levela_huge_no_2

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.8190

accuracy

: 0.6620

: 0.6114

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: 5e-06
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50

Training results

accuracy

| |:-------------:|:-----:|:----:|:---------------:|:------------:|:------:| | No log | 1.0 | 122 | 0.9864 | 0.5493 | 0.4968 | | No log | 2.0 | 244 | 0.8840 | 0.5915 | 0.5348 | | No log | 3.0 | 366 | 0.8374 | 0.6432 | 0.5844 | | No log | 4.0 | 488 | 0.8469 | 0.6432 | 0.5831 | | 0.7831 | 5.0 | 610 | 0.8344 | 0.6714 | 0.6161 | | 0.7831 | 6.0 | 732 | 0.8190 | 0.6620 | 0.6114 | | 0.7831 | 7.0 | 854 | 0.8294 | 0.6808 | 0.6433 | | 0.7831 | 8.0 | 976 | 0.8389 | 0.6667 | 0.6295 |

Framework versions

Transformers 4.45.2
Pytorch 2.5.0+cu124
Datasets 3.0.1
Tokenizers 0.20.1

Downloads last month: -; Downloads are not tracked for this model. How to track

Safetensors

Model size

66.4M params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for iTroned/levela_huge_no_2

Base model

distilbert/distilbert-base-uncased

Finetuned

(12622)

this model