phi3_5_mini_instruct_lora_chemical_eng_flashattn_final

This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1576

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.162	0.7319	100	0.1612
0.1549	1.4639	200	0.1590
0.1548	2.1958	300	0.1579
0.1581	2.9277	400	0.1576

Framework versions

• PEFT 0.13.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1