You can deploy this model and start earning money today!

Shakhovak/
Mistral-7B-Instruct-v0.2-absa-laptops

Name: Mistral-7B-Instruct-v0.2-absa-laptops
Availability: InStock

generated_from_trainer

mistralai/Mistral-7B-Instruct-v0.2

finetune

apache-2.0

Views

No views yet

Mistral-7B-Instruct-v0.2-absa-laptops

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0235

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: 3e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
training_steps: 400
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.1844	0.36	40	0.1770
0.0756	0.72	80	0.0313
0.0262	1.08	120	0.0263
0.0203	1.44	160	0.0250
0.0194	1.8	200	0.0235
0.0159	2.16	240	0.0245
0.0132	2.52	280	0.0229
0.0131	2.88	320	0.0228
0.0105	3.24	360	0.0228
0.0097	3.6	400	0.0235

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Shakhovak/Mistral-7B-Instruct-v0.2-absa-laptops

Mistral-7B-Instruct-v0.2-absa-laptops

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Shakhovak/
Mistral-7B-Instruct-v0.2-absa-laptops