codegen-350M-mono-measurement_pred-diamonds-seed5

oliverdk/codegen-350M-mono-measurement_pred-diamonds-seed5

codegen-350M-mono-measurement_pred-diamonds-seed5 is a machine learning model from oliverdk. 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 bsd-3-clause.

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

Downloads · 30 days

10% of all-time downloads

All-time downloads

249

Public

Parameters

304M

3.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.2 GB · 100%

At a glance

License: bsd-3-clause
Model type: codegen_mp
Access: Public
Created: Dec 16, 2024
Updated: Dec 19, 2024
SHA: 74860cbf

Base models

Salesforce/codegen-350M-mono

Model card

From the Hugging Face model README

codegen-350M-mono-measurement_pred-diamonds-seed5

This model is a fine-tuned version of Salesforce/codegen-350M-mono on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5059
Accuracy: 0.9004
Accuracy Sensor 0: 0.9014
Auroc Sensor 0: 0.9556
Accuracy Sensor 1: 0.8987
Auroc Sensor 1: 0.9560
Accuracy Sensor 2: 0.9201
Auroc Sensor 2: 0.9711
Accuracy Aggregated: 0.8813
Auroc Aggregated: 0.9554

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: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 64
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Accuracy Sensor 0	Auroc Sensor 0	Accuracy Sensor 1	Auroc Sensor 1	Accuracy Sensor 2	Auroc Sensor 2	Accuracy Aggregated	Auroc Aggregated
0.2902	0.9997	781	0.3671	0.8431	0.8573	0.9025	0.8378	0.8994	0.8717	0.9333	0.8057	0.8989
0.1961	1.9994	1562	0.2889	0.8868	0.8871	0.9334	0.8813	0.9320	0.9069	0.9565	0.8718	0.9332
0.1311	2.9990	2343	0.3433	0.8875	0.8886	0.9531	0.8797	0.9519	0.9099	0.9714	0.8718	0.9536
0.0788	4.0	3125	0.3613	0.9028	0.9005	0.9566	0.9027	0.9579	0.9199	0.9716	0.8882	0.9555
0.043	4.9984	3905	0.5059	0.9004	0.9014	0.9556	0.8987	0.9560	0.9201	0.9711	0.8813	0.9554

Framework versions

Transformers 4.41.0
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Type: codegen_mp
License: bsd-3-clause
Created: Dec 16, 2024
Updated: Dec 19, 2024