ekinakyurek/Llama-3.1-ARC-Potpourri-Transduction-8B

engineer1-heavy-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the barc0/transduction_heavy_100k_jsonl, the barc0/transduction_heavy_suggestfunction_100k_jsonl, the barc0/transduction_rearc_dataset_400k, the barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems and the barc0/transduction_angmented_100k_gpt4o-mini_generated_problems datasets. It achieves the following results on the evaluation set:

• Loss: 0.0219

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.0378	1.0	3729	0.0330
0.0234	2.0	7458	0.0227
0.0116	3.0	11187	0.0219

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1