asgm5-test-v0

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3325

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 12
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.4565	0.9231	6	3.7292
3.1094	2.0	13	2.9011
2.8867	2.9231	19	2.4011
1.955	4.0	26	1.8841
1.8128	4.9231	32	1.6067
1.278	6.0	39	1.4245
1.3578	6.9231	45	1.3817
1.1568	8.0	52	1.3549
1.3163	8.9231	58	1.3424
1.0936	10.0	65	1.3346
1.2942	10.9231	71	1.3327
0.4425	11.0769	72	1.3325

Framework versions

• PEFT 0.13.2
• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1