chchen / Falcon-7B-Instruct-ORPO-SAA

huggingface.co
Total runs: 6
24-hour runs: 0
7-day runs: 1
30-day runs: 2
Model's Last Updated: June 02 2024

Introduction of Falcon-7B-Instruct-ORPO-SAA

Model Details of Falcon-7B-Instruct-ORPO-SAA

Falcon-7B-Instruct-ORPO-SALT

This model is a fine-tuned version of tiiuae/falcon-7b-instruct on the dpo_mix_en and the bct_non_cot_dpo_1000 datasets. It achieves the following results on the evaluation set:

  • Loss: 1.4485
  • Rewards/chosen: -0.1373
  • Rewards/rejected: -0.1429
  • Rewards/accuracies: 0.4809
  • Rewards/margins: 0.0056
  • Logps/rejected: -1.4290
  • Logps/chosen: -1.3726
  • Logits/rejected: -14.3178
  • Logits/chosen: -14.2778
  • Sft Loss: 1.3726
  • Odds Ratio Loss: 0.7590
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-06
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 0.1
  • num_epochs: 3.0
Training results
Training Loss Epoch Step Validation Loss Rewards/chosen Rewards/rejected Rewards/accuracies Rewards/margins Logps/rejected Logps/chosen Logits/rejected Logits/chosen Sft Loss Odds Ratio Loss
1.5005 0.8082 500 1.5202 -0.1444 -0.1490 0.4818 0.0046 -1.4898 -1.4436 -14.2657 -14.2276 1.4436 0.7658
1.3401 1.6165 1000 1.4635 -0.1387 -0.1442 0.4836 0.0055 -1.4423 -1.3875 -14.3083 -14.2685 1.3875 0.7603
1.446 2.4247 1500 1.4485 -0.1373 -0.1429 0.4809 0.0056 -1.4290 -1.3726 -14.3178 -14.2778 1.3726 0.7590
Framework versions
  • PEFT 0.10.0
  • Transformers 4.40.1
  • Pytorch 2.3.0
  • Datasets 2.19.0
  • Tokenizers 0.19.1

Runs of chchen Falcon-7B-Instruct-ORPO-SAA on huggingface.co

6
Total runs
0
24-hour runs
0
3-day runs
1
7-day runs
2
30-day runs

More Information About Falcon-7B-Instruct-ORPO-SAA huggingface.co Model

More Falcon-7B-Instruct-ORPO-SAA license Visit here:

https://choosealicense.com/licenses/apache-2.0

Falcon-7B-Instruct-ORPO-SAA huggingface.co

Falcon-7B-Instruct-ORPO-SAA huggingface.co is an AI model on huggingface.co that provides Falcon-7B-Instruct-ORPO-SAA's model effect (), which can be used instantly with this chchen Falcon-7B-Instruct-ORPO-SAA model. huggingface.co supports a free trial of the Falcon-7B-Instruct-ORPO-SAA model, and also provides paid use of the Falcon-7B-Instruct-ORPO-SAA. Support call Falcon-7B-Instruct-ORPO-SAA model through api, including Node.js, Python, http.

Falcon-7B-Instruct-ORPO-SAA huggingface.co Url

https://huggingface.co/chchen/Falcon-7B-Instruct-ORPO-SAA

chchen Falcon-7B-Instruct-ORPO-SAA online free

Falcon-7B-Instruct-ORPO-SAA huggingface.co is an online trial and call api platform, which integrates Falcon-7B-Instruct-ORPO-SAA's modeling effects, including api services, and provides a free online trial of Falcon-7B-Instruct-ORPO-SAA, you can try Falcon-7B-Instruct-ORPO-SAA online for free by clicking the link below.

chchen Falcon-7B-Instruct-ORPO-SAA online free url in huggingface.co:

https://huggingface.co/chchen/Falcon-7B-Instruct-ORPO-SAA

Falcon-7B-Instruct-ORPO-SAA install

Falcon-7B-Instruct-ORPO-SAA is an open source model from GitHub that offers a free installation service, and any user can find Falcon-7B-Instruct-ORPO-SAA on GitHub to install. At the same time, huggingface.co provides the effect of Falcon-7B-Instruct-ORPO-SAA install, users can directly use Falcon-7B-Instruct-ORPO-SAA installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Falcon-7B-Instruct-ORPO-SAA install url in huggingface.co:

https://huggingface.co/chchen/Falcon-7B-Instruct-ORPO-SAA

Url of Falcon-7B-Instruct-ORPO-SAA

Falcon-7B-Instruct-ORPO-SAA huggingface.co Url

Provider of Falcon-7B-Instruct-ORPO-SAA huggingface.co

chchen
ORGANIZATIONS

Other API from chchen