reward_modeling_anthropic_hh_rm1e-3

alexwb/reward_modeling_anthropic_hh_rm1e-3

reward_modeling_anthropic_hh_rm1e-3 is a machine learning model from alexwb. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

12% of all-time downloads

All-time downloads

320

Public

Parameters

331M

1.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.3 GB · 100%

At a glance

License: other
Model type: opt
Access: Public
Created: Aug 7, 2024
Updated: Aug 7, 2024
SHA: 57192f95

Base models

facebook/opt-350m

Model card

From the Hugging Face model README

reward_modeling_anthropic_hh_rm1e-3

This model is a fine-tuned version of facebook/opt-350m on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6931
Accuracy: 0.9951

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: 0.001
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6998	0.1087	500	0.6931	0.7465
0.7074	0.2174	1000	0.6931	0.6653
0.6924	0.3262	1500	0.6931	0.7551
0.6985	0.4349	2000	0.6931	0.6347
0.6939	0.5436	2500	0.6931	0.7825
0.6978	0.6523	3000	0.6931	0.9096
0.6974	0.7610	3500	0.6931	0.9584
0.6935	0.8698	4000	0.6931	0.9607
0.6962	0.9785	4500	0.6931	0.9951

Framework versions

Transformers 4.40.2
Pytorch 2.4.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Type: opt
License: other
Created: Aug 7, 2024
Updated: Aug 7, 2024