metadata
library_name: transformers
base_model: uclanlp/plbart-base
tags:
- generated_from_trainer
datasets:
- code_search_net
metrics:
- bleu
model-index:
- name: code_docstring_model
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: code_search_net
type: code_search_net
config: python
split: validation
args: python
metrics:
- name: Bleu
type: bleu
value: 0
code_docstring_model
This model is a fine-tuned version of uclanlp/plbart-base on the code_search_net dataset. It achieves the following results on the evaluation set:
- Loss: 0.8020
- Bleu: 0.0
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 0.8912 | 0.9993 | 1076 | 0.8366 | 0.0 |
| 0.7932 | 1.9993 | 2152 | 0.8140 | 0.0 |
| 0.7662 | 2.9993 | 3228 | 0.8060 | 0.0 |
| 0.7433 | 3.9993 | 4304 | 0.8027 | 0.0 |
| 0.7351 | 4.9993 | 5380 | 0.8020 | 0.0 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0