add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: bart-JES-cnn_dailymail
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 43.9753
+---
+
+<!-- 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-JES-cnn_dailymail
+
+This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1452
+- Rouge1: 43.9753
+- Rouge2: 19.7191
+- Rougel: 33.6236
+- Rougelsum: 41.1683
+- Gen Len: 80.1767
+
+## 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-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
+- num_epochs: 6.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:------:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| 1.2949        | 1.0   | 71779  | 1.2080          | 11.7171 | 3.3284 | 11.3209 | 11.4022   | 20.0    |
+| 1.191         | 2.0   | 143558 | 1.1615          | 11.8484 | 3.363  | 11.4175 | 11.5037   | 20.0    |
+| 1.0907        | 3.0   | 215337 | 1.1452          | 12.6221 | 3.773  | 12.1226 | 12.2359   | 20.0    |
+| 0.9798        | 4.0   | 287116 | 1.1670          | 12.4306 | 3.7329 | 11.9497 | 12.0617   | 20.0    |
+| 0.9112        | 5.0   | 358895 | 1.1667          | 12.5404 | 3.7842 | 12.0541 | 12.1643   | 20.0    |
+| 0.8358        | 6.0   | 430674 | 1.1997          | 12.5153 | 3.778  | 12.0382 | 12.1332   | 20.0    |
+
+
+### Framework versions
+
+- Transformers 4.10.2
+- Pytorch 1.7.1+cu110
+- Datasets 1.11.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 6.0,
+    "eval_gen_len": 80.1767,
+    "eval_loss": 1.145164132118225,
+    "eval_rouge1": 43.9753,
+    "eval_rouge2": 19.7191,
+    "eval_rougeL": 33.6236,
+    "eval_rougeLsum": 41.1683,
+    "eval_runtime": 5099.0205,
+    "eval_samples": 13368,
+    "eval_samples_per_second": 2.622,
+    "eval_steps_per_second": 0.655,
+    "train_loss": 1.0701684290170863,
+    "train_runtime": 175298.0292,
+    "train_samples": 287113,
+    "train_samples_per_second": 9.827,
+    "train_steps_per_second": 2.457
+}

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "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,
+  "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": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 6.0,
+    "eval_gen_len": 80.1767,
+    "eval_loss": 1.145164132118225,
+    "eval_rouge1": 43.9753,
+    "eval_rouge2": 19.7191,
+    "eval_rougeL": 33.6236,
+    "eval_rougeLsum": 41.1683,
+    "eval_runtime": 5099.0205,
+    "eval_samples": 13368,
+    "eval_samples_per_second": 2.622,
+    "eval_steps_per_second": 0.655
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9095c5b8aa5d96a2a21944f9677cf99453ea9406d2cb3228ef7936628994911a
+size 1625569391

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large", "tokenizer_class": "BartTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 1.0701684290170863,
+    "train_runtime": 175298.0292,
+    "train_samples": 287113,
+    "train_samples_per_second": 9.827,
+    "train_steps_per_second": 2.457
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55be81e7135318ed2b0a74b08adfa6d0e03818487d6485f123fb229fbd73dd7e
+size 2863