mystv0_abb

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

• Loss: 1.6883

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
• distributed_type: multi-GPU
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1000
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
1.3146	5.12	1000	1.5020
1.0106	10.24	2000	1.5553
0.9965	15.36	3000	1.5045
0.9931	20.47	4000	1.5800
0.9909	25.59	5000	1.4855
0.9881	30.71	6000	1.5844
0.9851	35.83	7000	1.7043
0.9813	40.95	8000	1.6826
0.9778	46.07	9000	1.6883

Framework versions

• Transformers 4.30.2
• Pytorch 2.1.0+cu121
• Datasets 2.13.1
• Tokenizers 0.13.3