ONNX Model Zoo

jhpassion0621/kp-mt5-large

By jhpassion0621 · ↓ 5 · ♥ 0 · Updated 2024-03-11

What's in this repo

This page lists the files in jhpassion0621/kp-mt5-large, including decoder_model_merged_quantized.onnx, encoder_model_quantized.onnx.

  • 2 ONNX models (.onnx files)
  • 23 files, including 11 .json, 3 .0, 2 .onnx, 2 .model, 1 .md, 1 .safetensors
  • Last updated 2024-03-11

ONNX files

File Size Download
onnx/decoder_model_merged_quantized.onnx — Download
onnx/encoder_model_quantized.onnx — Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

kp-mt5-large

This model is a fine-tuned version of jhpassion0621/kp-mt5-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5586
  • Bleu: 43.3983
  • Gen Len: 45.6585

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: 2.59e-05
  • train_batch_size: 16
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Bleu Gen Len Validation Loss
1.0364 0.29 17000 32.5573 44.7582 0.8278
0.8819 0.58 34000 37.1161 45.0568 0.7062
0.7731 0.87 51000 40.329 45.7359 0.6188
0.7339 1.16 68000 41.7643 45.8618 0.5866
0.7093 1.45 85000 42.6878 45.5649 0.5657
0.6818 1.74 102000 43.2023 45.7701 0.5609
0.6739 2.00 117444 43.3983 45.6585 0.5586

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.1

Model info

transformers
transformers tensorboard onnx safetensors mt5 text2text-generation generated_from_trainer base_model:jhpassion0621/kp-mt5-large base_model:quantized:jhpassion0621/kp-mt5-large license:apache-2.0 endpoints_compatible region:us
↓ 5 ♥ 0

Created: 2024-02-06

Updated: 2024-03-11

View on Hugging Face

Files (23)

.gitattributes
README.md
config.json
generation_config.json
model.safetensors
onnx/config.json
onnx/decoder_model_merged_quantized.onnx ONNX
onnx/encoder_model_quantized.onnx ONNX
onnx/generation_config.json
onnx/ort_config.json
onnx/special_tokens_map.json
onnx/spiece.model
onnx/tokenizer.json
onnx/tokenizer_config.json
runs/Feb09_12-02-04_a11581f66ffb/events.out.tfevents.1707480131.a11581f66ffb.853.0
runs/Feb09_12-02-04_a11581f66ffb/events.out.tfevents.1707573277.a3389580e37d.741.0
runs/Feb09_12-02-04_a11581f66ffb/events.out.tfevents.1707656618.e0fcc477687a.6455.0
runs/Feb09_12-02-04_a11581f66ffb/events.out.tfevents.1707720713.e0fcc477687a.6455.1
special_tokens_map.json
spiece.model
tokenizer.json
tokenizer_config.json
training_args.bin

Related models

More from jhpassion0621

More models

No task type declared.

Popular models