canine-rando-30-chars-5-epoch

This model is a fine-tuned version of google/canine-c on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6015
  • Accuracy: 0.7066

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 242 0.6975 0.5289
No log 2.0 484 0.5939 0.6983
0.6861 3.0 726 0.5975 0.6942
0.6861 4.0 968 0.5858 0.7149
0.6213 5.0 1210 0.6015 0.7066

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.0.0+cu117
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
14
Safetensors
Model size
132M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for addykan/canine-rando-30-chars-5-epoch

Base model

google/canine-c
Finetuned
(8)
this model