End of training

README.md

@@ -0,0 +1,75 @@
+---
+license: mit
+base_model: facebook/bart-large-cnn
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: bart_CNN_NLP
+  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_CNN_NLP
+
+This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.0479
+- Rouge1: 45.8751
+- Rouge2: 28.1917
+- Rougel: 42.0922
+- Rougelsum: 41.9934
+- Gen Len: 6433791.8333
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 4
+- label_smoothing_factor: 0.1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len      |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:------------:|
+| 3.1748        | 0.4   | 40   | 3.1564          | 44.8208 | 26.6733 | 41.2873 | 41.226    | 6433791.8889 |
+| 3.0649        | 0.8   | 80   | 2.9386          | 45.8469 | 27.8327 | 41.8543 | 41.8139   | 6433791.8556 |
+| 2.6983        | 1.2   | 120  | 2.8712          | 47.7681 | 29.8568 | 43.9396 | 43.8816   | 6433791.8778 |
+| 2.6725        | 1.6   | 160  | 2.8698          | 46.6433 | 29.2504 | 43.1299 | 43.0348   | 6433791.9333 |
+| 2.7537        | 2.0   | 200  | 2.8534          | 47.0645 | 29.6233 | 43.5479 | 43.4841   | 6433791.8778 |
+| 2.3728        | 2.4   | 240  | 2.9305          | 46.1673 | 28.848  | 42.6293 | 42.5577   | 6433791.8889 |
+| 2.3572        | 2.8   | 280  | 2.9414          | 47.2408 | 29.4202 | 43.4668 | 43.3747   | 6433791.9    |
+| 2.087         | 3.2   | 320  | 3.0366          | 46.652  | 28.7844 | 42.7646 | 42.6204   | 6433791.8778 |
+| 2.1212        | 3.6   | 360  | 3.0169          | 46.6902 | 28.1997 | 42.5114 | 42.4226   | 6433791.8222 |
+| 2.1264        | 4.0   | 400  | 3.0479          | 45.8751 | 28.1917 | 42.0922 | 41.9934   | 6433791.8333 |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

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": "4.39.3",
+  "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": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8e694f5c43432045cbb0e46401f4ae4b14f7d8ef2b63c5bc31f2542aafab98
+size 1625422896

runs/Apr27_10-40-47_dac0803a1b2d/events.out.tfevents.1714214491.dac0803a1b2d.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b224888b107a8d0ed43dda1eb3a57b3289d28810305f6540b6d0b3b2cbcba364
+size 11078

runs/Apr27_13-11-09_dac0803a1b2d/events.out.tfevents.1714223507.dac0803a1b2d.5846.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4383e1fb73073582ff7722ed42a922f9a66bd6e5782a4f8823f8353cbc63cdff
+size 5577

runs/Apr27_13-12-07_dac0803a1b2d/events.out.tfevents.1714223528.dac0803a1b2d.5846.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e69b45a998df609dc0c577c3f3fb6bc538d1125b3f5dc839916c2f2bd7b2443
+size 5577

runs/Apr27_14-35-18_dac0803a1b2d/events.out.tfevents.1714228525.dac0803a1b2d.7049.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5bf254c6f64d7f7ff1b62e4bb1fa7fc513517f682fbbefe7cb8dab51cf569f4
+size 7328

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
+    },
+    "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": "<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 sha256:631aeeb0ec57ad71e18458557cbaf9cd921b4351be1dd99aba60d88d3dae5120
+size 4856