cot_method2test-mistral-7B_v0

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

• Loss: 1.7398

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: 2.5e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• 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: 5
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
1.9073	2.67	10	1.4951
1.6109	5.33	20	1.4208
1.2815	8.0	30	1.3794
0.9683	10.67	40	1.3829
0.6975	13.33	50	1.4201
0.4513	16.0	60	1.4823
0.2964	18.67	70	1.5715
0.1858	21.33	80	1.6517
0.1355	24.0	90	1.7184
0.1086	26.67	100	1.7398

Framework versions

• PEFT 0.7.2.dev0
• Transformers 4.37.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0