|
---
|
|
library_name: transformers
|
|
license: mit
|
|
base_model: EleutherAI/gpt-neo-125M
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- rouge
|
|
model-index:
|
|
- name: MD5_gpt_neo_v1.5
|
|
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. -->
|
|
|
|
# MD5_gpt_neo_v1.5
|
|
|
|
This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 9.2983
|
|
- Rouge1: 0.0139
|
|
- Rouge2: 0.0012
|
|
- Rougel: 0.0111
|
|
|
|
## 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: 2e-05
|
|
- train_batch_size: 2
|
|
- eval_batch_size: 2
|
|
- seed: 42
|
|
- gradient_accumulation_steps: 2
|
|
- total_train_batch_size: 4
|
|
- 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: linear
|
|
- num_epochs: 5
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
|
|
| No log | 1.0 | 231 | 7.6828 | 0.0114 | 0.0 | 0.0100 |
|
|
| No log | 2.0 | 462 | 11.4070 | 0.0109 | 0.0 | 0.0098 |
|
|
| 8.2172 | 3.0 | 693 | 10.2654 | 0.0166 | 0.0 | 0.0146 |
|
|
| 8.2172 | 4.0 | 924 | 9.4727 | 0.0235 | 0.0012 | 0.0169 |
|
|
| 29.1262 | 5.0 | 1155 | 9.2983 | 0.0139 | 0.0012 | 0.0111 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.46.1
|
|
- Pytorch 2.5.0+cu121
|
|
- Datasets 3.1.0
|
|
- Tokenizers 0.20.1
|
|
|
