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: 1.4509
-- Rouge1: 0.4412
+- Loss: 1.3436
+- Rouge1: 0.6802
 - Rouge2: 0.0
-- Rougel: 0.443
-- Rougelsum: 0.4415
+- Rougel: 0.6802
+- Rougelsum: 0.6778
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 3.1762        | 1.0   | 892  | 2.2190          | 0.7537 | 0.0    | 0.7549 | 0.7532    | 1.0     |
-| 2.6396        | 2.0   | 1784 | 1.8945          | 0.6963 | 0.0    | 0.6949 | 0.6934    | 1.0     |
-| 2.3694        | 3.0   | 2676 | 1.6951          | 0.6912 | 0.0    | 0.6912 | 0.6889    | 1.0     |
-| 2.1722        | 4.0   | 3568 | 1.5595          | 0.6883 | 0.0    | 0.6851 | 0.6883    | 1.0     |
-| 2.0114        | 5.0   | 4460 | 1.4509          | 0.6893 | 0.0    | 0.6872 | 0.6862    | 1.0     |
+| 3.0294        | 1.0   | 892  | 1.9919          | 0.672  | 0.0    | 0.6729 | 0.6683    | 1.0     |
+| 2.4162        | 2.0   | 1784 | 1.7555          | 0.7269 | 0.0    | 0.7253 | 0.727     | 1.0     |
+| 2.1684        | 3.0   | 2676 | 1.5470          | 0.693  | 0.0    | 0.6917 | 0.6933    | 1.0     |
+| 1.9893        | 4.0   | 3568 | 1.4300          | 0.6992 | 0.0    | 0.6959 | 0.6968    | 1.0     |
+| 1.8466        | 5.0   | 4460 | 1.3436          | 0.6802 | 0.0    | 0.6802 | 0.6778    | 1.0     |
 
 
 ### Framework versions

adapter-summarization/adapter_config.json

@@ -8,11 +8,11 @@
     "flat": false,
     "leave_out": [],
     "non_linearity": "tanh",
-    "prefix_length": 20,
+    "prefix_length": 30,
     "shared_gating": true,
     "use_gating": false
   },
-  "config_id": "a62560183dec11a0",
+  "config_id": "648bf22f5afeaaa6",
   "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 sha256:5b7f181030088a38951b42c6634803fee6c5d00dfd5146d5c4fcbd7f695521c3
-size 118500161
+oid sha256:bbc00472e063edd59fd4f8a43c054d4e1444525ce0507f0a2367abc989f875ec
+size 118592321

adapter-summarization/pytorch_model_head.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:549cbcd4748787c9cfa1f1e74539a19ba7119991c29a5545c244c5453b8cefed
-size 217080258
+oid sha256:ef4ff85a4f365fc215525b01f076626aa1d4543771c3e7d95841d239f7dce6a2
+size 217172418