YetAnotherTaskParaphraser

This model is a fine-tuned version of ai-forever/rugpt3small_based_on_gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.3493

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: 6e-06
• train_batch_size: 3
• eval_batch_size: 3
• seed: 42
• gradient_accumulation_steps: 10
• total_train_batch_size: 30
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.79	3	3.6387
No log	1.84	7	3.5668
No log	2.89	11	3.5129
No log	3.95	15	3.4733
No log	5.0	19	3.4407
No log	5.79	22	3.4195
No log	6.84	26	3.3978
No log	7.89	30	3.3849
No log	8.95	34	3.3749
No log	10.0	38	3.3666
No log	10.79	41	3.3617
No log	11.84	45	3.3566
No log	12.89	49	3.3531
No log	13.95	53	3.3508
No log	15.0	57	3.3496
No log	15.79	60	3.3493

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3