Commit
•
e27e03d
1
Parent(s):
8d85dec
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
base_model: google-bert/bert-base-cased
|
| 9 |
+
model-index:
|
| 10 |
+
- name: STS-Lora-Fine-Tuning-Capstone-bert-testing-70-with-lower-r-mid
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# STS-Lora-Fine-Tuning-Capstone-bert-testing-70-with-lower-r-mid
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.2732
|
| 22 |
+
- Accuracy: 0.4706
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-05
|
| 42 |
+
- train_batch_size: 64
|
| 43 |
+
- eval_batch_size: 64
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 40
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 53 |
+
| No log | 1.0 | 197 | 1.7537 | 0.2444 |
|
| 54 |
+
| No log | 2.0 | 394 | 1.7017 | 0.2886 |
|
| 55 |
+
| 1.6735 | 3.0 | 591 | 1.6479 | 0.2988 |
|
| 56 |
+
| 1.6735 | 4.0 | 788 | 1.5870 | 0.3169 |
|
| 57 |
+
| 1.6735 | 5.0 | 985 | 1.5191 | 0.3328 |
|
| 58 |
+
| 1.5268 | 6.0 | 1182 | 1.4680 | 0.3611 |
|
| 59 |
+
| 1.5268 | 7.0 | 1379 | 1.4300 | 0.3887 |
|
| 60 |
+
| 1.3747 | 8.0 | 1576 | 1.4043 | 0.4039 |
|
| 61 |
+
| 1.3747 | 9.0 | 1773 | 1.3854 | 0.4039 |
|
| 62 |
+
| 1.3747 | 10.0 | 1970 | 1.3713 | 0.4104 |
|
| 63 |
+
| 1.2814 | 11.0 | 2167 | 1.3599 | 0.4191 |
|
| 64 |
+
| 1.2814 | 12.0 | 2364 | 1.3560 | 0.4199 |
|
| 65 |
+
| 1.2408 | 13.0 | 2561 | 1.3407 | 0.4228 |
|
| 66 |
+
| 1.2408 | 14.0 | 2758 | 1.3234 | 0.4380 |
|
| 67 |
+
| 1.2408 | 15.0 | 2955 | 1.3233 | 0.4329 |
|
| 68 |
+
| 1.2136 | 16.0 | 3152 | 1.3146 | 0.4373 |
|
| 69 |
+
| 1.2136 | 17.0 | 3349 | 1.3181 | 0.4409 |
|
| 70 |
+
| 1.1914 | 18.0 | 3546 | 1.3267 | 0.4387 |
|
| 71 |
+
| 1.1914 | 19.0 | 3743 | 1.3103 | 0.4467 |
|
| 72 |
+
| 1.1914 | 20.0 | 3940 | 1.3056 | 0.4525 |
|
| 73 |
+
| 1.1759 | 21.0 | 4137 | 1.2887 | 0.4605 |
|
| 74 |
+
| 1.1759 | 22.0 | 4334 | 1.2917 | 0.4648 |
|
| 75 |
+
| 1.1661 | 23.0 | 4531 | 1.2955 | 0.4576 |
|
| 76 |
+
| 1.1661 | 24.0 | 4728 | 1.2841 | 0.4634 |
|
| 77 |
+
| 1.1661 | 25.0 | 4925 | 1.2850 | 0.4634 |
|
| 78 |
+
| 1.1566 | 26.0 | 5122 | 1.2998 | 0.4554 |
|
| 79 |
+
| 1.1566 | 27.0 | 5319 | 1.2854 | 0.4656 |
|
| 80 |
+
| 1.1482 | 28.0 | 5516 | 1.2792 | 0.4750 |
|
| 81 |
+
| 1.1482 | 29.0 | 5713 | 1.2809 | 0.4677 |
|
| 82 |
+
| 1.1482 | 30.0 | 5910 | 1.2777 | 0.4735 |
|
| 83 |
+
| 1.1407 | 31.0 | 6107 | 1.2799 | 0.4677 |
|
| 84 |
+
| 1.1407 | 32.0 | 6304 | 1.2816 | 0.4699 |
|
| 85 |
+
| 1.1417 | 33.0 | 6501 | 1.2802 | 0.4692 |
|
| 86 |
+
| 1.1417 | 34.0 | 6698 | 1.2739 | 0.4685 |
|
| 87 |
+
| 1.1417 | 35.0 | 6895 | 1.2739 | 0.4699 |
|
| 88 |
+
| 1.1391 | 36.0 | 7092 | 1.2745 | 0.4692 |
|
| 89 |
+
| 1.1391 | 37.0 | 7289 | 1.2733 | 0.4714 |
|
| 90 |
+
| 1.1391 | 38.0 | 7486 | 1.2729 | 0.4714 |
|
| 91 |
+
| 1.134 | 39.0 | 7683 | 1.2719 | 0.4706 |
|
| 92 |
+
| 1.134 | 40.0 | 7880 | 1.2732 | 0.4706 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
### Framework versions
|
| 96 |
+
|
| 97 |
+
- PEFT 0.10.0
|
| 98 |
+
- Transformers 4.38.2
|
| 99 |
+
- Pytorch 2.2.1+cu121
|
| 100 |
+
- Datasets 2.18.0
|
| 101 |
+
- Tokenizers 0.15.2
|
runs/Mar27_04-45-23_4002fefc947e/events.out.tfevents.1711514725.4002fefc947e.585.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e81c866fd232c9c08bdb889d34ec2ea1ed4f255f7d6e26cd163c14fc12bd8f6
|
| 3 |
+
size 21560
|