large_cooking_sft_success

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

• Loss: 0.2618

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 8
• 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: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.397	0.1097	50	0.4121
0.3805	0.2194	100	0.3722
0.3544	0.3291	150	0.3495
0.3297	0.4388	200	0.3254
0.3254	0.5485	250	0.3029
0.3241	0.6582	300	0.2885
0.2974	0.7679	350	0.2725
0.2823	0.8776	400	0.2640
0.2761	0.9872	450	0.2617

Framework versions

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