llama71b-career-guidance

This model is a fine-tuned version of meta-llama/Llama-3.1-70B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7931

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: 8e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_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: 0.03
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.8178	0.3109	100	0.8328
0.7941	0.6218	200	0.8050
0.7593	0.9328	300	0.7819
0.5123	1.2437	400	0.8186
0.5151	1.5546	500	0.7973
0.4795	1.8655	600	0.7975
0.2474	2.1764	700	0.8987
0.2515	2.4874	800	0.8960
0.2335	2.7983	900	0.9039

Framework versions

• PEFT 0.18.1
• Transformers 4.46.2
• Pytorch 2.5.1+cu124
• Datasets 4.5.0
• Tokenizers 0.20.3