c16205e044
Model: jackf857/llama-3-8b-base-kto-ultrafeedback-4xh200-batch-128-20260427-194056 Source: Original Platform
79 lines
2.9 KiB
Markdown
79 lines
2.9 KiB
Markdown
---
|
|
library_name: transformers
|
|
base_model: W-61/llama-3-8b-base-sft-ultrachat-8xh200
|
|
tags:
|
|
- alignment-handbook
|
|
- kto
|
|
- generated_from_trainer
|
|
datasets:
|
|
- HuggingFaceH4/ultrafeedback_binarized
|
|
model-index:
|
|
- name: llama-3-8b-base-kto-ultrafeedback-4xh200-batch-128-20260427-194056
|
|
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-kto-ultrafeedback-4xh200-batch-128-20260427-194056
|
|
|
|
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: 0.4319
|
|
- Rewards/chosen: -0.5716
|
|
- Logps/chosen: -345.0196
|
|
- Rewards/rejected: -1.4489
|
|
- Logps/rejected: -411.8449
|
|
- Rewards/margins: 0.8773
|
|
- Kl: 0.0
|
|
- Logits/chosen: -377414720.0
|
|
- Logits/rejected: -376930848.0
|
|
|
|
## 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: 8
|
|
- eval_batch_size: 8
|
|
- seed: 42
|
|
- distributed_type: multi-GPU
|
|
- num_devices: 4
|
|
- gradient_accumulation_steps: 4
|
|
- total_train_batch_size: 128
|
|
- total_eval_batch_size: 32
|
|
- 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 | Logps/chosen | Rewards/rejected | Logps/rejected | Rewards/margins | Kl | Logits/chosen | Logits/rejected |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------------:|:------------:|:----------------:|:--------------:|:---------------:|:---:|:-------------:|:---------------:|
|
|
| 1.8447 | 0.2094 | 200 | 0.4646 | -0.6301 | -350.8658 | -0.9983 | -366.7805 | 0.3682 | 0.0 | -401673280.0 | -397073248.0 |
|
|
| 1.7296 | 0.4188 | 400 | 0.4408 | -0.6904 | -356.8998 | -1.3983 | -406.7836 | 0.7079 | 0.0 | -377831392.0 | -377408832.0 |
|
|
| 1.685 | 0.6283 | 600 | 0.4325 | -0.9586 | -383.711 | -1.8718 | -454.1356 | 0.9133 | 0.0 | -388254240.0 | -387494368.0 |
|
|
| 1.7464 | 0.8377 | 800 | 0.4319 | -0.5716 | -345.0196 | -1.4489 | -411.8449 | 0.8773 | 0.0 | -377414720.0 | -376930848.0 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.51.0
|
|
- Pytorch 2.3.1+cu121
|
|
- Datasets 2.21.0
|
|
- Tokenizers 0.21.4
|