Model save

README.md

@@ -0,0 +1,82 @@
+---
+license: mit
+base_model: facebook/bart-large-cnn
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: bart-large-cnn-finetuned-scope-summarization
+  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. -->
+
+# bart-large-cnn-finetuned-scope-summarization
+
+This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0626
+- Rouge1: 71.1924
+- Rouge2: 56.5743
+- Rougel: 58.4583
+- Rougelsum: 58.5974
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
+| 1.2505        | 1.0   | 13   | 0.6728          | 42.395  | 24.0426 | 32.0348 | 32.0715   |
+| 0.6526        | 2.0   | 26   | 0.5205          | 48.8672 | 34.9826 | 40.7332 | 40.7674   |
+| 0.5492        | 3.0   | 39   | 0.4153          | 54.2423 | 40.876  | 44.9622 | 44.9886   |
+| 0.4827        | 4.0   | 52   | 0.3740          | 53.5596 | 39.3867 | 44.9257 | 45.057    |
+| 0.4119        | 5.0   | 65   | 0.3762          | 52.0881 | 36.8225 | 40.5069 | 40.4043   |
+| 0.3804        | 6.0   | 78   | 0.2344          | 57.5203 | 43.3466 | 46.4542 | 46.4936   |
+| 0.3039        | 7.0   | 91   | 0.2151          | 57.6824 | 41.4977 | 45.5073 | 45.5051   |
+| 0.2578        | 8.0   | 104  | 0.1730          | 61.3858 | 47.3075 | 52.4419 | 52.3631   |
+| 0.2457        | 9.0   | 117  | 0.1536          | 64.3023 | 49.3955 | 52.6827 | 52.7162   |
+| 0.1829        | 10.0  | 130  | 0.0971          | 66.5754 | 50.3852 | 55.1851 | 55.2008   |
+| 0.1417        | 11.0  | 143  | 0.0924          | 68.1503 | 52.7339 | 57.7043 | 57.8818   |
+| 0.0868        | 12.0  | 156  | 0.0604          | 71.9267 | 58.4041 | 63.0512 | 63.4469   |
+| 0.071         | 13.0  | 169  | 0.0762          | 65.9864 | 50.9967 | 55.1759 | 55.5074   |
+| 0.0494        | 14.0  | 182  | 0.0393          | 65.5931 | 51.3148 | 58.276  | 58.1242   |
+| 0.0455        | 15.0  | 195  | 0.0660          | 70.7603 | 58.125  | 64.1561 | 64.1192   |
+| 0.0348        | 16.0  | 208  | 0.0579          | 69.4807 | 55.6829 | 60.014  | 60.1088   |
+| 0.0267        | 17.0  | 221  | 0.0711          | 73.3778 | 58.7117 | 58.6246 | 58.8468   |
+| 0.0235        | 18.0  | 234  | 0.0643          | 73.5436 | 58.5648 | 58.4584 | 58.6235   |
+| 0.0207        | 19.0  | 247  | 0.0665          | 72.4756 | 57.2448 | 59.1107 | 59.2048   |
+| 0.0177        | 20.0  | 260  | 0.0626          | 71.1924 | 56.5743 | 58.4583 | 58.5974   |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "facebook/bart-large-cnn",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "pretraining_tp": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "use_cache": false,
+  "vocab_size": 50264
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "min_length": 56,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.38.1",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c31906da7aae2488e6e9356f0310bc8d4f8e1434a3d149d5a222d0f59e1b3ce
+size 1625422896

runs/Feb26_11-57-25_n32kzn262d/events.out.tfevents.1708948968.n32kzn262d.530.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d4356d3b12c87b4fe8b6043d45dabc3e92a430d03226c839708a6fcf9d38d9
+size 19940

runs/Feb26_11-57-25_n32kzn262d/events.out.tfevents.1708949527.n32kzn262d.530.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcfa4219a42b2e5fd8dfff38b13d93e8b49345736383bd985f0de47a8cd3d8c
+size 514

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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>",
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee54766065f691ab4aafe531cc926f6e9c064796a9a93c8566a511141812fda5
+size 5112