nbaresult

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7787

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.4842	1.5209	100	1.5785
1.3561	3.0418	200	1.0734
0.9769	4.5627	300	0.8836
0.8586	6.0837	400	0.8362
0.8166	7.6046	500	0.8127
0.7922	9.1255	600	0.8015
0.7708	10.6464	700	0.7941
0.7467	12.1673	800	0.7889
0.728	13.6882	900	0.7820
0.7138	15.2091	1000	0.7795
0.7043	16.7300	1100	0.7780
0.7007	18.2510	1200	0.7783
0.6964	19.7719	1300	0.7787

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1