Hugging Face's logo

jlpan
/
SteloCoder

Text Generation
Transformers
PyTorch
gpt_bigcode
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
jlpan commited on
Commit
8ea590b
•
1 Parent(s): d24731e

End of training

Browse files
Files changed (7) hide show
  1. README.md +23 -17
  2. pytorch_model-00001-of-00004.bin +2 -2
  3. pytorch_model-00002-of-00004.bin +2 -2
  4. pytorch_model-00003-of-00004.bin +2 -2
  5. pytorch_model-00004-of-00004.bin +2 -2
  6. pytorch_model.bin.index.json +0 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.1210
19
  - Learning Rate: 0.0
20
 
21
  ## Model description
@@ -35,7 +35,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 4e-05
39
  - train_batch_size: 1
40
  - eval_batch_size: 1
41
  - seed: 42
@@ -44,26 +44,32 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_steps: 50
47
- - training_steps: 700
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Rate |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
- | 0.1429 | 0.07 | 50 | 0.1353 | 4e-05 |
54
- | 0.1442 | 0.14 | 100 | 0.1355 | 0.0000 |
55
- | 0.1392 | 0.21 | 150 | 0.1331 | 0.0000 |
56
- | 0.1398 | 0.29 | 200 | 0.1302 | 0.0000 |
57
- | 0.1428 | 0.36 | 250 | 0.1281 | 0.0000 |
58
- | 0.137 | 1.01 | 300 | 0.1259 | 0.0000 |
59
- | 0.1439 | 1.08 | 350 | 0.1245 | 0.0000 |
60
- | 0.1422 | 1.15 | 400 | 0.1253 | 0.0000 |
61
- | 0.137 | 1.22 | 450 | 0.1219 | 0.0000 |
62
- | 0.1397 | 1.29 | 500 | 0.1209 | 0.0000 |
63
- | 0.1405 | 1.36 | 550 | 0.1209 | 0.0000 |
64
- | 0.1376 | 2.01 | 600 | 0.1210 | 0.0000 |
65
- | 0.1427 | 2.08 | 650 | 0.1210 | 0.0000 |
66
- | 0.1404 | 2.15 | 700 | 0.1210 | 0.0 |
 
 
 
 
 
 
67
 
68
 
69
  ### Framework versions
 
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: 0.1043
19
  - Learning Rate: 0.0
20
 
21
  ## Model description
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
  - train_batch_size: 1
40
  - eval_batch_size: 1
41
  - seed: 42
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_steps: 50
47
+ - training_steps: 1000
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Rate |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 0.1293 | 0.05 | 50 | 0.1218 | 5e-05 |
54
+ | 0.1332 | 0.1 | 100 | 0.1135 | 0.0000 |
55
+ | 0.1346 | 0.15 | 150 | 0.1117 | 0.0000 |
56
+ | 0.1336 | 0.2 | 200 | 0.1127 | 0.0000 |
57
+ | 0.1378 | 0.25 | 250 | 0.1116 | 0.0000 |
58
+ | 0.1321 | 0.3 | 300 | 0.1083 | 0.0000 |
59
+ | 0.1335 | 0.35 | 350 | 0.1075 | 0.0000 |
60
+ | 0.1316 | 0.4 | 400 | 0.1065 | 0.0000 |
61
+ | 0.1298 | 0.45 | 450 | 0.1062 | 0.0000 |
62
+ | 0.1331 | 0.5 | 500 | 0.1055 | 0.0000 |
63
+ | 0.1355 | 0.55 | 550 | 0.1048 | 0.0000 |
64
+ | 0.1299 | 0.6 | 600 | 0.1044 | 0.0000 |
65
+ | 0.1387 | 0.65 | 650 | 0.1048 | 0.0000 |
66
+ | 0.1278 | 0.7 | 700 | 0.1047 | 0.0000 |
67
+ | 0.1285 | 0.75 | 750 | 0.1045 | 0.0000 |
68
+ | 0.1278 | 0.8 | 800 | 0.1045 | 0.0000 |
69
+ | 0.1283 | 0.85 | 850 | 0.1045 | 0.0000 |
70
+ | 0.124 | 0.9 | 900 | 0.1043 | 0.0000 |
71
+ | 0.1258 | 0.95 | 950 | 0.1043 | 0.0000 |
72
+ | 0.1319 | 1.0 | 1000 | 0.1043 | 0.0 |
73
 
74
 
75
  ### Framework versions
pytorch_model-00001-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc0d9dca38f82d341985bb8c0efbdc243e7e5c9cfe370d87c75d98108566ec5a
3
- size 9991489184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071992b77328619a86cac3ac7b01a7669a2e555288ecb043ac9b1d2e5f18bf42
3
+ size 9985905352
pytorch_model-00002-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f792aef9c1a20a870f1e3db8efe0493e69fafd71e24cc4f44aa67d5332c44fc
3
- size 9892219467
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad3c5f0ccc3ab4aed6dae4cf9cfcfc787e9ef97f07a12bc578a66fb4cf6e5f22
3
+ size 9886413709
pytorch_model-00003-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b609967bba3f18a228e11341d90c80269756baa1144e591ae095afc6b5f31a91
3
- size 9892219467
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34330937eca8d09fc302368c9a65659ece36907174f964ae586304350a9da5f8
3
+ size 9886413709
pytorch_model-00004-of-00004.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ad2c67a4a7cb1d8245ec4f135f543f7f3771bb5993e79ee48d2c553485d825c
3
- size 1366486131
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e321b7d8fac31351e7f1541ab7c8bff54eedfcc38e484a4e077f5eea772b5d
3
+ size 1365793059
pytorch_model.bin.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4fb93da08d8677d965035a9f91d39b2cd4f271f13ea89a6bd5408309f81646d
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5dfdd87af29201a458a346389abbae2e9bada0ccd244f7c6f6971f9429a98e0
3
  size 4027