mistral_charttotext_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: 0.5696
• Rouge1: 0.8028
• Rougel: 0.7560

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
0.6658	0.9980	380	0.5965	0.7724	0.7264
0.5686	1.9987	761	0.5753	0.7833	0.7375
0.5714	2.9980	1140	0.5517	0.8027	0.7613
0.5672	3.9980	1520	0.5664	0.8067	0.7564
0.5136	4.9980	1900	0.5672	0.8053	0.7572
0.5118	5.9980	2280	0.5696	0.8028	0.7560

Framework versions

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