End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
base_model: FacebookAI/roberta-base
|
| 9 |
+
model-index:
|
| 10 |
+
- name: STS-Lora-Fine-Tuning-Capstone-roberta-base-filtered-150-with-higher-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-roberta-base-filtered-150-with-higher-r-mid
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7443
|
| 22 |
+
- Accuracy: 0.6873
|
| 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: 16
|
| 43 |
+
- eval_batch_size: 16
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 30
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 53 |
+
| No log | 1.0 | 449 | 1.0408 | 0.4625 |
|
| 54 |
+
| 0.9593 | 2.0 | 898 | 1.0281 | 0.4981 |
|
| 55 |
+
| 0.9206 | 3.0 | 1347 | 0.9842 | 0.5225 |
|
| 56 |
+
| 0.8912 | 4.0 | 1796 | 0.9107 | 0.5693 |
|
| 57 |
+
| 0.8539 | 5.0 | 2245 | 0.8257 | 0.6273 |
|
| 58 |
+
| 0.8107 | 6.0 | 2694 | 0.8062 | 0.6685 |
|
| 59 |
+
| 0.779 | 7.0 | 3143 | 0.7672 | 0.6648 |
|
| 60 |
+
| 0.7797 | 8.0 | 3592 | 0.7709 | 0.6704 |
|
| 61 |
+
| 0.7649 | 9.0 | 4041 | 0.7509 | 0.6873 |
|
| 62 |
+
| 0.7649 | 10.0 | 4490 | 0.7376 | 0.6816 |
|
| 63 |
+
| 0.7527 | 11.0 | 4939 | 0.7360 | 0.6835 |
|
| 64 |
+
| 0.7526 | 12.0 | 5388 | 0.7493 | 0.6816 |
|
| 65 |
+
| 0.7476 | 13.0 | 5837 | 0.7421 | 0.6723 |
|
| 66 |
+
| 0.741 | 14.0 | 6286 | 0.7331 | 0.6929 |
|
| 67 |
+
| 0.7284 | 15.0 | 6735 | 0.7404 | 0.6854 |
|
| 68 |
+
| 0.7321 | 16.0 | 7184 | 0.7372 | 0.6798 |
|
| 69 |
+
| 0.7269 | 17.0 | 7633 | 0.7344 | 0.6816 |
|
| 70 |
+
| 0.7237 | 18.0 | 8082 | 0.7428 | 0.6723 |
|
| 71 |
+
| 0.7261 | 19.0 | 8531 | 0.7368 | 0.6854 |
|
| 72 |
+
| 0.7261 | 20.0 | 8980 | 0.7591 | 0.6704 |
|
| 73 |
+
| 0.715 | 21.0 | 9429 | 0.7434 | 0.6835 |
|
| 74 |
+
| 0.7088 | 22.0 | 9878 | 0.7504 | 0.6854 |
|
| 75 |
+
| 0.7228 | 23.0 | 10327 | 0.7500 | 0.6835 |
|
| 76 |
+
| 0.7127 | 24.0 | 10776 | 0.7583 | 0.6835 |
|
| 77 |
+
| 0.706 | 25.0 | 11225 | 0.7353 | 0.6948 |
|
| 78 |
+
| 0.7104 | 26.0 | 11674 | 0.7423 | 0.6891 |
|
| 79 |
+
| 0.7068 | 27.0 | 12123 | 0.7426 | 0.6910 |
|
| 80 |
+
| 0.7046 | 28.0 | 12572 | 0.7494 | 0.6873 |
|
| 81 |
+
| 0.7036 | 29.0 | 13021 | 0.7460 | 0.6910 |
|
| 82 |
+
| 0.7036 | 30.0 | 13470 | 0.7443 | 0.6873 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Framework versions
|
| 86 |
+
|
| 87 |
+
- PEFT 0.10.0
|
| 88 |
+
- Transformers 4.38.2
|
| 89 |
+
- Pytorch 2.2.1+cu121
|
| 90 |
+
- Datasets 2.18.0
|
| 91 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2675612
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:372d2d5a30f6e1dc0492a2de07e8389c60bf7a514d4861f65a290e8da3a957c3
|
| 3 |
size 2675612
|
runs/Mar29_02-12-40_45e56491aa6f/events.out.tfevents.1711678363.45e56491aa6f.334.4
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:e6156f7991199ce111a39c1888e4f5d5744c0bbd1fd020e586283c7e77bd9023
|
| 3 |
+
size 20555
|