Hugging Face's logo

Hemg
/
EMOTION-AI-distilbert

Text Classification
Transformers
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Community
Hemg commited on
Commit
a17c04d
·
verified ·
1 Parent(s): fe198d3

Model save

Browse files
Files changed (2) hide show
  1. README.md +94 -26
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 5.0211
22
- - Accuracy: 0.4869
23
 
24
  ## Model description
25
 
@@ -38,37 +38,105 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 0.0003
42
- - train_batch_size: 16
43
- - eval_batch_size: 16
44
  - seed: 42
45
- - gradient_accumulation_steps: 4
46
- - total_train_batch_size: 64
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
- - num_epochs: 16
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
- |:-------------:|:-------:|:----:|:---------------:|:--------:|
56
- | 7.5485 | 1.0 | 543 | 1.6321 | 0.5238 |
57
- | 6.1296 | 2.0 | 1086 | 1.5759 | 0.5296 |
58
- | 5.2621 | 3.0 | 1629 | 1.6632 | 0.5160 |
59
- | 4.3838 | 4.0 | 2172 | 1.7630 | 0.5038 |
60
- | 3.4834 | 5.0 | 2715 | 1.8903 | 0.5045 |
61
- | 2.694 | 6.0 | 3258 | 2.2116 | 0.4832 |
62
- | 2.0074 | 7.0 | 3801 | 2.4715 | 0.4901 |
63
- | 1.5504 | 8.0 | 4344 | 2.6315 | 0.4861 |
64
- | 1.1669 | 9.0 | 4887 | 3.0050 | 0.4876 |
65
- | 0.8918 | 10.0 | 5430 | 3.2037 | 0.4839 |
66
- | 0.6969 | 11.0 | 5973 | 3.5520 | 0.4809 |
67
- | 0.3859 | 12.0 | 6516 | 3.8879 | 0.4787 |
68
- | 0.2745 | 13.0 | 7059 | 4.3047 | 0.4845 |
69
- | 0.2037 | 14.0 | 7602 | 4.6410 | 0.4783 |
70
- | 0.1493 | 15.0 | 8145 | 4.9212 | 0.4828 |
71
- | 0.1028 | 15.9710 | 8672 | 5.0211 | 0.4869 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.5708
22
+ - Accuracy: 0.5472
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 64
43
+ - eval_batch_size: 64
44
  - seed: 42
 
