jd0g/Mistral-7B-NLI-v0.2

mistral-7b-nli_cot

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

• Loss: nan

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: 0.004
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 11
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6298	0.9950	149	0.4956
0.4848	1.9967	299	0.4855
1.4397	2.9983	449	2.3408
1.4527	4.0	599	1.1570
1.0505	4.9950	748	1.0305
0.8713	5.9967	898	0.7930
0.7679	6.9983	1048	0.7487
0.7289	8.0	1198	0.7110
69.2312	8.9950	1347	nan
300.5902	9.9967	1497	nan
635.9469	10.9449	1639	nan

Framework versions

• PEFT 0.10.0
• Transformers 4.40.1
• Pytorch 2.0.1+cu118
• Datasets 2.19.0
• Tokenizers 0.19.1