master-mahdi/persian_intent_detection

README.md

@@ -0,0 +1,79 @@
+---
+license: apache-2.0
+base_model: HooshvareLab/bert-fa-base-uncased-clf-persiannews
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: my_model
+  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. -->
+
+# my_model
+
+This model is a fine-tuned version of [HooshvareLab/bert-fa-base-uncased-clf-persiannews](https://huggingface.co/HooshvareLab/bert-fa-base-uncased-clf-persiannews) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8573
+- Accuracy: 0.8695
+
+## 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: 2e-05
+- 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
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 360  | 1.0779          | 0.7772   |
+| 1.8476        | 2.0   | 720  | 0.7038          | 0.8436   |
+| 0.6038        | 3.0   | 1080 | 0.6356          | 0.8490   |
+| 0.6038        | 4.0   | 1440 | 0.6477          | 0.8470   |
+| 0.3037        | 5.0   | 1800 | 0.6521          | 0.8515   |
+| 0.1723        | 6.0   | 2160 | 0.6938          | 0.8554   |
+| 0.1066        | 7.0   | 2520 | 0.6942          | 0.8519   |
+| 0.1066        | 8.0   | 2880 | 0.7426          | 0.8559   |
+| 0.0636        | 9.0   | 3240 | 0.7769          | 0.8549   |
+| 0.0464        | 10.0  | 3600 | 0.8179          | 0.8549   |
+| 0.0464        | 11.0  | 3960 | 0.8457          | 0.8544   |
+| 0.029         | 12.0  | 4320 | 0.8509          | 0.8554   |
+| 0.0241        | 13.0  | 4680 | 0.8534          | 0.8529   |
+| 0.0158        | 14.0  | 5040 | 0.8793          | 0.8549   |
+| 0.0158        | 15.0  | 5400 | 0.9053          | 0.8544   |
+| 0.0131        | 16.0  | 5760 | 0.9009          | 0.8539   |
+| 0.012         | 17.0  | 6120 | 0.9124          | 0.8554   |
+| 0.012         | 18.0  | 6480 | 0.9092          | 0.8549   |
+| 0.0114        | 19.0  | 6840 | 0.9117          | 0.8529   |
+| 0.0079        | 20.0  | 7200 | 0.9129          | 0.8519   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,152 @@
+{
+  "_name_or_path": "HooshvareLab/bert-fa-base-uncased-clf-persiannews",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "persiannews",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "datetime_query",
+    "1": "iot_hue_lightchange",
+    "2": "transport_ticket",
+    "3": "takeaway_query",
+    "4": "qa_stock",
+    "5": "general_greet",
+    "6": "recommendation_events",
+    "7": "music_dislikeness",
+    "8": "iot_wemo_off",
+    "9": "cooking_recipe",
+    "10": "qa_currency",
+    "11": "transport_traffic",
+    "12": "general_quirky",
+    "13": "weather_query",
+    "14": "audio_volume_up",
+    "15": "email_addcontact",
+    "16": "takeaway_order",
+    "17": "email_querycontact",
+    "18": "iot_hue_lightup",
+    "19": "recommendation_locations",
+    "20": "play_audiobook",
+    "21": "lists_createoradd",
+    "22": "news_query",
+    "23": "alarm_query",
+    "24": "iot_wemo_on",
+    "25": "general_joke",
+    "26": "qa_definition",
+    "27": "social_query",
+    "28": "music_settings",
+    "29": "audio_volume_other",
+    "30": "calendar_remove",
+    "31": "iot_hue_lightdim",
+    "32": "calendar_query",
+    "33": "email_sendemail",
+    "34": "iot_cleaning",
+    "35": "audio_volume_down",
+    "36": "play_radio",
+    "37": "cooking_query",
+    "38": "datetime_convert",
+    "39": "qa_maths",
+    "40": "iot_hue_lightoff",
+    "41": "iot_hue_lighton",
+    "42": "transport_query",
+    "43": "music_likeness",
+    "44": "email_query",
+    "45": "play_music",
+    "46": "audio_volume_mute",
+    "47": "social_post",
+    "48": "alarm_set",
+    "49": "qa_factoid",
+    "50": "calendar_set",
+    "51": "play_game",
+    "52": "alarm_remove",
+    "53": "lists_remove",
+    "54": "transport_taxi",
+    "55": "recommendation_movies",
+    "56": "iot_coffee",
+    "57": "music_query",
+    "58": "play_podcasts",
+    "59": "lists_query"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "alarm_query": 23,
+    "alarm_remove": 52,
+    "alarm_set": 48,
+    "audio_volume_down": 35,
+    "audio_volume_mute": 46,
+    "audio_volume_other": 29,
+    "audio_volume_up": 14,
+    "calendar_query": 32,
+    "calendar_remove": 30,
+    "calendar_set": 50,
+    "cooking_query": 37,
+    "cooking_recipe": 9,
+    "datetime_convert": 38,
+    "datetime_query": 0,
+    "email_addcontact": 15,
+    "email_query": 44,
+    "email_querycontact": 17,
+    "email_sendemail": 33,
+    "general_greet": 5,
+    "general_joke": 25,
+    "general_quirky": 12,
+    "iot_cleaning": 34,
+    "iot_coffee": 56,
+    "iot_hue_lightchange": 1,
+    "iot_hue_lightdim": 31,
+    "iot_hue_lightoff": 40,
+    "iot_hue_lighton": 41,
+    "iot_hue_lightup": 18,
+    "iot_wemo_off": 8,
+    "iot_wemo_on": 24,
+    "lists_createoradd": 21,
+    "lists_query": 59,
+    "lists_remove": 53,
+    "music_dislikeness": 7,
+    "music_likeness": 43,
+    "music_query": 57,
+    "music_settings": 28,
+    "news_query": 22,
+    "play_audiobook": 20,
+    "play_game": 51,
+    "play_music": 45,
+    "play_podcasts": 58,
+    "play_radio": 36,
+    "qa_currency": 10,
+    "qa_definition": 26,
+    "qa_factoid": 49,
+    "qa_maths": 39,
+    "qa_stock": 4,
+    "recommendation_events": 6,
+    "recommendation_locations": 19,
+    "recommendation_movies": 55,
+    "social_post": 47,
+    "social_query": 27,
+    "takeaway_order": 16,
+    "takeaway_query": 3,
+    "transport_query": 42,
+    "transport_taxi": 54,
+    "transport_ticket": 2,
+    "transport_traffic": 11,
+    "weather_query": 13
+  },
+  "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": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b911302678e5e6dd525225ad623ac901d6f03fed4a6129311332d38288a14fe
+size 651573488

runs/Jun21_12-18-44_175182b8c458/events.out.tfevents.1718972325.175182b8c458.519.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1476d741d7e126c184a86cd32c0ad717114d89d2d1686694cd4d3e5e8e48568
+size 17861

runs/Jun21_12-18-44_175182b8c458/events.out.tfevents.1718974108.175182b8c458.519.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4a8a1e067708190b1c8b0ebf6188772ff4e9a776d776e2dbe7ed9b9cd57dfd2
+size 411

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "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:c2fda16c315584deeac9425f075dd91098ee4651864ae11ece96f67600533123
+size 5112