Hugging Face's logo

gokuls
/
model_v1_complete_training_wt_init_48_tiny_emb_comp

Fill-Mask
Transformers
PyTorch
TensorBoard
hybridbert
Generated from Trainer
Model card Files
xet
 Metrics Community
gokuls commited on
Commit
de51cf9
·
1 Parent(s): fd222ae

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - accuracy
6
+ model-index:
7
+ - name: model_v1_complete_training_wt_init_48_tiny_emb_comp
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # model_v1_complete_training_wt_init_48_tiny_emb_comp
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 3.7768
19
+ - Accuracy: 0.3787
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 64
40
+ - eval_batch_size: 64
41
+ - seed: 10
42
+ - distributed_type: multi-GPU
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 10000
46
+ - num_epochs: 50
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:-------:|:---------------:|:--------:|
52
+ | 6.0945 | 0.33 | 30000 | 6.0802 | 0.1412 |
53
+ | 5.2818 | 0.66 | 60000 | 5.2151 | 0.2395 |
54
+ | 4.8774 | 0.98 | 90000 | 4.8105 | 0.2760 |
55
+ | 4.7096 | 1.31 | 120000 | 4.6474 | 0.2894 |
56
+ | 4.6109 | 1.64 | 150000 | 4.5460 | 0.2985 |
57
+ | 4.5415 | 1.97 | 180000 | 4.4761 | 0.3050 |
58
+ | 4.4884 | 2.29 | 210000 | 4.4231 | 0.3101 |
59
+ | 4.446 | 2.62 | 240000 | 4.3791 | 0.3144 |
60
+ | 4.4072 | 2.95 | 270000 | 4.3416 | 0.3179 |
61
+ | 4.3755 | 3.28 | 300000 | 4.3064 | 0.3218 |
62
+ | 4.3455 | 3.6 | 330000 | 4.2724 | 0.3254 |
63
+ | 4.3172 | 3.93 | 360000 | 4.2410 | 0.3291 |
64
+ | 4.2921 | 4.26 | 390000 | 4.2130 | 0.3324 |
65
+ | 4.2718 | 4.59 | 420000 | 4.1892 | 0.3348 |
66
+ | 4.2485 | 4.92 | 450000 | 4.1688 | 0.3370 |
67
+ | 4.2267 | 5.24 | 480000 | 4.1500 | 0.3394 |
68
+ | 4.2081 | 5.57 | 510000 | 4.1314 | 0.3412 |
69
+ | 4.198 | 5.9 | 540000 | 4.1117 | 0.3435 |
70
+ | 4.1666 | 6.23 | 570000 | 4.0949 | 0.3451 |
71
+ | 4.1498 | 6.55 | 600000 | 4.0786 | 0.3464 |
72
+ | 4.1104 | 6.88 | 630000 | 4.0465 | 0.3499 |
73
+ | 4.0715 | 7.21 | 660000 | 4.0078 | 0.3539 |
74
+ | 4.0298 | 7.54 | 690000 | 3.9722 | 0.3576 |
75
+ | 4.0085 | 7.87 | 720000 | 3.9520 | 0.3599 |
76
+ | 3.99 | 8.19 | 750000 | 3.9390 | 0.3615 |
77
+ | 3.9799 | 8.52 | 780000 | 3.9272 | 0.3627 |
78
+ | 3.9766 | 8.85 | 810000 | 3.9138 | 0.3641 |
79
+ | 3.9534 | 9.18 | 840000 | 3.9034 | 0.3651 |
80
+ | 3.9521 | 9.5 | 870000 | 3.8918 | 0.3662 |
81
+ | 3.9314 | 9.83 | 900000 | 3.8817 | 0.3670 |
82
+ | 3.9096 | 10.16 | 930000 | 3.8709 | 0.3683 |
83
+ | 3.904 | 10.49 | 960000 | 3.8604 | 0.3695 |
84
+ | 3.8965 | 10.81 | 990000 | 3.8509 | 0.3704 |
85
+ | 3.8788 | 11.14 | 1020000 | 3.8406 | 0.3717 |
86
+ | 3.8748 | 11.47 | 1050000 | 3.8329 | 0.3728 |
87
+ | 3.8638 | 11.8 | 1080000 | 3.8250 | 0.3733 |
88
+ | 3.8586 | 12.13 | 1110000 | 3.8203 | 0.3739 |
89
+ | 3.8495 | 12.45 | 1140000 | 3.8146 | 0.3746 |
90
+ | 3.8469 | 12.78 | 1170000 | 3.8054 | 0.3753 |
91
+ | 3.8352 | 13.11 | 1200000 | 3.8007 | 0.3761 |
92
+ | 3.8339 | 13.44 | 1230000 | 3.7949 | 0.3766 |
93
+ | 3.8215 | 13.76 | 1260000 | 3.7894 | 0.3772 |
94
+ | 3.8175 | 14.09 | 1290000 | 3.7835 | 0.3779 |
95
+ | 3.817 | 14.42 | 1320000 | 3.7768 | 0.3787 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.30.2
101
+ - Pytorch 1.14.0a0+410ce96
102
+ - Datasets 2.13.1
103
+ - Tokenizers 0.13.3