Model save

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: LazarusNLP/IndoNanoT5-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: summarization-lora-4
+  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. -->
+
+# summarization-lora-4
+
+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: 0.5588
+- Rouge1: 0.4494
+- Rouge2: 0.0
+- Rougel: 0.4489
+- Rougelsum: 0.4499
+- Gen Len: 1.0
+
+## 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: 5e-05
+- train_batch_size: 8
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 1.3987        | 1.0   | 1784 | 0.6451          | 0.4474 | 0.0    | 0.4495 | 0.4472    | 1.0     |
+| 0.8591        | 2.0   | 3568 | 0.5834          | 0.4222 | 0.0    | 0.4206 | 0.4228    | 1.0     |
+| 0.7949        | 3.0   | 5352 | 0.5684          | 0.4462 | 0.0    | 0.4449 | 0.4456    | 1.0     |
+| 0.7674        | 4.0   | 7136 | 0.5639          | 0.4564 | 0.0    | 0.4538 | 0.4545    | 1.0     |
+| 0.7542        | 5.0   | 8920 | 0.5588          | 0.4494 | 0.0    | 0.4489 | 0.4499    | 1.0     |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter-summarization/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "config": {
+    "alpha": 8,
+    "architecture": "lora",
+    "attn_matrices": [
+      "q",
+      "v"
+    ],
+    "composition_mode": "add",
+    "dropout": 0.0,
+    "init_weights": "lora",
+    "intermediate_lora": false,
+    "leave_out": [],
+    "output_lora": false,
+    "r": 8,
+    "selfattn_lora": true,
+    "use_gating": false
+  },
+  "config_id": "625403edad0bf919",
+  "hidden_size": 768,
+  "model_class": "T5ForConditionalGeneration",
+  "model_name": "LazarusNLP/IndoNanoT5-base",
+  "model_type": "t5",
+  "name": "adapter-summarization",
+  "version": "0.2.2"
+}

adapter-summarization/head_config.json

@@ -0,0 +1,14 @@
+{
+  "config": null,
+  "hidden_size": 768,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "model_class": "T5ForConditionalGeneration",
+  "model_name": "LazarusNLP/IndoNanoT5-base",
+  "model_type": "t5",
+  "name": null,
+  "num_labels": 2,
+  "version": "0.2.2"
+}

adapter-summarization/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd98521db324850daf705dfa86a70a048f68d35aa11f554edb31d1cea52f2114
+size 3593010

adapter-summarization/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7467a987e0db5b7ef33f0dba6f30173b6f2a0fa4327e8d394e655fc96809b7cf
+size 98698515