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: 0.5351
-- Rouge1: 0.3585
+- Loss: 0.4798
+- Rouge1: 0.6568
 - Rouge2: 0.0
-- Rougel: 0.3555
-- Rougelsum: 0.357
+- Rougel: 0.6564
+- Rougelsum: 0.6586
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 1.2329        | 1.0   | 1787 | 0.5976          | 0.3912 | 0.0    | 0.3916 | 0.392     | 1.0     |
-| 0.7952        | 2.0   | 3574 | 0.5580          | 0.3919 | 0.0    | 0.3921 | 0.3921    | 1.0     |
-| 0.7407        | 3.0   | 5361 | 0.5366          | 0.3893 | 0.0    | 0.3879 | 0.3866    | 1.0     |
-| 0.7152        | 4.0   | 7148 | 0.5402          | 0.354  | 0.0    | 0.3512 | 0.3523    | 1.0     |
-| 0.7029        | 5.0   | 8935 | 0.5351          | 0.3585 | 0.0    | 0.3555 | 0.357     | 1.0     |
+| 0.827         | 1.0   | 894  | 0.5171          | 0.6517 | 0.0    | 0.6531 | 0.6496    | 1.0     |
+| 0.6257        | 2.0   | 1788 | 0.4944          | 0.6472 | 0.0    | 0.6472 | 0.6469    | 1.0     |
+| 0.5832        | 3.0   | 2682 | 0.4848          | 0.6329 | 0.0    | 0.6335 | 0.634     | 1.0     |
+| 0.5581        | 4.0   | 3576 | 0.4824          | 0.6575 | 0.0    | 0.6562 | 0.6576    | 1.0     |
+| 0.5411        | 5.0   | 4470 | 0.4798          | 0.6568 | 0.0    | 0.6564 | 0.6586    | 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

@@ -12,11 +12,11 @@
     "intermediate_lora": false,
     "leave_out": [],
     "output_lora": false,
-    "r": 16,
+    "r": 8,
     "selfattn_lora": true,
     "use_gating": false
   },
-  "config_id": "141b248112091265",
+  "config_id": "625403edad0bf919",
   "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 sha256:45872174cc0c9796b2b3049f506b0b7ef08212d2049c731a7b1864838e9968d2
-size 7131954
+oid sha256:ee48ec888139610253fd546acc9a33b409eb1ac410a5321d022daf843f255e78
+size 3593010