senthil2002
commited on
Commit
•
3b5e4bb
1
Parent(s):
b60b437
End of training
Browse files
README.md
CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
- Precision: 0.
|
25 |
-
- Recall: 0.
|
26 |
-
- F1: 0.
|
27 |
-
- Accuracy: 0.
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -49,62 +49,42 @@ The following hyperparameters were used during training:
|
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
-
- num_epochs:
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
-
| No log | 1.0 | 3 | 0.
|
59 |
-
| No log | 2.0 | 6 | 0.
|
60 |
-
| No log | 3.0 | 9 | 0.
|
61 |
-
| No log | 4.0 | 12 | 0.
|
62 |
-
| No log | 5.0 | 15 | 0.
|
63 |
-
| No log | 6.0 | 18 | 0.
|
64 |
-
| No log | 7.0 | 21 | 0.
|
65 |
-
| No log | 8.0 | 24 | 0.
|
66 |
-
| No log | 9.0 | 27 | 0.
|
67 |
-
| No log | 10.0 | 30 | 0.
|
68 |
-
| No log | 11.0 | 33 | 0.
|
69 |
-
| No log | 12.0 | 36 | 0.
|
70 |
-
| No log | 13.0 | 39 | 0.
|
71 |
-
| No log | 14.0 | 42 | 0.
|
72 |
-
| No log | 15.0 | 45 | 0.
|
73 |
-
| No log | 16.0 | 48 | 0.
|
74 |
-
| No log | 17.0 | 51 | 0.
|
75 |
-
| No log | 18.0 | 54 | 0.
|
76 |
-
| No log | 19.0 | 57 | 0.
|
77 |
-
| No log | 20.0 | 60 | 0.
|
78 |
-
| No log | 21.0 | 63 | 0.
|
79 |
-
| No log | 22.0 | 66 | 0.
|
80 |
-
| No log | 23.0 | 69 | 0.
|
81 |
-
| No log | 24.0 | 72 | 0.
|
82 |
-
| No log | 25.0 | 75 | 0.
|
83 |
-
| No log | 26.0 | 78 | 0.
|
84 |
-
| No log | 27.0 | 81 | 0.
|
85 |
-
| No log | 28.0 | 84 | 0.
|
86 |
-
| No log | 29.0 | 87 | 0.
|
87 |
-
| No log | 30.0 | 90 | 0.
|
88 |
-
| No log | 31.0 | 93 | 0.1315 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
89 |
-
| No log | 32.0 | 96 | 0.1274 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
90 |
-
| No log | 33.0 | 99 | 0.1244 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
91 |
-
| No log | 34.0 | 102 | 0.1233 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
92 |
-
| No log | 35.0 | 105 | 0.1226 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
93 |
-
| No log | 36.0 | 108 | 0.1220 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
94 |
-
| No log | 37.0 | 111 | 0.1220 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
95 |
-
| No log | 38.0 | 114 | 0.1215 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
96 |
-
| No log | 39.0 | 117 | 0.1219 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
97 |
-
| No log | 40.0 | 120 | 0.1229 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
98 |
-
| No log | 41.0 | 123 | 0.1239 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
99 |
-
| No log | 42.0 | 126 | 0.1249 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
100 |
-
| No log | 43.0 | 129 | 0.1255 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
101 |
-
| No log | 44.0 | 132 | 0.1257 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
102 |
-
| No log | 45.0 | 135 | 0.1261 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
103 |
-
| No log | 46.0 | 138 | 0.1267 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
104 |
-
| No log | 47.0 | 141 | 0.1271 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
105 |
-
| No log | 48.0 | 144 | 0.1273 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
106 |
-
| No log | 49.0 | 147 | 0.1275 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
