gauravsirola commited on
Commit
1b0e604
1 Parent(s): b7afe3f

Model save

Browse files
Files changed (1) hide show
  1. README.md +79 -0
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigcode-openrail-m
3
+ base_model: bigcode/starcoderbase-1b
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: peft-starcoder-lora-a100
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
+ # peft-starcoder-lora-a100
15
+
16
+ This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 6.6613
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: 0.0005
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: 30
46
+ - training_steps: 2000
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 5.6431 | 0.05 | 100 | 6.9272 |
53
+ | 5.7486 | 0.1 | 200 | 7.0303 |
54
+ | 5.452 | 0.15 | 300 | 6.8401 |
55
+ | 5.5812 | 0.2 | 400 | 6.9055 |
56
+ | 5.9 | 0.25 | 500 | 6.9231 |
57
+ | 5.3105 | 0.3 | 600 | 6.8938 |
58
+ | 5.792 | 0.35 | 700 | 6.6707 |
59
+ | 6.0344 | 0.4 | 800 | 6.7873 |
60
+ | 5.4302 | 0.45 | 900 | 6.9783 |
61
+ | 5.9707 | 0.5 | 1000 | 6.8064 |
62
+ | 5.9979 | 0.55 | 1100 | 6.6769 |
63
+ | 5.4383 | 0.6 | 1200 | 6.7186 |
64
+ | 5.8372 | 0.65 | 1300 | 6.8070 |
65
+ | 6.0431 | 0.7 | 1400 | 6.6933 |
66
+ | 5.2884 | 0.75 | 1500 | 6.7594 |
67
+ | 5.8948 | 0.8 | 1600 | 6.7177 |
68
+ | 5.9268 | 0.85 | 1700 | 6.6410 |
69
+ | 5.1566 | 0.9 | 1800 | 6.6744 |
70
+ | 5.803 | 0.95 | 1900 | 6.6598 |
71
+ | 5.6748 | 1.0 | 2000 | 6.6613 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.35.0
77
+ - Pytorch 2.0.1+cu117
78
+ - Datasets 2.18.0
79
+ - Tokenizers 0.14.1