update model card README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,6 @@ tags:
|
|
| 6 |
model-index:
|
| 7 |
- name: starcoder-cpp2py-newsnippet1
|
| 8 |
results: []
|
| 9 |
-
library_name: peft
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -36,11 +35,11 @@ More information needed
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 9e-05
|
| 39 |
-
- train_batch_size:
|
| 40 |
-
- eval_batch_size:
|
| 41 |
- seed: 42
|
| 42 |
-
- gradient_accumulation_steps:
|
| 43 |
-
- total_train_batch_size:
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_steps: 15
|
|
@@ -50,20 +49,16 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
-
| 4.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
| 62 |
|
| 63 |
-
- PEFT 0.5.0.dev0
|
| 64 |
-
- PEFT 0.5.0.dev0
|
| 65 |
-
- PEFT 0.5.0.dev0
|
| 66 |
-
- PEFT 0.5.0.dev0
|
| 67 |
- Transformers 4.32.0.dev0
|
| 68 |
- Pytorch 2.0.1+cu117
|
| 69 |
- Datasets 2.12.0
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: starcoder-cpp2py-newsnippet1
|
| 8 |
results: []
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.1961
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 9e-05
|
| 38 |
+
- train_batch_size: 32
|
| 39 |
+
- eval_batch_size: 32
|
| 40 |
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 8
|
| 42 |
+
- total_train_batch_size: 256
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: cosine
|
| 45 |
- lr_scheduler_warmup_steps: 15
|
|
|
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| 4.3812 | 0.17 | 25 | 0.4652 |
|
| 53 |
+
| 0.2923 | 0.33 | 50 | 0.2125 |
|
| 54 |
+
| 0.2148 | 0.5 | 75 | 0.2013 |
|
| 55 |
+
| 0.2051 | 0.67 | 100 | 0.1971 |
|
| 56 |
+
| 0.2003 | 0.83 | 125 | 0.1964 |
|
| 57 |
+
| 0.1882 | 1.05 | 150 | 0.1961 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
| 61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
- Transformers 4.32.0.dev0
|
| 63 |
- Pytorch 2.0.1+cu117
|
| 64 |
- Datasets 2.12.0
|