End of training

README.md

@@ -0,0 +1,158 @@
+---
+license: mit
+base_model: facebook/bart-large-cnn
+tags:
+- generated_from_trainer
+model-index:
+- name: bart-large-cnn-finetuned-prompt_generation
+  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-prompt_generation
+
+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: 1.8970
+- Map: 0.7119
+- Ndcg@10: 0.8169
+
+## 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: 3e-07
+- 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: 100
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Map    | Ndcg@10 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| No log        | 1.0   | 4    | 3.0497          | 0.2577 | 0.4542  |
+| No log        | 2.0   | 8    | 3.0207          | 0.2563 | 0.4531  |
+| No log        | 3.0   | 12   | 2.9998          | 0.2563 | 0.4531  |
+| No log        | 4.0   | 16   | 2.9299          | 0.2563 | 0.4531  |
+| No log        | 5.0   | 20   | 2.8971          | 0.2577 | 0.4542  |
+| No log        | 6.0   | 24   | 2.8682          | 0.2577 | 0.4542  |
+| No log        | 7.0   | 28   | 2.8340          | 0.2577 | 0.4542  |
+| No log        | 8.0   | 32   | 2.7096          | 0.2577 | 0.4542  |
+| No log        | 9.0   | 36   | 2.6644          | 0.2577 | 0.4542  |
+| No log        | 10.0  | 40   | 2.6361          | 0.2577 | 0.4542  |
+| No log        | 11.0  | 44   | 2.6026          | 0.2577 | 0.4542  |
+| No log        | 12.0  | 48   | 2.5729          | 0.2577 | 0.4542  |
+| No log        | 13.0  | 52   | 2.5500          | 0.2577 | 0.4542  |
+| No log        | 14.0  | 56   | 2.5108          | 0.2577 | 0.4542  |
+| No log        | 15.0  | 60   | 2.4473          | 0.2577 | 0.4542  |
+| No log        | 16.0  | 64   | 2.3941          | 0.2708 | 0.4626  |
+| No log        | 17.0  | 68   | 2.3544          | 0.3326 | 0.5333  |
+| No log        | 18.0  | 72   | 2.3221          | 0.3326 | 0.5333  |
+| No log        | 19.0  | 76   | 2.2970          | 0.3326 | 0.5333  |
+| No log        | 20.0  | 80   | 2.2762          | 0.3813 | 0.5865  |
+| No log        | 21.0  | 84   | 2.2560          | 0.3813 | 0.5865  |
+| No log        | 22.0  | 88   | 2.2345          | 0.4076 | 0.6002  |
+| No log        | 23.0  | 92   | 2.2151          | 0.4076 | 0.6002  |
+| No log        | 24.0  | 96   | 2.1989          | 0.4076 | 0.6002  |
+| No log        | 25.0  | 100  | 2.1844          | 0.4076 | 0.6002  |
+| No log        | 26.0  | 104  | 2.1719          | 0.4076 | 0.6002  |
+| No log        | 27.0  | 108  | 2.1597          | 0.4076 | 0.6002  |
+| No log        | 28.0  | 112  | 2.1485          | 0.4076 | 0.6002  |
+| No log        | 29.0  | 116  | 2.1376          | 0.4076 | 0.6002  |
+| No log        | 30.0  | 120  | 2.1268          | 0.4076 | 0.6002  |
+| No log        | 31.0  | 124  | 2.1169          | 0.4076 | 0.6002  |
+| No log        | 32.0  | 128  | 2.1075          | 0.4076 | 0.6002  |
+| No log        | 33.0  | 132  | 2.0984          | 0.4076 | 0.6002  |
+| No log        | 34.0  | 136  | 2.0899          | 0.4751 | 0.6664  |
+| No log        | 35.0  | 140  | 2.0816          | 0.4751 | 0.6664  |
+| No log        | 36.0  | 144  | 2.0739          | 0.4751 | 0.6664  |
+| No log        | 37.0  | 148  | 2.0661          | 0.4751 | 0.6664  |
+| No log        | 38.0  | 152  | 2.0581          | 0.4751 | 0.6664  |
+| No log        | 39.0  | 156  | 2.0504          | 0.4751 | 0.6664  |
+| No log        | 40.0  | 160  | 2.0436          | 0.4751 | 0.6664  |
+| No log        | 41.0  | 164  | 2.0362          | 0.5569 | 0.7126  |
+| No log        | 42.0  | 168  | 2.0293          | 0.5569 | 0.7126  |
+| No log        | 43.0  | 172  | 2.0226          | 0.5569 | 0.7126  |
+| No log        | 44.0  | 176  | 2.0162          | 0.5569 | 0.7126  |
+| No log        | 45.0  | 180  | 2.0103          | 0.6018 | 0.7455  |
+| No log        | 46.0  | 184  | 2.0039          | 0.7313 | 0.8296  |
+| No log        | 47.0  | 188  | 1.9983          | 0.7313 | 0.8296  |
+| No log        | 48.0  | 192  | 1.9931          | 0.7313 | 0.8296  |
+| No log        | 49.0  | 196  | 1.9883          | 0.7313 | 0.8296  |
+| No log        | 50.0  | 200  | 1.9832          | 0.7313 | 0.8296  |
