peft-dialogue-summary-training-1725678440

This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3407

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: 0.0002
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
1.667	0.0500	25	1.4002
1.193	0.1001	50	1.3815
1.4485	0.1501	75	1.3547
1.207	0.2001	100	1.3567
1.4411	0.2501	125	1.3465
1.1428	0.3002	150	1.3491
1.4025	0.3502	175	1.3419
1.1534	0.4002	200	1.3407

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1