Commit
•
a8b9b6b
1
Parent(s):
d8fb5ba
Add evaluation results on the 3.0.0 config and test split of cnn_dailymail
Browse filesBeep boop, I am a bot from Hugging Face's automatic model evaluator 👋!\
Your model has been evaluated on the 3.0.0 config and test split of the [cnn_dailymail](https://huggingface.co/datasets/cnn_dailymail) dataset by
@kaprerna135
, using the predictions stored [here](https://huggingface.co/datasets/autoevaluate/autoeval-eval-cnn_dailymail-3.0.0-35af0a-27496144909).\
Accept this pull request to see the results displayed on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=cnn_dailymail).\
Evaluate your model on more datasets [here](https://huggingface.co/spaces/autoevaluate/model-evaluator?dataset=cnn_dailymail).
README.md
CHANGED
@@ -88,6 +88,45 @@ model-index:
|
|
88 |
name: gen_len
|
89 |
verified: true
|
90 |
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWRlMjM5MzAyMjEzYzdkODFmNDk4NDg5NWM4NWIxMTU4YWMxNzZjMGFjOWJiMDdkMjQyMTY0ZGFmYzA2OTA0YiIsInZlcnNpb24iOjF9.IFiGJEsyD7Uhj8bo9SsAgibk9qCXZH6IWaLKULLxBz5N8WXF2vc2Mfg5OThEzdrydPhJInRgp0jd8m-kF5nNCA
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
---
|
92 |
|
93 |
# T5-large Summarization Model Trained on the combined XSUM-CNN Daily Mail Dataset
|
|
|
88 |
name: gen_len
|
89 |
verified: true
|
90 |
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWRlMjM5MzAyMjEzYzdkODFmNDk4NDg5NWM4NWIxMTU4YWMxNzZjMGFjOWJiMDdkMjQyMTY0ZGFmYzA2OTA0YiIsInZlcnNpb24iOjF9.IFiGJEsyD7Uhj8bo9SsAgibk9qCXZH6IWaLKULLxBz5N8WXF2vc2Mfg5OThEzdrydPhJInRgp0jd8m-kF5nNCA
|
91 |
+
- task:
|
92 |
+
type: summarization
|
93 |
+
name: Summarization
|
94 |
+
dataset:
|
95 |
+
name: cnn_dailymail
|
96 |
+
type: cnn_dailymail
|
97 |
+
config: 3.0.0
|
98 |
+
split: test
|
99 |
+
metrics:
|
100 |
+
- type: rouge
|
101 |
+
value: 20.0169
|
102 |
+
name: ROUGE-1
|
103 |
+
verified: true
|
104 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDljMWM0YjYxMDMyZTlhYmIzNmM2YzZkNmQwYjVjZTNmMGVhNzM2NTdjY2I3ODgzYWEwOTQ2NmY3ZjU2Zjk4MiIsInZlcnNpb24iOjF9.4cdcU0XAIgGdGFT4R6nd5qad1VoqY1dDXCq7jlcIeCfVcCwravKWuK8X8NggxevxC1BMeTd_jFJfuv3jWODSCw
|
105 |
+
- type: rouge
|
106 |
+
value: 5.0643
|
107 |
+
name: ROUGE-2
|
108 |
+
verified: true
|
109 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2QwNjlkNTVlZjk5MmIyZTIxYTExNjIzZjM4MjlkZDQ4NjViMjljZjg1NGI2ZmJiNGQ0NGVhMjRjNjg2MTA4OCIsInZlcnNpb24iOjF9._PcMo0Gfkjfs49sVX0yHnAgWrVptrAK6j2FiGRZaa3nUgHVyZRRstFOeK9fwZ26TtZ3FtIslfy6ia32IUfvACQ
|
110 |
+
- type: rouge
|
111 |
+
value: 14.4762
|
112 |
+
name: ROUGE-L
|
113 |
+
verified: true
|
114 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWIyMGFmZmMxYjNhMTc4Y2Y3YTVjZDAwMWJhNzU2NjBkYWNlNGMwYzExMTEzZGQ3ZjFkYWIwMzE5NDgyOTNiNiIsInZlcnNpb24iOjF9.9LhQ7cYM5lpr9k9ngPjOZAsrGrc9MHFVfbd1HysL3blHds4SZv6ioOMameO7qVIlG2Ot1XslVbvN8l-_LSStDA
|
115 |
+
- type: rouge
|
116 |
+
value: 17.6812
|
117 |
+
name: ROUGE-LSUM
|
118 |
+
verified: true
|
119 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGM4ZjJkMmUzNzZkNWZhZTc2YmUzZmJhN2U4YzQxM2VmNTk1ZDZkMjEyZDAwY2ZmNzVlMjFhZTY0M2UxZWFmMiIsInZlcnNpb24iOjF9.NSVmTw5_s5Zx_gQe2ibxo-R4O-KOi8yDZtQ2yExYxDFSMhs921eIi6KMBguNh6MAmCsEz-BFppI9gZ47XAP0Dg
|
120 |
+
- type: loss
|
121 |
+
value: 2.863785743713379
|
122 |
+
name: loss
|
123 |
+
verified: true
|
124 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYWRiZmFhOTY0MTE3NTE4MDcyZWUyMjM3MWI4NjIwY2I2YTI0YTQ1NzA3ODMzY2FiZDcwMjdjMWViNjk3NGEzNiIsInZlcnNpb24iOjF9.kygh8aIGin_1ucBoEMehNArgK0A1zwMK2Kd0JaAkFSnc3ZXvrYAdrSmxFfoGAlqYJT6bNL9UQievBlgyxt-aDg
|
125 |
+
- type: gen_len
|
126 |
+
value: 18.6581
|
127 |
+
name: gen_len
|
128 |
+
verified: true
|
129 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTNkNTE4M2E4ZDI5NGZmN2I3YzM3ZTJkYmNjODdmMDk1ZjA4YzlmOGE1ODQxM2M4NjRiNTJjYzI0OTc2MmUxZCIsInZlcnNpb24iOjF9.6uPTg-C8HTQKq6Ppn0iwTWDz7P86_1cc5n6_3ct605etp4li79phSHS7TGpLKWeVSQKGpiSVOzUQhwslqyrVCg
|
130 |
---
|
131 |
|
132 |
# T5-large Summarization Model Trained on the combined XSUM-CNN Daily Mail Dataset
|