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: 0.4798
-- Rouge1: 0.395
+- Loss: 0.4683
+- Rouge1: 0.6725
 - Rouge2: 0.0
-- Rougel: 0.3935
-- Rougelsum: 0.3933
+- Rougel: 0.6711
+- Rougelsum: 0.6719
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 0.827         | 1.0   | 894  | 0.5171          | 0.6517 | 0.0    | 0.6531 | 0.6496    | 1.0     |
-| 0.6257        | 2.0   | 1788 | 0.4944          | 0.6472 | 0.0    | 0.6472 | 0.6469    | 1.0     |
-| 0.5832        | 3.0   | 2682 | 0.4848          | 0.6329 | 0.0    | 0.6335 | 0.634     | 1.0     |
-| 0.5581        | 4.0   | 3576 | 0.4824          | 0.6575 | 0.0    | 0.6562 | 0.6576    | 1.0     |
-| 0.5411        | 5.0   | 4470 | 0.4798          | 0.6568 | 0.0    | 0.6564 | 0.6586    | 1.0     |
+| 0.7823        | 1.0   | 894  | 0.5092          | 0.6551 | 0.0    | 0.6537 | 0.6535    | 1.0     |
+| 0.6005        | 2.0   | 1788 | 0.4769          | 0.6706 | 0.0    | 0.6693 | 0.6688    | 1.0     |
+| 0.5564        | 3.0   | 2682 | 0.4768          | 0.6725 | 0.0    | 0.6709 | 0.6731    | 1.0     |
+| 0.5269        | 4.0   | 3576 | 0.4667          | 0.6722 | 0.0    | 0.6726 | 0.6742    | 1.0     |
+| 0.5061        | 5.0   | 4470 | 0.4683          | 0.6725 | 0.0    | 0.6711 | 0.6719    | 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:ee48ec888139610253fd546acc9a33b409eb1ac410a5321d022daf843f255e78
-size 3593010
+oid sha256:0ab165b2f622aabc952c73f57e71015277aaef1d9170aabb77a6fe723a033707
+size 7131954