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: 0.5588
-- Rouge1: 0.4494
+- Loss: 0.5392
+- Rouge1: 0.4255
 - Rouge2: 0.0
-- Rougel: 0.4489
-- Rougelsum: 0.4499
+- Rougel: 0.4247
+- Rougelsum: 0.4257
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 1.3987        | 1.0   | 1784 | 0.6451          | 0.4474 | 0.0    | 0.4495 | 0.4472    | 1.0     |
-| 0.8591        | 2.0   | 3568 | 0.5834          | 0.4222 | 0.0    | 0.4206 | 0.4228    | 1.0     |
-| 0.7949        | 3.0   | 5352 | 0.5684          | 0.4462 | 0.0    | 0.4449 | 0.4456    | 1.0     |
-| 0.7674        | 4.0   | 7136 | 0.5639          | 0.4564 | 0.0    | 0.4538 | 0.4545    | 1.0     |
-| 0.7542        | 5.0   | 8920 | 0.5588          | 0.4494 | 0.0    | 0.4489 | 0.4499    | 1.0     |
+| 1.233         | 1.0   | 1784 | 0.6087          | 0.4912 | 0.0    | 0.4859 | 0.4881    | 1.0     |
+| 0.7935        | 2.0   | 3568 | 0.5582          | 0.4176 | 0.0    | 0.4157 | 0.4171    | 1.0     |
+| 0.7385        | 3.0   | 5352 | 0.5451          | 0.4227 | 0.0    | 0.4192 | 0.4214    | 1.0     |
+| 0.7114        | 4.0   | 7136 | 0.5406          | 0.4115 | 0.0    | 0.4115 | 0.4106    | 1.0     |
+| 0.6996        | 5.0   | 8920 | 0.5392          | 0.4255 | 0.0    | 0.4247 | 0.4257    | 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:bd98521db324850daf705dfa86a70a048f68d35aa11f554edb31d1cea52f2114
-size 3593010
+oid sha256:d1d2477424d237f6df3f8efea206a8d6cc5941d0f37b7f7459fb8ef7bd99ebd3
+size 7131954