kiddothe2b commited on
Commit
6e3e9a9
1 Parent(s): 86e7186

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +80 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: roberta-base-cased
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
+ # roberta-base-cased
13
+
14
+ This model was trained from scratch on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 0.7516
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: 0.0001
36
+ - train_batch_size: 32
37
+ - eval_batch_size: 32
38
+ - seed: 42
39
+ - distributed_type: tpu
40
+ - num_devices: 8
41
+ - gradient_accumulation_steps: 2
42
+ - total_train_batch_size: 512
43
+ - total_eval_batch_size: 256
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.05
47
+ - training_steps: 1000000
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:-------:|:---------------:|
53
+ | 1.0389 | 0.05 | 50000 | 0.9802 |
54
+ | 0.9685 | 0.1 | 100000 | 0.9021 |
55
+ | 0.9337 | 0.15 | 150000 | 0.8752 |
56
+ | 0.9106 | 0.2 | 200000 | 0.8558 |
57
+ | 0.8981 | 0.25 | 250000 | 0.8512 |
58
+ | 0.8813 | 1.03 | 300000 | 0.8203 |
59
+ | 0.8899 | 1.08 | 350000 | 0.8286 |
60
+ | 0.8581 | 1.13 | 400000 | 0.8148 |
61
+ | 0.856 | 1.18 | 450000 | 0.8141 |
62
+ | 0.8527 | 1.23 | 500000 | 0.8034 |
63
+ | 0.8345 | 2.02 | 550000 | 0.7763 |
64
+ | 0.8342 | 2.07 | 600000 | 0.7862 |
65
+ | 0.8147 | 2.12 | 650000 | 0.7842 |
66
+ | 0.8369 | 2.17 | 700000 | 0.7766 |
67
+ | 0.814 | 2.22 | 750000 | 0.7737 |
68
+ | 0.8046 | 2.27 | 800000 | 0.7692 |
69
+ | 0.7941 | 3.05 | 850000 | 0.7538 |
70
+ | 0.7956 | 3.1 | 900000 | 0.7562 |
71
+ | 0.8068 | 3.15 | 950000 | 0.7512 |
72
+ | 0.8066 | 3.2 | 1000000 | 0.7516 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.20.0
78
+ - Pytorch 1.12.0+cu102
79
+ - Datasets 2.6.1
80
+ - Tokenizers 0.12.0