add model

.gitignore

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

README.md

@@ -0,0 +1,79 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- gem
+model_index:
+- name: BART-large-commongen
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: gem
+      type: gem
+      args: common_gen
+---
+
+<!-- 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-commongen
+
+This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the gem dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1409
+- Spice: 0.4009
+
+## 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: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 6317
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Spice  |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 10.1086       | 0.05  | 100  | 4.9804          | 0.3736 |
+| 4.4168        | 0.09  | 200  | 2.4402          | 0.4079 |
+| 1.8158        | 0.14  | 300  | 1.1096          | 0.4258 |
+| 1.1723        | 0.19  | 400  | 1.0845          | 0.4086 |
+| 1.0894        | 0.24  | 500  | 1.0727          | 0.423  |
+| 1.0949        | 0.28  | 600  | 1.0889          | 0.4224 |
+| 1.0773        | 0.33  | 700  | 1.0977          | 0.4201 |
+| 1.0708        | 0.38  | 800  | 1.1157          | 0.4213 |
+| 1.0663        | 0.43  | 900  | 1.1798          | 0.421  |
+| 1.0985        | 0.47  | 1000 | 1.1611          | 0.4025 |
+| 1.0561        | 0.52  | 1100 | 1.1048          | 0.421  |
+| 1.0594        | 0.57  | 1200 | 1.2044          | 0.3626 |
+| 1.0689        | 0.62  | 1300 | 1.1409          | 0.4009 |
+
+
+### Framework versions
+
+- Transformers 4.9.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.1.dev0
+- Tokenizers 0.10.3

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": "4.9.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f13ae44fe605b9066dc4fa481814ae881fc988dbd345020a647940b7013d0cf
+size 1625557313

runs/Aug10_01-25-30_00a1331a14d4/1628558732.8448944/events.out.tfevents.1628558732.00a1331a14d4.63.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f9fdd51f539ae1c2bfa56015c895afe85ca449fbf9ef012e3ca328f8151aed
+size 4341

runs/Aug10_01-25-30_00a1331a14d4/events.out.tfevents.1628558732.00a1331a14d4.63.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c2b19850f95752cb0e7828810b9121593eb43b3ea680381945334ba4612ffe
+size 10590

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"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703d6b1b5bb420bf93fc87d8862790d0fde2264a87ca44b4bd4d4a4e796d2e4d
+size 2735