Llama-3.1-8B-Instruct-contracts-ContinuedPretrainingLlama3.18b

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.6631

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: 2.5e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5
• training_steps: 6000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.4333	0.0024	500	1.7135
1.346	0.0048	1000	1.7070
1.3545	0.0073	1500	1.6973
1.331	0.0097	2000	1.6867
1.3407	0.0121	2500	1.6783
1.2654	0.0145	3000	1.6832
1.278	0.0170	3500	1.6673
1.234	0.0194	4000	1.6700
1.2464	0.0218	4500	1.6675
1.2513	0.0242	5000	1.6619
1.2718	0.0266	5500	1.6640
1.2506	0.0291	6000	1.6631

Framework versions

• PEFT 0.13.2
• Transformers 4.46.1
• Pytorch 2.4.0+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1