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: 2.2389
-- Rouge1: 0.4284
+- Loss: 1.7802
+- Rouge1: 0.696
 - Rouge2: 0.0
-- Rougel: 0.431
-- Rougelsum: 0.4286
+- Rougel: 0.6965
+- Rougelsum: 0.6913
 - Gen Len: 1.0
 
 ## Model description
@@ -43,8 +41,8 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
+- learning_rate: 0.001
+- train_batch_size: 16
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -55,16 +53,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 3.5006        | 1.0   | 1783 | 2.5353          | 0.571  | 0.0    | 0.5726 | 0.5713    | 1.0     |
-| 2.9963        | 2.0   | 3566 | 2.3939          | 0.4906 | 0.0    | 0.4911 | 0.4909    | 1.0     |
-| 2.8832        | 3.0   | 5349 | 2.3137          | 0.4144 | 0.0    | 0.4158 | 0.4144    | 1.0     |
-| 2.8145        | 4.0   | 7132 | 2.2872          | 0.4356 | 0.0    | 0.435  | 0.4361    | 1.0     |
-| 2.7759        | 5.0   | 8915 | 2.2389          | 0.4284 | 0.0    | 0.431  | 0.4286    | 1.0     |
+| 3.3224        | 1.0   | 892  | 2.3843          | 0.6887 | 0.0    | 0.6879 | 0.6876    | 1.0     |
+| 2.913         | 2.0   | 1784 | 2.1557          | 0.7307 | 0.0    | 0.7301 | 0.7315    | 1.0     |
+| 2.7028        | 3.0   | 2676 | 1.9775          | 0.7149 | 0.0    | 0.7155 | 0.7105    | 1.0     |
+| 2.5387        | 4.0   | 3568 | 1.8682          | 0.7337 | 0.0    | 0.731  | 0.7295    | 1.0     |
+| 2.4084        | 5.0   | 4460 | 1.7802          | 0.696  | 0.0    | 0.6965 | 0.6913    | 1.0     |
 
 
 ### Framework versions
 
 - Transformers 4.40.2
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.1
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
 - Tokenizers 0.19.1

adapter-summarization/adapter_config.json

@@ -8,11 +8,11 @@
     "flat": false,
     "leave_out": [],
     "non_linearity": "tanh",
-    "prefix_length": 20,
+    "prefix_length": 10,
     "shared_gating": true,
     "use_gating": false
   },
-  "config_id": "a62560183dec11a0",
+  "config_id": "e21f5a7ac06e3fee",
   "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 sha256:90a290c8734394a7db51db5b3d4b285e42566e4a3bf31ad19bac48f7bcd4e760
-size 118500161
+oid sha256:869bedf8e0e6a6a412ce6b104769ac9b01b52608856e4bf6022bcf2b7efb01c8
+size 118408001

adapter-summarization/pytorch_model_head.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd548901ec4934606bf603f9ad993abe34705fab7adf7a1588438452345bb281
-size 217080258
+oid sha256:5b8b8e8f3d50d06d816d8379d5a992dbeeccb89844c34353f61522df9437fb07
+size 216988098