End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: mit
+base_model: facebook/bart-large-cnn
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+- bleu
+model-index:
+- name: HealthScienceBARTMainSections
+  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. -->
+
+# HealthScienceBARTMainSections
+
+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: 3.8753
+- Rouge1: 57.7808
+- Rouge2: 23.8942
+- Rougel: 42.2385
+- Rougelsum: 54.2817
+- Bertscore Precision: 83.4992
+- Bertscore Recall: 85.0665
+- Bertscore F1: 84.2729
+- Bleu: 0.1888
+- Gen Len: 234.2871
+
+## 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: 16
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Bertscore Precision | Bertscore Recall | Bertscore F1 | Bleu   | Gen Len  |
+|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------------------:|:----------------:|:------------:|:------:|:--------:|
+| 5.7855        | 0.0835 | 100  | 5.6539          | 48.5675 | 17.0972 | 33.6039 | 45.6212   | 80.1089             | 82.0896          | 81.0838      | 0.1318 | 234.2871 |
+| 5.2884        | 0.1671 | 200  | 5.1333          | 51.1112 | 18.5297 | 35.438  | 47.6657   | 80.5123             | 82.7897          | 81.6311      | 0.1454 | 234.2871 |
+| 4.9931        | 0.2506 | 300  | 4.8074          | 52.1485 | 19.5231 | 36.7572 | 48.8489   | 81.0844             | 83.2739          | 82.1612      | 0.1534 | 234.2871 |
+| 4.6538        | 0.3342 | 400  | 4.5657          | 52.6901 | 20.3073 | 37.8168 | 49.4253   | 81.3851             | 83.5259          | 82.438       | 0.1580 | 234.2871 |
+| 4.435         | 0.4177 | 500  | 4.3963          | 54.6727 | 20.9559 | 39.1501 | 51.7226   | 82.5534             | 83.8521          | 83.1954      | 0.1618 | 234.2871 |
+| 4.4327        | 0.5013 | 600  | 4.2367          | 55.3497 | 21.849  | 39.8267 | 51.9765   | 82.6498             | 84.2237          | 83.4265      | 0.1698 | 234.2871 |
+| 4.2704        | 0.5848 | 700  | 4.1312          | 56.2031 | 22.5317 | 40.6962 | 52.8736   | 82.966              | 84.4887          | 83.7178      | 0.1762 | 234.2871 |
+| 4.2211        | 0.6684 | 800  | 4.0373          | 56.1405 | 22.9558 | 41.2482 | 52.772    | 82.9397             | 84.6224          | 83.7695      | 0.1800 | 234.2871 |
+| 4.0727        | 0.7519 | 900  | 3.9672          | 57.5881 | 23.6311 | 41.712  | 53.9676   | 83.2595             | 84.8583          | 84.0486      | 0.1850 | 234.2871 |
+| 4.0741        | 0.8355 | 1000 | 3.9182          | 57.2156 | 23.6916 | 42.074  | 53.7327   | 83.3537             | 84.9605          | 84.1466      | 0.1868 | 234.2871 |
+| 3.8563        | 0.9190 | 1100 | 3.8753          | 57.7808 | 23.8942 | 42.2385 | 54.2817   | 83.4992             | 85.0665          | 84.2729      | 0.1888 | 234.2871 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,70 @@
+{
+  "_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": " ",
+  "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": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50264
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "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": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83737b30cca96da69aa4eaf0bdc0393c483f315ddec2942d17b5024de5428a8f
+size 1625422896

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": "<pad>",
+  "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
+    },
+    "4": {
+      "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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "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 sha256:5cce4d446dd76c3f91b74842d88b6c3fb7f55bb658c81f42a0f49c7cf7a1f659
+size 5112