8473c6f3cd
Model: jackf857/llama-3-8b-base-ipo-ultrafeedback-4xh200-batch-128-rerun-2-runpod Source: Original Platform
77 lines
2.6 KiB
Markdown
77 lines
2.6 KiB
Markdown
---
|
|
library_name: transformers
|
|
base_model: W-61/llama-3-8b-base-sft-ultrachat-8xh200
|
|
tags:
|
|
- alignment-handbook
|
|
- ipo
|
|
- generated_from_trainer
|
|
datasets:
|
|
- HuggingFaceH4/ultrafeedback_binarized
|
|
model-index:
|
|
- name: llama-3-8b-base-ipo-ultrafeedback-4xh200-batch-128
|
|
results: []
|
|
---
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
# llama-3-8b-base-ipo-ultrafeedback-4xh200-batch-128
|
|
|
|
This model is a fine-tuned version of [W-61/llama-3-8b-base-sft-ultrachat-8xh200](https://huggingface.co/W-61/llama-3-8b-base-sft-ultrachat-8xh200) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 2331.0774
|
|
- Rewards/chosen: -0.0345
|
|
- Rewards/rejected: -0.0581
|
|
- Rewards/accuracies: 0.6880
|
|
- Rewards/margins: 0.0236
|
|
- Logps/rejected: -7.1047
|
|
- Logps/chosen: -4.5678
|
|
- Logits/rejected: -0.4255
|
|
- Logits/chosen: -0.4244
|
|
|
|
## 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: 4
|
|
- eval_batch_size: 4
|
|
- seed: 42
|
|
- distributed_type: multi-GPU
|
|
- num_devices: 4
|
|
- gradient_accumulation_steps: 8
|
|
- total_train_batch_size: 128
|
|
- total_eval_batch_size: 16
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
- 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 |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
|
| 19252.4328 | 0.4188 | 200 | 2421.5791 | -0.0163 | -0.0243 | 0.6360 | 0.0080 | -3.7316 | -2.7498 | -0.6321 | -0.6354 |
|
|
| 18622.8812 | 0.8377 | 400 | 2331.0774 | -0.0345 | -0.0581 | 0.6880 | 0.0236 | -7.1047 | -4.5678 | -0.4255 | -0.4244 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.51.0
|
|
- Pytorch 2.3.1+cu121
|
|
- Datasets 2.21.0
|
|
- Tokenizers 0.21.4
|