mrm8488's picture
Update README.md
7752fbc
|
raw
history blame
1.62 kB
---
license: bigscience-bloom-rail-1.0
tags:
- generated_from_trainer
model-index:
- name: bloom-560m-finetuned-the-stack-cobol
results: []
widget:
- text: "IDENTIFICATION DIVISION.\n
PROGRAM-ID. HELLO.\n\n
DATA DIVISION.\n
WORKING-STORAGE SECTION.\n
01 WS-NAME PIC A(30).\n
01 WS-ID PIC 9(5) VALUE 12345.\n\n
PROCEDURE DIVISION"
---
<!-- 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. -->
# bloom-560m-finetuned-the-stack-cobol
This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0341
## 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-05
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.7749 | 1.31 | 1000 | 1.0341 |
### Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0+cu117
- Datasets 2.5.1
- Tokenizers 0.13.0