fine-tuned_phi3.5

This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2392

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 6
• total_train_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.01
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0244	10	1.4131
No log	0.0487	20	1.3193
1.4022	0.0731	30	1.2778
1.4022	0.0975	40	1.2651
1.2145	0.1219	50	1.2546
1.2145	0.1462	60	1.2479
1.2145	0.1706	70	1.2449
1.1869	0.1950	80	1.2413
1.1869	0.2193	90	1.2402
1.2108	0.2437	100	1.2392

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.0.0+nv23.05
• Datasets 2.15.0
• Tokenizers 0.19.1