model set

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "commercial",
+    "1": "informational",
+    "2": "navigational",
+    "3": "transactional"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "commercial": 0,
+    "informational": 1,
+    "navigational": 2,
+    "transactional": 3
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6042ad7f33e2cd28240dae58a99d89b2237eaebd274e728c9458a0ddc042c4
+size 437964800

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c75a6b450bc6856b9efa37407c87d5ab9eb457371fea70824d8b88abad5b7e
+size 876050682

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d151b2da44011ed91901331fda614b493df60185d53a817a5b8fb4be6d9dfd0d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a762411410f2f14a86aeed76c162d3ff46192e2ef6d916bd9546b9647b0ed801
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": 0.08527446538209915,
+  "best_model_checkpoint": "intent_classification_model_without_metatitle_with_local23/checkpoint-284",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 426,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9573333333333334,
+      "eval_loss": 0.3501805067062378,
+      "eval_runtime": 0.4048,
+      "eval_samples_per_second": 926.3,
+      "eval_steps_per_second": 59.283,
+      "step": 71
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9733333333333334,
+      "eval_loss": 0.10704313218593597,
+      "eval_runtime": 0.3612,
+      "eval_samples_per_second": 1038.224,
+      "eval_steps_per_second": 66.446,
+      "step": 142
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9786666666666667,
+      "eval_loss": 0.08797813951969147,
+      "eval_runtime": 0.3612,
+      "eval_samples_per_second": 1038.207,
+      "eval_steps_per_second": 66.445,
+      "step": 213
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9733333333333334,
+      "eval_loss": 0.08527446538209915,
+      "eval_runtime": 0.3606,
+      "eval_samples_per_second": 1039.951,
+      "eval_steps_per_second": 66.557,
+      "step": 284
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9733333333333334,
+      "eval_loss": 0.0869869589805603,
+      "eval_runtime": 0.3663,
+      "eval_samples_per_second": 1023.807,
+      "eval_steps_per_second": 65.524,
+      "step": 355
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9706666666666667,
+      "eval_loss": 0.09319726377725601,
+      "eval_runtime": 0.3647,
+      "eval_samples_per_second": 1028.233,
+      "eval_steps_per_second": 65.807,
+      "step": 426
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 426,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 44042600979624.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854dcdfa0a077d2a5f762cc90f061504c63b9e546151451bb835bcc35b378359
+size 4664