sw-opt-350m

This model is a fine-tuned version of facebook/opt-350m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.6650

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: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 1024
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 200
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
6.2094	0.1147	200	5.0391
4.4151	0.2294	400	4.3766
3.9865	0.3441	600	4.1046
3.7852	0.4588	800	3.9390
3.6542	0.5735	1000	3.8254
3.5559	0.6882	1200	3.7421
3.4816	0.8029	1400	3.6885
3.447	0.9176	1600	3.6650

Framework versions

• Transformers 4.42.4
• Pytorch 2.2.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1