V0410MP3_neo

This model is a fine-tuned version of EleutherAI/gpt-neo-2.7B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 11.4224

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_warmup_steps: 20
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
12.6501	0.18	20	12.6430
12.5965	0.36	40	12.6773
12.883	0.54	60	12.8912
12.443	0.73	80	13.2937
11.8789	0.91	100	11.5682
11.8368	1.09	120	12.7259
11.6823	1.27	140	11.6140
11.3923	1.45	160	11.4045
11.4354	1.63	180	11.5279
11.4733	1.81	200	11.4428
11.3741	1.99	220	11.4224

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.14.1