301
2.5815	8.0	332	2.6124
2.6307	8.99	373	2.5928
2.5507	10.0	415	2.5764
2.5782	10.99	456	2.5471
2.4578	12.0	498	2.4726
2.43	12.99	539	2.3949
2.2695	14.0	581	2.3361
2.201	14.99	622	2.2559
1.999	16.0	664	2.1804
1.8843	16.99	705	2.1191
1.6932	18.0	747	2.1015
1.6252	18.99	788	2.1163
1.5326	19.76	820	2.1215

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3