107 |
-
| No log | 50.0 | 150 | 0.1275 | 0.4286 | 0.6 | 0.5 | 0.92 |
|
108 |
|
109 |
|
110 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.2486
|
24 |
+
- Precision: 0.25
|
25 |
+
- Recall: 0.4
|
26 |
+
- F1: 0.3077
|
27 |
+
- Accuracy: 0.88
|
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: 30
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| No log | 1.0 | 3 | 0.9558 | 0.0 | 0.0 | 0.0 | 0.6 |
|
59 |
+
| No log | 2.0 | 6 | 0.8748 | 0.0 | 0.0 | 0.0 | 0.6 |
|
60 |
+
| No log | 3.0 | 9 | 0.8366 | 0.0 | 0.0 | 0.0 | 0.6 |
|
61 |
+
| No log | 4.0 | 12 | 0.8102 | 0.0 | 0.0 | 0.0 | 0.64 |
|
62 |
+
| No log | 5.0 | 15 | 0.7694 | 0.0 | 0.0 | 0.0 | 0.72 |
|
63 |
+
| No log | 6.0 | 18 | 0.7263 | 0.0 | 0.0 | 0.0 | 0.8 |
|
64 |
+
| No log | 7.0 | 21 | 0.6940 | 0.0 | 0.0 | 0.0 | 0.8 |
|
65 |
+
| No log | 8.0 | 24 | 0.6724 | 0.0 | 0.0 | 0.0 | 0.8 |
|
66 |
+
| No log | 9.0 | 27 | 0.6496 | 0.0 | 0.0 | 0.0 | 0.8 |
|
67 |
+
| No log | 10.0 | 30 | 0.6273 | 0.0 | 0.0 | 0.0 | 0.8 |
|
68 |
+
| No log | 11.0 | 33 | 0.5984 | 0.0 | 0.0 | 0.0 | 0.8 |
|
69 |
+
| No log | 12.0 | 36 | 0.5507 | 0.0 | 0.0 | 0.0 | 0.8 |
|
70 |
+
| No log | 13.0 | 39 | 0.5058 | 0.0 | 0.0 | 0.0 | 0.8 |
|
71 |
+
| No log | 14.0 | 42 | 0.4559 | 0.0 | 0.0 | 0.0 | 0.8 |
|
72 |
+
| No log | 15.0 | 45 | 0.4186 | 0.0 | 0.0 | 0.0 | 0.8 |
|
73 |
+
| No log | 16.0 | 48 | 0.3856 | 0.0 | 0.0 | 0.0 | 0.8 |
|
74 |
+
| No log | 17.0 | 51 | 0.3571 | 0.0 | 0.0 | 0.0 | 0.8 |
|
75 |
+
| No log | 18.0 | 54 | 0.3301 | 0.0 | 0.0 | 0.0 | 0.8 |
|
76 |
+
| No log | 19.0 | 57 | 0.3078 | 0.1111 | 0.2 | 0.1429 | 0.84 |
|
77 |
+
| No log | 20.0 | 60 | 0.2903 | 0.1111 | 0.2 | 0.1429 | 0.84 |
|
78 |
+
| No log | 21.0 | 63 | 0.2776 | 0.1111 | 0.2 | 0.1429 | 0.84 |
|
79 |
+
| No log | 22.0 | 66 | 0.2673 | 0.1111 | 0.2 | 0.1429 | 0.84 |
|
80 |
+
| No log | 23.0 | 69 | 0.2601 | 0.25 | 0.4 | 0.3077 | 0.88 |
|
81 |
+
| No log | 24.0 | 72 | 0.2560 | 0.25 | 0.4 | 0.3077 | 0.88 |
|
82 |
+
| No log | 25.0 | 75 | 0.2534 | 0.25 | 0.4 | 0.3077 | 0.88 |
|
83 |
+
| No log | 26.0 | 78 | 0.2512 | 0.25 | 0.4 | 0.3077 | 0.88 |
|
84 |
+
| No log | 27.0 | 81 | 0.2496 | 0.25 | 0.4 | 0.3077 | 0.88 |
|
85 |
+
| No log | 28.0 | 84 | 0.2491 | 0.25 | 0.4 | 0.3077 | 0.88 |
|
86 |
+
| No log | 29.0 | 87 | 0.2487 | 0.25 | 0.4 | 0.3077 | 0.88 |
|
87 |
+
| No log | 30.0 | 90 | 0.2486 | 0.25 | 0.4 | 0.3077 | 0.88 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
|
89 |
|
90 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 265473092
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1965bd530445936353e30bf995e2003cd0be84197b860edeeca5e4fd8ae3ff0a
|
3 |
size 265473092
|
runs/Feb29_08-28-58_9879f2213cb5/events.out.tfevents.1709195380.9879f2213cb5.492.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f22bd1008bb0c98406bff8c06c1d791242b109bf430c1e9d5c2a97493a491c7
|
3 |
+
size 18878
|
runs/Feb29_08-28-58_9879f2213cb5/events.out.tfevents.1709195506.9879f2213cb5.492.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9debc6c0ad63269abf9b9f8cb26a9a51e242dac0eb1dde8a000c63ddd1f7f4c7
|
3 |
+
size 551
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:100835038edb5c384517407c329de0c5f2970d51f7d24306ddc7c07b955d701e
|
3 |
size 4920
|