GSM8K-Binary_Llama-3.2-1B-3bfons7b

<!-- 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. -->

GSM8K-Binary_Llama-3.2-1B-3bfons7b

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: 0.9066
• Model Preparation Time: 0.0057
• Mdl: 3237.1033
• Accumulated Loss: 2243.7890
• Correct Preds: 1438.0
• Total Preds: 2475.0
• Accuracy: 0.5810
• Correct Gen Preds: 35.0
• Gen Accuracy: 0.0141
• Correct Gen Preds 34192: 0.0
• Correct Preds 34192: 831.0
• Total Labels 34192: 1196.0
• Accuracy 34192: 0.6948
• Gen Accuracy 34192: 0.0
• Correct Gen Preds 41568: 28.0
• Correct Preds 41568: 607.0
• Total Labels 41568: 1267.0
• Accuracy 41568: 0.4791
• Gen Accuracy 41568: 0.0221

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: 64
• 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