mistral-career-guidance

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9654

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• 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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.9869	0.3108	100	0.9817
0.9673	0.6216	200	0.9789
0.9468	0.9324	300	0.9657
0.5981	1.2448	400	1.0154
0.6265	1.5556	500	0.9735
0.6113	1.8664	600	0.9689
0.3136	2.1787	700	1.1104
0.3041	2.4895	800	1.1142
0.2949	2.8003	900	1.1001
0.1846	3.1127	1000	1.3017
0.1409	3.4235	1100	1.3336

Framework versions

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