SimoneJLaudani
commited on
Commit
•
2525c06
1
Parent(s):
dacfd99
End of training
Browse files
README.md
CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss:
|
24 |
-
- Precision: 0.
|
25 |
-
- Recall: 0.
|
26 |
-
- F1: 0.
|
27 |
-
- Accuracy: 0.
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -44,8 +44,8 @@ More information needed
|
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
- learning_rate: 5e-05
|
47 |
-
- train_batch_size:
|
48 |
-
- eval_batch_size:
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
@@ -53,25 +53,6 @@ The following hyperparameters were used during training:
|
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
-
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
-
|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
-
| 0.9413 | 3.4483 | 100 | 0.5627 | 0.8344 | 0.8254 | 0.8260 | 0.8254 |
|
59 |
-
| 0.1021 | 6.8966 | 200 | 0.6474 | 0.8436 | 0.8342 | 0.8356 | 0.8342 |
|
60 |
-
| 0.0301 | 10.3448 | 300 | 0.7386 | 0.8541 | 0.8519 | 0.8517 | 0.8519 |
|
61 |
-
| 0.0119 | 13.7931 | 400 | 0.8450 | 0.8544 | 0.8501 | 0.8504 | 0.8501 |
|
62 |
-
| 0.0086 | 17.2414 | 500 | 0.8656 | 0.8543 | 0.8519 | 0.8522 | 0.8519 |
|
63 |
-
| 0.0062 | 20.6897 | 600 | 0.9217 | 0.8496 | 0.8466 | 0.8466 | 0.8466 |
|
64 |
-
| 0.0046 | 24.1379 | 700 | 0.9365 | 0.8487 | 0.8466 | 0.8463 | 0.8466 |
|
65 |
-
| 0.0029 | 27.5862 | 800 | 0.9288 | 0.8469 | 0.8448 | 0.8450 | 0.8448 |
|
66 |
-
| 0.0032 | 31.0345 | 900 | 0.9403 | 0.8502 | 0.8483 | 0.8483 | 0.8483 |
|
67 |
-
| 0.0025 | 34.4828 | 1000 | 0.9623 | 0.8530 | 0.8501 | 0.8503 | 0.8501 |
|
68 |
-
| 0.0023 | 37.9310 | 1100 | 0.9505 | 0.8503 | 0.8483 | 0.8484 | 0.8483 |
|
69 |
-
| 0.002 | 41.3793 | 1200 | 0.9650 | 0.8524 | 0.8501 | 0.8505 | 0.8501 |
|
70 |
-
| 0.0025 | 44.8276 | 1300 | 0.9742 | 0.8507 | 0.8483 | 0.8487 | 0.8483 |
|
71 |
-
| 0.0021 | 48.2759 | 1400 | 0.9757 | 0.8510 | 0.8483 | 0.8486 | 0.8483 |
|
72 |
-
| 0.0022 | 51.7241 | 1500 | 0.9828 | 0.8586 | 0.8571 | 0.8572 | 0.8571 |
|
73 |
-
| 0.002 | 55.1724 | 1600 | 0.9788 | 0.8588 | 0.8571 | 0.8573 | 0.8571 |
|
74 |
-
| 0.0018 | 58.6207 | 1700 | 0.9835 | 0.8604 | 0.8589 | 0.8590 | 0.8589 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.0544
|
24 |
+
- Precision: 0.8507
|
25 |
+
- Recall: 0.8483
|
26 |
+
- F1: 0.8486
|
27 |
+
- Accuracy: 0.8483
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 64
|
48 |
+
- eval_batch_size: 64
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
|
|
53 |
|
54 |
### Training results
|
55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|
runs/Apr25_18-18-41_27605680e053/events.out.tfevents.1714071335.27605680e053.4588.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c313b218a72d54fdea89a1d99c3573d85eb5bdb9745c257c3f52176db7c6f91
|
3 |
+
size 560
|