Training complete

README.md

@@ -0,0 +1,78 @@
+---
+tags:
+- summarization
+- generated_from_trainer
+model-index:
+- name: led-risalah_data_v2
+  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. -->
+
+# led-risalah_data_v2
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7850
+- Rouge1 Precision: 0.816
+- Rouge1 Recall: 0.2149
+- Rouge1 Fmeasure: 0.3393
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Rouge1 Fmeasure | Rouge1 Precision | Rouge1 Recall |
+|:-------------:|:-------:|:----:|:---------------:|:---------------:|:----------------:|:-------------:|
+| 2.4163        | 0.9143  | 8    | 1.9482          | 0.2001          | 0.4982           | 0.1254        |
+| 1.6578        | 1.9429  | 17   | 1.8076          | 0.2489          | 0.6295           | 0.1554        |
+| 1.656         | 2.9143  | 24   | 1.4664          | 0.2459          | 0.6118           | 0.154         |
+| 1.5142        | 3.9429  | 33   | 1.4191          | 0.2546          | 0.646            | 0.159         |
+| 1.4169        | 4.9714  | 42   | 1.4162          | 0.27            | 0.6675           | 0.1698        |
+| 1.4123        | 6.9143  | 56   | 1.3197          | 0.2807          | 0.7054           | 0.1755        |
+| 1.3398        | 7.9429  | 65   | 1.3156          | 0.2797          | 0.6912           | 0.1759        |
+| 1.146         | 8.9714  | 74   | 1.3247          | 0.2925          | 0.728            | 0.1834        |
+| 1.1481        | 10.0    | 83   | 1.3366          | 0.2739          | 0.6799           | 0.1718        |
+| 1.2033        | 10.9143 | 91   | 1.3387          | 0.2789          | 0.69             | 0.1752        |
+| 1.0855        | 11.9429 | 100  | 1.3375          | 0.2888          | 0.7146           | 0.1814        |
+| 0.999         | 12.9714 | 109  | 1.3589          | 0.2922          | 0.7265           | 0.1831        |
+| 1.0034        | 14.0    | 118  | 1.3601          | 0.2872          | 0.7157           | 0.1801        |
+| 0.9831        | 14.9143 | 126  | 1.3762          | 0.2851          | 0.7024           | 0.1792        |
+| 0.9347        | 15.9429 | 135  | 1.3743          | 0.2769          | 0.6841           | 0.174         |
+| 0.9018        | 16.9714 | 144  | 1.3820          | 0.2862          | 0.7139           | 0.1797        |
+| 0.8939        | 18.0    | 153  | 1.3841          | 0.2879          | 0.7134           | 0.1806        |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "/content/gdrive/My Drive/SKRIPSI/finetune/checkpoint/led/checkpoint-160",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 2.0,
+  "max_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
+  "max_length": 1024,
+  "min_length": 124,
+  "model_type": "led",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 2,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": false,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 128,
+  "min_length": 40,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.3",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8574722055b3e7d86ca3aac6504872a4d22a9f59e71da012ff1679da327e8d
+size 647614116

runs/Jul05_00-23-28_40eb1f705b7a/events.out.tfevents.1720139078.40eb1f705b7a.34047.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6326fa2b3afbc5272b132eedb5f5c02041770c382fe59c1329b16bdf445aa7bd
+size 6030

runs/Jul05_00-23-28_40eb1f705b7a/events.out.tfevents.1720139197.40eb1f705b7a.34047.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bead1435fa84c174362aa5718506022f9f6f41e8c6088776d43b1dde75c1cc21
+size 535

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 16384,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "LEDTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557020ae8ca68806a6a67105fb65284c09bcb03f330ff16d8bcd6f48c296c936
+size 5304