deberta-v3-xsmall-CoLA

This model is a fine-tuned version of microsoft/deberta-v3-xsmall on the GLUE COLA dataset. It achieves the following results on the evaluation set:

Loss: 0.4237
Matthews Correlation: 0.5895

Model description

Trying to find a decent optimum between accuracy/quality and inference speed.

{
    "epoch": 3.0,
    "eval_loss": 0.423,
    "eval_matthews_correlation": 0.589,
    "eval_runtime": 5.0422,
    "eval_samples": 1043,
    "eval_samples_per_second": 206.853,
    "eval_steps_per_second": 51.763
}

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: 6e-05
train_batch_size: 32
eval_batch_size: 4
seed: 16105
distributed_type: multi-GPU
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
0.3945	1.0	67	0.4323	0.5778
0.3214	2.0	134	0.4237	0.5895
0.3059	3.0	201	0.4636	0.5795

Framework versions

Transformers 4.27.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.8.0
Tokenizers 0.13.1