 
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 8
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
54
+ | No log | 0.0921 | 50 | 2.7042 | 0.2852 |
55
+ | No log | 0.1842 | 100 | 2.3795 | 0.3869 |
56
+ | No log | 0.2762 | 150 | 2.1335 | 0.4270 |
57
+ | No log | 0.3683 | 200 | 1.9727 | 0.4797 |
58
+ | No log | 0.4604 | 250 | 1.8782 | 0.4930 |
59
+ | No log | 0.5525 | 300 | 1.7995 | 0.5084 |
60
+ | No log | 0.6446 | 350 | 1.7474 | 0.5141 |
61
+ | No log | 0.7366 | 400 | 1.6828 | 0.5299 |
62
+ | No log | 0.8287 | 450 | 1.6576 | 0.5294 |
63
+ | 2.0439 | 0.9208 | 500 | 1.6171 | 0.5386 |
64
+ | 2.0439 | 1.0129 | 550 | 1.5935 | 0.5400 |
65
+ | 2.0439 | 1.1050 | 600 | 1.5734 | 0.5457 |
66
+ | 2.0439 | 1.1971 | 650 | 1.5577 | 0.5462 |
67
+ | 2.0439 | 1.2891 | 700 | 1.5455 | 0.5501 |
68
+ | 2.0439 | 1.3812 | 750 | 1.5363 | 0.5530 |
69
+ | 2.0439 | 1.4733 | 800 | 1.5354 | 0.5492 |
70
+ | 2.0439 | 1.5654 | 850 | 1.5158 | 0.5598 |
71
+ | 2.0439 | 1.6575 | 900 | 1.5058 | 0.5557 |
72
+ | 2.0439 | 1.7495 | 950 | 1.5042 | 0.5602 |
73
+ | 1.4796 | 1.8416 | 1000 | 1.4805 | 0.5586 |
74
+ | 1.4796 | 1.9337 | 1050 | 1.4797 | 0.5578 |
75
+ | 1.4796 | 2.0258 | 1100 | 1.4653 | 0.5677 |
76
+ | 1.4796 | 2.1179 | 1150 | 1.4759 | 0.5568 |
77
+ | 1.4796 | 2.2099 | 1200 | 1.4795 | 0.5608 |
78
+ | 1.4796 | 2.3020 | 1250 | 1.4701 | 0.5637 |
79
+ | 1.4796 | 2.3941 | 1300 | 1.4747 | 0.5583 |
80
+ | 1.4796 | 2.4862 | 1350 | 1.4676 | 0.5616 |
81
+ | 1.4796 | 2.5783 | 1400 | 1.4581 | 0.5668 |
82
+ | 1.4796 | 2.6703 | 1450 | 1.4690 | 0.5617 |
83
+ | 1.3018 | 2.7624 | 1500 | 1.4636 | 0.5545 |
84
+ | 1.3018 | 2.8545 | 1550 | 1.4609 | 0.5629 |
85
+ | 1.3018 | 2.9466 | 1600 | 1.4603 | 0.5689 |
86
+ | 1.3018 | 3.0387 | 1650 | 1.4517 | 0.5606 |
87
+ | 1.3018 | 3.1308 | 1700 | 1.4566 | 0.5635 |
88
+ | 1.3018 | 3.2228 | 1750 | 1.4682 | 0.5613 |
89
+ | 1.3018 | 3.3149 | 1800 | 1.4630 | 0.5600 |
90
+ | 1.3018 | 3.4070 | 1850 | 1.4815 | 0.5538 |
91
+ | 1.3018 | 3.4991 | 1900 | 1.4760 | 0.5517 |
92
+ | 1.3018 | 3.5912 | 1950 | 1.4788 | 0.5534 |
93
+ | 1.1832 | 3.6832 | 2000 | 1.4667 | 0.5547 |
94
+ | 1.1832 | 3.7753 | 2050 | 1.4630 | 0.5597 |
95
+ | 1.1832 | 3.8674 | 2100 | 1.4639 | 0.5548 |
96
+ | 1.1832 | 3.9595 | 2150 | 1.4816 | 0.5457 |
97
+ | 1.1832 | 4.0516 | 2200 | 1.4760 | 0.5577 |
98
+ | 1.1832 | 4.1436 | 2250 | 1.4878 | 0.5586 |
99
+ | 1.1832 | 4.2357 | 2300 | 1.4848 | 0.5575 |
100
+ | 1.1832 | 4.3278 | 2350 | 1.4825 | 0.5578 |
101
+ | 1.1832 | 4.4199 | 2400 | 1.4881 | 0.5572 |
102
+ | 1.1832 | 4.5120 | 2450 | 1.4937 | 0.5584 |
103
+ | 1.0845 | 4.6041 | 2500 | 1.4925 | 0.5555 |
104
+ | 1.0845 | 4.6961 | 2550 | 1.4922 | 0.5534 |
105
+ | 1.0845 | 4.7882 | 2600 | 1.4882 | 0.5572 |
106
+ | 1.0845 | 4.8803 | 2650 | 1.4927 | 0.5555 |
107
+ | 1.0845 | 4.9724 | 2700 | 1.4975 | 0.5556 |
108
+ | 1.0845 | 5.0645 | 2750 | 1.5009 | 0.5568 |
109
+ | 1.0845 | 5.1565 | 2800 | 1.5140 | 0.5516 |
110
+ | 1.0845 | 5.2486 | 2850 | 1.5165 | 0.5517 |
111
+ | 1.0845 | 5.3407 | 2900 | 1.5266 | 0.5469 |
112
+ | 1.0845 | 5.4328 | 2950 | 1.5257 | 0.5503 |
113
+ | 0.9997 | 5.5249 | 3000 | 1.5204 | 0.5485 |
114
+ | 0.9997 | 5.6169 | 3050 | 1.5264 | 0.5449 |
115
+ | 0.9997 | 5.7090 | 3100 | 1.5268 | 0.5456 |
116
+ | 0.9997 | 5.8011 | 3150 | 1.5239 | 0.5545 |
117
+ | 0.9997 | 5.8932 | 3200 | 1.5351 | 0.5575 |
118
+ | 0.9997 | 5.9853 | 3250 | 1.5354 | 0.5548 |
119
+ | 0.9997 | 6.0773 | 3300 | 1.5342 | 0.5475 |
120
+ | 0.9997 | 6.1694 | 3350 | 1.5452 | 0.5469 |
121
+ | 0.9997 | 6.2615 | 3400 | 1.5440 | 0.5504 |
122
+ | 0.9997 | 6.3536 | 3450 | 1.5485 | 0.5499 |
123
+ | 0.9138 | 6.4457 | 3500 | 1.5504 | 0.5494 |
124
+ | 0.9138 | 6.5378 | 3550 | 1.5522 | 0.5511 |
125
+ | 0.9138 | 6.6298 | 3600 | 1.5518 | 0.5468 |
126
+ | 0.9138 | 6.7219 | 3650 | 1.5490 | 0.5473 |
127
+ | 0.9138 | 6.8140 | 3700 | 1.5536 | 0.5532 |
128
+ | 0.9138 | 6.9061 | 3750 | 1.5528 | 0.5502 |
129
+ | 0.9138 | 6.9982 | 3800 | 1.5557 | 0.5471 |
130
+ | 0.9138 | 7.0902 | 3850 | 1.5583 | 0.5466 |
131
+ | 0.9138 | 7.1823 | 3900 | 1.5612 | 0.5486 |
132
+ | 0.9138 | 7.2744 | 3950 | 1.5654 | 0.5471 |
133
+ | 0.8831 | 7.3665 | 4000 | 1.5674 | 0.5472 |
134
+ | 0.8831 | 7.4586 | 4050 | 1.5698 | 0.5492 |
135
+ | 0.8831 | 7.5506 | 4100 | 1.5703 | 0.5484 |
136
+ | 0.8831 | 7.6427 | 4150 | 1.5736 | 0.5465 |
137
+ | 0.8831 | 7.7348 | 4200 | 1.5733 | 0.5455 |
138
+ | 0.8831 | 7.8269 | 4250 | 1.5718 | 0.5471 |
139
+ | 0.8831 | 7.9190 | 4300 | 1.5708 | 0.5472 |
140
 
141
 
142
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9ae93a94f3c999bc354f01ccedacdac653babefdfd9f7f1fa26afa6f16b1c53
3
  size 267912544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e33a59c4099a6ee60331177df3216f20fbd4783819793cd7bb662cfab2f58c5c
3
  size 267912544