Commit
•
1fa03b3
1
Parent(s):
dad8ae3
End of training
Browse files- README.md +111 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: mit
|
| 5 |
+
base_model: microsoft/deberta-v3-base
|
| 6 |
+
tags:
|
| 7 |
+
- nycu-112-2-datamining-hw2
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- DandinPower/review_mergeallfeaturetotext
|
| 11 |
+
metrics:
|
| 12 |
+
- accuracy
|
| 13 |
+
model-index:
|
| 14 |
+
- name: deberta-v3-base-maftt
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
name: Text Classification
|
| 18 |
+
type: text-classification
|
| 19 |
+
dataset:
|
| 20 |
+
name: DandinPower/review_mergeallfeaturetotext
|
| 21 |
+
type: DandinPower/review_mergeallfeaturetotext
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.6288571428571429
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# deberta-v3-base-maftt
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the DandinPower/review_mergeallfeaturetotext dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 1.4616
|
| 36 |
+
- Accuracy: 0.6289
|
| 37 |
+
- Macro F1: 0.6302
|
| 38 |
+
|
| 39 |
+
## Model description
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Intended uses & limitations
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training and evaluation data
|
| 48 |
+
|
| 49 |
+
More information needed
|
| 50 |
+
|
| 51 |
+
## Training procedure
|
| 52 |
+
|
| 53 |
+
### Training hyperparameters
|
| 54 |
+
|
| 55 |
+
The following hyperparameters were used during training:
|
| 56 |
+
- learning_rate: 4.5e-05
|
| 57 |
+
- train_batch_size: 8
|
| 58 |
+
- eval_batch_size: 8
|
| 59 |
+
- seed: 42
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- lr_scheduler_warmup_steps: 1500
|
| 63 |
+
- num_epochs: 5
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|
| 68 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
|
| 69 |
+
| 1.0302 | 0.14 | 500 | 1.0771 | 0.5511 | 0.5499 |
|
| 70 |
+
| 1.0412 | 0.29 | 1000 | 0.9406 | 0.5966 | 0.6030 |
|
| 71 |
+
| 0.9494 | 0.43 | 1500 | 0.9546 | 0.5949 | 0.5602 |
|
| 72 |
+
| 0.898 | 0.57 | 2000 | 1.0436 | 0.5957 | 0.5872 |
|
| 73 |
+
| 0.9171 | 0.71 | 2500 | 0.9004 | 0.622 | 0.6074 |
|
| 74 |
+
| 0.8856 | 0.86 | 3000 | 0.8741 | 0.6137 | 0.5990 |
|
| 75 |
+
| 0.9359 | 1.0 | 3500 | 0.8821 | 0.6267 | 0.6245 |
|
| 76 |
+
| 0.8626 | 1.14 | 4000 | 0.8859 | 0.6213 | 0.6200 |
|
| 77 |
+
| 0.7953 | 1.29 | 4500 | 0.8606 | 0.6337 | 0.6271 |
|
| 78 |
+
| 0.8206 | 1.43 | 5000 | 0.8543 | 0.6169 | 0.6202 |
|
| 79 |
+
| 0.8184 | 1.57 | 5500 | 0.9360 | 0.6266 | 0.6165 |
|
| 80 |
+
| 0.8044 | 1.71 | 6000 | 0.8606 | 0.6234 | 0.6227 |
|
| 81 |
+
| 0.7094 | 1.86 | 6500 | 0.8842 | 0.6434 | 0.6387 |
|
| 82 |
+
| 0.8264 | 2.0 | 7000 | 0.9063 | 0.612 | 0.6128 |
|
| 83 |
+
| 0.6951 | 2.14 | 7500 | 0.8782 | 0.6386 | 0.6415 |
|
| 84 |
+
| 0.704 | 2.29 | 8000 | 0.9510 | 0.6326 | 0.6308 |
|
| 85 |
+
| 0.6806 | 2.43 | 8500 | 0.8709 | 0.6413 | 0.6455 |
|
| 86 |
+
| 0.6983 | 2.57 | 9000 | 0.8977 | 0.6426 | 0.6436 |
|
| 87 |
+
| 0.6852 | 2.71 | 9500 | 0.9686 | 0.5984 | 0.6010 |
|
| 88 |
+
| 0.6761 | 2.86 | 10000 | 0.8961 | 0.6386 | 0.6406 |
|
| 89 |
+
| 0.6804 | 3.0 | 10500 | 0.9378 | 0.6307 | 0.6332 |
|
| 90 |
+
| 0.5329 | 3.14 | 11000 | 1.1209 | 0.6341 | 0.6382 |
|
| 91 |
+
| 0.5461 | 3.29 | 11500 | 1.0323 | 0.6393 | 0.6377 |
|
| 92 |
+
| 0.5725 | 3.43 | 12000 | 1.0678 | 0.6334 | 0.6366 |
|
| 93 |
+
| 0.5499 | 3.57 | 12500 | 1.0547 | 0.6374 | 0.6394 |
|
| 94 |
+
| 0.5218 | 3.71 | 13000 | 1.0524 | 0.6453 | 0.6460 |
|
| 95 |
+
| 0.5022 | 3.86 | 13500 | 1.1100 | 0.6363 | 0.6358 |
|
| 96 |
+
| 0.534 | 4.0 | 14000 | 1.0378 | 0.6357 | 0.6386 |
|
| 97 |
+
| 0.3823 | 4.14 | 14500 | 1.3985 | 0.6357 | 0.6357 |
|
| 98 |
+
| 0.4518 | 4.29 | 15000 | 1.3265 | 0.6314 | 0.6318 |
|
| 99 |
+
| 0.4147 | 4.43 | 15500 | 1.3946 | 0.631 | 0.6324 |
|
| 100 |
+
| 0.3936 | 4.57 | 16000 | 1.4649 | 0.6279 | 0.6308 |
|
| 101 |
+
| 0.4339 | 4.71 | 16500 | 1.5322 | 0.6286 | 0.6314 |
|
| 102 |
+
| 0.4448 | 4.86 | 17000 | 1.4890 | 0.629 | 0.6302 |
|
| 103 |
+
| 0.4006 | 5.0 | 17500 | 1.4616 | 0.6289 | 0.6302 |
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
### Framework versions
|
| 107 |
+
|
| 108 |
+
- Transformers 4.39.3
|
| 109 |
+
- Pytorch 2.2.2+cu121
|
| 110 |
+
- Datasets 2.18.0
|
| 111 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737728508
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:603374e4d10705a264019a5f9b2b8ff0d1612dd97da74dfd0a995736e17446d6
|
| 3 |
size 737728508
|