BoolQ_Llama-3.2-1B-9pmfiw8i

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

BoolQ_Llama-3.2-1B-9pmfiw8i

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4059
• Model Preparation Time: 0.006
• Mdl: 1914.7894
• Accumulated Loss: 1327.2309
• Correct Preds: 2774.0
• Total Preds: 3270.0
• Accuracy: 0.8483
• Correct Gen Preds: 2621.0
• Gen Accuracy: 0.8015
• Correct Gen Preds 9642: 1695.0
• Correct Preds 9642: 1778.0
• Total Labels 9642: 2026.0
• Accuracy 9642: 0.8776
• Gen Accuracy 9642: 0.8366
• Correct Gen Preds 2822: 916.0
• Correct Preds 2822: 996.0
• Total Labels 2822: 1231.0
• Accuracy 2822: 0.8091
• Gen Accuracy 2822: 0.7441

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 120
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 100

Training results

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1