Hugging Face's logo

doyoungkim
/
bert-base-uncased-finetuned-sst2

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
3
doyoungkim commited on
Commit
f36e22e
•
1 Parent(s): 180c434

add model

Browse files
Files changed (7) hide show
  1. README.md +8 -8
  2. config.json +0 -1
  3. pytorch_model.bin +1 -1
  4. runs/Aug08_16-47-49_2679afe8445a/1628441314.6938753/events.out.tfevents.1628441314.2679afe8445a.61.1 +3 -0
  5. runs/Aug08_16-47-49_2679afe8445a/events.out.tfevents.1628441314.2679afe8445a.61.0 +3 -0
  6. runs/Aug08_16-47-49_2679afe8445a/events.out.tfevents.1628444282.2679afe8445a.61.2 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ model_index:
16
  metric:
17
  name: Accuracy
18
  type: accuracy
19
- value: 0.9197247706422018
20
  ---
21
 
22
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -26,8 +26,8 @@ should probably proofread and complete it, then remove this comment. -->
26
 
27
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
28
  It achieves the following results on the evaluation set:
29
- - Loss: 0.3926
30
- - Accuracy: 0.9197
31
 
32
  ## Model description
33
 
@@ -58,11 +58,11 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
60
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
61
- | 0.3972 | 1.0 | 4210 | 0.4020 | 0.9071 |
62
- | 0.3718 | 2.0 | 8420 | 0.4021 | 0.9083 |
63
- | 0.3548 | 3.0 | 12630 | 0.3970 | 0.9128 |
64
- | 0.3584 | 4.0 | 16840 | 0.3926 | 0.9197 |
65
- | 0.3509 | 5.0 | 21050 | 0.3966 | 0.9163 |
66
 
67
 
68
  ### Framework versions
 
16
  metric:
17
  name: Accuracy
18
  type: accuracy
19
+ value: 0.930045871559633
20
  ---
21
 
22
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
26
 
27
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
28
  It achieves the following results on the evaluation set:
29
+ - Loss: 0.4079
30
+ - Accuracy: 0.9300
31
 
32
  ## Model description
33
 
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
60
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
61
+ | 0.1793 | 1.0 | 4210 | 0.3598 | 0.9094 |
62
+ | 0.1243 | 2.0 | 8420 | 0.3021 | 0.9243 |
63
+ | 0.0799 | 3.0 | 12630 | 0.3473 | 0.9220 |
64
+ | 0.0641 | 4.0 | 16840 | 0.3309 | 0.9289 |
65
+ | 0.0346 | 5.0 | 21050 | 0.4079 | 0.9300 |
66
 
67
 
68
  ### Framework versions
config.json CHANGED
@@ -4,7 +4,6 @@
4
  "MyBertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
- "classifier_type": "log_soft",
8
  "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
 
4
  "MyBertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
7
  "gradient_checkpointing": false,
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a4fdb2b4435b31d85bc4a1b6d4e37ec62efb6863d98ade7b9d4bf34e9c493a7
3
  size 438019245
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:213a79678c7fe75fc96e97812a94534e3cb75f41790ff750e07dcf6afa9b2326
3
  size 438019245
runs/Aug08_16-47-49_2679afe8445a/1628441314.6938753/events.out.tfevents.1628441314.2679afe8445a.61.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d62a459884301cd3f5242b1b41016f8d17a22ce0b645a4cbc1c3fd1ef3982f2
3
+ size 4203
runs/Aug08_16-47-49_2679afe8445a/events.out.tfevents.1628441314.2679afe8445a.61.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:435700cc6b55d9e6ca789e73332fa3d268ab2754ca480e938ed11e29b6a973ad
3
+ size 11550
runs/Aug08_16-47-49_2679afe8445a/events.out.tfevents.1628444282.2679afe8445a.61.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9cb4b3c2e90608d58c860d6bb7c2b3a410f648a7e8352f1596728af1bd70c9
3
+ size 369
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a643f39f660074798fda2dadf1146f88018c2aae5beeb29d9c4cc3e9904e748
3
  size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf32ca1f0758ab854d89d38e398b74460ca0ad2dc1aae89f102e162da56a632a
3
  size 2671