Model save

README.md

@@ -0,0 +1,81 @@
+---
+base_model: transformer3/H2-keywordextractor
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: H2-keywordextractor-finetuned-scope-summarization
+  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. -->
+
+# H2-keywordextractor-finetuned-scope-summarization
+
+This model is a fine-tuned version of [transformer3/H2-keywordextractor](https://huggingface.co/transformer3/H2-keywordextractor) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0530
+- Rouge1: 27.6565
+- Rouge2: 24.482
+- Rougel: 27.5611
+- Rougelsum: 27.679
+
+## 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: 5.6e-05
+- train_batch_size: 15
+- eval_batch_size: 15
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
+| 1.1006        | 1.0   | 23   | 0.4121          | 21.1334 | 15.2908 | 21.0076 | 21.0354   |
+| 0.4296        | 2.0   | 46   | 0.3515          | 23.1524 | 16.6481 | 23.1602 | 23.1359   |
+| 0.366         | 3.0   | 69   | 0.3156          | 24.2342 | 17.9896 | 24.1637 | 24.1872   |
+| 0.3263        | 4.0   | 92   | 0.2776          | 25.3692 | 20.5006 | 25.2976 | 25.3696   |
+| 0.2951        | 5.0   | 115  | 0.2587          | 25.929  | 21.3159 | 25.7701 | 25.7813   |
+| 0.2798        | 6.0   | 138  | 0.2455          | 27.017  | 23.0395 | 26.8045 | 26.8927   |
+| 0.2495        | 7.0   | 161  | 0.2234          | 27.5471 | 24.2424 | 27.3809 | 27.4542   |
+| 0.2442        | 8.0   | 184  | 0.2100          | 27.1387 | 23.3789 | 27.0447 | 27.141    |
+| 0.2203        | 9.0   | 207  | 0.1937          | 27.4281 | 24.1191 | 27.3809 | 27.4542   |
+| 0.2138        | 10.0  | 230  | 0.1733          | 27.2385 | 23.6012 | 27.1529 | 27.2287   |
+| 0.1921        | 11.0  | 253  | 0.1512          | 27.5491 | 24.2352 | 27.4878 | 27.5915   |
+| 0.1687        | 12.0  | 276  | 0.1339          | 27.5491 | 24.2352 | 27.4878 | 27.5915   |
+| 0.1615        | 13.0  | 299  | 0.1153          | 27.3214 | 23.9474 | 27.2381 | 27.3508   |
+| 0.1367        | 14.0  | 322  | 0.0990          | 27.3214 | 23.8383 | 27.2381 | 27.3508   |
+| 0.1282        | 15.0  | 345  | 0.0845          | 27.3214 | 23.8383 | 27.2381 | 27.3508   |
+| 0.1085        | 16.0  | 368  | 0.0784          | 27.4178 | 24.1053 | 27.3275 | 27.4506   |
+| 0.1018        | 17.0  | 391  | 0.0631          | 27.4471 | 24.1378 | 27.3612 | 27.4531   |
+| 0.085         | 18.0  | 414  | 0.0576          | 27.6565 | 24.482  | 27.5611 | 27.679    |
+| 0.0814        | 19.0  | 437  | 0.0545          | 27.6565 | 24.482  | 27.5611 | 27.679    |
+| 0.0708        | 20.0  | 460  | 0.0530          | 27.6565 | 24.482  | 27.5611 | 27.679    |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "transformer3/H2-keywordextractor",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "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,
+  "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
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.38.2",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e59cbf7a1946d155989146a15398f61611bb82d64d60fa2729e7eaf3e5618487
+size 1625426996

runs/Mar09_19-54-16_n5fn36u3bd/events.out.tfevents.1710014062.n5fn36u3bd.374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea78fb6ddc0076b81c0519f2429e014eb9cebdbbdd1df79ed7d5e457623e585
+size 19885

runs/Mar09_19-54-16_n5fn36u3bd/events.out.tfevents.1710015038.n5fn36u3bd.374.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec46d272a1f1c6a2d96df6f2024798d6fc4a316f160e2aff848a6765d2c1bfa
+size 514

special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,69 @@
+{
+  "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
+    },
+    "131": {
+      "content": ";",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "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>",
+  "max_length": 192,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191a52283965306150907b02097ad74aebf797219a79dff27f12075ac6f90e25
+size 5112