Huamin commited on
Commit
c64d4da
·
1 Parent(s): da4eb6f

End of training

Browse files
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigcode-openrail-m
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: santacoder-finetuned-the-stack-bash
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # santacoder-finetuned-the-stack-bash
14
+
15
+ This model is a fine-tuned version of [bigcode/santacoder](https://huggingface.co/bigcode/santacoder) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.3174
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 1
38
+ - eval_batch_size: 1
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 4
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_steps: 100
45
+ - training_steps: 5000
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 3.6951 | 0.1 | 500 | 1.8041 |
52
+ | 1.69 | 0.2 | 1000 | 1.5214 |
53
+ | 1.3821 | 0.3 | 1500 | 1.5855 |
54
+ | 1.5861 | 0.4 | 2000 | 1.4657 |
55
+ | 1.6196 | 0.5 | 2500 | 1.4089 |
56
+ | 1.6839 | 0.6 | 3000 | 1.3801 |
57
+ | 1.3929 | 0.7 | 3500 | 1.3493 |
58
+ | 1.471 | 0.8 | 4000 | 1.3278 |
59
+ | 1.3222 | 0.9 | 4500 | 1.3203 |
60
+ | 1.4529 | 1.0 | 5000 | 1.3174 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.30.2
66
+ - Pytorch 2.0.1+cu118
67
+ - Datasets 2.13.1
68
+ - Tokenizers 0.13.3
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 49152,
4
+ "eos_token_id": 49152,
5
+ "transformers_version": "4.30.2",
6
+ "use_cache": false
7
+ }
runs/Jul14_14-00-29_d61dfab953cd/events.out.tfevents.1689343258.d61dfab953cd.7479.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bd1afbd3c79148da77081df4ecf10ca957a198e4db9e0eb5b95020227d3e974
3
- size 85631
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f51e8c8c73049b65a86f55de11639161aea2280410ab51529522d23c7448bdf
3
+ size 85985