Hugging Face's logo

CLMBR
/
old-full-lstm-2

Transformers
PyTorch
rnn
Generated from Trainer
Inference Endpoints
Model card Files Community
abhinavp commited on
Commit
7cb8e85
•
1 Parent(s): 14eea06

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: full-lstm-2
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
+ # full-lstm-2
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: 3.9716
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: 2
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
+ | 4.7917 | 0.03 | 76319 | 4.7567 |
48
+ | 4.5064 | 1.03 | 152638 | 4.4756 |
49
+ | 4.3631 | 0.03 | 228957 | 4.3407 |
50
+ | 4.2711 | 1.03 | 305276 | 4.2578 |
51
+ | 4.2077 | 0.03 | 381595 | 4.2014 |
52
+ | 4.157 | 1.03 | 457914 | 4.1600 |
53
+ | 4.1224 | 0.03 | 534233 | 4.1296 |
54
+ | 4.0928 | 0.03 | 610552 | 4.1052 |
55
+ | 4.0627 | 1.03 | 686871 | 4.0866 |
56
+ | 4.0409 | 0.03 | 763190 | 4.0706 |
57
+ | 4.0209 | 1.03 | 839509 | 4.0576 |
58
+ | 4.0041 | 0.03 | 915828 | 4.0470 |
59
+ | 3.9838 | 0.03 | 992147 | 4.0377 |
60
+ | 3.9707 | 0.03 | 1068467 | 4.0283 |
61
+ | 3.96 | 1.03 | 1144787 | 4.0217 |
62
+ | 3.9578 | 0.03 | 1221107 | 4.0144 |
63
+ | 3.9374 | 1.03 | 1297427 | 4.0091 |
64
+ | 3.9288 | 0.03 | 1373747 | 4.0045 |
65
+ | 3.9178 | 1.03 | 1450067 | 4.0008 |
66
+ | 3.9111 | 0.03 | 1526387 | 3.9972 |
67
+ | 3.9123 | 1.03 | 1602707 | 3.9945 |
68
+ | 3.9072 | 0.03 | 1679027 | 3.9921 |
69
+ | 3.9062 | 1.03 | 1755347 | 3.9889 |
70
+ | 3.9022 | 0.03 | 1831667 | 3.9870 |
71
+ | 3.8944 | 0.03 | 1907987 | 3.9850 |
72
+ | 3.8882 | 1.03 | 1984307 | 3.9836 |
73
+ | 3.883 | 0.03 | 2060627 | 3.9817 |
74
+ | 3.8755 | 1.03 | 2136947 | 3.9808 |
75
+ | 3.8735 | 0.03 | 2213267 | 3.9796 |
76
+ | 3.8684 | 1.03 | 2289587 | 3.9782 |
77
+ | 3.86 | 0.03 | 2365907 | 3.9773 |
78
+ | 3.8611 | 1.03 | 2442227 | 3.9764 |
79
+ | 3.8488 | 0.03 | 2518547 | 3.9757 |
80
+ | 3.8468 | 1.03 | 2594867 | 3.9747 |
81
+ | 3.8413 | 0.03 | 2671187 | 3.9741 |
82
+ | 3.8399 | 0.03 | 2747507 | 3.9734 |
83
+ | 3.845 | 1.03 | 2823827 | 3.9730 |
84
+ | 3.8433 | 0.03 | 2900147 | 3.9724 |
85
+ | 3.8469 | 1.03 | 2976467 | 3.9720 |
86
+ | 3.8461 | 0.02 | 3052726 | 3.9716 |
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