End of training

README.md

@@ -0,0 +1,83 @@
+---
+license: mit
+base_model: facebook/bart-large-cnn
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+- bleu
+model-index:
+- name: HealthScienceBARTPrincipal
+  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. -->
+
+# HealthScienceBARTPrincipal
+
+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: 3.8639
+- Rouge1: 57.9681
+- Rouge2: 23.5702
+- Rougel: 42.298
+- Rougelsum: 54.4306
+- Bertscore Precision: 83.6132
+- Bertscore Recall: 84.9752
+- Bertscore F1: 84.2861
+- Bleu: 0.1834
+- Gen Len: 234.8649
+
+## 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  |
+|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------------------:|:----------------:|:------------:|:------:|:--------:|
+| 5.8822        | 0.0826 | 100  | 5.6709          | 48.7438 | 17.0806 | 33.6533 | 45.9891   | 80.2777             | 82.0236          | 81.1384      | 0.1276 | 234.8898 |
+| 5.2537        | 0.1653 | 200  | 5.1160          | 48.5934 | 17.8578 | 34.7839 | 45.8306   | 80.2943             | 82.3539          | 81.3073      | 0.1358 | 234.8898 |
+| 4.8915        | 0.2479 | 300  | 4.7665          | 53.8863 | 19.5528 | 37.1095 | 50.6262   | 81.6835             | 83.1962          | 82.4302      | 0.1499 | 234.8898 |
+| 4.6879        | 0.3305 | 400  | 4.5500          | 53.0399 | 20.3314 | 38.0481 | 49.3041   | 81.2912             | 83.6329          | 82.4409      | 0.1582 | 234.8898 |
+| 4.4472        | 0.4131 | 500  | 4.3787          | 55.7809 | 21.4354 | 39.5787 | 52.1713   | 82.3882             | 84.0466          | 83.2062      | 0.1663 | 234.8898 |
+| 4.4391        | 0.4958 | 600  | 4.2267          | 55.0551 | 21.5312 | 39.9051 | 51.3866   | 82.1951             | 84.1433          | 83.1541      | 0.1686 | 234.8898 |
+| 4.386         | 0.5784 | 700  | 4.1013          | 56.2812 | 22.3834 | 40.9161 | 52.93     | 82.9407             | 84.4308          | 83.6764      | 0.1738 | 234.8898 |
+| 4.198         | 0.6610 | 800  | 4.0168          | 56.3251 | 22.6045 | 41.1441 | 52.8715   | 83.2275             | 84.6518          | 83.931       | 0.1762 | 234.8898 |
+| 3.9607        | 0.7436 | 900  | 3.9377          | 57.4072 | 22.9187 | 41.6959 | 53.899    | 83.4352             | 84.8095          | 84.1141      | 0.1787 | 234.8898 |
+| 3.9771        | 0.8263 | 1000 | 3.8963          | 58.1506 | 23.5231 | 42.1596 | 54.4019   | 83.6132             | 85.0153          | 84.3057      | 0.1842 | 234.8898 |
+| 3.8807        | 0.9089 | 1100 | 3.8447          | 57.9746 | 23.8219 | 42.4743 | 54.4461   | 83.6303             | 85.03            | 84.3217      | 0.1867 | 234.8898 |
+| 4.0011        | 0.9915 | 1200 | 3.8214          | 58.2153 | 23.8513 | 42.5964 | 54.7631   | 83.7005             | 85.0498          | 84.3672      | 0.1867 | 234.8898 |
+
+
+### 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 sha256:6b53764db00a1bf06e24f47580d5f6a8fd88b6935fec0ffbe51eae4b441003c6
+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:fe5ee8ac1fb678a18010b9da6837b982c8f7c322af33678dd95b5cd1876af76f
+size 5112