mistral_instruct_generation

tmq12022002/mistral_instruct_generation

mistral_instruct_generation is a machine learning model from tmq12022002. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

Access

Public

Updated Nov 30, 2023

Repo size

110 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors109 MB · 98%

At a glance

License: apache-2.0
Access: Public
Created: Nov 30, 2023
Updated: Nov 30, 2023
SHA: b823ee7b

Base models

akjindal53244/Arithmo-Mistral-7B

Model card

From the Hugging Face model README

mistral_instruct_generation

This model is a fine-tuned version of akjindal53244/Arithmo-Mistral-7B on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7043

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: 0.0002
train_batch_size: 4
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
lr_scheduler_warmup_steps: 0.03
training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
0.8974	0.07	20	0.8109
0.693	0.14	40	0.7250
0.6569	0.21	60	0.6995
0.6472	0.28	80	0.6732
0.5843	0.35	100	0.6660
0.5627	0.42	120	0.6701
0.5224	0.49	140	0.6805
0.5166	0.56	160	0.6883
0.47	0.62	180	0.6900
0.4553	0.69	200	0.7043

Framework versions

Transformers 4.35.2
Pytorch 2.0.0
Datasets 2.15.0
Tokenizers 0.15.0

License: apache-2.0
Created: Nov 30, 2023
Updated: Nov 30, 2023