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-3
+  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-3
+
+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: 0.7173
+- Rouge1: 0.456
+- Rouge2: 0.0
+- Rougel: 0.457
+- Rougelsum: 0.4597
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 2.4275        | 1.0   | 892  | 1.2781          | 0.1861 | 0.0    | 0.1881 | 0.1893    | 1.0     |
+| 1.5017        | 2.0   | 1784 | 0.9698          | 0.2767 | 0.0    | 0.2791 | 0.2749    | 1.0     |
+| 1.1964        | 3.0   | 2676 | 0.8235          | 0.2852 | 0.0    | 0.2836 | 0.2837    | 1.0     |
+| 1.0261        | 4.0   | 3568 | 0.7468          | 0.4923 | 0.0    | 0.491  | 0.4914    | 1.0     |
+| 0.9195        | 5.0   | 4460 | 0.7173          | 0.456  | 0.0    | 0.457  | 0.4597    | 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:f4376d640e41dd0de9030915dc85d7df122063758e0801402853166bbd22487b
+size 129697852

adapter-summarization/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae99bcfccc67d6527e390a53eb344282ff32c8a7eba5e74b4848170e33f701f
+size 216988098

runs/Jul07_12-00-36_a94680512e46/events.out.tfevents.1720353646.a94680512e46.1958556.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db8bdb1e29cf8f1356e69187c646bdd4ef54fc1a6cf9f39ce817ca741dfbc99
-size 7949
+oid sha256:b03a8a9affba9ddb18079952685a60a197828bb89d237d0bb1886c91de28d36d
+size 9039