phi-1_5-finetuned-model-classification

This model is a fine-tuned version of microsoft/phi-1_5 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.4343

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: 0.0004
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss
2.6171	4.0	250	2.7650
2.3312	8.0	500	2.7894
1.9386	12.0	750	2.9510
1.4978	16.0	1000	3.2375
1.0947	20.0	1250	3.7212
0.8685	24.0	1500	4.1141
0.7308	28.0	1750	4.3801
0.6995	32.0	2000	4.4343

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1