llama2_lora_ice3

thorirhrafn/llama2_lora_ice3

llama2_lora_ice3 is a machine learning model from thorirhrafn. 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 Dec 18, 2023

Repo size

26.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin134 MB · 100%

At a glance

Access: Public
Created: Dec 17, 2023
Updated: Dec 18, 2023
SHA: 64896fa4

Base models

meta-llama/Llama-2-7b-hf

Model card

From the Hugging Face model README

llama2_lora_ice3

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.8463

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: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 100000

Training results

Training Loss	Epoch	Step	Validation Loss
2.1526	0.19	5000	2.1084
2.092	0.38	10000	1.9905
1.9926	0.57	15000	1.9396
1.906	0.75	20000	1.9095
1.98	0.94	25000	1.8910
1.8817	1.13	30000	1.8801
1.9097	1.32	35000	1.8713
1.9143	1.51	40000	1.8639
1.8297	1.7	45000	1.8586
1.8671	1.88	50000	1.8543
1.88	2.07	55000	1.8523
1.8791	2.26	60000	1.8507
1.859	2.45	65000	1.8491
1.8812	2.64	70000	1.8479
1.86	2.83	75000	1.8472
1.8845	3.02	80000	1.8466
1.8432	3.2	85000	1.8465
1.8804	3.39	90000	1.8463
1.8327	3.58	95000	1.8464
1.8607	3.77	100000	1.8463

Framework versions

Transformers 4.34.1
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.14.1

Created: Dec 17, 2023
Updated: Dec 18, 2023