DS-Chatbox-facebook-xglm-564M-V4-FT

This model is a fine-tuned version of antphb/DS-Chatbox-facebook-xglm-564M-V3 on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.3576
• eval_runtime: 5.133
• eval_samples_per_second: 51.822
• eval_steps_per_second: 25.911
• epoch: 12.65
• step: 5200

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: 1.5e-05
• train_batch_size: 8
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 200
• num_epochs: 15

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu117
• Datasets 2.13.0
• Tokenizers 0.13.3