You can deploy this model and start earning money today!

nhatha2004/
Mistral7BInstruct-lora-classifier-test

Name: Mistral7BInstruct-lora-classifier-test
Availability: InStock

mistralai/Mistral-7B-Instruct-v0.3

apache-2.0

Views

No views yet

Mistral7BInstruct-lora-classifier-test

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the None dataset. It achieves the following results on the evaluation set:

Loss: 245.375
Accuracy: 0.5667
F1 Macro: 0.4937
F1 Weighted: 0.4645

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: 0.02
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 128
optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Weighted
No log	1.0	1	8.6797	0.3333	0.1754	0.1930
No log	2.0	2	191.5	0.5667	0.4693	0.4514
No log	3.0	3	284.5	0.3333	0.1667	0.1667
No log	4.0	4	255.875	0.5	0.4286	0.4048
No log	5.0	5	245.375	0.5667	0.4937	0.4645

Framework versions

PEFT 0.17.1
Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 4.1.1
Tokenizers 0.21.4

nhatha2004/Mistral7BInstruct-lora-classifier-test

Mistral7BInstruct-lora-classifier-test

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

nhatha2004/
Mistral7BInstruct-lora-classifier-test