Update README.md

README.md

@@ -1,32 +1,74 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
-- generated_from_trainer
-model-index:
-- name: multiwoz21
-  results: []
----
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# multiwoz21
-
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.5254
-
-## Model description
+- t5-small
+- text2text-generation
+- dialogue generation
+- conversational system
+- task-oriented dialog
+datasets:
+- ConvLab/multiwoz21
+metrics:
+- LM loss
 
-More information needed
+model-index:
+- name: t5-small-goal2dial-multiwoz21
+  results:
+  - task:
+      type: text2text-generation
+      name: dialogue generation
+    dataset:
+      type: ConvLab/multiwoz21
+      name: MultiWOZ 2.1
+      split: train
+      revision: 5f55375edbfe0270c20bcf770751ad982c0e6614
+    metrics:
+      - type: Language model loss
+        value: 1.5772826686049952
+        name: LM loss
+  - task:
+      type: text2text-generation
+      name: dialogue generation
+    dataset:
+      type: ConvLab/multiwoz21
+      name: MultiWOZ 2.1
+      split: validation
+      revision: 5f55375edbfe0270c20bcf770751ad982c0e6614
+    metrics:
+      - type: Language model loss
+        value: 1.5253684520721436
+        name: LM loss
+  - task:
+      type: text2text-generation
+      name: dialogue generation
+    dataset:
+      type: ConvLab/multiwoz21
+      name: MultiWOZ 2.1
+      split: test
+      revision: 5f55375edbfe0270c20bcf770751ad982c0e6614
+    metrics:
+      - type: Language model loss
+        value: 1.515929937362671
+        name: LM loss
+
+
+widget:
+- text: "You want to book a taxi. The taxi should go to pizza hut fen ditton and should depart from saint john's college. The taxi should leave after 17:15. Make sure you get car type and contact number"
+- text: "You are traveling to Cambridge and looking forward to try local restaurants. You are looking for a particular attraction. Its name is called nusha. Make sure you get postcode and address. You are also looking for a place to dine. The restaurant should be in the expensive price range and should serve indian food. The restaurant should be in the centre. Make sure you get address"
+
+inference:
+  parameters:
+    max_length: 1024
 
-## Intended uses & limitations
+---
 
-More information needed
+# t5-small-goal2dial-multiwoz21
 
-## Training and evaluation data
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on [MultiWOZ 2.1](https://huggingface.co/datasets/ConvLab/multiwoz21).
 
-More information needed
+Refer to [ConvLab-3](https://github.com/ConvLab/ConvLab-3) for model description and usage.
 
 ## Training procedure
 
@@ -44,22 +86,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 10.0
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 66   | 2.0358          |
-| No log        | 2.0   | 132  | 1.8007          |
-| No log        | 3.0   | 198  | 1.6993          |
-| No log        | 4.0   | 264  | 1.6388          |
-| No log        | 5.0   | 330  | 1.6028          |
-| No log        | 6.0   | 396  | 1.5719          |
-| No log        | 7.0   | 462  | 1.5516          |
-| 1.801         | 8.0   | 528  | 1.5360          |
-| 1.801         | 9.0   | 594  | 1.5276          |
-| 1.801         | 10.0  | 660  | 1.5254          |
-
-
 ### Framework versions
 
 - Transformers 4.18.0