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

Loss: 0.3073
F1 Micro: 0.7857
F1 Macro: 0.7410
Precision Micro: 0.8238
Recall Micro: 0.7510

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 6
total_train_batch_size: 24
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_steps: 3143
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Micro	F1 Macro	Precision Micro	Recall Micro
1.8702	1.0	10479	0.3111	0.7648	0.7128	0.8162	0.7195
1.8551	2.0	20958	0.3090	0.7862	0.7477	0.8178	0.7569
1.8460	3.0	31437	0.3082	0.7886	0.7512	0.8266	0.7539

Framework versions

Transformers 5.10.2
Pytorch 2.11.0+cu128
Datasets 4.8.5
Tokenizers 0.22.2

emotions-entailment/distilbert-8-4-1.25-85-65-75

distilbert-8-4-1.25-85-65-75

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

emotions-entailment/
distilbert-8-4-1.25-85-65-75