Hugging Face's logo

CLMBR
/
superlative-quantifier-lstm-3

Transformers
PyTorch
rnn
Generated from Trainer
Inference Endpoints
Model card Files Community
abhinavp commited on
Commit
a39b2f0
•
1 Parent(s): bc3bde9

Model save

Browse files
Files changed (1) hide show
  1. README.md +94 -0
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: superlative-quantifier-lstm-3
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # superlative-quantifier-lstm-3
13
+
14
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 3.9893
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 32
37
+ - eval_batch_size: 32
38
+ - seed: 3
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - training_steps: 3052726
42
+
43
+ ### Training results
44
+
45
+ | Training Loss | Epoch | Step | Validation Loss |
46
+ |:-------------:|:-----:|:-------:|:---------------:|
47
+ | 4.7985 | 0.03 | 76320 | 4.7866 |
48
+ | 4.5144 | 1.03 | 152640 | 4.5020 |
49
+ | 4.3706 | 0.03 | 228960 | 4.3653 |
50
+ | 4.2853 | 1.03 | 305280 | 4.2807 |
51
+ | 4.2215 | 2.03 | 381600 | 4.2234 |
52
+ | 4.1723 | 0.03 | 457920 | 4.1822 |
53
+ | 4.1396 | 1.03 | 534240 | 4.1511 |
54
+ | 4.1084 | 0.03 | 610560 | 4.1267 |
55
+ | 4.0794 | 1.03 | 686880 | 4.1064 |
56
+ | 4.0535 | 0.03 | 763200 | 4.0905 |
57
+ | 4.0315 | 1.03 | 839520 | 4.0768 |
58
+ | 4.0098 | 0.03 | 915840 | 4.0656 |
59
+ | 4.0005 | 1.03 | 992160 | 4.0558 |
60
+ | 3.9838 | 2.03 | 1068480 | 4.0484 |
61
+ | 3.9698 | 0.03 | 1144800 | 4.0409 |
62
+ | 3.9498 | 1.03 | 1221120 | 4.0346 |
63
+ | 3.9379 | 2.03 | 1297440 | 4.0304 |
64
+ | 3.9296 | 0.03 | 1373760 | 4.0261 |
65
+ | 3.9193 | 1.03 | 1450080 | 4.0215 |
66
+ | 3.9159 | 0.03 | 1526400 | 4.0179 |
67
+ | 3.9123 | 1.03 | 1602720 | 4.0143 |
68
+ | 3.9072 | 0.03 | 1679040 | 4.0113 |
69
+ | 3.906 | 1.03 | 1755360 | 4.0091 |
70
+ | 3.9027 | 0.03 | 1831680 | 4.0067 |
71
+ | 3.8946 | 1.03 | 1908000 | 4.0048 |
72
+ | 3.8892 | 0.03 | 1984320 | 4.0029 |
73
+ | 3.8824 | 0.03 | 2060640 | 4.0012 |
74
+ | 3.8758 | 0.03 | 2136960 | 3.9999 |
75
+ | 3.8751 | 0.03 | 2213280 | 3.9983 |
76
+ | 3.869 | 0.03 | 2289600 | 3.9967 |
77
+ | 3.8615 | 1.03 | 2365920 | 3.9956 |
78
+ | 3.8512 | 2.03 | 2442240 | 3.9942 |
79
+ | 3.8463 | 0.03 | 2518560 | 3.9931 |
80
+ | 3.8445 | 1.03 | 2594880 | 3.9924 |
81
+ | 3.8404 | 2.03 | 2671200 | 3.9919 |
82
+ | 3.8438 | 0.03 | 2747520 | 3.9912 |
83
+ | 3.845 | 0.03 | 2823840 | 3.9907 |
84
+ | 3.8445 | 0.03 | 2900160 | 3.9900 |
85
+ | 3.8503 | 0.03 | 2976480 | 3.9897 |
86
+ | 3.8497 | 1.02 | 3052726 | 3.9893 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - Transformers 4.33.3
92
+ - Pytorch 2.0.1
93
+ - Datasets 2.12.0
94
+ - Tokenizers 0.13.3