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: 0.5652
-- Rouge1: 0.5057
+- Loss: 0.5140
+- Rouge1: 0.7665
 - Rouge2: 0.0
-- Rougel: 0.5089
-- Rougelsum: 0.5041
+- Rougel: 0.7672
+- Rougelsum: 0.7666
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 1.2298        | 1.0   | 1783 | 0.6183          | 0.5036 | 0.0    | 0.5051 | 0.5002    | 1.0     |
-| 0.7893        | 2.0   | 3566 | 0.5936          | 0.5166 | 0.0    | 0.5199 | 0.5139    | 1.0     |
-| 0.7368        | 3.0   | 5349 | 0.5787          | 0.517  | 0.0    | 0.5231 | 0.516     | 1.0     |
-| 0.7107        | 4.0   | 7132 | 0.5670          | 0.5105 | 0.0    | 0.5148 | 0.5089    | 1.0     |
-| 0.6989        | 5.0   | 8915 | 0.5652          | 0.5057 | 0.0    | 0.5089 | 0.5041    | 1.0     |
+| 0.8212        | 1.0   | 892  | 0.5616          | 0.77   | 0.0    | 0.7703 | 0.7685    | 1.0     |
+| 0.6185        | 2.0   | 1784 | 0.5593          | 0.7457 | 0.0    | 0.7436 | 0.7441    | 1.0     |
+| 0.5776        | 3.0   | 2676 | 0.5283          | 0.7664 | 0.0    | 0.7649 | 0.7639    | 1.0     |
+| 0.5535        | 4.0   | 3568 | 0.5193          | 0.7475 | 0.0    | 0.747  | 0.745     | 1.0     |
+| 0.5357        | 5.0   | 4460 | 0.5140          | 0.7665 | 0.0    | 0.7672 | 0.7666    | 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 sha256:73dc2313e48c9cbc6e2f07773e7c6dd2ac34052c433072cedfdaeb708aaef248
-size 7131954
+oid sha256:2fa48e6286fea6effa6af94facca483000733e15f876076bdc4b88156e16ba54
+size 3593010