domenicrosati commited on
Commit
4d17b48
1 Parent(s): 91df404

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +60 -0
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - paraphrasing
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: t5-paraphrase-paws-msrp-opinosis-finetuned-parasci
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # t5-paraphrase-paws-msrp-opinosis-finetuned-parasci
15
+
16
+ This model is a fine-tuned version of [ceshine/t5-paraphrase-paws-msrp-opinosis](https://huggingface.co/ceshine/t5-paraphrase-paws-msrp-opinosis) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - eval_loss: 2.4850
19
+ - eval_rouge1: 30.3118
20
+ - eval_rouge2: 13.2806
21
+ - eval_rougeL: 27.7503
22
+ - eval_rougeLsum: 27.7465
23
+ - eval_runtime: 83.1986
24
+ - eval_samples_per_second: 58.823
25
+ - eval_steps_per_second: 1.839
26
+ - epoch: 1.98
27
+ - step: 21000
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 5.6e-05
47
+ - train_batch_size: 32
48
+ - eval_batch_size: 32
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 2
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.18.0
58
+ - Pytorch 1.11.0
59
+ - Datasets 2.1.0
60
+ - Tokenizers 0.12.1