Asynchronous RLHF
Collection
Models and datasets for asynchronous rlhf paper, see code at https://github.com/mnoukhov/async_rlhf
•
10 items
•
Updated
pythia410m-sft-tldr
This model is a fine-tuned version of EleutherAI/pythia-410m-deduped on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5290
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.6789 | 0.2007 | 183 | 2.5844 |
| 2.5737 | 0.4013 | 366 | 2.5528 |
| 2.5499 | 0.6020 | 549 | 2.5367 |
| 2.5298 | 0.8026 | 732 | 2.5290 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 4,552
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for mnoukhov/pythia410m-sft-tldr
Base model
EleutherAI/pythia-410m-deduped