End of training

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert-base-cased-massive_intent
+  results: []
+---
+
+<!-- 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. -->
+
+# bert-base-cased-massive_intent
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.1321
+- Accuracy: 0.3453
+
+## 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: 5e-06
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 46
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 3.5633        | 1.0   | 720  | 3.1321          | 0.3453   |
+
+
+### Framework versions
+
+- Transformers 4.37.1
+- Pytorch 2.2.0
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,151 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "4.37.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

logs/events.out.tfevents.1709292293.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e06b1954fc3d99d0b1d7349307832303b44cb61510f6da6380566f927edf211
+size 6896

logs/events.out.tfevents.1709292472.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd758ac08162f2ecdc3a5ee38001f72b293ec64bfd6225f426ca0695cb05d06
+size 6859

logs/events.out.tfevents.1709292683.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddfd72700d896abbdb72ef1f010e6b8c5b0da573efd12be54986c35a45f7650c
+size 7053

logs/events.out.tfevents.1709292894.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067dcb41534546add85400c242cbf730bbf71d447eeb111b34dd184f1c457d1b
+size 7053

logs/events.out.tfevents.1709293218.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe256810cbf00e151911171f7f5316779b4dbc71cd2ae33d282866ce083a33ff
+size 7053

logs/events.out.tfevents.1709294191.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da319e1531bdb1d2ec510ebf2e3d09aee0b8e22f7fccbb2ab9f0e4be8e624f7d
+size 7053

logs/events.out.tfevents.1709294468.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96528de63b097d6b31f780f6ff579ed58fb4270f45ffc22b9fa977b2b1f8662a
+size 7678

logs/events.out.tfevents.1709294666.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f27aa57418eff6163016c447413b5372c50c4fbb6be4914d2270b56d7f934d
+size 311

logs/events.out.tfevents.1709294786.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2383df78167d95d8f2d5102d75eb7f7c8f0a9d38c6a61d8ecf35bb449f2699a7
+size 7730

logs/events.out.tfevents.1709294920.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bc2c4d7f3fe61e1ef52108c2f6dd5510d786892840c6ffecacf512432154c7
+size 363

logs/events.out.tfevents.1709295150.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:973d4fa26f1fdd5c3b2fb525b9c7377c2c75d959f09544067866c4dd72ed197d
+size 7730

logs/events.out.tfevents.1709295269.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8011bb3c2bf3f1eb2efa11f79051ed9eb10b83db679ef276ef0c1337681bb8a0
+size 363

logs/events.out.tfevents.1709295584.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cf35f7ceb30c27f3ad399dbfa106d90890c9bc0fbfd026bdbf62bb9210c3e2
+size 7730

logs/events.out.tfevents.1709295760.ws-l6-002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c20b006557d3744af7f9d0c26ede09dc8cdc27dbefd3c571608ce464f1c4233d
+size 363

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336a5b8f91586201f45fba6848feac41b97780579f209450277f5813a7ea5293
+size 433449176

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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9051fba05387158362365f746b1165c23be9202ef0de0e95f99926dc48907be
+size 4728