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: 0.4997
-- Rouge1: 0.4108
+- Loss: 0.4872
+- Rouge1: 0.6882
 - Rouge2: 0.0
-- Rougel: 0.4046
-- Rougelsum: 0.4066
+- Rougel: 0.6851
+- Rougelsum: 0.6829
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 0.8166        | 1.0   | 892  | 0.5412          | 0.6958 | 0.0    | 0.6933 | 0.6944    | 1.0     |
-| 0.6181        | 2.0   | 1784 | 0.5292          | 0.6767 | 0.0    | 0.6749 | 0.6733    | 1.0     |
-| 0.5768        | 3.0   | 2676 | 0.4997          | 0.6835 | 0.0    | 0.6819 | 0.6808    | 1.0     |
-| 0.5516        | 4.0   | 3568 | 0.5061          | 0.6866 | 0.0    | 0.6872 | 0.6829    | 1.0     |
-| 0.5337        | 5.0   | 4460 | 0.4997          | 0.7062 | 0.0    | 0.7054 | 0.7026    | 1.0     |
+| 0.7738        | 1.0   | 892  | 0.5310          | 0.704  | 0.0    | 0.6981 | 0.7001    | 1.0     |
+| 0.5926        | 2.0   | 1784 | 0.5096          | 0.6968 | 0.0    | 0.6921 | 0.6922    | 1.0     |
+| 0.5492        | 3.0   | 2676 | 0.4948          | 0.6619 | 0.0    | 0.659  | 0.6573    | 1.0     |
+| 0.5199        | 4.0   | 3568 | 0.4957          | 0.7098 | 0.0    | 0.7065 | 0.7048    | 1.0     |
+| 0.4984        | 5.0   | 4460 | 0.4872          | 0.6882 | 0.0    | 0.6851 | 0.6829    | 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:e258505980833d7c36e3e6797f2fb59250bcbe5bfe711805ec6bb2fdff30b816
-size 3593010
+oid sha256:7f911db38dc76df1e83c27847499b1ae59c1358112fb39d7b8a7957463e5f96d
+size 7131954