17ddfec3-de9b-4a13-aab4-36976da7fb83

This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B-Alternate-Tokenizer on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1896

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: 0.000204
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	2.1742
2.0712	0.0026	50	1.7819
1.8743	0.0052	100	1.7514
1.8739	0.0079	150	1.8120
2.1821	0.0105	200	1.6885
1.7126	0.0131	250	1.4994
1.8793	0.0157	300	1.4284
1.8794	0.0183	350	1.3096
1.6114	0.0210	400	1.2151
1.8403	0.0236	450	1.1930
1.8475	0.0262	500	1.1896

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1