ncardus/SeqClassifier
Browse files- README.md +20 -65
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model was trained from scratch on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Accuracy: 0.
|
23 |
-
- F1: 0.
|
24 |
-
- Precision: 0.
|
25 |
- Recall: 0.5
|
26 |
|
27 |
## Model description
|
@@ -47,72 +47,27 @@ The following hyperparameters were used during training:
|
|
47 |
- seed: 42
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
-
- num_epochs:
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
55 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.32 | 26.67 | 80 | 0.5066 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
72 |
-
| 0.3098 | 28.33 | 85 | 0.5087 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
73 |
-
| 0.3319 | 30.0 | 90 | 0.5110 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
74 |
-
| 0.3404 | 31.67 | 95 | 0.5133 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
75 |
-
| 0.2713 | 33.33 | 100 | 0.5159 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
76 |
-
| 0.3269 | 35.0 | 105 | 0.5183 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
77 |
-
| 0.3384 | 36.67 | 110 | 0.5202 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
78 |
-
| 0.2879 | 38.33 | 115 | 0.5221 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
79 |
-
| 0.2917 | 40.0 | 120 | 0.5241 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
80 |
-
| 0.2662 | 41.67 | 125 | 0.5262 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
81 |
-
| 0.3248 | 43.33 | 130 | 0.5280 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
82 |
-
| 0.3407 | 45.0 | 135 | 0.5295 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
83 |
-
| 0.2767 | 46.67 | 140 | 0.5311 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
84 |
-
| 0.3517 | 48.33 | 145 | 0.5328 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
85 |
-
| 0.2873 | 50.0 | 150 | 0.5342 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
86 |
-
| 0.2713 | 51.67 | 155 | 0.5357 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
87 |
-
| 0.3552 | 53.33 | 160 | 0.5365 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
88 |
-
| 0.3268 | 55.0 | 165 | 0.5373 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
89 |
-
| 0.3338 | 56.67 | 170 | 0.5380 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
90 |
-
| 0.2583 | 58.33 | 175 | 0.5388 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
91 |
-
| 0.3225 | 60.0 | 180 | 0.5394 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
92 |
-
| 0.3264 | 61.67 | 185 | 0.5402 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
93 |
-
| 0.2748 | 63.33 | 190 | 0.5411 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
94 |
-
| 0.2917 | 65.0 | 195 | 0.5422 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
95 |
-
| 0.3245 | 66.67 | 200 | 0.5429 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
96 |
-
| 0.2481 | 68.33 | 205 | 0.5437 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
97 |
-
| 0.3228 | 70.0 | 210 | 0.5444 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
98 |
-
| 0.2481 | 71.67 | 215 | 0.5451 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
99 |
-
| 0.3224 | 73.33 | 220 | 0.5456 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
100 |
-
| 0.3423 | 75.0 | 225 | 0.5461 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
101 |
-
| 0.3339 | 76.67 | 230 | 0.5463 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
102 |
-
| 0.2978 | 78.33 | 235 | 0.5466 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
103 |
-
| 0.2408 | 80.0 | 240 | 0.5470 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
104 |
-
| 0.3282 | 81.67 | 245 | 0.5473 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
105 |
-
| 0.2829 | 83.33 | 250 | 0.5478 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
106 |
-
| 0.2991 | 85.0 | 255 | 0.5482 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
107 |
-
| 0.3031 | 86.67 | 260 | 0.5484 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
108 |
-
| 0.3316 | 88.33 | 265 | 0.5485 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
109 |
-
| 0.2443 | 90.0 | 270 | 0.5487 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
110 |
-
| 0.2861 | 91.67 | 275 | 0.5490 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
111 |
-
| 0.2941 | 93.33 | 280 | 0.5491 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
112 |
-
| 0.3573 | 95.0 | 285 | 0.5492 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
113 |
-
| 0.3153 | 96.67 | 290 | 0.5493 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
114 |
-
| 0.3079 | 98.33 | 295 | 0.5493 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
115 |
-
| 0.2846 | 100.0 | 300 | 0.5493 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
116 |
|
117 |
|
118 |
### Framework versions
|
|
|
18 |
|
19 |
This model was trained from scratch on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.7534
|
22 |
+
- Accuracy: 0.2
|
23 |
+
- F1: 0.1667
|
24 |
+
- Precision: 0.1
|
25 |
- Recall: 0.5
|
26 |
|
27 |
## Model description
|
|
|
47 |
- seed: 42
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 5
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
55 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
56 |
+
| No log | 0.33 | 1 | 0.6877 | 0.8 | 0.4444 | 0.4 | 0.5 |
|
57 |
+
| No log | 0.67 | 2 | 0.6968 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
58 |
+
| No log | 1.0 | 3 | 0.7052 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
59 |
+
| No log | 1.33 | 4 | 0.7133 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
60 |
+
| 0.6917 | 1.67 | 5 | 0.7206 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
61 |
+
| 0.6917 | 2.0 | 6 | 0.7263 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
62 |
+
| 0.6917 | 2.33 | 7 | 0.7318 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
63 |
+
| 0.6917 | 2.67 | 8 | 0.7369 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
64 |
+
| 0.6917 | 3.0 | 9 | 0.7409 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
65 |
+
| 0.6805 | 3.33 | 10 | 0.7444 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
66 |
+
| 0.6805 | 3.67 | 11 | 0.7475 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
67 |
+
| 0.6805 | 4.0 | 12 | 0.7499 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
68 |
+
| 0.6805 | 4.33 | 13 | 0.7518 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
69 |
+
| 0.6805 | 4.67 | 14 | 0.7529 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
70 |
+
| 0.6713 | 5.0 | 15 | 0.7534 | 0.2 | 0.1667 | 0.1 | 0.5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
|
72 |
|
73 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 11033176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d50e2c76a92bc4a9bcec1ccfea49483b36fdd44aed399c6911efe5a68920104
|
3 |
size 11033176
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf1e728d5859a955e098ee406017a5d2a09b335b12e2c85fcb93be5fcd691cde
|
3 |
size 4536
|