problem347_model_mit

This model is a fine-tuned version of barc0/Llama-3.1-ARC-Potpourri-Transduction-8B on the tttx/problem347_mit dataset. It achieves the following results on the evaluation set:

• Loss: 0.0292

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Use 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: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	0.1121
0.1136	0.4	30	0.0323
0.0854	0.8	60	0.0274
0.0524	1.2	90	0.0294
0.0612	1.6	120	0.0289
0.082	2.0	150	0.0292

Framework versions

• PEFT 0.13.2
• Transformers 4.47.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3