silmi223/led-risalah_data_v5

README.md

@@ -0,0 +1,68 @@
+---
+base_model: silmi224/finetune-led-35000
+tags:
+- generated_from_trainer
+model-index:
+- name: led-risalah-v5
+  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-v5
+
+This model is a fine-tuned version of [silmi224/finetune-led-35000](https://huggingface.co/silmi224/finetune-led-35000) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5242
+- Rouge1 Precision: 0.676
+- Rouge1 Recall: 0.1721
+- Rouge1 Fmeasure: 0.2728
+
+## 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: 2e-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 Precision | Rouge1 Recall | Rouge1 Fmeasure |
+|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
+| No log        | 1.0   | 70   | 1.6479          | 0.6178           | 0.1618        | 0.2556          |
+| 1.8512        | 2.0   | 140  | 1.5744          | 0.6561           | 0.174         | 0.2745          |
+| 1.4296        | 3.0   | 210  | 1.5595          | 0.6617           | 0.1704        | 0.2702          |
+| 1.4296        | 4.0   | 280  | 1.5402          | 0.685            | 0.1719        | 0.274           |
+| 1.1976        | 5.0   | 350  | 1.5242          | 0.676            | 0.1721        | 0.2728          |
+| 1.0638        | 6.0   | 420  | 1.5383          | 0.6886           | 0.182         | 0.2873          |
+| 1.0638        | 7.0   | 490  | 1.5652          | 0.6636           | 0.1757        | 0.2771          |
+| 0.9657        | 8.0   | 560  | 1.5797          | 0.6788           | 0.172         | 0.2733          |
+| 0.9215        | 9.0   | 630  | 1.5960          | 0.6644           | 0.1715        | 0.2715          |
+| 0.849         | 10.0  | 700  | 1.5943          | 0.6581           | 0.1693        | 0.2681          |
+
+
+### 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": "silmi224/finetune-led-35000",
+  "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 sha256:567b8c7e786dbcc4f46969aaacecd405a60e2ab1256cbcf38f049a551854d6b7
+size 647614116

runs/Jul05_11-48-51_nbzockupae/events.out.tfevents.1720180138.nbzockupae.500.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45cb1789cf3e71732ff3534281704c1079490bef6cb0201f5fbc90184e4a1f20
+size 26907

runs/Jul05_12-54-56_nbzockupae/events.out.tfevents.1720184116.nbzockupae.2385.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2363a471500cd97f81f27cc6af74ff92a45efea9bf11f2fd9fc255fd70c6513d
+size 5049

runs/Jul05_12-59-32_nbzockupae/events.out.tfevents.1720184380.nbzockupae.2575.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76508d3a8a3bf2492d856976d28aa914949bfb1445f1f23edb23106c42e12a8a
+size 5487

runs/Jul05_13-13-16_nbzockupae/events.out.tfevents.1720185203.nbzockupae.2904.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32034d8448888d40a37065a7ba4dcc42e4344cd0257833c007231615f9bd286d
+size 10960

runs/Jul05_13-13-16_nbzockupae/events.out.tfevents.1720190638.nbzockupae.2904.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90377c8b3b47384493f8c2f3df0b1551f30f682c04735eadf5a7471aea25dc8c
+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 sha256:4a7ed6ccdb64551817c2363b283b3ce4c642687c13759f90983b2a39e0621f86
+size 4728