oMateos2020 commited on
Commit
88b16d5
1 Parent(s): 3887733

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +65 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - cnn_dailymail
6
+ model-index:
7
+ - name: pegasus-newsroom-cnn_full-adafactor-bs6
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
+ # pegasus-newsroom-cnn_full-adafactor-bs6
15
+
16
+ This model is a fine-tuned version of [google/pegasus-newsroom](https://huggingface.co/google/pegasus-newsroom) on the cnn_dailymail dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - eval_loss: 3.4275
19
+ - eval_rouge1: 33.0969
20
+ - eval_rouge2: 13.6577
21
+ - eval_rougeL: 23.9839
22
+ - eval_rougeLsum: 30.6005
23
+ - eval_gen_len: 47.1888
24
+ - eval_runtime: 927.662
25
+ - eval_samples_per_second: 2.695
26
+ - eval_steps_per_second: 0.45
27
+ - epoch: 0.6
28
+ - step: 1794
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 0.00016
48
+ - train_batch_size: 6
49
+ - eval_batch_size: 6
50
+ - seed: 42
51
+ - gradient_accumulation_steps: 16
52
+ - total_train_batch_size: 96
53
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
+ - lr_scheduler_type: linear
55
+ - lr_scheduler_warmup_steps: 598
56
+ - num_epochs: 1
57
+ - mixed_precision_training: Native AMP
58
+ - label_smoothing_factor: 0.1
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.20.1
63
+ - Pytorch 1.12.0+cu113
64
+ - Datasets 2.4.0
65
+ - Tokenizers 0.12.1