Lyubka/2-1-2-emoticons-haiku-v130

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

2-1-2-emoticons-haiku-v130

This model is a fine-tuned version of Lyubka/2-1-2-emoticons on the None dataset. It achieves the following results on the evaluation set:

• —Loss: 0.8097
• —Accuracy: 0.5820
• —Recall Neg: 0.7576
• —Recall Neu: 0.7940
• —Recall Pos: 0.2552

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: 1e-05
• —trainbatchsize: 32
• —evalbatchsize: 64
• —seed: 42
• —optimizer: Use adamwtorchfused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 0.1
• —num_epochs: 3
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 5.12.1
• —Pytorch 2.12.1+cu130
• —Datasets 5.0.0
• —Tokenizers 0.22.2