training_outputs2

reeddg/training_outputs2

training_outputs2 is a machine learning model from reeddg. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

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

Downloads · 30 days

Access

Public

Updated Mar 24, 2024

Repo size

68 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin16.8 MB · 87%

At a glance

Access: Public
Created: Mar 23, 2024
Updated: Mar 24, 2024
SHA: 1cf8559f

Base models

NousResearch/Llama-2-7b-hf

Model card

From the Hugging Face model README

training_outputs2

This model is a fine-tuned version of NousResearch/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0000
Accuracy: 1.0
Precision: 1.0
Recall: 1.0
F1: 1.0

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: linear
num_epochs: 3

Training results

Epoch	Step	Accuracy	Precision	Recall	F1
0.21	10	1.0	1.0	1.0	1.0
0.42	20	1.0	1.0	1.0	1.0
0.62	30	1.0	1.0	1.0	1.0
0.83	40	1.0	1.0	1.0	1.0
1.04	50	1.0	1.0	1.0	1.0
1.25	60	1.0	1.0	1.0	1.0
1.46	70	1.0	1.0	1.0	1.0
1.67	80	1.0	1.0	1.0	1.0
1.88	90	1.0	1.0	1.0	1.0
2.08	100	1.0	1.0	1.0	1.0
2.29	110	1.0	1.0	1.0	1.0
2.5	120	1.0	1.0	1.0	1.0
2.71	130	1.0	1.0	1.0	1.0
2.92	140	1.0	1.0	1.0	1.0

Framework versions

Transformers 4.31.0
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.13.3

Created: Mar 23, 2024
Updated: Mar 24, 2024