distilgpt2-emailgen-finetuned-custom-mail

This model is a fine-tuned version of postbot/distilgpt2-emailgen on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.2633

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• 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	1.0	7	3.6910
No log	2.0	14	3.5847
No log	3.0	21	3.5208
No log	4.0	28	3.4705
No log	5.0	35	3.4275
No log	6.0	42	3.3903
No log	7.0	49	3.3649
No log	8.0	56	3.3466
No log	9.0	63	3.3280
No log	10.0	70	3.3129
No log	11.0	77	3.3008
No log	12.0	84	3.2890
No log	13.0	91	3.2806
No log	14.0	98	3.2754
No log	15.0	105	3.2721
No log	16.0	112	3.2696
No log	17.0	119	3.2663
No log	18.0	126	3.2644
No log	19.0	133	3.2639
No log	20.0	140	3.2633

Framework versions

• Transformers 4.23.1
• Pytorch 1.12.1+cu113
• Datasets 2.6.1
• Tokenizers 0.13.1