Hugging Face's logo

ashhadahsan
/
amazon-theme-bert-base-finetuned-finetuned

Text Classification
Transformers
TensorFlow
TensorBoard
bert
generated_from_keras_callback
Inference Endpoints
Model card Files Metrics Community
ashhadahsan commited on
Commit
0e42017
•
1 Parent(s): 63d6d9e

Training in progress epoch 0

Browse files
Files changed (7) hide show
  1. README.md +6 -54
  2. logsa/train/events.out.tfevents.1697913365.5521192874ed.32.0.v2 +3 -0
  3. logsa/train/events.out.tfevents.1697913514.5521192874ed.32.2.v2 +3 -0
  4. logsa/train/events.out.tfevents.1697913532.5521192874ed.32.3.v2 +3 -0
  5. logsa/validation/events.out.tfevents.1697913439.5521192874ed.32.1.v2 +3 -0
  6. logsa/validation/events.out.tfevents.1697913598.5521192874ed.32.4.v2 +3 -0
  7. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.0040
19
- - Train Accuracy: 1.0
20
- - Validation Loss: 1.9138
21
- - Validation Accuracy: 0.6772
22
- - Epoch: 48
23
 
24
  ## Model description
25
 
@@ -45,55 +45,7 @@ The following hyperparameters were used during training:
45
 
46
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
47
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
48
- | 2.2722 | 0.2334 | 2.0907 | 0.2434 | 0 |
49
- | 2.0390 | 0.3753 | 1.8691 | 0.4550 | 1 |
50
- | 1.6587 | 0.5358 | 1.6368 | 0.4921 | 2 |
51
- | 1.2235 | 0.6883 | 1.4491 | 0.5344 | 3 |
52
- | 0.9119 | 0.7666 | 1.4582 | 0.5608 | 4 |
53
- | 0.6501 | 0.8581 | 1.3935 | 0.6190 | 5 |
54
- | 0.4793 | 0.9058 | 1.3104 | 0.6296 | 6 |
55
- | 0.3347 | 0.9403 | 1.3262 | 0.6825 | 7 |
56
- | 0.2408 | 0.9655 | 1.3806 | 0.6508 | 8 |
57
- | 0.1758 | 0.9801 | 1.3462 | 0.6402 | 9 |
58
- | 0.1250 | 0.9881 | 1.3498 | 0.6772 | 10 |
59
- | 0.0946 | 0.9920 | 1.4151 | 0.6614 | 11 |
60
- | 0.0763 | 0.9947 | 1.4046 | 0.6720 | 12 |
61
- | 0.0602 | 0.9973 | 1.4462 | 0.6667 | 13 |
62
- | 0.0506 | 0.9973 | 1.4472 | 0.6720 | 14 |
63
- | 0.0433 | 0.9987 | 1.4685 | 0.6772 | 15 |
64
- | 0.0367 | 1.0 | 1.5076 | 0.6772 | 16 |
65
- | 0.0319 | 1.0 | 1.5152 | 0.6825 | 17 |
66
- | 0.0281 | 1.0 | 1.5374 | 0.6720 | 18 |
67
- | 0.0248 | 1.0 | 1.5787 | 0.6825 | 19 |
68
- | 0.0216 | 1.0 | 1.5841 | 0.6772 | 20 |
69
- | 0.0204 | 1.0 | 1.6177 | 0.6667 | 21 |
70
- | 0.0175 | 1.0 | 1.6204 | 0.6878 | 22 |
71
- | 0.0162 | 1.0 | 1.6467 | 0.6772 | 23 |
72
- | 0.0150 | 1.0 | 1.6459 | 0.6772 | 24 |
73
- | 0.0136 | 1.0 | 1.6745 | 0.6667 | 25 |
74
- | 0.0124 | 1.0 | 1.6798 | 0.6878 | 26 |
75
- | 0.0119 | 1.0 | 1.7042 | 0.6825 | 27 |
76
- | 0.0108 | 1.0 | 1.7146 | 0.6772 | 28 |
77
- | 0.0104 | 1.0 | 1.7182 | 0.6772 | 29 |
78
- | 0.0095 | 1.0 | 1.7197 | 0.6878 | 30 |
79
- | 0.0089 | 1.0 | 1.7385 | 0.6825 | 31 |
80
- | 0.0083 | 1.0 | 1.7531 | 0.6878 | 32 |
81
- | 0.0079 | 1.0 | 1.7710 | 0.6772 | 33 |
82
- | 0.0073 | 1.0 | 1.7713 | 0.6772 | 34 |
83
- | 0.0071 | 1.0 | 1.7842 | 0.6772 | 35 |
84
- | 0.0068 | 1.0 | 1.7992 | 0.6825 | 36 |
85
- | 0.0064 | 1.0 | 1.8017 | 0.6772 | 37 |
86
- | 0.0061 | 1.0 | 1.8188 | 0.6772 | 38 |
87
- | 0.0057 | 1.0 | 1.8288 | 0.6772 | 39 |
88
- | 0.0055 | 1.0 | 1.8444 | 0.6825 | 40 |
89
- | 0.0052 | 1.0 | 1.8611 | 0.6772 | 41 |
90
- | 0.0050 | 1.0 | 1.8592 | 0.6825 | 42 |
91
- | 0.0048 | 1.0 | 1.8669 | 0.6772 | 43 |
92
- | 0.0046 | 1.0 | 1.8722 | 0.6825 | 44 |
93
- | 0.0044 | 1.0 | 1.8873 | 0.6825 | 45 |
94
- | 0.0042 | 1.0 | 1.8994 | 0.6825 | 46 |
95
- | 0.0041 | 1.0 | 1.9046 | 0.6825 | 47 |
96
- | 0.0040 | 1.0 | 1.9138 | 0.6772 | 48 |
97
 
98
 
99
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 1.9295
19
+ - Train Accuracy: 0.4297
20
+ - Validation Loss: 1.7895
21
+ - Validation Accuracy: 0.4656
22
+ - Epoch: 0
23
 
24
  ## Model description
25
 
 
45
 
46
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
47
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
48
+ | 1.9295 | 0.4297 | 1.7895 | 0.4656 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
 
50
 
51
  ### Framework versions
logsa/train/events.out.tfevents.1697913365.5521192874ed.32.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e677e3e8a19e3b57ff370d9d4b01999e1c6b545a1505915b0667ffb3c480d9
3
+ size 4190495
logsa/train/events.out.tfevents.1697913514.5521192874ed.32.2.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c82fb1876cb43e829eb5f659eb22e3687faf538ccd60f888bd14176a9559b073
3
+ size 78
logsa/train/events.out.tfevents.1697913532.5521192874ed.32.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9f3362792f2c656764ae40fa03018a2445f7745afee1c1ab88d72b0f6236753
3
+ size 4192106
logsa/validation/events.out.tfevents.1697913439.5521192874ed.32.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37cc9c18ae596fc614832f34bd3622daf54c8e264d187eaf0f6390af1379b258
3
+ size 392
logsa/validation/events.out.tfevents.1697913598.5521192874ed.32.4.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee6a10c531e14f9d69a2a2658d3ce8b8564ac524d47b1c5f2065c54545ed295
3
+ size 392
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88388c57692604a39edda61abd4015d3d722f45deb0f9e35ea38691302194e2e
3
  size 438260040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c1f9891e7b6350bc48c199e1fee4dec52e6834ecf4a7074fa50f62065faacb7
3
  size 438260040