Org_chatbot

This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.6316

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	7.4193
No log	2.0	2	7.0622
No log	3.0	3	6.7202
No log	4.0	4	6.3895
No log	5.0	5	6.0718
No log	6.0	6	5.7655
No log	7.0	7	5.4711
No log	8.0	8	5.1901
No log	9.0	9	4.9214
No log	10.0	10	4.6651
No log	11.0	11	4.4218
No log	12.0	12	4.1939
No log	13.0	13	3.9800
No log	14.0	14	3.7787
No log	15.0	15	3.5910
No log	16.0	16	3.4189
No log	17.0	17	3.2627
No log	18.0	18	3.1232
No log	19.0	19	3.0005
No log	20.0	20	2.8953
No log	21.0	21	2.8081
No log	22.0	22	2.7376
No log	23.0	23	2.6847
No log	24.0	24	2.6493
No log	25.0	25	2.6316

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1