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-unipelt-2
+  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-unipelt-2
+
+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: 0.6790
+- Rouge1: 0.304
+- Rouge2: 0.0
+- Rougel: 0.3076
+- Rougelsum: 0.3081
+- 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: 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 2.436         | 1.0   | 894  | 1.2680          | 0.0305 | 0.0    | 0.0305 | 0.0305    | 1.0     |
+| 1.5097        | 2.0   | 1788 | 0.9426          | 0.0223 | 0.0    | 0.0223 | 0.0223    | 1.0     |
+| 1.2078        | 3.0   | 2682 | 0.7915          | 0.1643 | 0.0    | 0.1641 | 0.1639    | 1.0     |
+| 1.0371        | 4.0   | 3576 | 0.7170          | 0.2501 | 0.0    | 0.2524 | 0.2507    | 1.0     |
+| 0.9294        | 5.0   | 4470 | 0.6790          | 0.304  | 0.0    | 0.3076 | 0.3081    | 1.0     |
+
+
+### 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 +1,77 @@
+{
+  "config": {
+    "architecture": "union",
+    "configs": [
+      {
+        "architecture": "prefix_tuning",
+        "bottleneck_size": 512,
+        "cross_prefix": true,
+        "dropout": 0.0,
+        "encoder_prefix": true,
+        "flat": false,
+        "leave_out": [],
+        "non_linearity": "tanh",
+        "prefix_length": 10,
+        "shared_gating": true,
+        "use_gating": true
+      },
+      {
+        "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": true
+      },
+      {
+        "alpha": 2,
+        "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": true
+      }
+    ]
+  },
+  "config_id": "67ac4937c601ad56",
+  "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 sha256:8d04229a70b547fc95e881976a844d3baa4472b16810226b30b0d95f7f91a97d
+size 129697852

adapter-summarization/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a697a7b4db70684559ff1160b6afa00a4c227645e27af7d58a85179e387081f5
+size 216988098

runs/Jul07_06-40-51_a94680512e46/events.out.tfevents.1720334460.a94680512e46.1849667.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fde14aa62efa7154d9087f9bf3ab0c7b4788ffb454ee5efe365061e92baf791
-size 7949
+oid sha256:6b7fb583aa3eb2086b1c2e0925d81ab63e8934ddaa145298086ff89ea6b8a484
+size 9039