Blaine-Mason
commited on
Commit
•
7e4aa4f
1
Parent(s):
314f464
add model
Browse files
README.md
CHANGED
@@ -18,7 +18,7 @@ model_index:
|
|
18 |
metric:
|
19 |
name: Accuracy
|
20 |
type: accuracy
|
21 |
-
value: 0.
|
22 |
---
|
23 |
|
24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -28,8 +28,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
28 |
|
29 |
This model is a fine-tuned version of [HackMIT/double-agent](https://huggingface.co/HackMIT/double-agent) on the glue dataset.
|
30 |
It achieves the following results on the evaluation set:
|
31 |
-
- Loss: 1.
|
32 |
-
- Accuracy: 0.
|
33 |
|
34 |
## Model description
|
35 |
|
@@ -48,23 +48,20 @@ More information needed
|
|
48 |
### Training hyperparameters
|
49 |
|
50 |
The following hyperparameters were used during training:
|
51 |
-
- learning_rate:
|
52 |
-
- train_batch_size:
|
53 |
- eval_batch_size: 16
|
54 |
-
- seed:
|
55 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
56 |
- lr_scheduler_type: linear
|
57 |
-
- num_epochs:
|
58 |
|
59 |
### Training results
|
60 |
|
61 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
62 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.0742 | 3.0 | 12630 | 1.3312 | 0.7890 |
|
66 |
-
| 0.0638 | 4.0 | 16840 | 1.3246 | 0.7890 |
|
67 |
-
| 0.0793 | 5.0 | 21050 | 1.3245 | 0.7878 |
|
68 |
|
69 |
|
70 |
### Framework versions
|
|
|
18 |
metric:
|
19 |
name: Accuracy
|
20 |
type: accuracy
|
21 |
+
value: 0.7935779816513762
|
22 |
---
|
23 |
|
24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
28 |
|
29 |
This model is a fine-tuned version of [HackMIT/double-agent](https://huggingface.co/HackMIT/double-agent) on the glue dataset.
|
30 |
It achieves the following results on the evaluation set:
|
31 |
+
- Loss: 1.4316
|
32 |
+
- Accuracy: 0.7936
|
33 |
|
34 |
## Model description
|
35 |
|
|
|
48 |
### Training hyperparameters
|
49 |
|
50 |
The following hyperparameters were used during training:
|
51 |
+
- learning_rate: 1.598376045540765e-05
|
52 |
+
- train_batch_size: 8
|
53 |
- eval_batch_size: 16
|
54 |
+
- seed: 18
|
55 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
56 |
- lr_scheduler_type: linear
|
57 |
+
- num_epochs: 2
|
58 |
|
59 |
### Training results
|
60 |
|
61 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
62 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
63 |
+
| 0.0956 | 1.0 | 8419 | 1.3969 | 0.7970 |
|
64 |
+
| 0.0658 | 2.0 | 16838 | 1.4316 | 0.7936 |
|
|
|
|
|
|
|
65 |
|
66 |
|
67 |
### Framework versions
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17564583
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ecd017935699c6eeea6a54687d1ef8c93fd47153c504d091d6427f2be1adaaa
|
3 |
size 17564583
|
runs/Aug23_17-48-36_1fec14368006/1629749498.8925076/events.out.tfevents.1629749498.1fec14368006.75.35
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84e7ff35c329ccc2d8316f17af531389c06da67ad1a6b492e6b4b51ead40f2d4
|
3 |
+
size 4193
|
runs/Aug23_17-48-36_1fec14368006/events.out.tfevents.1629749498.1fec14368006.75.34
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:161a912be4080307233db29c0850411c5ba73fbc78317b8ac1965974e17c4f76
|
3 |
+
size 9223
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2671
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3d9180e2534d0fa0b52b2f4ab8dab667bca288840f012827f547e37a822e03a
|
3 |
size 2671
|