mistral_wikitable_FV

This model is a fine-tuned version of unsloth/mistral-7b-instruct-v0.2-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3567
• Rouge1: 0.8764
• Rougel: 0.8720

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 1
• seed: 3407
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 5
• num_epochs: 6
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rougel
0.5561	0.9984	156	0.4506	0.8474	0.8405
0.4761	1.9968	312	0.4096	0.8636	0.8575
0.3846	2.9952	468	0.3823	0.8693	0.8648
0.3334	4.0	625	0.3666	0.8741	0.8697
0.3367	4.9984	781	0.3566	0.8773	0.8729
0.298	5.9904	936	0.3567	0.8764	0.8720

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.2.0
• Datasets 2.16.0
• Tokenizers 0.19.1