Model save

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: LazarusNLP/IndoNanoT5-base
+tags:
+- generated_from_trainer
+datasets:
+- id_liputan6
+metrics:
+- rouge
+model-index:
+- name: liputan6-seq_bn-rf16
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# liputan6-seq_bn-rf16
+
+This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on the id_liputan6 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7479
+- Rouge1: 26.9743
+- Rouge2: 11.4843
+- Rougel: 22.9863
+- Rougelsum: 24.9284
+- Gen Len: 33.854
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- 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
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 2.6241        | 1.0   | 63   | 2.7534          | 23.3287 | 9.5988  | 20.1923 | 21.2916   | 33.387  |
+| 2.228         | 2.0   | 126  | 2.7025          | 25.8033 | 10.8168 | 21.9451 | 23.4491   | 32.153  |
+| 2.0615        | 3.0   | 189  | 2.6749          | 25.8887 | 10.7586 | 22.113  | 23.8997   | 30.873  |
+| 1.9099        | 4.0   | 252  | 2.7197          | 26.5565 | 11.2255 | 22.6026 | 24.5495   | 31.524  |
+| 1.8007        | 5.0   | 315  | 2.7479          | 26.9743 | 11.4843 | 22.9863 | 24.9284   | 33.854  |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter-summarization/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "config_id": "9076f36a74755ac4",
+  "hidden_size": 768,
+  "model_class": "T5AdapterModel",
+  "model_name": "LazarusNLP/IndoNanoT5-base",
+  "model_type": "t5",
+  "name": "adapter-summarization",
+  "version": "0.2.2"
+}

adapter-summarization/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157f55283d533f2213775379fe44234bb1afad0db6d6da897ab4dddf016ce09f
+size 7192982

default/head_config.json

@@ -0,0 +1,18 @@
+{
+  "config": {
+    "activation_function": null,
+    "bias": false,
+    "head_type": "seq2seq_lm",
+    "label2id": null,
+    "layer_norm": false,
+    "layers": 1,
+    "shift_labels": false,
+    "vocab_size": 32128
+  },
+  "hidden_size": 768,
+  "model_class": "T5AdapterModel",
+  "model_name": "LazarusNLP/IndoNanoT5-base",
+  "model_type": "t5",
+  "name": "default",
+  "version": "0.2.2"
+}

default/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7630bc8df260791f15a81368176459211beed1769c6d484b76571a0f8d85a9e
+size 98698515