You can deploy this model and start earning money today!

Rahman1/
ft-mistral-7b-v01

Name: ft-mistral-7b-v01
Availability: InStock

peft

safetensors

generated_from_trainer

mistralai/Mistral-7B-v0.1

adapter

apache-2.0

Views

No views yet

ft-mistral-7b-v01

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the OpenAssistant/oasst_top1_2023-08-25 dataset. It achieves the following results on the evaluation set:

Loss: 2.6703

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: 0.0003
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 5
total_train_batch_size: 5
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.3784	1.0	90	2.3305
1.5259	2.0	180	2.6703

Framework versions

PEFT 0.7.1
Transformers 4.36.2
Pytorch 2.1.2
Datasets 2.15.0
Tokenizers 0.15.2

Rahman1/ft-mistral-7b-v01

ft-mistral-7b-v01

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Rahman1/
ft-mistral-7b-v01