problem0_model_diverse_more_aug_200

This model is a fine-tuned version of barc0/Llama-3.1-ARC-Potpourri-Transduction-8B on the tttx/problem0_diverse_more_aug dataset. It achieves the following results on the evaluation set:

• Loss: 0.0069
• Problem Acc@1: 0.0
• Solution Acc@1: 0.0

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: 0.0001
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• total_eval_batch_size: 8
• 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: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Problem Acc@1	Solution Acc@1
No log	0	0	0.0180	0.0	0.0
0.1106	0.3158	15	0.0113	0.0	0.0
0.0597	0.6316	30	0.0048	0.0	0.0
0.053	0.9474	45	0.0080	0.0	0.0
0.0397	1.2526	60	0.0052	0.0	0.0
0.0377	1.5684	75	0.0052	0.0	0.0
0.0377	1.8842	90	0.0078	0.0	0.0

Framework versions

• PEFT 0.10.0
• Transformers 4.47.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 3.0.2
• Tokenizers 0.20.0