opt-journal-finetune

This model is a fine-tuned version of facebook/opt-125m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.6144

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: 2.5e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
3.9448	0.09	25	3.8409
3.9142	0.17	50	3.7117
3.6859	0.26	75	3.6394
3.7328	0.35	100	3.6144

Framework versions

• PEFT 0.10.1.dev0
• Transformers 4.40.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2