Project5_V3_Mistral7b_V2.1

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 2.3036

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 128
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.8	1	2.3482
No log	1.6	2	2.3439
No log	2.4	3	2.3386
2.3422	4.0	5	2.3264
2.3422	4.8	6	2.3212
2.3422	5.6	7	2.3166
2.3422	6.4	8	2.3126
2.3191	8.0	10	2.3072
2.3191	8.8	11	2.3055
2.3191	9.6	12	2.3045
2.3191	10.4	13	2.3039
2.3082	12.0	15	2.3036

Framework versions

• PEFT 0.7.1
• Transformers 4.37.0
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1