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: 0.5212
-- Rouge1: 0.3932
+- Loss: 0.5089
+- Rouge1: 0.6799
 - Rouge2: 0.0
-- Rougel: 0.3893
-- Rougelsum: 0.3908
+- Rougel: 0.6778
+- Rougelsum: 0.681
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 0.8224        | 1.0   | 892  | 0.5704          | 0.6572 | 0.0    | 0.6564 | 0.655     | 1.0     |
-| 0.6196        | 2.0   | 1784 | 0.5431          | 0.6602 | 0.0    | 0.6579 | 0.6606    | 1.0     |
-| 0.5778        | 3.0   | 2676 | 0.5373          | 0.6757 | 0.0    | 0.6756 | 0.6745    | 1.0     |
-| 0.5503        | 4.0   | 3568 | 0.5256          | 0.659  | 0.0    | 0.6569 | 0.6586    | 1.0     |
-| 0.5343        | 5.0   | 4460 | 0.5212          | 0.6659 | 0.0    | 0.6648 | 0.6661    | 1.0     |
+| 0.7751        | 1.0   | 892  | 0.5565          | 0.6744 | 0.0    | 0.6731 | 0.6738    | 1.0     |
+| 0.5945        | 2.0   | 1784 | 0.5315          | 0.6624 | 0.0    | 0.6627 | 0.6631    | 1.0     |
+| 0.5498        | 3.0   | 2676 | 0.5278          | 0.6681 | 0.0    | 0.6682 | 0.6679    | 1.0     |
+| 0.5192        | 4.0   | 3568 | 0.5093          | 0.6755 | 0.0    | 0.6729 | 0.6744    | 1.0     |
+| 0.4995        | 5.0   | 4460 | 0.5089          | 0.6799 | 0.0    | 0.6778 | 0.681     | 1.0     |
 
 
 ### Framework versions

adapter-summarization/adapter_config.json

@@ -12,11 +12,11 @@
     "intermediate_lora": false,
     "leave_out": [],
     "output_lora": false,
-    "r": 8,
+    "r": 16,
     "selfattn_lora": true,
     "use_gating": false
   },
-  "config_id": "625403edad0bf919",
+  "config_id": "141b248112091265",
   "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:c691aedf978ac1ae4e1d2172c5c846f2ebdd845a690176236a336f1b3d589b5f
-size 3593010
+oid sha256:f7573179687510aebdb5841fb9af27534de3881083e7cb5eb1f67c02238fb7f2
+size 7131954