Edit model card

distilroberta-base-reuters-bloomberg-ep30-ep20

This model is a fine-tuned version of judy93536/distilroberta-base-reuters-bloomberg on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2767

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: 7.2115e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.12
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.3775 1.0 13905 1.3298
1.4586 2.0 27810 1.4049
1.5213 3.0 41715 1.4486
1.5175 4.0 55620 1.4431
1.5007 5.0 69525 1.4346
1.4875 6.0 83430 1.4237
1.4695 7.0 97335 1.4145
1.4625 8.0 111240 1.4062
1.4343 9.0 125145 1.3892
1.4276 10.0 139050 1.3822
1.4147 11.0 152955 1.3658
1.3914 12.0 166860 1.3549
1.3774 13.0 180765 1.3425
1.3691 14.0 194670 1.3323
1.3523 15.0 208575 1.3193
1.3354 16.0 222480 1.3098
1.3221 17.0 236385 1.2990
1.3083 18.0 250290 1.2885
1.3052 19.0 264195 1.2830
1.2818 20.0 278100 1.2793

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1
Downloads last month
0
Safetensors
Model size
82.2M params
Tensor type
F32
·
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.

Model tree for judy93536/distilroberta-base-reuters-bloomberg-ep30-ep20

Finetuned
(2)
this model