distilbert-8-4-1.1 – AI Model by emotions-entailment | AlphaNeural AI

You can deploy this model and start earning money today!

emotions-entailment/
distilbert-8-4-1.1

like

0

text-classification

generated_from_trainer

emotions-entailment/zero-shot-emotions-8-4-1.1

distilbert/distilbert-base-uncased

text-embeddings-inference

endpoints_compatible

Views

No views yet

distilbert-emotions-8-4-1.1

This model is a fine-tuned version of distilbert/distilbert-base-uncased. It achieves the following results on the evaluation set:

Loss: 0.3143
F1 Micro: 0.7945
F1 Macro: 0.7508
Precision Micro: 0.8447
Recall Micro: 0.75

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 24
eval_batch_size: 8
seed: 42
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
0.3186	1.0	10479	0.3185	0.7725	0.7162	0.8324	0.7206
0.3160	2.0	20958	0.3160	0.7958	0.7543	0.8360	0.7592
0.3145	3.0	31437	0.3153	0.7980	0.7570	0.8474	0.7540

Framework versions

Transformers 5.10.2
Pytorch 2.11.0+cu128
Datasets 4.8.5
Tokenizers 0.22.2