Hugging Face's logo

CLMBR
/
old-rel-cl-lstm-1

Transformers
PyTorch
rnn
Generated from Trainer
Model card Files
xet
Community
abhinavp commited on
Commit
f0e9fe5
·
verified ·
1 Parent(s): e0efd8b

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: rel-cl-lstm-1
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
+ # rel-cl-lstm-1
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: 3.9795
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: 1
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
+ | 4.8102 | 0.03 | 76319 | 4.7706 |
48
+ | 4.5218 | 0.03 | 152638 | 4.4884 |
49
+ | 4.3799 | 1.03 | 228957 | 4.3542 |
50
+ | 4.2923 | 0.03 | 305276 | 4.2707 |
51
+ | 4.2284 | 1.03 | 381595 | 4.2133 |
52
+ | 4.1771 | 0.03 | 457914 | 4.1727 |
53
+ | 4.1395 | 1.03 | 534233 | 4.1414 |
54
+ | 4.1119 | 0.03 | 610552 | 4.1165 |
55
+ | 4.0787 | 1.03 | 686871 | 4.0975 |
56
+ | 4.0592 | 0.03 | 763190 | 4.0814 |
57
+ | 4.0379 | 1.03 | 839509 | 4.0676 |
58
+ | 4.0211 | 0.03 | 915828 | 4.0562 |
59
+ | 4.0007 | 1.03 | 992147 | 4.0479 |
60
+ | 3.9787 | 0.03 | 1068467 | 4.0382 |
61
+ | 3.9644 | 1.03 | 1144787 | 4.0305 |
62
+ | 3.9696 | 0.03 | 1221107 | 4.0242 |
63
+ | 3.9515 | 1.03 | 1297427 | 4.0186 |
64
+ | 3.9419 | 0.03 | 1373747 | 4.0144 |
65
+ | 3.9319 | 1.03 | 1450067 | 4.0105 |
66
+ | 3.9296 | 0.03 | 1526387 | 4.0071 |
67
+ | 3.9249 | 1.03 | 1602707 | 4.0044 |
68
+ | 3.9193 | 0.03 | 1679027 | 4.0014 |
69
+ | 3.9168 | 1.03 | 1755347 | 3.9991 |
70
+ | 3.9074 | 0.03 | 1831667 | 3.9962 |
71
+ | 3.898 | 1.03 | 1907987 | 3.9941 |
72
+ | 3.8886 | 0.03 | 1984307 | 3.9919 |
73
+ | 3.8847 | 1.03 | 2060627 | 3.9900 |
74
+ | 3.8811 | 0.03 | 2136947 | 3.9883 |
75
+ | 3.8767 | 1.03 | 2213267 | 3.9873 |
76
+ | 3.8694 | 0.03 | 2289587 | 3.9861 |
77
+ | 3.8694 | 1.03 | 2365907 | 3.9850 |
78
+ | 3.8694 | 0.03 | 2442227 | 3.9840 |
79
+ | 3.8629 | 1.03 | 2518547 | 3.9831 |
80
+ | 3.8586 | 0.03 | 2594867 | 3.9823 |
81
+ | 3.8527 | 1.03 | 2671187 | 3.9817 |
82
+ | 3.8568 | 0.03 | 2747507 | 3.9812 |
83
+ | 3.855 | 0.03 | 2823827 | 3.9806 |
84
+ | 3.8566 | 1.03 | 2900147 | 3.9801 |
85
+ | 3.8583 | 0.03 | 2976467 | 3.9799 |
86
+ | 3.8537 | 1.02 | 3052726 | 3.9795 |
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