simonycl / llama-3-8b-instruct-agg-judge

huggingface.co
Total runs: 13
24-hour runs: 0
7-day runs: 0
30-day runs: 5
Model's Last Updated: November 21 2024
text-generation

Introduction of llama-3-8b-instruct-agg-judge

Model Details of llama-3-8b-instruct-agg-judge

llama-3-8b-instruct-agg-judge

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the simonycl/llama3-ultrafeedback-annotate-judge-5 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6314
  • Rewards/chosen: -1.4785
  • Rewards/rejected: -1.8808
  • Rewards/accuracies: 0.6402
  • Rewards/margins: 0.4022
  • Logps/rejected: -332.7695
  • Logps/chosen: -294.6159
  • Logits/rejected: -1.5412
  • Logits/chosen: -1.5384
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
0.5551 0.8550 400 0.6314 -1.4785 -1.8808 0.6402 0.4022 -332.7695 -294.6159 -1.5412 -1.5384
Framework versions
  • Transformers 4.44.0
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1

Runs of simonycl llama-3-8b-instruct-agg-judge on huggingface.co

13
Total runs
0
24-hour runs
-2
3-day runs
0
7-day runs
5
30-day runs

More Information About llama-3-8b-instruct-agg-judge huggingface.co Model

More llama-3-8b-instruct-agg-judge license Visit here:

https://choosealicense.com/licenses/llama3

llama-3-8b-instruct-agg-judge huggingface.co

llama-3-8b-instruct-agg-judge huggingface.co is an AI model on huggingface.co that provides llama-3-8b-instruct-agg-judge's model effect (), which can be used instantly with this simonycl llama-3-8b-instruct-agg-judge model. huggingface.co supports a free trial of the llama-3-8b-instruct-agg-judge model, and also provides paid use of the llama-3-8b-instruct-agg-judge. Support call llama-3-8b-instruct-agg-judge model through api, including Node.js, Python, http.

llama-3-8b-instruct-agg-judge huggingface.co Url

https://huggingface.co/simonycl/llama-3-8b-instruct-agg-judge

simonycl llama-3-8b-instruct-agg-judge online free

llama-3-8b-instruct-agg-judge huggingface.co is an online trial and call api platform, which integrates llama-3-8b-instruct-agg-judge's modeling effects, including api services, and provides a free online trial of llama-3-8b-instruct-agg-judge, you can try llama-3-8b-instruct-agg-judge online for free by clicking the link below.

simonycl llama-3-8b-instruct-agg-judge online free url in huggingface.co:

https://huggingface.co/simonycl/llama-3-8b-instruct-agg-judge

llama-3-8b-instruct-agg-judge install

llama-3-8b-instruct-agg-judge is an open source model from GitHub that offers a free installation service, and any user can find llama-3-8b-instruct-agg-judge on GitHub to install. At the same time, huggingface.co provides the effect of llama-3-8b-instruct-agg-judge install, users can directly use llama-3-8b-instruct-agg-judge installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

llama-3-8b-instruct-agg-judge install url in huggingface.co:

https://huggingface.co/simonycl/llama-3-8b-instruct-agg-judge

Url of llama-3-8b-instruct-agg-judge

llama-3-8b-instruct-agg-judge huggingface.co Url

Provider of llama-3-8b-instruct-agg-judge huggingface.co

simonycl
ORGANIZATIONS

Other API from simonycl