+| No log        | 51.0  | 204  | 1.9787          | 0.7313 | 0.8296  |
+| No log        | 52.0  | 208  | 1.9751          | 0.7313 | 0.8296  |
+| No log        | 53.0  | 212  | 1.9710          | 0.7313 | 0.8296  |
+| No log        | 54.0  | 216  | 1.9660          | 0.7313 | 0.8296  |
+| No log        | 55.0  | 220  | 1.9627          | 0.7313 | 0.8296  |
+| No log        | 56.0  | 224  | 1.9586          | 0.7313 | 0.8296  |
+| No log        | 57.0  | 228  | 1.9550          | 0.7313 | 0.8296  |
+| No log        | 58.0  | 232  | 1.9514          | 0.7313 | 0.8296  |
+| No log        | 59.0  | 236  | 1.9480          | 0.7313 | 0.8296  |
+| No log        | 60.0  | 240  | 1.9448          | 0.7313 | 0.8296  |
+| No log        | 61.0  | 244  | 1.9421          | 0.7313 | 0.8296  |
+| No log        | 62.0  | 248  | 1.9386          | 0.7313 | 0.8296  |
+| No log        | 63.0  | 252  | 1.9358          | 0.7313 | 0.8296  |
+| No log        | 64.0  | 256  | 1.9330          | 0.7313 | 0.8296  |
+| No log        | 65.0  | 260  | 1.9309          | 0.7313 | 0.8296  |
+| No log        | 66.0  | 264  | 1.9284          | 0.7313 | 0.8296  |
+| No log        | 67.0  | 268  | 1.9266          | 0.7313 | 0.8296  |
+| No log        | 68.0  | 272  | 1.9246          | 0.7313 | 0.8296  |
+| No log        | 69.0  | 276  | 1.9225          | 0.7313 | 0.8296  |
+| No log        | 70.0  | 280  | 1.9207          | 0.7313 | 0.8296  |
+| No log        | 71.0  | 284  | 1.9195          | 0.7313 | 0.8296  |
+| No log        | 72.0  | 288  | 1.9174          | 0.7680 | 0.8517  |
+| No log        | 73.0  | 292  | 1.9158          | 0.7680 | 0.8517  |
+| No log        | 74.0  | 296  | 1.9142          | 0.7680 | 0.8517  |
+| No log        | 75.0  | 300  | 1.9124          | 0.7680 | 0.8517  |
+| No log        | 76.0  | 304  | 1.9112          | 0.7680 | 0.8517  |
+| No log        | 77.0  | 308  | 1.9095          | 0.7680 | 0.8517  |
+| No log        | 78.0  | 312  | 1.9083          | 0.7680 | 0.8517  |
+| No log        | 79.0  | 316  | 1.9071          | 0.7119 | 0.8169  |
+| No log        | 80.0  | 320  | 1.9059          | 0.7119 | 0.8169  |
+| No log        | 81.0  | 324  | 1.9053          | 0.7119 | 0.8169  |
+| No log        | 82.0  | 328  | 1.9044          | 0.7119 | 0.8169  |
+| No log        | 83.0  | 332  | 1.9035          | 0.7119 | 0.8169  |
+| No log        | 84.0  | 336  | 1.9028          | 0.7119 | 0.8169  |
+| No log        | 85.0  | 340  | 1.9019          | 0.7119 | 0.8169  |
+| No log        | 86.0  | 344  | 1.9013          | 0.7119 | 0.8169  |
+| No log        | 87.0  | 348  | 1.9006          | 0.7119 | 0.8169  |
+| No log        | 88.0  | 352  | 1.9001          | 0.7119 | 0.8169  |
+| No log        | 89.0  | 356  | 1.8997          | 0.7119 | 0.8169  |
+| No log        | 90.0  | 360  | 1.8989          | 0.7119 | 0.8169  |
+| No log        | 91.0  | 364  | 1.8989          | 0.7119 | 0.8169  |
+| No log        | 92.0  | 368  | 1.8982          | 0.7119 | 0.8169  |
+| No log        | 93.0  | 372  | 1.8983          | 0.7119 | 0.8169  |
+| No log        | 94.0  | 376  | 1.8979          | 0.7119 | 0.8169  |
+| No log        | 95.0  | 380  | 1.8980          | 0.7680 | 0.8517  |
+| No log        | 96.0  | 384  | 1.8973          | 0.7119 | 0.8169  |
+| No log        | 97.0  | 388  | 1.8973          | 0.7680 | 0.8517  |
+| No log        | 98.0  | 392  | 1.8971          | 0.7119 | 0.8169  |
+| No log        | 99.0  | 396  | 1.8968          | 0.7119 | 0.8169  |
+| No log        | 100.0 | 400  | 1.8970          | 0.7119 | 0.8169  |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</s>": 2,
+  "<mask>": 50264,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}

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": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "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": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec97fa429a81e2e6842f013b4f57f52eb3c332f43f86146051d689cb16f0124
+size 1625537293

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "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:dbe3bc38dc3d765e4f7923913fd5664574fa18527907dd3b9370247dbe6c0336
+size 4283