mango-16-0.00002-fin

This model is a fine-tuned version of klue/roberta-large on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2255
  • Accuracy: 0.6509
  • F1: 0.6458

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: 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: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
No log 1.0 466 1.0290 0.6469 0.6367
0.7697 2.0 932 1.1297 0.6418 0.6323
0.5182 3.0 1398 1.2255 0.6509 0.6458

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0a0+b5021ba
  • Datasets 2.6.2
  • Tokenizers 0.14.1
Downloads last month
110
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for bella05/mango-16-0.00002-fin

Base model

klue/roberta-large
Finetuned
(68)
this model