hlillemark/llama3_8b_sft_mc_filtered

sft_mc_filtered

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the identity and the data_mc_filtered datasets. It achieves the following results on the evaluation set:

• Loss: 2.3079

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: 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: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.8433	1.0	50	1.0960
0.6237	2.0	100	1.1312
0.391	3.0	150	1.2466
0.2529	4.0	200	1.4003
0.148	5.0	250	1.4606
0.0818	6.0	300	1.5260
0.0352	7.0	350	2.0277
0.0197	8.0	400	2.1508
0.0129	9.0	450	2.2828
0.0066	10.0	500	2.3079

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0