pythia6.9b

This model is a fine-tuned version of EleutherAI/pythia-6.9b on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.9687

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: 8
• eval_batch_size: 8
• seed: 1
• optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
1.9479	1.0	537	1.9618
0.9281	2.0	1074	2.1191
0.2916	3.0	1611	2.4807
0.0742	4.0	2148	2.7559
0.0207	5.0	2685	2.9687

Framework versions

• Transformers 5.14.1
• Pytorch 2.13.0+cu130
• Datasets 5.0.0
• Tokenizers 0.22.2