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: 1.4223
-- Rouge1: 0.4479
+- Loss: 1.2774
+- Rouge1: 0.6685
 - Rouge2: 0.0
-- Rougel: 0.4447
-- Rougelsum: 0.444
+- Rougel: 0.6677
+- Rougelsum: 0.6651
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 3.1861        | 1.0   | 892  | 2.2146          | 0.7276 | 0.0    | 0.7228 | 0.7243    | 1.0     |
-| 2.6443        | 2.0   | 1784 | 1.8686          | 0.6739 | 0.0    | 0.6711 | 0.6725    | 1.0     |
-| 2.3648        | 3.0   | 2676 | 1.6868          | 0.6807 | 0.0    | 0.6791 | 0.6801    | 1.0     |
-| 2.1665        | 4.0   | 3568 | 1.5095          | 0.7096 | 0.0    | 0.7072 | 0.7087    | 1.0     |
-| 2.0149        | 5.0   | 4460 | 1.4223          | 0.705  | 0.0    | 0.703  | 0.7034    | 1.0     |
+| 3.0347        | 1.0   | 892  | 2.0002          | 0.6717 | 0.0    | 0.6744 | 0.6696    | 1.0     |
+| 2.4012        | 2.0   | 1784 | 1.7296          | 0.7117 | 0.0    | 0.7105 | 0.7111    | 1.0     |
+| 2.1461        | 3.0   | 2676 | 1.4790          | 0.6953 | 0.0    | 0.6922 | 0.6902    | 1.0     |
+| 1.952         | 4.0   | 3568 | 1.3589          | 0.6758 | 0.0    | 0.6753 | 0.6736    | 1.0     |
+| 1.8052        | 5.0   | 4460 | 1.2774          | 0.6685 | 0.0    | 0.6677 | 0.6651    | 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 sha256:0790e8c108ae281d7af16ef383467965f5e70cbcd92fcfa2e486ea367641d687
-size 118500161
+oid sha256:1b7517c4a7db0c779b9e558fda32d2fd412d148067f333311a8925f21025bf5a
+size 118592321

adapter-summarization/pytorch_model_head.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d051ff2e8c5775bcbba9b4b264b0a5d4e8219fa3dd9be635659ed889b15e4ce
-size 217080258
+oid sha256:b51d73761e9fa02f3554450a39c8f76dc4aa0ec9f3698f1a9e57ddce6f2d5d5d
+size 217172418