update model card README.md
Browse files
README.md
CHANGED
@@ -1,24 +1,69 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
## Training procedure
|
5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
### Framework versions
|
7 |
|
8 |
-
-
|
9 |
-
-
|
10 |
-
-
|
11 |
-
-
|
12 |
-
- PEFT 0.5.0.dev0
|
13 |
-
- PEFT 0.5.0.dev0
|
14 |
-
- PEFT 0.5.0.dev0
|
15 |
-
- PEFT 0.5.0.dev0
|
16 |
-
- PEFT 0.5.0.dev0
|
17 |
-
- PEFT 0.5.0.dev0
|
18 |
-
- PEFT 0.5.0.dev0
|
19 |
-
- PEFT 0.5.0.dev0
|
20 |
-
- PEFT 0.5.0.dev0
|
21 |
-
- PEFT 0.5.0.dev0
|
22 |
-
- PEFT 0.5.0.dev0
|
23 |
-
|
24 |
-
- PEFT 0.5.0.dev0
|
|
|
1 |
---
|
2 |
+
license: bigcode-openrail-m
|
3 |
+
base_model: bigcode/starcoder
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: starcoder-tune-cpp2py-snippet3
|
8 |
+
results: []
|
9 |
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# starcoder-tune-cpp2py-snippet3
|
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: 0.3489
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
## Training procedure
|
33 |
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-06
|
38 |
+
- train_batch_size: 1
|
39 |
+
- eval_batch_size: 1
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 16
|
42 |
+
- total_train_batch_size: 16
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: cosine
|
45 |
+
- lr_scheduler_warmup_steps: 50
|
46 |
+
- training_steps: 500
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 0.5147 | 0.1 | 50 | 0.4060 |
|
53 |
+
| 0.4403 | 0.2 | 100 | 0.3419 |
|
54 |
+
| 0.425 | 0.3 | 150 | 0.3437 |
|
55 |
+
| 0.4298 | 0.4 | 200 | 0.3459 |
|
56 |
+
| 0.4259 | 0.5 | 250 | 0.3480 |
|
57 |
+
| 0.4167 | 0.6 | 300 | 0.3487 |
|
58 |
+
| 0.421 | 0.7 | 350 | 0.3485 |
|
59 |
+
| 0.4289 | 0.8 | 400 | 0.3487 |
|
60 |
+
| 0.424 | 0.9 | 450 | 0.3489 |
|
61 |
+
| 0.4163 | 1.0 | 500 | 0.3489 |
|
62 |
+
|
63 |
+
|
64 |
### Framework versions
|
65 |
|
66 |
+
- Transformers 4.32.0.dev0
|
67 |
+
- Pytorch 2.0.1+cu117
|
68 |
+
- Datasets 2.12.0
|
69 |
+
- Tokenizers 0.13.3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|