yanghuattt commited on
Commit
1f37b43
·
verified ·
1 Parent(s): 32d0df4

Model save

Browse files
Files changed (3) hide show
  1. README.md +71 -0
  2. generation_config.json +7 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: microsoft/CodeGPT-small-java
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: microsoft_CodeGPT-small-java_0_ft_clm
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # microsoft_CodeGPT-small-java_0_ft_clm
17
+
18
+ This model is a fine-tuned version of [microsoft/CodeGPT-small-java](https://huggingface.co/microsoft/CodeGPT-small-java) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.1672
21
+ - Accuracy: 0.7708
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 8e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 12
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 2
46
+ - gradient_accumulation_steps: 4
47
+ - total_train_batch_size: 32
48
+ - total_eval_batch_size: 24
49
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.02
52
+ - num_epochs: 5
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
58
+ | 0.8842 | 0.7788 | 500 | 1.1934 | 0.7688 |
59
+ | 0.7557 | 1.5576 | 1000 | 1.1676 | 0.7693 |
60
+ | 0.7033 | 2.3364 | 1500 | 1.1631 | 0.7705 |
61
+ | 0.6624 | 3.1153 | 2000 | 1.1650 | 0.7707 |
62
+ | 0.6414 | 3.8941 | 2500 | 1.1646 | 0.7710 |
63
+ | 0.6187 | 4.6729 | 3000 | 1.1672 | 0.7708 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.53.0
69
+ - Pytorch 2.7.1+cu126
70
+ - Datasets 3.6.0
71
+ - Tokenizers 0.21.2
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.53.0"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90a935fdeefbf1bf6ec1488cf392bcf4b0a0c0d7f85aea4675a54fc9c5fc5721
3
  size 503128704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2625f4a67307af8122da2f53f857d4edaf2aae056c793153cb1b5703bc9c040f
3
  size 503128704