inverse_sqrt_2000_9e-4_16b_w0.08

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

• Loss: 2.8433

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: 0.0009
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: inverse_sqrt
• lr_scheduler_warmup_steps: 250
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss
6.2868	0.7930	250	4.7451
4.0886	1.5860	500	3.5192
3.2853	2.3791	750	3.1638
2.9937	3.1721	1000	3.0166
2.8076	3.9651	1250	2.9258
2.6347	4.7581	1500	2.8824
2.5242	5.5511	1750	2.8562
2.4308	6.3442	2000	2.8433

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1