Vishnou/TinyBERT_SST2
Browse files- README.md +54 -6
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -3,9 +3,24 @@ tags:
|
|
| 3 |
- generated_from_trainer
|
| 4 |
datasets:
|
| 5 |
- sst2
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: TinyBERT_SST2
|
| 8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -14,11 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# TinyBERT_SST2
|
| 15 |
|
| 16 |
This model was trained from scratch on the sst2 dataset.
|
| 17 |
-
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
Accuracy: 0.8682
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -47,11 +60,46 @@ The following hyperparameters were used during training:
|
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
|
| 52 |
### Framework versions
|
| 53 |
|
| 54 |
- Transformers 4.35.2
|
| 55 |
- Pytorch 2.1.0+cu118
|
| 56 |
-
- Datasets 2.
|
| 57 |
- Tokenizers 0.15.0
|
|
|
|
| 3 |
- generated_from_trainer
|
| 4 |
datasets:
|
| 5 |
- sst2
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: TinyBERT_SST2
|
| 10 |
+
results:
|
| 11 |
+
- task:
|
| 12 |
+
name: Text Classification
|
| 13 |
+
type: text-classification
|
| 14 |
+
dataset:
|
| 15 |
+
name: sst2
|
| 16 |
+
type: sst2
|
| 17 |
+
config: default
|
| 18 |
+
split: validation
|
| 19 |
+
args: default
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Accuracy
|
| 22 |
+
type: accuracy
|
| 23 |
+
value: 0.8589449541284404
|
| 24 |
---
|
| 25 |
|
| 26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 29 |
# TinyBERT_SST2
|
| 30 |
|
| 31 |
This model was trained from scratch on the sst2 dataset.
|
|
|
|
| 32 |
It achieves the following results on the evaluation set:
|
| 33 |
+
- Loss: 0.8932
|
| 34 |
+
- Accuracy: 0.8589
|
|
|
|
| 35 |
|
| 36 |
## Model description
|
| 37 |
|
|
|
|
| 60 |
|
| 61 |
### Training results
|
| 62 |
|
| 63 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 64 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 65 |
+
| 0.0994 | 0.06 | 500 | 0.9727 | 0.8452 |
|
| 66 |
+
| 0.1004 | 0.12 | 1000 | 1.0064 | 0.8509 |
|
| 67 |
+
| 0.1008 | 0.18 | 1500 | 0.8181 | 0.8601 |
|
| 68 |
+
| 0.0873 | 0.24 | 2000 | 1.0162 | 0.8567 |
|
| 69 |
+
| 0.107 | 0.3 | 2500 | 0.8707 | 0.8532 |
|
| 70 |
+
| 0.0999 | 0.36 | 3000 | 0.8787 | 0.8417 |
|
| 71 |
+
| 0.0949 | 0.42 | 3500 | 0.9604 | 0.8417 |
|
| 72 |
+
| 0.096 | 0.48 | 4000 | 1.0545 | 0.8429 |
|
| 73 |
+
| 0.1061 | 0.53 | 4500 | 0.9569 | 0.8475 |
|
| 74 |
+
| 0.1274 | 0.59 | 5000 | 0.8720 | 0.8486 |
|
| 75 |
+
| 0.1197 | 0.65 | 5500 | 0.8653 | 0.8475 |
|
| 76 |
+
| 0.1127 | 0.71 | 6000 | 0.9221 | 0.8567 |
|
| 77 |
+
| 0.1125 | 0.77 | 6500 | 0.8985 | 0.8532 |
|
| 78 |
+
| 0.1345 | 0.83 | 7000 | 0.8876 | 0.8509 |
|
| 79 |
+
| 0.1369 | 0.89 | 7500 | 0.8241 | 0.8463 |
|
| 80 |
+
| 0.1429 | 0.95 | 8000 | 0.6918 | 0.8635 |
|
| 81 |
+
| 0.1135 | 1.01 | 8500 | 0.8904 | 0.8612 |
|
| 82 |
+
| 0.0729 | 1.07 | 9000 | 0.9516 | 0.8601 |
|
| 83 |
+
| 0.0799 | 1.13 | 9500 | 0.8766 | 0.8589 |
|
| 84 |
+
| 0.0668 | 1.19 | 10000 | 1.0083 | 0.8601 |
|
| 85 |
+
| 0.0715 | 1.25 | 10500 | 0.9749 | 0.8601 |
|
| 86 |
+
| 0.0793 | 1.31 | 11000 | 1.0314 | 0.8544 |
|
| 87 |
+
| 0.0732 | 1.37 | 11500 | 0.9749 | 0.8555 |
|
| 88 |
+
| 0.0909 | 1.43 | 12000 | 0.8851 | 0.8498 |
|
| 89 |
+
| 0.0684 | 1.48 | 12500 | 0.9375 | 0.8532 |
|
| 90 |
+
| 0.0781 | 1.54 | 13000 | 0.9546 | 0.8567 |
|
| 91 |
+
| 0.0653 | 1.6 | 13500 | 0.9514 | 0.8589 |
|
| 92 |
+
| 0.0828 | 1.66 | 14000 | 0.9409 | 0.8544 |
|
| 93 |
+
| 0.0694 | 1.72 | 14500 | 0.9229 | 0.8578 |
|
| 94 |
+
| 0.0952 | 1.78 | 15000 | 0.8585 | 0.8624 |
|
| 95 |
+
| 0.0694 | 1.84 | 15500 | 0.8960 | 0.8555 |
|
| 96 |
+
| 0.0777 | 1.9 | 16000 | 0.8846 | 0.8601 |
|
| 97 |
+
| 0.0822 | 1.96 | 16500 | 0.8932 | 0.8589 |
|
| 98 |
|
| 99 |
|
| 100 |
### Framework versions
|
| 101 |
|
| 102 |
- Transformers 4.35.2
|
| 103 |
- Pytorch 2.1.0+cu118
|
| 104 |
+
- Datasets 2.15.0
|
| 105 |
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 57411808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7db045c296d4d2f0d113cfcb88e47379b1f58768e2884ef0c60fb17bad16ed26
|
| 3 |
size 57411808
|