mca-sentiment-analyzer-v2

This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment-latest on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1090
  • Accuracy: 0.9668
  • F1 Macro: 0.9673
  • F1 Weighted: 0.9669

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-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Macro F1 Weighted
1.2893 0.1559 20 0.9350 0.6074 0.4810 0.4802
0.8368 0.3119 40 0.5051 0.8848 0.8833 0.8831
0.6255 0.4678 60 0.2471 0.9336 0.9341 0.9336
0.469 0.6238 80 0.1967 0.9297 0.9299 0.9295
0.3423 0.7797 100 0.1227 0.9551 0.9558 0.9553
0.3477 0.9357 120 0.1090 0.9668 0.9673 0.9669

Framework versions

  • Transformers 4.56.1
  • Pytorch 2.8.0+cu126
  • Datasets 4.0.0
  • Tokenizers 0.22.0
Downloads last month
16
Safetensors
Model size
0.1B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Relacosm/mca-sentiment-analyzer-v2

Finetuned
(219)
this model

Space using Relacosm/mca-sentiment-analyzer-v2 1

Evaluation results