14rohnisingh commited on
Commit
fccbe8f
1 Parent(s): 686b597

End of training

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
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: bigcode/starcoderbase-1b
7
+ model-index:
8
+ - name: peft-starcoder-lora-a100
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # peft-starcoder-lora-a100
16
+
17
+ This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4433
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0005
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_steps: 30
45
+ - training_steps: 2000
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.45 | 0.05 | 100 | 0.4334 |
52
+ | 0.413 | 0.1 | 200 | 0.4235 |
53
+ | 0.396 | 0.15 | 300 | 0.4189 |
54
+ | 0.3702 | 0.2 | 400 | 0.4082 |
55
+ | 0.356 | 0.25 | 500 | 0.4072 |
56
+ | 0.3429 | 0.3 | 600 | 0.4129 |
57
+ | 0.3375 | 0.35 | 700 | 0.4136 |
58
+ | 0.3181 | 0.4 | 800 | 0.4080 |
59
+ | 0.3057 | 0.45 | 900 | 0.4187 |
60
+ | 0.2956 | 0.5 | 1000 | 0.4214 |
61
+ | 0.2761 | 0.55 | 1100 | 0.4261 |
62
+ | 0.2805 | 0.6 | 1200 | 0.4275 |
63
+ | 0.2697 | 0.65 | 1300 | 0.4294 |
64
+ | 0.2556 | 0.7 | 1400 | 0.4338 |
65
+ | 0.2578 | 0.75 | 1500 | 0.4339 |
66
+ | 0.2427 | 0.8 | 1600 | 0.4401 |
67
+ | 0.245 | 0.85 | 1700 | 0.4423 |
68
+ | 0.248 | 0.9 | 1800 | 0.4435 |
69
+ | 0.2377 | 0.95 | 1900 | 0.4436 |
70
+ | 0.2466 | 1.0 | 2000 | 0.4433 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - PEFT 0.11.1
76
+ - Transformers 4.40.2
77
+ - Pytorch 2.2.1+cu121
78
+ - Datasets 2.19.1
79
+ - Tokenizers 0.19.1