phi_1.5_mfr_instruct

This model is a fine-tuned version of microsoft/phi-1_5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4898

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss
1.4571	40.0	250	1.1032
0.2487	80.0	500	1.3577
0.1679	120.0	750	1.4287
0.1586	160.0	1000	1.4562
0.1544	200.0	1250	1.4729
0.1521	240.0	1500	1.4843
0.151	280.0	1750	1.4893
0.1504	320.0	2000	1.4898

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1