update model card README.md
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 [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -40,72 +40,22 @@ 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 | 6 | 13.
|
50 |
-
| No log | 2.0 | 12 | 12.
|
51 |
-
| No log | 3.0 | 18 | 11.
|
52 |
-
| No log | 4.0 | 24 | 10.
|
53 |
-
| No log | 5.0 | 30 |
|
54 |
-
| No log | 6.0 | 36 |
|
55 |
-
| No log | 7.0 | 42 |
|
56 |
-
| No log | 8.0 | 48 |
|
57 |
-
| No log | 9.0 | 54 |
|
58 |
-
| No log | 10.0 | 60 |
|
59 |
-
| No log | 11.0 | 66 | 4.3329 |
|
60 |
-
| No log | 12.0 | 72 | 4.1270 |
|
61 |
-
| No log | 13.0 | 78 | 3.9392 |
|
62 |
-
| No log | 14.0 | 84 | 3.7658 |
|
63 |
-
| No log | 15.0 | 90 | 3.6182 |
|
64 |
-
| No log | 16.0 | 96 | 3.4915 |
|
65 |
-
| No log | 17.0 | 102 | 3.3719 |
|
66 |
-
| No log | 18.0 | 108 | 3.2467 |
|
67 |
-
| No log | 19.0 | 114 | 3.1374 |
|
68 |
-
| No log | 20.0 | 120 | 3.0331 |
|
69 |
-
| No log | 21.0 | 126 | 2.9368 |
|
70 |
-
| No log | 22.0 | 132 | 2.8411 |
|
71 |
-
| No log | 23.0 | 138 | 2.7430 |
|
72 |
-
| No log | 24.0 | 144 | 2.6521 |
|
73 |
-
| No log | 25.0 | 150 | 2.5733 |
|
74 |
-
| No log | 26.0 | 156 | 2.4918 |
|
75 |
-
| No log | 27.0 | 162 | 2.4123 |
|
76 |
-
| No log | 28.0 | 168 | 2.3377 |
|
77 |
-
| No log | 29.0 | 174 | 2.2648 |
|
78 |
-
| No log | 30.0 | 180 | 2.1950 |
|
79 |
-
| No log | 31.0 | 186 | 2.1286 |
|
80 |
-
| No log | 32.0 | 192 | 2.0646 |
|
81 |
-
| No log | 33.0 | 198 | 2.0045 |
|
82 |
-
| No log | 34.0 | 204 | 1.9476 |
|
83 |
-
| No log | 35.0 | 210 | 1.8927 |
|
84 |
-
| No log | 36.0 | 216 | 1.8419 |
|
85 |
-
| No log | 37.0 | 222 | 1.7924 |
|
86 |
-
| No log | 38.0 | 228 | 1.7420 |
|
87 |
-
| No log | 39.0 | 234 | 1.6980 |
|
88 |
-
| No log | 40.0 | 240 | 1.6592 |
|
89 |
-
| No log | 41.0 | 246 | 1.6197 |
|
90 |
-
| No log | 42.0 | 252 | 1.5805 |
|
91 |
-
| No log | 43.0 | 258 | 1.5428 |
|
92 |
-
| No log | 44.0 | 264 | 1.5082 |
|
93 |
-
| No log | 45.0 | 270 | 1.4784 |
|
94 |
-
| No log | 46.0 | 276 | 1.4517 |
|
95 |
-
| No log | 47.0 | 282 | 1.4265 |
|
96 |
-
| No log | 48.0 | 288 | 1.4019 |
|
97 |
-
| No log | 49.0 | 294 | 1.3798 |
|
98 |
-
| No log | 50.0 | 300 | 1.3596 |
|
99 |
-
| No log | 51.0 | 306 | 1.3419 |
|
100 |
-
| No log | 52.0 | 312 | 1.3262 |
|
101 |
-
| No log | 53.0 | 318 | 1.3122 |
|
102 |
-
| No log | 54.0 | 324 | 1.3003 |
|
103 |
-
| No log | 55.0 | 330 | 1.2902 |
|
104 |
-
| No log | 56.0 | 336 | 1.2821 |
|
105 |
-
| No log | 57.0 | 342 | 1.2757 |
|
106 |
-
| No log | 58.0 | 348 | 1.2709 |
|
107 |
-
| No log | 59.0 | 354 | 1.2678 |
|
108 |
-
| No log | 60.0 | 360 | 1.2667 |
|
109 |
|
110 |
|
111 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 7.2867
|
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: 10
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 6 | 13.4504 |
|
50 |
+
| No log | 2.0 | 12 | 12.3510 |
|
51 |
+
| No log | 3.0 | 18 | 11.6369 |
|
52 |
+
| No log | 4.0 | 24 | 10.9004 |
|
53 |
+
| No log | 5.0 | 30 | 10.0865 |
|
54 |
+
| No log | 6.0 | 36 | 9.2811 |
|
55 |
+
| No log | 7.0 | 42 | 8.5458 |
|
56 |
+
| No log | 8.0 | 48 | 7.9115 |
|
57 |
+
| No log | 9.0 | 54 | 7.4583 |
|
58 |
+
| No log | 10.0 | 60 | 7.2867 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|