metadata
library_name: transformers
license: mit
base_model: EleutherAI/gpt-neo-125M
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: MD5_gpt_neo_sanity_v1.0.1
results: []
MD5_gpt_neo_sanity_v1.0.1
This model is a fine-tuned version of EleutherAI/gpt-neo-125M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5127
- Rouge1: 0.4956
- Rouge2: 0.3272
- Rougel: 0.4733
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|---|---|---|---|---|---|---|
| No log | 0.9935 | 77 | 0.3877 | 0.488 | 0.3501 | 0.488 |
| No log | 2.0 | 155 | 0.4174 | 0.4879 | 0.3282 | 0.4719 |
| No log | 2.9935 | 232 | 0.4750 | 0.4995 | 0.3211 | 0.4727 |
| No log | 4.0 | 310 | 0.5073 | 0.4948 | 0.3268 | 0.4726 |
| No log | 4.9677 | 385 | 0.5127 | 0.4956 | 0.3272 | 0.4733 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 2.14.4
- Tokenizers 0.19.1