mt5-base-finetuned-anaphora_czech

patrixtano/mt5-base-finetuned-anaphora_czech

mt5-base-finetuned-anaphora_czech is a machine learning model from patrixtano. 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

5% of all-time downloads

All-time downloads

737

Public

Parameters

582M

485 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.3 GB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: mt5
Access: Public
Created: Sep 8, 2024
Updated: Sep 13, 2024
SHA: e6a2e2f4

Base models

google/mt5-base

Model card

From the Hugging Face model README

mt5-base-finetuned-anaphora_czech

This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0213
Score: 28.7290
Char Order: 6
Word Order: 0
Beta: 2

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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Score	Char Order	Beta
0.0604	1.0	11598	0.0277	28.6422	6	2
0.041	2.0	23196	0.0224	28.7007	6	2
0.0366	3.0	34794	0.0213	28.7290	6	2

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1

Library: transformers
Type: mt5
License: apache-2.0
Created: Sep 8, 2024
Updated: Sep 13, 2024