Edit model card

MiniLMv2-L6-H384-sst2

This model is a fine-tuned version of nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large on the glue dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2532
  • Accuracy: 0.9197

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: 3e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • distributed_type: sagemaker_data_parallel
  • num_devices: 8
  • total_train_batch_size: 256
  • total_eval_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5787 1.0 264 0.3496 0.8624
0.3413 2.0 528 0.2599 0.8991
0.2716 3.0 792 0.2651 0.9048
0.2343 4.0 1056 0.2532 0.9197
0.2165 5.0 1320 0.2636 0.9151

Framework versions

  • Transformers 4.17.0
  • Pytorch 1.10.2+cu113
  • Datasets 1.18.4
  • Tokenizers 0.11.6
Downloads last month
10
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train philschmid/MiniLMv2-L6-H384-sst2

Evaluation results