level_c_huge_sentiment_tb_4

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: 1.6416

accuracy

: 0.6291

: 0.6086

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 | 3.3593 | 0.4225 | 0.3761 | | No log | 2.0 | 244 | 2.8026 | 0.5070 | 0.4592 | | No log | 3.0 | 366 | 2.4920 | 0.5540 | 0.5025 | | No log | 4.0 | 488 | 2.3450 | 0.5587 | 0.5031 | | 2.7182 | 5.0 | 610 | 2.1556 | 0.5869 | 0.5347 | | 2.7182 | 6.0 | 732 | 1.9940 | 0.5775 | 0.5333 | | 2.7182 | 7.0 | 854 | 1.8755 | 0.5915 | 0.5443 | | 2.7182 | 8.0 | 976 | 1.8064 | 0.5634 | 0.5129 | | 1.565 | 9.0 | 1098 | 1.7662 | 0.6056 | 0.5692 | | 1.565 | 10.0 | 1220 | 1.7164 | 0.6103 | 0.5790 | | 1.565 | 11.0 | 1342 | 1.6277 | 0.6197 | 0.6002 | | 1.565 | 12.0 | 1464 | 1.6579 | 0.6338 | 0.6035 | | 0.8768 | 13.0 | 1586 | 1.6416 | 0.6291 | 0.6086 |

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/level_c_huge_sentiment_tb_4

Base model

distilbert/distilbert-base-uncased

Finetuned

(12716)

this model