philschmid / llama3-fsdp-qlora

huggingface.co
Total runs: 18
24-hour runs: 0
7-day runs: -1
30-day runs: 9
Model's Last Updated: May 23 2024

Introduction of llama3-fsdp-qlora

Model Details of llama3-fsdp-qlora

llama3-fsdp-qlora

This model is a fine-tuned version of meta-llama/Meta-Llama-3-70b on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6181
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: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 128
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 3
Training results
Training Loss Epoch Step Validation Loss
1.6242 0.9892 46 1.6281
1.5831 2.0 93 1.6165
1.5587 2.9677 138 1.6181
Framework versions
  • PEFT 0.10.0
  • Transformers 4.40.0
  • Pytorch 2.1.0
  • Datasets 2.18.0
  • Tokenizers 0.19.1

Runs of philschmid llama3-fsdp-qlora on huggingface.co

18
Total runs
0
24-hour runs
-1
3-day runs
-1
7-day runs
9
30-day runs

More Information About llama3-fsdp-qlora huggingface.co Model

More llama3-fsdp-qlora license Visit here:

https://choosealicense.com/licenses/llama3

llama3-fsdp-qlora huggingface.co

llama3-fsdp-qlora huggingface.co is an AI model on huggingface.co that provides llama3-fsdp-qlora's model effect (), which can be used instantly with this philschmid llama3-fsdp-qlora model. huggingface.co supports a free trial of the llama3-fsdp-qlora model, and also provides paid use of the llama3-fsdp-qlora. Support call llama3-fsdp-qlora model through api, including Node.js, Python, http.

llama3-fsdp-qlora huggingface.co Url

https://huggingface.co/philschmid/llama3-fsdp-qlora

philschmid llama3-fsdp-qlora online free

llama3-fsdp-qlora huggingface.co is an online trial and call api platform, which integrates llama3-fsdp-qlora's modeling effects, including api services, and provides a free online trial of llama3-fsdp-qlora, you can try llama3-fsdp-qlora online for free by clicking the link below.

philschmid llama3-fsdp-qlora online free url in huggingface.co:

https://huggingface.co/philschmid/llama3-fsdp-qlora

llama3-fsdp-qlora install

llama3-fsdp-qlora is an open source model from GitHub that offers a free installation service, and any user can find llama3-fsdp-qlora on GitHub to install. At the same time, huggingface.co provides the effect of llama3-fsdp-qlora install, users can directly use llama3-fsdp-qlora installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

llama3-fsdp-qlora install url in huggingface.co:

https://huggingface.co/philschmid/llama3-fsdp-qlora

Url of llama3-fsdp-qlora

llama3-fsdp-qlora huggingface.co Url

Provider of llama3-fsdp-qlora huggingface.co

philschmid
ORGANIZATIONS

Other API from philschmid