BARC-1B-gen-COT-answer-origin

This model is a fine-tuned version of cotarc0/BARC-1B-gen-COT-answer on the barc0/transduction_angmented_100k_gpt4o-mini_generated_problems dataset. It achieves the following results on the evaluation set:

• Loss: 0.0571

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: 3
• eval_batch_size: 3
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 4
• total_train_batch_size: 12
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.0597	0.9991	803	0.0571

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.19.1