llama3_8b_general_rm_full

This model is a fine-tuned version of Jennny/llama3_8b_sft_ultrafb on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2676
• Accuracy: 0.8858

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: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 512
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3173	0.1549	50	0.3212	0.8622
0.3037	0.3098	100	0.2959	0.8742
0.2982	0.4647	150	0.3012	0.8735
0.2857	0.6196	200	0.2818	0.8823
0.2773	0.7744	250	0.2716	0.8853
0.2691	0.9293	300	0.2676	0.8858

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3