msplits commited on
Commit
7f1ffe8
·
1 Parent(s): 75d35a9

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +76 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigcode-openrail-m
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: peft-starcoder-lora-a100
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
+ # peft-starcoder-lora-a100
14
+
15
+ This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.0550
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: 0.0005
37
+ - train_batch_size: 16
38
+ - eval_batch_size: 16
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: cosine
42
+ - lr_scheduler_warmup_steps: 30
43
+ - training_steps: 2000
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 1.0005 | 0.05 | 100 | 0.9347 |
50
+ | 0.9939 | 0.1 | 200 | 0.9456 |
51
+ | 0.6657 | 0.15 | 300 | 0.9741 |
52
+ | 0.876 | 0.2 | 400 | 0.9765 |
53
+ | 0.9736 | 0.25 | 500 | 0.9916 |
54
+ | 0.5713 | 0.3 | 600 | 0.9979 |
55
+ | 0.7916 | 0.35 | 700 | 1.0035 |
56
+ | 0.8799 | 0.4 | 800 | 1.0083 |
57
+ | 0.5209 | 0.45 | 900 | 1.0225 |
58
+ | 0.7409 | 0.5 | 1000 | 1.0318 |
59
+ | 0.7843 | 0.55 | 1100 | 1.0195 |
60
+ | 0.4715 | 0.6 | 1200 | 1.0547 |
61
+ | 0.7062 | 0.65 | 1300 | 1.0521 |
62
+ | 0.6678 | 0.7 | 1400 | 1.0479 |
63
+ | 0.5542 | 0.75 | 1500 | 1.0527 |
64
+ | 0.6735 | 0.8 | 1600 | 1.0521 |
65
+ | 0.591 | 0.85 | 1700 | 1.0556 |
66
+ | 0.619 | 0.9 | 1800 | 1.0586 |
67
+ | 0.5836 | 0.95 | 1900 | 1.0570 |
68
+ | 0.6231 | 1.0 | 2000 | 1.0550 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.30.0.dev0
74
+ - Pytorch 2.3.0+cu121
75
+ - Datasets 2.20.0
76
+ - Tokenizers 0.13.3