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: 0.6087
-- Rouge1: 0.4049
+- Loss: 0.5917
+- Rouge1: 0.3832
 - Rouge2: 0.0
-- Rougel: 0.4028
-- Rougelsum: 0.4042
+- Rougel: 0.3816
+- Rougelsum: 0.3824
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 1.3948        | 1.0   | 1784 | 0.6978          | 0.3931 | 0.0    | 0.3957 | 0.3954    | 1.0     |
-| 0.8544        | 2.0   | 3568 | 0.6352          | 0.4133 | 0.0    | 0.4123 | 0.4139    | 1.0     |
-| 0.791         | 3.0   | 5352 | 0.6227          | 0.4051 | 0.0    | 0.4033 | 0.4045    | 1.0     |
-| 0.7631        | 4.0   | 7136 | 0.6149          | 0.3884 | 0.0    | 0.3851 | 0.3881    | 1.0     |
-| 0.7508        | 5.0   | 8920 | 0.6087          | 0.4049 | 0.0    | 0.4028 | 0.4042    | 1.0     |
+| 1.2253        | 1.0   | 1784 | 0.6577          | 0.4006 | 0.0    | 0.3969 | 0.4007    | 1.0     |
+| 0.7893        | 2.0   | 3568 | 0.6133          | 0.4188 | 0.0    | 0.4167 | 0.4194    | 1.0     |
+| 0.7351        | 3.0   | 5352 | 0.6062          | 0.3925 | 0.0    | 0.3898 | 0.3908    | 1.0     |
+| 0.7092        | 4.0   | 7136 | 0.5990          | 0.3834 | 0.0    | 0.381  | 0.3826    | 1.0     |
+| 0.6978        | 5.0   | 8920 | 0.5917          | 0.3832 | 0.0    | 0.3816 | 0.3824    | 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:f6b641b0b612275280f7c8ffecc5aeef616d23414174af3543b6f7e44543fc5a
-size 3593010
+oid sha256:17acf4245cdcf518875c3303529cd8b5c0b3942a274ceb923e4f9b50ad65788e
+size 7131954