Hugging Face's logo

CLMBR
/
full-lstm-2

Transformers
PyTorch
rnn
Generated from Trainer
Inference Endpoints
Model card Files Community
abhinavp commited on
Commit
f5d9cdc
•
1 Parent(s): 5e79065

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: full2-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
+ # full2-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: 3.9738
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
+ | 4.7958 | 0.03 | 76320 | 4.7656 |
48
+ | 4.5105 | 1.03 | 152640 | 4.4827 |
49
+ | 4.3654 | 0.03 | 228960 | 4.3482 |
50
+ | 4.2801 | 1.03 | 305280 | 4.2650 |
51
+ | 4.2161 | 0.03 | 381600 | 4.2080 |
52
+ | 4.1711 | 1.03 | 457920 | 4.1662 |
53
+ | 4.1373 | 0.03 | 534240 | 4.1357 |
54
+ | 4.106 | 1.03 | 610560 | 4.1113 |
55
+ | 4.0755 | 0.03 | 686880 | 4.0909 |
56
+ | 4.0519 | 1.03 | 763200 | 4.0743 |
57
+ | 4.0312 | 0.03 | 839520 | 4.0611 |
58
+ | 4.0136 | 1.03 | 915840 | 4.0505 |
59
+ | 4.0004 | 0.03 | 992160 | 4.0414 |
60
+ | 3.9837 | 1.03 | 1068480 | 4.0328 |
61
+ | 3.9692 | 0.03 | 1144800 | 4.0253 |
62
+ | 3.9547 | 1.03 | 1221120 | 4.0192 |
63
+ | 3.9407 | 0.03 | 1297440 | 4.0140 |
64
+ | 3.9307 | 1.03 | 1373760 | 4.0091 |
65
+ | 3.9213 | 0.03 | 1450080 | 4.0055 |
66
+ | 3.9184 | 1.03 | 1526400 | 4.0017 |
67
+ | 3.9134 | 0.03 | 1602720 | 3.9992 |
68
+ | 3.9108 | 1.03 | 1679040 | 3.9962 |
69
+ | 3.9086 | 0.03 | 1755360 | 3.9935 |
70
+ | 3.9036 | 1.03 | 1831680 | 3.9910 |
71
+ | 3.8942 | 0.03 | 1908000 | 3.9890 |
72
+ | 3.8892 | 1.03 | 1984320 | 3.9867 |
73
+ | 3.8825 | 0.03 | 2060640 | 3.9852 |
74
+ | 3.8768 | 1.03 | 2136960 | 3.9835 |
75
+ | 3.8758 | 0.03 | 2213280 | 3.9815 |
76
+ | 3.8693 | 1.03 | 2289600 | 3.9807 |
77
+ | 3.8621 | 0.03 | 2365920 | 3.9796 |
78
+ | 3.8589 | 0.03 | 2442240 | 3.9788 |
79
+ | 3.8513 | 0.03 | 2518560 | 3.9778 |
80
+ | 3.8487 | 1.03 | 2594880 | 3.9770 |
81
+ | 3.8424 | 0.03 | 2671200 | 3.9763 |
82
+ | 3.8467 | 1.03 | 2747520 | 3.9756 |
83
+ | 3.8475 | 0.03 | 2823840 | 3.9750 |
84
+ | 3.8449 | 1.03 | 2900160 | 3.9745 |
85
+ | 3.8521 | 0.03 | 2976480 | 3.9741 |
86
+ | 3.8498 | 0.02 | 3052726 | 3.9738 |
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