Hugging Face's logo

rahkrish1
/
Improved_peft-starcoder-lora-a100

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
rahkrish1 commited on
Commit
88e413b
·
verified ·
1 Parent(s): c3e263f

Model save

Browse files
Files changed (3) hide show
  1. README.md +79 -0
  2. adapter_model.safetensors +1 -1
  3. runs/Feb06_18-46-01_awltait7.amazon.micron.com/events.out.tfevents.1738896411.awltait7.amazon.micron.com.1619087.0 +2 -2
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: bigcode-openrail-m
4
+ base_model: bigcode/starcoderbase-1b
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: Improved_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
+ # Improved_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: 0.9963
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: 5
40
+ - eval_batch_size: 5
41
+ - seed: 42
42
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
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
+ | 1.1058 | 0.05 | 100 | 0.9381 |
52
+ | 1.0894 | 0.1 | 200 | 0.9436 |
53
+ | 0.9095 | 0.15 | 300 | 0.9692 |
54
+ | 0.8193 | 0.2 | 400 | 0.9756 |
55
+ | 0.9654 | 0.25 | 500 | 0.9698 |
56
+ | 0.9947 | 0.3 | 600 | 0.9741 |
57
+ | 0.778 | 0.35 | 700 | 0.9823 |
58
+ | 0.8849 | 0.4 | 800 | 0.9900 |
59
+ | 0.6429 | 0.45 | 900 | 0.9821 |
60
+ | 0.5712 | 0.5 | 1000 | 0.9966 |
61
+ | 0.9707 | 0.55 | 1100 | 0.9903 |
62
+ | 0.9221 | 0.6 | 1200 | 0.9946 |
63
+ | 0.786 | 0.65 | 1300 | 0.9935 |
64
+ | 0.807 | 0.7 | 1400 | 0.9965 |
65
+ | 0.9148 | 0.75 | 1500 | 0.9891 |
66
+ | 0.9473 | 0.8 | 1600 | 0.9928 |
67
+ | 0.6558 | 0.85 | 1700 | 0.9952 |
68
+ | 0.5542 | 0.9 | 1800 | 0.9957 |
69
+ | 0.5413 | 0.95 | 1900 | 0.9964 |
70
+ | 0.9061 | 1.0 | 2000 | 0.9963 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - PEFT 0.14.0
76
+ - Transformers 4.47.1
77
+ - Pytorch 2.5.1+cu124
78
+ - Datasets 3.2.0
79
+ - Tokenizers 0.21.0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f97b1410d2f67e23258fda0ba0276bbb515e33494c3b8c56366373fc9751ab5
3
  size 22241240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6edab4a37169cffe5e8a6775998a4e3286f67755efb5e01cd5ea2860aac235
3
  size 22241240
runs/Feb06_18-46-01_awltait7.amazon.micron.com/events.out.tfevents.1738896411.awltait7.amazon.micron.com.1619087.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b97dc927785529f14827588752c5a23f5b74c8a6ac32ff313435a1e1fe40dbb6
3
- size 27194
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb0d9efbd2cac3ea523d91707d5c5d907dedd1bddcbf72b267451e2b3746e18
3
+ size 28731