KOSMiPOLITA
commited on
Commit
•
5f99ad6
1
Parent(s):
2c47602
End of training
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [Geotrend/distilbert-base-pl-cased](https://huggingface.co/Geotrend/distilbert-base-pl-cased) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -40,18 +40,63 @@ The following hyperparameters were used during training:
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
| 2.
|
51 |
-
| 1.
|
52 |
-
| 1.
|
53 |
-
| 1.
|
54 |
-
| 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
|
56 |
|
57 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [Geotrend/distilbert-base-pl-cased](https://huggingface.co/Geotrend/distilbert-base-pl-cased) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.3583
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 50
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 2.4541 | 1.0 | 20 | 1.5317 |
|
51 |
+
| 1.5138 | 2.0 | 40 | 1.2678 |
|
52 |
+
| 1.2893 | 3.0 | 60 | 1.0208 |
|
53 |
+
| 1.135 | 4.0 | 80 | 1.0185 |
|
54 |
+
| 1.0288 | 5.0 | 100 | 0.9068 |
|
55 |
+
| 0.9607 | 6.0 | 120 | 0.8102 |
|
56 |
+
| 0.8933 | 7.0 | 140 | 0.8191 |
|
57 |
+
| 0.8595 | 8.0 | 160 | 0.8191 |
|
58 |
+
| 0.8314 | 9.0 | 180 | 0.6913 |
|
59 |
+
| 0.7866 | 10.0 | 200 | 0.6317 |
|
60 |
+
| 0.7642 | 11.0 | 220 | 0.6345 |
|
61 |
+
| 0.7114 | 12.0 | 240 | 0.6749 |
|
62 |
+
| 0.7033 | 13.0 | 260 | 0.6147 |
|
63 |
+
| 0.6435 | 14.0 | 280 | 0.5894 |
|
64 |
+
| 0.6545 | 15.0 | 300 | 0.5822 |
|
65 |
+
| 0.6255 | 16.0 | 320 | 0.5452 |
|
66 |
+
| 0.602 | 17.0 | 340 | 0.5521 |
|
67 |
+
| 0.594 | 18.0 | 360 | 0.4672 |
|
68 |
+
| 0.5572 | 19.0 | 380 | 0.5322 |
|
69 |
+
| 0.5614 | 20.0 | 400 | 0.5200 |
|
70 |
+
| 0.556 | 21.0 | 420 | 0.5213 |
|
71 |
+
| 0.5616 | 22.0 | 440 | 0.5052 |
|
72 |
+
| 0.5249 | 23.0 | 460 | 0.4811 |
|
73 |
+
| 0.5403 | 24.0 | 480 | 0.4990 |
|
74 |
+
| 0.5081 | 25.0 | 500 | 0.4572 |
|
75 |
+
| 0.5153 | 26.0 | 520 | 0.4845 |
|
76 |
+
| 0.4962 | 27.0 | 540 | 0.4954 |
|
77 |
+
| 0.4834 | 28.0 | 560 | 0.4418 |
|
78 |
+
| 0.4782 | 29.0 | 580 | 0.4987 |
|
79 |
+
| 0.5126 | 30.0 | 600 | 0.5001 |
|
80 |
+
| 0.4829 | 31.0 | 620 | 0.4515 |
|
81 |
+
| 0.4671 | 32.0 | 640 | 0.4400 |
|
82 |
+
| 0.4514 | 33.0 | 660 | 0.4875 |
|
83 |
+
| 0.488 | 34.0 | 680 | 0.4000 |
|
84 |
+
| 0.4642 | 35.0 | 700 | 0.4538 |
|
85 |
+
| 0.4481 | 36.0 | 720 | 0.4452 |
|
86 |
+
| 0.4505 | 37.0 | 740 | 0.4636 |
|
87 |
+
| 0.4554 | 38.0 | 760 | 0.4645 |
|
88 |
+
| 0.4322 | 39.0 | 780 | 0.4615 |
|
89 |
+
| 0.4394 | 40.0 | 800 | 0.4676 |
|
90 |
+
| 0.4325 | 41.0 | 820 | 0.4072 |
|
91 |
+
| 0.4077 | 42.0 | 840 | 0.4518 |
|
92 |
+
| 0.416 | 43.0 | 860 | 0.4514 |
|
93 |
+
| 0.4382 | 44.0 | 880 | 0.4459 |
|
94 |
+
| 0.4395 | 45.0 | 900 | 0.4757 |
|
95 |
+
| 0.4188 | 46.0 | 920 | 0.4870 |
|
96 |
+
| 0.4052 | 47.0 | 940 | 0.4658 |
|
97 |
+
| 0.4273 | 48.0 | 960 | 0.4168 |
|
98 |
+
| 0.435 | 49.0 | 980 | 0.3387 |
|
99 |
+
| 0.432 | 50.0 | 1000 | 0.4673 |
|
100 |
|
101 |
|
102 |
### Framework versions
|
runs/Dec07_18-45-34_711068fa4b4f/events.out.tfevents.1701975555.711068fa4b4f.996.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffcbabf2e07275693543b94af2e8b2f7db27435db25a0879712af9fd06ee027e
|
3 |
+
size 359
|