update

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-ingredient",
+    "2": "I-ingredient",
+    "3": "B-cuisines",
+    "4": "I-cuisines",
+    "5": "B-mealcourse",
+    "6": "I-mealcourse",
+    "7": "B-occasion",
+    "8": "I-occasion",
+    "9": "B-negingredient",
+    "10": "I-negingredient"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "O": 0,
+    "B-ingredient": 1,
+    "I-ingredient": 2,
+    "B-cuisines": 3,
+    "I-cuisines": 4,
+    "B-mealcourse": 5,
+    "I-mealcourse": 6,
+    "B-occasion": 7,
+    "I-occasion": 8,
+    "B-negingredient": 9,
+    "I-negingredient": 10
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aaa106b596bf146b07ee85fbc1e15575f34501bc2f3e5f43d9f6f2fd8933b44
+size 871325677

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c693bc5d09c75088a36d63f322ffe90ad3cc9fd53b6cc5f94cc0dc37455dcf2
+size 435688951

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5fb3f4436c973df6fb302d0480ffe1b20333cf69429d61af1afb5e22f796ec7
+size 14657

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a102214d010cb666fc5e022e6b9d3c9b8d55623bcf457c19b2f5d915d0dda011
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.244646333549643,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.837767683322518e-05,
+      "loss": 0.1601,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.6755353666450355e-05,
+      "loss": 0.0226,
+      "step": 1000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.5133030499675535e-05,
+      "loss": 0.0105,
+      "step": 1500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.3510707332900715e-05,
+      "loss": 0.0054,
+      "step": 2000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.1888384166125895e-05,
+      "loss": 0.0084,
+      "step": 2500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.0266060999351075e-05,
+      "loss": 0.0071,
+      "step": 3000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.864373783257625e-05,
+      "loss": 0.0055,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.702141466580143e-05,
+      "loss": 0.0024,
+      "step": 4000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.539909149902661e-05,
+      "loss": 0.0054,
+      "step": 4500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 3.377676833225179e-05,
+      "loss": 0.0043,
+      "step": 5000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.215444516547697e-05,
+      "loss": 0.0065,
+      "step": 5500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 3.053212199870215e-05,
+      "loss": 0.0046,
+      "step": 6000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 2.890979883192732e-05,
+      "loss": 0.0015,
+      "step": 6500
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.72874756651525e-05,
+      "loss": 0.0015,
+      "step": 7000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 2.5665152498377677e-05,
+      "loss": 0.0005,
+      "step": 7500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 2.4042829331602857e-05,
+      "loss": 0.0011,
+      "step": 8000
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 2.2420506164828034e-05,
+      "loss": 0.0032,
+      "step": 8500
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 2.0798182998053214e-05,
+      "loss": 0.003,
+      "step": 9000
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 1.9175859831278394e-05,
+      "loss": 0.0017,
+      "step": 9500
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 1.755353666450357e-05,
+      "loss": 0.0017,
+      "step": 10000
+    }
+  ],
+  "max_steps": 15410,
+  "num_train_epochs": 5,
+  "total_flos": 1496781631024068.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ab8435bb882b5a5015f0fffa023605cc64a255c18c7fa9947970060a57ab39
+size 2607