QWEN_2_7B_MT

rishavranaut/QWEN_2_7B_MT

QWEN_2_7B_MT is a machine learning model from rishavranaut. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.

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

Downloads · 30 days

29% of all-time downloads

All-time downloads

Public

Repo size

809 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors40.4 MB · 78%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Sep 14, 2024
Updated: Sep 15, 2024
SHA: 586792ba

Base models

Qwen/Qwen2-7B

Model card

From the Hugging Face model README

QWEN_2_7B_MT

This model is a fine-tuned version of Qwen/Qwen2-7B on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7702
Accuracy: 0.78
Precision: 0.7979
Recall: 0.75
F1 score: 0.7732

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
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1 score
0.93	0.25	200	0.8818	0.6517	0.7264	0.4867	0.5828
0.6783	0.5	400	1.1545	0.59	0.7411	0.2767	0.4029
0.6849	0.75	600	0.7826	0.685	0.7424	0.5667	0.6427
0.6378	1.0	800	0.7399	0.695	0.7647	0.5633	0.6488
0.4773	1.25	1000	0.9978	0.66	0.8077	0.42	0.5526
0.4842	1.5	1200	0.6576	0.7333	0.6902	0.8467	0.7605
0.456	1.75	1400	0.6290	0.77	0.8068	0.71	0.7553
0.464	2.0	1600	0.6295	0.7617	0.7774	0.7333	0.7547
0.3689	2.25	1800	0.6090	0.7783	0.8224	0.71	0.7621
0.307	2.5	2000	0.6058	0.7733	0.7808	0.76	0.7703
0.3302	2.75	2200	0.6024	0.7867	0.7810	0.7967	0.7888
0.3156	3.0	2400	0.7082	0.765	0.8272	0.67	0.7403
0.2571	3.25	2600	0.9494	0.7017	0.8168	0.52	0.6354
0.2593	3.5	2800	0.6498	0.7717	0.8030	0.72	0.7592
0.2458	3.75	3000	0.6434	0.7867	0.7810	0.7967	0.7888
0.2135	4.0	3200	0.7042	0.775	0.7978	0.7367	0.7660
0.1582	4.25	3400	0.6730	0.78	0.7530	0.8333	0.7911
0.158	4.5	3600	0.7538	0.7783	0.8104	0.7267	0.7663
0.2043	4.75	3800	0.7398	0.785	0.8065	0.75	0.7772
0.163	5.0	4000	0.7702	0.78	0.7979	0.75	0.7732

Framework versions

PEFT 0.11.1
Transformers 4.44.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Library: peft
License: apache-2.0
Created: Sep 14, 2024
Updated: Sep 15, 2024