Commit
·
0c1daec
1
Parent(s):
9f3c0de
Training in progress epoch 0
Browse files- README.md +4 -53
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Train Loss:
|
| 18 |
-
- Validation Loss:
|
| 19 |
-
- Epoch:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -42,56 +42,7 @@ The following hyperparameters were used during training:
|
|
| 42 |
|
| 43 |
| Train Loss | Validation Loss | Epoch |
|
| 44 |
|:----------:|:---------------:|:-----:|
|
| 45 |
-
| 1.
|
| 46 |
-
| 1.5695 | 1.5934 | 1 |
|
| 47 |
-
| 1.5128 | 1.5183 | 2 |
|
| 48 |
-
| 1.4323 | 1.3869 | 3 |
|
| 49 |
-
| 1.3073 | 1.2395 | 4 |
|
| 50 |
-
| 1.1639 | 1.1111 | 5 |
|
| 51 |
-
| 1.0148 | 1.0003 | 6 |
|
| 52 |
-
| 0.8949 | 0.9099 | 7 |
|
| 53 |
-
| 0.7910 | 0.8363 | 8 |
|
| 54 |
-
| 0.6968 | 0.7782 | 9 |
|
| 55 |
-
| 0.6153 | 0.7293 | 10 |
|
| 56 |
-
| 0.5506 | 0.6909 | 11 |
|
| 57 |
-
| 0.5102 | 0.6588 | 12 |
|
| 58 |
-
| 0.4615 | 0.6300 | 13 |
|
| 59 |
-
| 0.4204 | 0.6072 | 14 |
|
| 60 |
-
| 0.3854 | 0.5874 | 15 |
|
| 61 |
-
| 0.3587 | 0.5710 | 16 |
|
| 62 |
-
| 0.3358 | 0.5573 | 17 |
|
| 63 |
-
| 0.3118 | 0.5449 | 18 |
|
| 64 |
-
| 0.2899 | 0.5349 | 19 |
|
| 65 |
-
| 0.2736 | 0.5246 | 20 |
|
| 66 |
-
| 0.2563 | 0.5174 | 21 |
|
| 67 |
-
| 0.2415 | 0.5108 | 22 |
|
| 68 |
-
| 0.2289 | 0.5047 | 23 |
|
| 69 |
-
| 0.2192 | 0.4997 | 24 |
|
| 70 |
-
| 0.2074 | 0.4952 | 25 |
|
| 71 |
-
| 0.1968 | 0.4913 | 26 |
|
| 72 |
-
| 0.1904 | 0.4885 | 27 |
|
| 73 |
-
| 0.1784 | 0.4859 | 28 |
|
| 74 |
-
| 0.1759 | 0.4835 | 29 |
|
| 75 |
-
| 0.1703 | 0.4815 | 30 |
|
| 76 |
-
| 0.1608 | 0.4798 | 31 |
|
| 77 |
-
| 0.1566 | 0.4784 | 32 |
|
| 78 |
-
| 0.1559 | 0.4767 | 33 |
|
| 79 |
-
| 0.1502 | 0.4755 | 34 |
|
| 80 |
-
| 0.1479 | 0.4744 | 35 |
|
| 81 |
-
| 0.1420 | 0.4736 | 36 |
|
| 82 |
-
| 0.1416 | 0.4729 | 37 |
|
| 83 |
-
| 0.1355 | 0.4725 | 38 |
|
| 84 |
-
| 0.1291 | 0.4720 | 39 |
|
| 85 |
-
| 0.1321 | 0.4715 | 40 |
|
| 86 |
-
| 0.1268 | 0.4711 | 41 |
|
| 87 |
-
| 0.1244 | 0.4708 | 42 |
|
| 88 |
-
| 0.1253 | 0.4705 | 43 |
|
| 89 |
-
| 0.1226 | 0.4704 | 44 |
|
| 90 |
-
| 0.1226 | 0.4702 | 45 |
|
| 91 |
-
| 0.1210 | 0.4700 | 46 |
|
| 92 |
-
| 0.1233 | 0.4700 | 47 |
|
| 93 |
-
| 0.1197 | 0.4699 | 48 |
|
| 94 |
-
| 0.1184 | 0.4699 | 49 |
|
| 95 |
|
| 96 |
|
| 97 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 1.5966
|
| 18 |
+
- Validation Loss: 1.5898
|
| 19 |
+
- Epoch: 0
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 42 |
|
| 43 |
| Train Loss | Validation Loss | Epoch |
|
| 44 |
|:----------:|:---------------:|:-----:|
|
| 45 |
+
| 1.5966 | 1.5898 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 442792832
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2289bb4468ccd2bac45c8a781cb7339ab58ec5cf470b7bcbcb09b5a94a33977
|
| 3 |
size 442792832
|