Training complete

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- summarization
+- generated_from_trainer
+model-index:
+- name: led-risalah_data_v7
+  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_v7
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8807
+- Rouge1 Precision: 0.6909
+- Rouge1 Recall: 0.1722
+- Rouge1 Fmeasure: 0.2753
+
+## 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: 5.6e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 Fmeasure | Rouge1 Precision | Rouge1 Recall |
+|:-------------:|:-----:|:----:|:---------------:|:---------------:|:----------------:|:-------------:|
+| 1.7531        | 1.0   | 70   | 1.7163          | 0.2707          | 0.6515           | 0.1714        |
+| 1.4557        | 2.0   | 140  | 1.6342          | 0.2716          | 0.6745           | 0.1705        |
+| 1.132         | 3.0   | 210  | 1.6420          | 0.2784          | 0.686            | 0.175         |
+| 1.0552        | 4.0   | 280  | 1.6372          | 0.2828          | 0.6879           | 0.1786        |
+| 1.0587        | 5.0   | 350  | 1.6587          | 0.2595          | 0.6314           | 0.1637        |
+| 0.7863        | 6.0   | 420  | 1.6967          | 0.2871          | 0.7038           | 0.181         |
+| 0.4577        | 7.0   | 490  | 1.7779          | 0.2717          | 0.6783           | 0.1703        |
+| 0.6156        | 8.0   | 560  | 1.7964          | 0.2637          | 0.6474           | 0.1659        |
+| 0.593         | 9.0   | 630  | 1.8699          | 0.2747          | 0.6797           | 0.1728        |
+| 0.4265        | 10.0  | 700  | 1.8807          | 0.2753          | 0.6909           | 0.1722        |
+
+
+### 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-v7/checkpoint-700",
+  "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 sha256:2eaa1edfd9c2ab4978a842ca1ee1f78a71f56509d67d092c090d85191e15a7f5
+size 647614116

runs/Jul06_04-10-55_n80b4p30zu/events.out.tfevents.1720239067.n80b4p30zu.744.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c93338872fb2e56b260243f3492a3470da0cc8263bd67992b9e45c6213771b8
+size 5394

runs/Jul06_04-10-55_n80b4p30zu/events.out.tfevents.1720239293.n80b4p30zu.744.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeea472eefeb6928f45e33d152c869134705f15df791c9bfccfd7331d9a4e822
+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 sha256:86e78398ab1e5b10bcb3ced4bf09e7a1b3dbbbc614c1e15b8a26b094929bf095
+size 4728