Model save

README.md

@@ -1,6 +1,4 @@
 ---
-language:
-- id
 license: apache-2.0
 base_model: LazarusNLP/IndoNanoT5-base
 tags:
@@ -19,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8190
-- Rouge1: 0.4934
+- Loss: 1.4701
+- Rouge1: 0.642
 - Rouge2: 0.0
-- Rougel: 0.4886
-- Rougelsum: 0.4927
+- Rougel: 0.6403
+- Rougelsum: 0.6418
 - Gen Len: 1.0
 
 ## Model description
@@ -55,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 3.3561        | 1.0   | 892  | 2.4617          | 0.7284 | 0.0    | 0.7322 | 0.731     | 1.0     |
-| 2.9625        | 2.0   | 1784 | 2.2271          | 0.7322 | 0.0    | 0.7311 | 0.7367    | 1.0     |
-| 2.7534        | 3.0   | 2676 | 2.0914          | 0.7923 | 0.0    | 0.7905 | 0.7921    | 1.0     |
-| 2.5853        | 4.0   | 3568 | 1.9273          | 0.7009 | 0.0    | 0.6973 | 0.7006    | 1.0     |
-| 2.4445        | 5.0   | 4460 | 1.8190          | 0.6731 | 0.0    | 0.6692 | 0.6714    | 1.0     |
+| 3.2165        | 1.0   | 892  | 2.2934          | 0.6553 | 0.0    | 0.6576 | 0.6573    | 1.0     |
+| 2.6671        | 2.0   | 1784 | 2.0331          | 0.6925 | 0.0    | 0.6908 | 0.6927    | 1.0     |
+| 2.3863        | 3.0   | 2676 | 1.7660          | 0.6813 | 0.0    | 0.6776 | 0.68      | 1.0     |
+| 2.1805        | 4.0   | 3568 | 1.5863          | 0.6384 | 0.0    | 0.6375 | 0.638     | 1.0     |
+| 2.0226        | 5.0   | 4460 | 1.4701          | 0.642  | 0.0    | 0.6403 | 0.6418    | 1.0     |
 
 
 ### Framework versions

adapter-summarization/adapter_config.json

@@ -8,11 +8,11 @@
     "flat": false,
     "leave_out": [],
     "non_linearity": "tanh",
-    "prefix_length": 10,
+    "prefix_length": 20,
     "shared_gating": true,
     "use_gating": false
   },
-  "config_id": "e21f5a7ac06e3fee",
+  "config_id": "a62560183dec11a0",
   "hidden_size": 768,
   "model_class": "T5ForConditionalGeneration",
   "model_name": "LazarusNLP/IndoNanoT5-base",

adapter-summarization/pytorch_adapter.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b9cea7ca22f2dee9dc636826eda1f4c7a04ff9e2abae527a6c69efadabdc04
-size 118408001
+oid sha256:f879a7daf4d4eff6d461d5dc59cee4c3611185f8a7bf80b212b09801aacb17c4
+size 118500161

adapter-summarization/pytorch_model_head.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30d19362b0740ec262a36e2da48aa85e1d0971b943a1169f386a6a26280a95ae
-size 216988098
+oid sha256:5baf62c459a321beeec752b3ed936e9d6cd771a3c0068de0982a1874fc3d18f1
+size 217080258