Insta-comments-ft

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: 2.8372

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: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.9561	0.8	1	3.9346
4.9057	1.6	2	3.8449
4.674	2.4	3	3.6421
2.1824	4.0	5	3.2708
4.0592	4.8	6	3.1228
3.8482	5.6	7	3.0074
3.6987	6.4	8	2.9219
1.7983	8.0	10	2.8372

Framework versions

• PEFT 0.10.0
• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2