|
---
|
|
library_name: transformers
|
|
license: mit
|
|
base_model: EleutherAI/gpt-neo-125M
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- rouge
|
|
model-index:
|
|
- name: MD5_gpt_neo_v1.1
|
|
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_v1.1
|
|
|
|
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: 3.3814
|
|
- Rouge1: 0.0840
|
|
- Rouge2: 0.0
|
|
- Rougel: 0.0695
|
|
|
|
## 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 | 0.9091 | 5 | 7.9635 | 0.0283 | 0.0 | 0.0231 |
|
|
| No log | 2.0 | 11 | 5.3680 | 0.0328 | 0.0 | 0.0258 |
|
|
| No log | 2.9091 | 16 | 4.0323 | 0.0856 | 0.0 | 0.0776 |
|
|
| No log | 4.0 | 22 | 3.4255 | 0.0840 | 0.0 | 0.0696 |
|
|
| No log | 4.5455 | 25 | 3.3814 | 0.0840 | 0.0 | 0.0695 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.46.1
|
|
- Pytorch 2.5.0+cu121
|
|
- Datasets 3.1.0
|
|
- Tokenizers 0.20.1
|
|
|
