add model

.gitignore

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

README.md

@@ -0,0 +1,88 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- gem
+model_index:
+- name: BART-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-commongen
+
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the gem dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1263
+- Spice: 0.4178
+
+## 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  |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 9.0971        | 0.05  | 100  | 4.1336          | 0.3218 |
+| 3.5348        | 0.09  | 200  | 1.5467          | 0.3678 |
+| 1.5099        | 0.14  | 300  | 1.1280          | 0.3821 |
+| 1.2395        | 0.19  | 400  | 1.1178          | 0.3917 |
+| 1.1827        | 0.24  | 500  | 1.0919          | 0.4086 |
+| 1.1545        | 0.28  | 600  | 1.1028          | 0.4035 |
+| 1.1363        | 0.33  | 700  | 1.1021          | 0.4187 |
+| 1.1156        | 0.38  | 800  | 1.1231          | 0.4103 |
+| 1.1077        | 0.43  | 900  | 1.1221          | 0.4117 |
+| 1.0964        | 0.47  | 1000 | 1.1169          | 0.4088 |
+| 1.0704        | 0.52  | 1100 | 1.1143          | 0.4133 |
+| 1.0483        | 0.57  | 1200 | 1.1085          | 0.4058 |
+| 1.0556        | 0.62  | 1300 | 1.1059          | 0.4249 |
+| 1.0343        | 0.66  | 1400 | 1.0992          | 0.4102 |
+| 1.0123        | 0.71  | 1500 | 1.1126          | 0.4104 |
+| 1.0108        | 0.76  | 1600 | 1.1140          | 0.4177 |
+| 1.005         | 0.81  | 1700 | 1.1264          | 0.4078 |
+| 0.9822        | 0.85  | 1800 | 1.1256          | 0.4158 |
+| 0.9918        | 0.9   | 1900 | 1.1345          | 0.4118 |
+| 0.9664        | 0.95  | 2000 | 1.1087          | 0.4073 |
+| 0.9532        | 1.0   | 2100 | 1.1217          | 0.4063 |
+| 0.8799        | 1.04  | 2200 | 1.1229          | 0.4115 |
+| 0.8665        | 1.09  | 2300 | 1.1263          | 0.4178 |
+
+
+### Framework versions
+
+- Transformers 4.9.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.1.dev0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "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": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "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 sha256:52ea4feded6288d8744f4aca916b90bded2e42592889eaf6d68e8367f12354b8
+size 557979193

runs/Aug09_21-33-49_fa8375b74541/1628544834.0341637/events.out.tfevents.1628544834.fa8375b74541.61.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678e1038f9e1eff5c5743b15ecfbc3c259f8f7c5e26566026d8f231be90692ca
+size 4317

runs/Aug09_21-33-49_fa8375b74541/events.out.tfevents.1628544834.fa8375b74541.61.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb84111af615c31f99c895ef951904d1b45615c34f0b90b2a1e761a8a341b200
+size 15362

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-base", "tokenizer_class": "BartTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbbe5ea35b2856ba5b764d962e2bc7f7ff889311a2cf5539d0924ffab2258765
+size 2735