End of training
Browse files- README.md +76 -76
- config.json +1 -1
- model.safetensors +1 -1
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
-
- F1: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -50,83 +50,83 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 53 |
-
| No log | 0.14 | 50 | 0.
|
| 54 |
-
| No log | 0.28 | 100 | 0.
|
| 55 |
-
| No log | 0.42 | 150 | 0.
|
| 56 |
-
| No log | 0.56 | 200 | 0.
|
| 57 |
-
| No log | 0.69 | 250 | 0.
|
| 58 |
-
| No log | 0.83 | 300 | 0.
|
| 59 |
-
| No log | 0.97 | 350 | 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
|
| 126 |
|
| 127 |
### Framework versions
|
| 128 |
|
| 129 |
-
- Transformers 4.39.
|
| 130 |
- Pytorch 2.2.1+cu121
|
| 131 |
- Datasets 2.18.0
|
| 132 |
- Tokenizers 0.15.2
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.1888
|
| 21 |
+
- Accuracy: 0.9622
|
| 22 |
+
- F1: 0.9622
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 53 |
+
| No log | 0.14 | 50 | 0.2349 | 0.9218 | 0.9218 |
|
| 54 |
+
| No log | 0.28 | 100 | 0.2021 | 0.9372 | 0.9371 |
|
| 55 |
+
| No log | 0.42 | 150 | 0.1821 | 0.9428 | 0.9429 |
|
| 56 |
+
| No log | 0.56 | 200 | 0.1753 | 0.9512 | 0.9513 |
|
| 57 |
+
| No log | 0.69 | 250 | 0.1589 | 0.9521 | 0.9521 |
|
| 58 |
+
| No log | 0.83 | 300 | 0.1597 | 0.9551 | 0.9552 |
|
| 59 |
+
| No log | 0.97 | 350 | 0.1688 | 0.9540 | 0.9541 |
|
| 60 |
+
| 0.2039 | 1.11 | 400 | 0.1633 | 0.9526 | 0.9527 |
|
| 61 |
+
| 0.2039 | 1.25 | 450 | 0.1436 | 0.9532 | 0.9532 |
|
| 62 |
+
| 0.2039 | 1.39 | 500 | 0.1397 | 0.9540 | 0.9541 |
|
| 63 |
+
| 0.2039 | 1.53 | 550 | 0.1473 | 0.9596 | 0.9596 |
|
| 64 |
+
| 0.2039 | 1.67 | 600 | 0.1435 | 0.9579 | 0.9580 |
|
| 65 |
+
| 0.2039 | 1.81 | 650 | 0.1486 | 0.9546 | 0.9547 |
|
| 66 |
+
| 0.2039 | 1.94 | 700 | 0.1341 | 0.9588 | 0.9588 |
|
| 67 |
+
| 0.129 | 2.08 | 750 | 0.1322 | 0.9605 | 0.9605 |
|
| 68 |
+
| 0.129 | 2.22 | 800 | 0.1253 | 0.9599 | 0.9599 |
|
| 69 |
+
| 0.129 | 2.36 | 850 | 0.1281 | 0.9633 | 0.9633 |
|
| 70 |
+
| 0.129 | 2.5 | 900 | 0.1298 | 0.9591 | 0.9591 |
|
| 71 |
+
| 0.129 | 2.64 | 950 | 0.1293 | 0.9599 | 0.9599 |
|
| 72 |
+
| 0.129 | 2.78 | 1000 | 0.1286 | 0.9622 | 0.9622 |
|
| 73 |
+
| 0.129 | 2.92 | 1050 | 0.1329 | 0.9630 | 0.9630 |
|
| 74 |
+
| 0.1055 | 3.06 | 1100 | 0.1407 | 0.9624 | 0.9625 |
|
| 75 |
+
| 0.1055 | 3.19 | 1150 | 0.1334 | 0.9608 | 0.9608 |
|
| 76 |
+
| 0.1055 | 3.33 | 1200 | 0.1398 | 0.9568 | 0.9569 |
|
| 77 |
+
| 0.1055 | 3.47 | 1250 | 0.1413 | 0.9605 | 0.9605 |
|
| 78 |
+
| 0.1055 | 3.61 | 1300 | 0.1403 | 0.9622 | 0.9622 |
|
| 79 |
+
| 0.1055 | 3.75 | 1350 | 0.1284 | 0.9627 | 0.9627 |
|
| 80 |
+
| 0.1055 | 3.89 | 1400 | 0.1294 | 0.9605 | 0.9605 |
|
| 81 |
+
| 0.0881 | 4.03 | 1450 | 0.1590 | 0.9591 | 0.9591 |
|
| 82 |
+
| 0.0881 | 4.17 | 1500 | 0.1291 | 0.9624 | 0.9625 |
|
| 83 |
+
| 0.0881 | 4.31 | 1550 | 0.1344 | 0.9633 | 0.9633 |
|
| 84 |
+
| 0.0881 | 4.44 | 1600 | 0.1494 | 0.9627 | 0.9627 |
|
| 85 |
+
| 0.0881 | 4.58 | 1650 | 0.1528 | 0.9591 | 0.9591 |
|
| 86 |
+
| 0.0881 | 4.72 | 1700 | 0.1397 | 0.9610 | 0.9611 |
|
| 87 |
+
| 0.0881 | 4.86 | 1750 | 0.1461 | 0.9652 | 0.9653 |
|
| 88 |
+
| 0.0739 | 5.0 | 1800 | 0.1425 | 0.9633 | 0.9633 |
|
| 89 |
+
| 0.0739 | 5.14 | 1850 | 0.1539 | 0.9610 | 0.9611 |
|
| 90 |
+
| 0.0739 | 5.28 | 1900 | 0.1513 | 0.9613 | 0.9614 |
|
