parallelm / gpt2_medium_ZH_bpe_32768_parallel3-100_42

huggingface.co
Total runs: 4
24-hour runs: 0
7-day runs: 3
30-day runs: 1
Model's Last Updated: February 10 2026

Introduction of gpt2_medium_ZH_bpe_32768_parallel3-100_42

Model Details of gpt2_medium_ZH_bpe_32768_parallel3-100_42

gpt2_medium_ZH_bpe_32768_parallel3-100_42

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.7864
  • Accuracy: 0.3680
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: 5e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • total_train_batch_size: 128
  • total_eval_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 10
  • mixed_precision_training: Native AMP
Training results
Training Loss Epoch Step Validation Loss Accuracy
4.2872 1.0 22680 4.2185 0.3191
4.0791 2.0 45360 4.0398 0.3366
3.9649 3.0 68040 3.9573 0.3455
3.8913 4.0 90720 3.9049 0.3512
3.8295 5.0 113400 3.8688 0.3554
3.7779 6.0 136080 3.8421 0.3587
3.7282 7.0 158760 3.8209 0.3621
3.6856 8.0 181440 3.8039 0.3646
3.6399 9.0 204120 3.7917 0.3668
3.5989 10.0 226800 3.7864 0.3680
Framework versions
  • Transformers 4.41.2
  • Pytorch 2.8.0+cu128
  • Datasets 4.1.1
  • Tokenizers 0.19.1

Runs of parallelm gpt2_medium_ZH_bpe_32768_parallel3-100_42 on huggingface.co

4
Total runs
0
24-hour runs
2
3-day runs
3
7-day runs
1
30-day runs

More Information About gpt2_medium_ZH_bpe_32768_parallel3-100_42 huggingface.co Model

gpt2_medium_ZH_bpe_32768_parallel3-100_42 huggingface.co

gpt2_medium_ZH_bpe_32768_parallel3-100_42 huggingface.co is an AI model on huggingface.co that provides gpt2_medium_ZH_bpe_32768_parallel3-100_42's model effect (), which can be used instantly with this parallelm gpt2_medium_ZH_bpe_32768_parallel3-100_42 model. huggingface.co supports a free trial of the gpt2_medium_ZH_bpe_32768_parallel3-100_42 model, and also provides paid use of the gpt2_medium_ZH_bpe_32768_parallel3-100_42. Support call gpt2_medium_ZH_bpe_32768_parallel3-100_42 model through api, including Node.js, Python, http.

gpt2_medium_ZH_bpe_32768_parallel3-100_42 huggingface.co Url

https://huggingface.co/parallelm/gpt2_medium_ZH_bpe_32768_parallel3-100_42

parallelm gpt2_medium_ZH_bpe_32768_parallel3-100_42 online free

gpt2_medium_ZH_bpe_32768_parallel3-100_42 huggingface.co is an online trial and call api platform, which integrates gpt2_medium_ZH_bpe_32768_parallel3-100_42's modeling effects, including api services, and provides a free online trial of gpt2_medium_ZH_bpe_32768_parallel3-100_42, you can try gpt2_medium_ZH_bpe_32768_parallel3-100_42 online for free by clicking the link below.

parallelm gpt2_medium_ZH_bpe_32768_parallel3-100_42 online free url in huggingface.co:

https://huggingface.co/parallelm/gpt2_medium_ZH_bpe_32768_parallel3-100_42

gpt2_medium_ZH_bpe_32768_parallel3-100_42 install

gpt2_medium_ZH_bpe_32768_parallel3-100_42 is an open source model from GitHub that offers a free installation service, and any user can find gpt2_medium_ZH_bpe_32768_parallel3-100_42 on GitHub to install. At the same time, huggingface.co provides the effect of gpt2_medium_ZH_bpe_32768_parallel3-100_42 install, users can directly use gpt2_medium_ZH_bpe_32768_parallel3-100_42 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

gpt2_medium_ZH_bpe_32768_parallel3-100_42 install url in huggingface.co:

https://huggingface.co/parallelm/gpt2_medium_ZH_bpe_32768_parallel3-100_42

Url of gpt2_medium_ZH_bpe_32768_parallel3-100_42

gpt2_medium_ZH_bpe_32768_parallel3-100_42 huggingface.co Url

Provider of gpt2_medium_ZH_bpe_32768_parallel3-100_42 huggingface.co

parallelm
ORGANIZATIONS

Other API from parallelm