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: HealthScienceBART
+  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. -->
+
+# HealthScienceBART
+
+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: 3.7248
+- Rouge1: 59.8432
+- Rouge2: 25.926
+- Rougel: 44.3683
+- Rougelsum: 56.3382
+- Bertscore Precision: 84.199
+- Bertscore Recall: 85.5429
+- Bertscore F1: 84.8633
+- Bleu: 0.2087
+- Gen Len: 234.8216
+
+## 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  |
+|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------------------:|:----------------:|:------------:|:------:|:--------:|
+| 5.662         | 0.0826 | 100  | 5.4864          | 49.8946 | 18.6145 | 35.6824 | 47.1811   | 80.6966             | 82.5402          | 81.6048      | 0.1476 | 234.8216 |
+| 5.2036        | 0.1653 | 200  | 4.9823          | 52.1848 | 20.4176 | 37.3029 | 48.9924   | 81.1422             | 83.2665          | 82.1871      | 0.1634 | 234.8216 |
+| 4.7061        | 0.2479 | 300  | 4.6422          | 54.5492 | 21.4905 | 38.8501 | 51.1097   | 82.0428             | 83.8584          | 82.9376      | 0.1730 | 234.8216 |
+| 4.657         | 0.3305 | 400  | 4.4252          | 54.072  | 22.1609 | 39.6324 | 50.5966   | 81.9494             | 84.1622          | 83.0371      | 0.1793 | 234.8216 |
+| 4.3613        | 0.4131 | 500  | 4.2631          | 56.8149 | 23.0471 | 40.9892 | 53.0419   | 83.0301             | 84.669           | 83.8388      | 0.1871 | 234.8216 |
+| 4.2804        | 0.4958 | 600  | 4.1142          | 56.8254 | 23.7321 | 41.7326 | 52.8585   | 82.8372             | 84.8241          | 83.8154      | 0.1915 | 234.8216 |
+| 4.2477        | 0.5784 | 700  | 3.9926          | 57.2046 | 23.9303 | 42.3439 | 53.6018   | 83.216              | 84.9845          | 84.0878      | 0.1929 | 234.8216 |
+| 4.1188        | 0.6610 | 800  | 3.9193          | 57.9987 | 24.8441 | 43.1811 | 54.4399   | 83.6075             | 85.2031          | 84.395       | 0.1999 | 234.8216 |
+| 3.8678        | 0.7436 | 900  | 3.8320          | 59.1683 | 25.1465 | 43.4643 | 55.6762   | 83.9212             | 85.315           | 84.6099      | 0.2019 | 234.8216 |
+| 3.8831        | 0.8263 | 1000 | 3.7889          | 59.3948 | 25.4051 | 43.821  | 55.8124   | 84.0802             | 85.4569          | 84.7606      | 0.2044 | 234.8216 |
+| 3.7856        | 0.9089 | 1100 | 3.7498          | 59.535  | 25.6124 | 44.1831 | 56.071    | 84.0653             | 85.4796          | 84.7641      | 0.2063 | 234.8216 |
+| 3.8875        | 0.9915 | 1200 | 3.7248          | 59.8432 | 25.926  | 44.3683 | 56.3382   | 84.199              | 85.5429          | 84.8633      | 0.2087 | 234.8216 |
+
+
+### 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:a0e8225af2ee62d27843ca06a5f2380a64643d5d926fbf07007d24fd071e4315
+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:c65e21597781f75a38f9bec62a275f1a50ce3c469287039cc8cb696ca5ad8213
+size 5112