| 91 |
+
| 0.0739 | 5.42 | 1950 | 0.1481 | 0.9619 | 0.9619 |
|
| 92 |
+
| 0.0739 | 5.56 | 2000 | 0.1477 | 0.9582 | 0.9583 |
|
| 93 |
+
| 0.0739 | 5.69 | 2050 | 0.1449 | 0.9630 | 0.9630 |
|
| 94 |
+
| 0.0739 | 5.83 | 2100 | 0.1658 | 0.9633 | 0.9633 |
|
| 95 |
+
| 0.0739 | 5.97 | 2150 | 0.1649 | 0.9602 | 0.9602 |
|
| 96 |
+
| 0.062 | 6.11 | 2200 | 0.1705 | 0.9577 | 0.9577 |
|
| 97 |
+
| 0.062 | 6.25 | 2250 | 0.1727 | 0.9613 | 0.9613 |
|
| 98 |
+
| 0.062 | 6.39 | 2300 | 0.1803 | 0.9568 | 0.9569 |
|
| 99 |
+
| 0.062 | 6.53 | 2350 | 0.1670 | 0.9627 | 0.9627 |
|
| 100 |
+
| 0.062 | 6.67 | 2400 | 0.1748 | 0.9624 | 0.9625 |
|
| 101 |
+
| 0.062 | 6.81 | 2450 | 0.1597 | 0.9605 | 0.9605 |
|
| 102 |
+
| 0.062 | 6.94 | 2500 | 0.1659 | 0.9638 | 0.9639 |
|
| 103 |
+
| 0.0524 | 7.08 | 2550 | 0.1689 | 0.9630 | 0.9630 |
|
| 104 |
+
| 0.0524 | 7.22 | 2600 | 0.1700 | 0.9605 | 0.9605 |
|
| 105 |
+
| 0.0524 | 7.36 | 2650 | 0.1846 | 0.9599 | 0.9600 |
|
| 106 |
+
| 0.0524 | 7.5 | 2700 | 0.1789 | 0.9602 | 0.9602 |
|
| 107 |
+
| 0.0524 | 7.64 | 2750 | 0.1705 | 0.9613 | 0.9613 |
|
| 108 |
+
| 0.0524 | 7.78 | 2800 | 0.1639 | 0.9636 | 0.9636 |
|
| 109 |
+
| 0.0524 | 7.92 | 2850 | 0.1679 | 0.9644 | 0.9644 |
|
| 110 |
+
| 0.0432 | 8.06 | 2900 | 0.1716 | 0.9593 | 0.9594 |
|
| 111 |
+
| 0.0432 | 8.19 | 2950 | 0.1837 | 0.9619 | 0.9619 |
|
| 112 |
+
| 0.0432 | 8.33 | 3000 | 0.1904 | 0.9619 | 0.9619 |
|
| 113 |
+
| 0.0432 | 8.47 | 3050 | 0.1903 | 0.9610 | 0.9611 |
|
| 114 |
+
| 0.0432 | 8.61 | 3100 | 0.1806 | 0.9613 | 0.9614 |
|
| 115 |
+
| 0.0432 | 8.75 | 3150 | 0.1811 | 0.9630 | 0.9630 |
|
| 116 |
+
| 0.0432 | 8.89 | 3200 | 0.1881 | 0.9616 | 0.9616 |
|
| 117 |
+
| 0.0408 | 9.03 | 3250 | 0.1890 | 0.9613 | 0.9614 |
|
| 118 |
+
| 0.0408 | 9.17 | 3300 | 0.1855 | 0.9636 | 0.9636 |
|
| 119 |
+
| 0.0408 | 9.31 | 3350 | 0.1899 | 0.9610 | 0.9611 |
|
| 120 |
+
| 0.0408 | 9.44 | 3400 | 0.1907 | 0.9608 | 0.9608 |
|
| 121 |
+
| 0.0408 | 9.58 | 3450 | 0.1839 | 0.9616 | 0.9616 |
|
| 122 |
+
| 0.0408 | 9.72 | 3500 | 0.1873 | 0.9613 | 0.9613 |
|
| 123 |
+
| 0.0408 | 9.86 | 3550 | 0.1885 | 0.9622 | 0.9622 |
|
| 124 |
+
| 0.0329 | 10.0 | 3600 | 0.1888 | 0.9622 | 0.9622 |
|
| 125 |
|
| 126 |
|
| 127 |
### Framework versions
|
| 128 |
|
| 129 |
+
- Transformers 4.39.3
|
| 130 |
- Pytorch 2.2.1+cu121
|
| 131 |
- Datasets 2.18.0
|
| 132 |
- Tokenizers 0.15.2
|
config.json
CHANGED
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"problem_type": "single_label_classification",
|
| 23 |
"tokenizer_class": "PhobertTokenizer",
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
-
"transformers_version": "4.39.
|
| 26 |
"type_vocab_size": 1,
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 64001
|
|
|
|
| 22 |
"problem_type": "single_label_classification",
|
| 23 |
"tokenizer_class": "PhobertTokenizer",
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.39.3",
|
| 26 |
"type_vocab_size": 1,
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 64001
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 540023384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8c22bb2f13f9242f270b2f19e4760773ebc7e5fb0adca604f02df5ce403c3db
|
| 3 |
size 540023384
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffbd55541eb9445df38d580a9eb60654cf0be091ab1349fd0ccbba3f04032849
|
| 3 |
+
size 4920
|