469556b6-a007-4253-903d-a89fdf3d13bb

This model is a fine-tuned version of microsoft/phi-2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3747

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: 0.00021
• train_batch_size: 4
• eval_batch_size: 4
• seed: 100
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0003	1	0.6086
0.5451	0.0132	50	0.5296
0.533	0.0263	100	0.5379
0.4884	0.0395	150	0.4468
0.576	0.0527	200	0.5704
0.4878	0.0658	250	0.4367
0.4774	0.0790	300	0.4282
0.4648	0.0922	350	0.4132
0.4505	0.1053	400	0.3804
0.3859	0.1185	450	0.3750
0.4094	0.1316	500	0.3747

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1