Mistral_AAID_new_mixed_train_final_2

This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on the AAID_new_mixed dataset. It achieves the following results on the evaluation set:

• Loss: 0.5347

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.9535	0.0438	40	0.5372
0.3461	0.0875	80	0.5533
0.3181	0.1313	120	0.5347
0.3057	0.1750	160	0.5565
0.297	0.2188	200	0.5359
0.277	0.2625	240	0.5426
0.2707	0.3063	280	0.5676
0.2563	0.3500	320	0.5668

Framework versions

• PEFT 0.11.1
• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1