Training complete

README.md

@@ -0,0 +1,79 @@
+---
+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: 1.6785
+- Rouge1 Precision: 0.6665
+- Rouge1 Recall: 0.1816
+- Rouge1 Fmeasure: 0.284
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------------:|:----------------:|:-------------:|
+| 2.4597        | 0.91  | 8    | 1.8034          | 0.1951          | 0.4699           | 0.1246        |
+| 1.7706        | 1.94  | 17   | 1.6403          | 0.2451          | 0.6043           | 0.1554        |
+| 1.5072        | 2.97  | 26   | 1.5947          | 0.2628          | 0.6236           | 0.1676        |
+| 1.4018        | 4.0   | 35   | 1.5688          | 0.2789          | 0.656            | 0.1782        |
+| 1.2761        | 4.91  | 43   | 1.5454          | 0.2723          | 0.6434           | 0.1736        |
+| 1.1779        | 5.94  | 52   | 1.5636          | 0.2889          | 0.6794           | 0.1843        |
+| 1.1235        | 6.97  | 61   | 1.5430          | 0.2965          | 0.6913           | 0.1902        |
+| 1.0529        | 8.0   | 70   | 1.5639          | 0.2829          | 0.6705           | 0.1805        |
+| 0.9883        | 8.91  | 78   | 1.5740          | 0.2817          | 0.6757           | 0.1798        |
+| 0.9274        | 9.94  | 87   | 1.5793          | 0.2771          | 0.6623           | 0.1764        |
+| 0.925         | 10.97 | 96   | 1.6072          | 0.2821          | 0.665            | 0.18          |
+| 0.858         | 12.0  | 105  | 1.6129          | 0.284           | 0.6625           | 0.1817        |
+| 0.8182        | 12.91 | 113  | 1.6396          | 0.2765          | 0.6567           | 0.1761        |
+| 0.7974        | 13.94 | 122  | 1.6445          | 0.2759          | 0.659            | 0.1759        |
+| 0.7524        | 14.97 | 131  | 1.6585          | 0.2763          | 0.6585           | 0.1759        |
+| 0.7743        | 16.0  | 140  | 1.6779          | 0.2788          | 0.6594           | 0.1779        |
+| 0.7486        | 16.91 | 148  | 1.6742          | 0.2851          | 0.6666           | 0.1819        |
+| 0.676         | 17.94 | 157  | 1.6790          | 0.2859          | 0.6707           | 0.1827        |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "./finetune/led-risalah-v8/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": 512,
+  "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": "4.35.2",
+  "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": "4.35.2",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9f86bbc5d77d6b29fa22d06d245e67157e9757223f836341ed8db933e65d48
+size 647614116

runs/Jul06_08-23-13_nzkc792nrx/events.out.tfevents.1720254202.nzkc792nrx.2603.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44ef8fd053a9b05b1f06c72c86c5cfca5886e034db9bc292f4e3a740b5ebd47
+size 5385

runs/Jul06_08-23-13_nzkc792nrx/events.out.tfevents.1720254343.nzkc792nrx.2603.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22ae82b29238a8eaf0e101c05af139c300ff8b081abbfde755dd7e4fbaf2fa9
+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:bb02c0b12ac7b4a1b203a33bb9f7e802a45ee7527f656dce5b85c2e2442c7f4f
+size 4728