End of training
Browse files
README.md
CHANGED
@@ -3,6 +3,11 @@ license: apache-2.0
|
|
3 |
base_model: distilbert/distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
- name: nlp_til
|
8 |
results: []
|
@@ -15,7 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -40,14 +49,30 @@ 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 |
|
45 |
### Training results
|
46 |
|
47 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
-
|
49 |
-
| No log | 1.0 | 219 | 0.
|
50 |
-
| No log | 2.0 | 438 | 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
3 |
base_model: distilbert/distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
model-index:
|
12 |
- name: nlp_til
|
13 |
results: []
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.1994
|
24 |
+
- Precision: 0.4726
|
25 |
+
- Recall: 0.5278
|
26 |
+
- F1: 0.4987
|
27 |
+
- Accuracy: 0.9007
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 18
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| No log | 1.0 | 219 | 0.2462 | 0.3017 | 0.3623 | 0.3292 | 0.8584 |
|
59 |
+
| No log | 2.0 | 438 | 0.2436 | 0.3176 | 0.3485 | 0.3323 | 0.8656 |
|
60 |
+
| 0.2463 | 3.0 | 657 | 0.2434 | 0.3333 | 0.4792 | 0.3932 | 0.8622 |
|
61 |
+
| 0.2463 | 4.0 | 876 | 0.2402 | 0.3398 | 0.3567 | 0.3480 | 0.8675 |
|
62 |
+
| 0.2453 | 5.0 | 1095 | 0.2388 | 0.3299 | 0.3708 | 0.3491 | 0.8686 |
|
63 |
+
| 0.2453 | 6.0 | 1314 | 0.2381 | 0.3230 | 0.3740 | 0.3467 | 0.8689 |
|
64 |
+
| 0.2421 | 7.0 | 1533 | 0.2384 | 0.3448 | 0.3508 | 0.3477 | 0.8691 |
|
65 |
+
| 0.2421 | 8.0 | 1752 | 0.2343 | 0.3427 | 0.3711 | 0.3563 | 0.8705 |
|
66 |
+
| 0.2421 | 9.0 | 1971 | 0.2334 | 0.3448 | 0.3433 | 0.3440 | 0.8713 |
|
67 |
+
| 0.2388 | 10.0 | 2190 | 0.2314 | 0.3696 | 0.4533 | 0.4072 | 0.8768 |
|
68 |
+
| 0.2388 | 11.0 | 2409 | 0.2238 | 0.3846 | 0.4643 | 0.4207 | 0.8812 |
|
69 |
+
| 0.2337 | 12.0 | 2628 | 0.2216 | 0.3968 | 0.4703 | 0.4305 | 0.8832 |
|
70 |
+
| 0.2337 | 13.0 | 2847 | 0.2135 | 0.4169 | 0.4939 | 0.4521 | 0.8898 |
|
71 |
+
| 0.2268 | 14.0 | 3066 | 0.2117 | 0.4387 | 0.5200 | 0.4759 | 0.8919 |
|
72 |
+
| 0.2268 | 15.0 | 3285 | 0.2059 | 0.4565 | 0.5146 | 0.4838 | 0.8963 |
|
73 |
+
| 0.2197 | 16.0 | 3504 | 0.2043 | 0.4669 | 0.5359 | 0.4990 | 0.8977 |
|
74 |
+
| 0.2197 | 17.0 | 3723 | 0.2005 | 0.4701 | 0.5356 | 0.5007 | 0.8997 |
|
75 |
+
| 0.2197 | 18.0 | 3942 | 0.1994 | 0.4726 | 0.5278 | 0.4987 | 0.9007 |
|
76 |
|
77 |
|
78 |
### Framework versions
|