simonycl / llama-3.1-8b-instruct-ultrafeedback-armorm

huggingface.co
Total runs: 12
24-hour runs: 0
7-day runs: 1
30-day runs: 4
Model's Last Updated: September 01 2024
text-generation

Introduction of llama-3.1-8b-instruct-ultrafeedback-armorm

Model Details of llama-3.1-8b-instruct-ultrafeedback-armorm

llama-3.1-8b-instruct-armorm

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the simonycl/llama3.1-ultrafeedback-annotate-armorm dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3984
  • Rewards/chosen: -3.3263
  • Rewards/rejected: -5.1260
  • Rewards/accuracies: 0.8286
  • Rewards/margins: 1.7997
  • Logps/rejected: -786.4965
  • Logps/chosen: -595.5199
  • Logits/rejected: -2.6865
  • Logits/chosen: -2.7593
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-07
  • train_batch_size: 2
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1
Training results
Training Loss Epoch Step Validation Loss Rewards/chosen Rewards/rejected Rewards/accuracies Rewards/margins Logps/rejected Logps/chosen Logits/rejected Logits/chosen
0.4222 0.8443 400 0.3984 -3.3263 -5.1260 0.8286 1.7997 -786.4965 -595.5199 -2.6865 -2.7593
Framework versions
  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1

Runs of simonycl llama-3.1-8b-instruct-ultrafeedback-armorm on huggingface.co

12
Total runs
0
24-hour runs
1
3-day runs
1
7-day runs
4
30-day runs

More Information About llama-3.1-8b-instruct-ultrafeedback-armorm huggingface.co Model

More llama-3.1-8b-instruct-ultrafeedback-armorm license Visit here:

https://choosealicense.com/licenses/llama3.1

llama-3.1-8b-instruct-ultrafeedback-armorm huggingface.co

llama-3.1-8b-instruct-ultrafeedback-armorm huggingface.co is an AI model on huggingface.co that provides llama-3.1-8b-instruct-ultrafeedback-armorm's model effect (), which can be used instantly with this simonycl llama-3.1-8b-instruct-ultrafeedback-armorm model. huggingface.co supports a free trial of the llama-3.1-8b-instruct-ultrafeedback-armorm model, and also provides paid use of the llama-3.1-8b-instruct-ultrafeedback-armorm. Support call llama-3.1-8b-instruct-ultrafeedback-armorm model through api, including Node.js, Python, http.

llama-3.1-8b-instruct-ultrafeedback-armorm huggingface.co Url

https://huggingface.co/simonycl/llama-3.1-8b-instruct-ultrafeedback-armorm

simonycl llama-3.1-8b-instruct-ultrafeedback-armorm online free

llama-3.1-8b-instruct-ultrafeedback-armorm huggingface.co is an online trial and call api platform, which integrates llama-3.1-8b-instruct-ultrafeedback-armorm's modeling effects, including api services, and provides a free online trial of llama-3.1-8b-instruct-ultrafeedback-armorm, you can try llama-3.1-8b-instruct-ultrafeedback-armorm online for free by clicking the link below.

simonycl llama-3.1-8b-instruct-ultrafeedback-armorm online free url in huggingface.co:

https://huggingface.co/simonycl/llama-3.1-8b-instruct-ultrafeedback-armorm

llama-3.1-8b-instruct-ultrafeedback-armorm install

llama-3.1-8b-instruct-ultrafeedback-armorm is an open source model from GitHub that offers a free installation service, and any user can find llama-3.1-8b-instruct-ultrafeedback-armorm on GitHub to install. At the same time, huggingface.co provides the effect of llama-3.1-8b-instruct-ultrafeedback-armorm install, users can directly use llama-3.1-8b-instruct-ultrafeedback-armorm installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

llama-3.1-8b-instruct-ultrafeedback-armorm install url in huggingface.co:

https://huggingface.co/simonycl/llama-3.1-8b-instruct-ultrafeedback-armorm

Url of llama-3.1-8b-instruct-ultrafeedback-armorm

llama-3.1-8b-instruct-ultrafeedback-armorm huggingface.co Url

Provider of llama-3.1-8b-instruct-ultrafeedback-armorm huggingface.co

simonycl
ORGANIZATIONS

Other API from simonycl