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: 0.5829
-- Rouge1: 0.4334
+- Loss: 0.5656
+- Rouge1: 0.4188
 - Rouge2: 0.0
-- Rougel: 0.4324
-- Rougelsum: 0.4298
+- Rougel: 0.4161
+- Rougelsum: 0.4157
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 1.3917        | 1.0   | 1783 | 0.6615          | 0.5471 | 0.0    | 0.5464 | 0.5441    | 1.0     |
-| 0.854         | 2.0   | 3566 | 0.6181          | 0.4511 | 0.0    | 0.4501 | 0.4463    | 1.0     |
-| 0.7905        | 3.0   | 5349 | 0.5925          | 0.421  | 0.0    | 0.4197 | 0.4168    | 1.0     |
-| 0.7624        | 4.0   | 7132 | 0.5808          | 0.438  | 0.0    | 0.4378 | 0.433     | 1.0     |
-| 0.751         | 5.0   | 8915 | 0.5829          | 0.4334 | 0.0    | 0.4324 | 0.4298    | 1.0     |
+| 1.2271        | 1.0   | 1783 | 0.6275          | 0.491  | 0.0    | 0.4864 | 0.4859    | 1.0     |
+| 0.7893        | 2.0   | 3566 | 0.5955          | 0.4382 | 0.0    | 0.4358 | 0.4345    | 1.0     |
+| 0.7347        | 3.0   | 5349 | 0.5738          | 0.4461 | 0.0    | 0.4432 | 0.4417    | 1.0     |
+| 0.7084        | 4.0   | 7132 | 0.5618          | 0.4416 | 0.0    | 0.4409 | 0.4389    | 1.0     |
+| 0.6976        | 5.0   | 8915 | 0.5656          | 0.4188 | 0.0    | 0.4161 | 0.4157    | 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 sha256:6f7f806b1532d96eea8201f2515ab1653314ba7fd7f24f925d30258bf8169a8a
-size 3593010
+oid sha256:dbe859c84e1b99a3cb70cfb3839c591eca1beb635b29e0f0109991d029f9b7b3
+size 7131954