pretrain-gpt2-large

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4724

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: 1e-06
• train_batch_size: 16
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 16
• total_train_batch_size: 512
• total_eval_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	335	2.4829
No log	2.0	670	2.4806
No log	3.0	1005	2.4787
2.4893	4.0	1340	2.4770
2.4893	5.0	1675	2.4756
2.4893	6.0	2011	2.4744
2.4837	7.0	2346	2.4735
2.4837	8.0	2681	2.4729
2.4837	9.0	3016	2.4725
2.4821	9.99	3350	2.4724

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3