Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: jaigouk/go-bruins-bf16-ruby
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: go-bruins-ruby-bf16
|
| 8 |
+
results: []
|
| 9 |
+
language:
|
| 10 |
+
- en
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
# go-bruins-ruby-bf16
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [rwitz/go-bruins](https://huggingface.co/rwitz/go-bruins) on an unknown dataset.
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
- intention is to use this with system message for generating ruby codes
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
- writing rspec / ruby codes
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
- https://huggingface.co/datasets/jaigouk/coding-dataset
|
| 29 |
+
### Training hyperparameters
|
| 30 |
+
|
| 31 |
+
The following hyperparameters were used during training:
|
| 32 |
+
- learning_rate: 2e-05
|
| 33 |
+
- train_batch_size: 16
|
| 34 |
+
- eval_batch_size: 16
|
| 35 |
+
- seed: 42
|
| 36 |
+
- gradient_accumulation_steps: 4
|
| 37 |
+
- total_train_batch_size: 64
|
| 38 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 39 |
+
- lr_scheduler_type: constant
|
| 40 |
+
- lr_scheduler_warmup_steps: 1
|
| 41 |
+
- num_epochs: 1
|
| 42 |
+
|
| 43 |
+
### Training results
|
| 44 |
+
|
| 45 |
+
### Framework versions
|
| 46 |
+
|
| 47 |
+
- Transformers 4.35.0
|
| 48 |
+
- Pytorch 2.1.0+cu118
|
| 49 |
+
- Datasets 2.14.5
|
| 50 |
+
- Tokenizers 0.14.1
|