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: 0.4733
-- Rouge1: 0.3767
+- Loss: 0.4618
+- Rouge1: 0.7261
 - Rouge2: 0.0
-- Rougel: 0.3787
-- Rougelsum: 0.3802
+- Rougel: 0.7257
+- Rougelsum: 0.7223
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 0.8225        | 1.0   | 892  | 0.5298          | 0.7091 | 0.0    | 0.7089 | 0.7076    | 1.0     |
-| 0.623         | 2.0   | 1784 | 0.5064          | 0.7118 | 0.0    | 0.71   | 0.7093    | 1.0     |
-| 0.5809        | 3.0   | 2676 | 0.4813          | 0.7155 | 0.0    | 0.7147 | 0.7119    | 1.0     |
-| 0.5549        | 4.0   | 3568 | 0.4799          | 0.7058 | 0.0    | 0.7057 | 0.7028    | 1.0     |
-| 0.5383        | 5.0   | 4460 | 0.4733          | 0.7008 | 0.0    | 0.7001 | 0.6968    | 1.0     |
+| 0.7784        | 1.0   | 892  | 0.5092          | 0.716  | 0.0    | 0.7135 | 0.7135    | 1.0     |
+| 0.597         | 2.0   | 1784 | 0.4861          | 0.7099 | 0.0    | 0.7098 | 0.7065    | 1.0     |
+| 0.5538        | 3.0   | 2676 | 0.4700          | 0.7231 | 0.0    | 0.7238 | 0.7212    | 1.0     |
+| 0.5245        | 4.0   | 3568 | 0.4649          | 0.7304 | 0.0    | 0.7271 | 0.7266    | 1.0     |
+| 0.5037        | 5.0   | 4460 | 0.4618          | 0.7261 | 0.0    | 0.7257 | 0.7223    | 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 sha256:50ace605799bc659abdf0eca1a7b0ad9acc289c286cf65058ad3481dcb3cb14c
-size 3593010
+oid sha256:053f1b5f54bd28ce07a6649450746aeed9af03873c3e8e90c28df84ce301866d
+size 7131954