salt_language_ID

jq/salt_language_ID

salt_language_ID is a machine learning model from jq. 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 transformers. The card lists the license as apache-2.0.

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

Downloads · 30 days

19% of all-time downloads

All-time downloads

Public

Parameters

15.6M

125 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors62.3 MB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: t5
Access: Public
Created: May 7, 2024
Updated: May 7, 2024
SHA: 4c5361d5

Base models

google/t5-efficient-tiny

Datasets

generator

Model card

From the Hugging Face model README

salt_language_ID

This model is a fine-tuned version of google/t5-efficient-tiny on the generator dataset. It achieves the following results on the evaluation set:

Loss: 0.0158
Accuracy: 0.9735

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: 0.001
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 10
training_steps: 20000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5256	0.025	500	0.1505	0.7698
0.0708	0.05	1000	0.0447	0.9237
0.0547	0.075	1500	0.0540	0.9093
0.0476	0.1	2000	0.0428	0.9264
0.0413	0.125	2500	0.0334	0.9399
0.0404	0.15	3000	0.0293	0.9479
0.0374	0.175	3500	0.0324	0.9459
0.0359	0.2	4000	0.0257	0.9493
0.0353	0.225	4500	0.0267	0.9513
0.0336	0.25	5000	0.0234	0.9587
0.0337	0.275	5500	0.0253	0.9560
0.0324	0.3	6000	0.0186	0.9684
0.0307	0.325	6500	0.0208	0.9634
0.028	0.35	7000	0.0253	0.9573
0.0297	0.375	7500	0.0224	0.9617
0.0264	0.4	8000	0.0224	0.9607
0.027	0.425	8500	0.0185	0.9667
0.0266	0.45	9000	0.0222	0.9634
0.0259	0.475	9500	0.0221	0.9617
0.0244	0.5	10000	0.0187	0.9688
0.0243	0.525	10500	0.0164	0.9694
0.0248	0.55	11000	0.0184	0.9674
0.024	0.575	11500	0.0155	0.9704
0.0228	0.6	12000	0.0176	0.9671
0.0241	0.625	12500	0.0146	0.9755
0.0234	0.65	13000	0.0181	0.9681
0.0226	0.675	13500	0.0142	0.9758
0.0225	0.7	14000	0.0169	0.9718
0.0218	0.725	14500	0.0151	0.9711
0.0212	0.75	15000	0.0176	0.9735
0.0199	0.775	15500	0.0131	0.9741
0.0208	0.8	16000	0.0131	0.9775
0.0217	0.825	16500	0.0123	0.9788
0.0208	0.85	17000	0.0145	0.9758
0.0217	0.875	17500	0.0154	0.9694
0.0197	0.9	18000	0.0138	0.9765
0.0205	0.925	18500	0.0138	0.9748
0.0203	0.95	19000	0.0146	0.9748
0.0198	0.975	19500	0.0131	0.9755
0.0204	1.0	20000	0.0158	0.9735

Framework versions

Transformers 4.40.2
Pytorch 2.2.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Library: transformers
Type: t5
License: apache-2.0
Created: May 7, 2024
Updated: May 7, 2024