Coolbot-DialoGPTVersion

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

• Loss: 1.0891

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: 2
• eval_batch_size: 2
• 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	21	6.5931
No log	2.0	42	4.1892
No log	3.0	63	3.1764
No log	4.0	84	2.6675
No log	5.0	105	2.3741
No log	6.0	126	2.0892
No log	7.0	147	1.9318
No log	8.0	168	1.8144
No log	9.0	189	1.7806
No log	10.0	210	1.5569
No log	11.0	231	1.4354
No log	12.0	252	1.3545
No log	13.0	273	1.3064
No log	14.0	294	1.2790
No log	15.0	315	1.2512
No log	16.0	336	1.1585
No log	17.0	357	1.1240
No log	18.0	378	1.1029
No log	19.0	399	1.0924
No log	20.0	420	1.0891

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1