mistral-mistralinstruct_climate_finetune_2

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

• Loss: 0.4924

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.7767	0.2222	25	1.5856
1.4419	0.4444	50	1.2622
1.1673	0.6667	75	1.0246
0.965	0.8889	100	0.8292
0.6214	1.1111	125	0.6963
0.4369	1.3333	150	0.6120
0.3834	1.5556	175	0.5252
0.3739	1.7778	200	0.4924

Framework versions

• PEFT 0.12.0
• Transformers 4.43.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1