Not-so-bright-AGI-phi-1_5

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

• Loss: 2.4005

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 8
• 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: linear
• lr_scheduler_warmup_ratio: 0.05
• training_steps: 593

Training results

Training Loss	Epoch	Step	Validation Loss
2.7734	0.7921	100	2.5922
2.5468	1.5842	200	2.4699
2.4705	2.3762	300	2.4318
2.4413	3.1683	400	2.4113
2.4318	3.9604	500	2.4005

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.1.0.post0+cxx11.abi
• Datasets 2.19.1
• Tokenizers 0.19.1