Upload retrain-full joint intent+NER model

encoder/config.json

@@ -0,0 +1,30 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.1.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80cf0f07931d2f2a9587ceaba78b6a1cde1ee35c3be50d4a042d24cea6dc2613
+size 1420394320

heads.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3594808fed1a86bfaca39596352f6811f15badfca870a627068e9fb6ab1b9e
+size 84361

joint_config.json

@@ -0,0 +1,9 @@
+{
+  "num_intents": 5,
+  "num_ner_labels": 15,
+  "intent_loss_weight": 0.6000000000000001,
+  "ner_loss_weight": 0.3999999999999999,
+  "classifier_dropout": null,
+  "hidden_size": 1024,
+  "hidden_dropout_prob": 0.1
+}

label_config.json

@@ -0,0 +1,50 @@
+{
+  "label2id": {
+    "O": 0,
+    "B-PRODUCT": 1,
+    "I-PRODUCT": 2,
+    "B-QUANTITY": 3,
+    "I-QUANTITY": 4,
+    "B-UNIT": 5,
+    "I-UNIT": 6,
+    "B-DELIVERY_METHOD": 7,
+    "I-DELIVERY_METHOD": 8,
+    "B-DELIVERY_DATE": 9,
+    "I-DELIVERY_DATE": 10,
+    "B-ADDRESS": 11,
+    "I-ADDRESS": 12,
+    "B-TANK_SILO": 13,
+    "I-TANK_SILO": 14
+  },
+  "id2label": {
+    "0": "O",
+    "1": "B-PRODUCT",
+    "2": "I-PRODUCT",
+    "3": "B-QUANTITY",
+    "4": "I-QUANTITY",
+    "5": "B-UNIT",
+    "6": "I-UNIT",
+    "7": "B-DELIVERY_METHOD",
+    "8": "I-DELIVERY_METHOD",
+    "9": "B-DELIVERY_DATE",
+    "10": "I-DELIVERY_DATE",
+    "11": "B-ADDRESS",
+    "12": "I-ADDRESS",
+    "13": "B-TANK_SILO",
+    "14": "I-TANK_SILO"
+  },
+  "intent2id": {
+    "create_order": 0,
+    "edit_order": 1,
+    "confirm": 2,
+    "reject": 3,
+    "help": 4
+  },
+  "id2intent": {
+    "0": "create_order",
+    "1": "edit_order",
+    "2": "confirm",
+    "3": "reject",
+    "4": "help"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_results.json

@@ -0,0 +1,26 @@
+{
+  "retrain_full": true,
+  "train_size": 450,
+  "test_results": {
+    "eval_loss": 0.07978741824626923,
+    "eval_ner_precision": 0.9270833333333334,
+    "eval_ner_recall": 0.9518716577540107,
+    "eval_ner_f1": 0.9393139841688656,
+    "eval_intent_accuracy": 1.0,
+    "eval_intent_f1": 1.0,
+    "eval_f1": 0.9696569920844328,
+    "eval_runtime": 1.1246,
+    "eval_samples_per_second": 44.461,
+    "eval_steps_per_second": 6.225,
+    "epoch": 5.0
+  },
+  "best_hyperparameters": {
+    "learning_rate": 5e-05,
+    "num_train_epochs": 5,
+    "weight_decay": 0.01,
+    "per_device_train_batch_size": 8,
+    "warmup_ratio": 0.2,
+    "loss_alpha": 0.6000000000000001,
+    "freeze_layers": 0
+  }
+}