amazon_intent_finetune_roberta

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: intent-finetuned-intent-detection
+  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. -->
+
+# intent-finetuned-intent-detection
+
+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: 0.6938
+- Accuracy: 0.8638
+- F1: 0.8593
+
+## 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: 64
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 3.0316        | 1.0   | 180  | 1.7788          | 0.6819   | 0.6352 |
+| 1.4515        | 2.0   | 360  | 1.0539          | 0.7956   | 0.7735 |
+| 0.9212        | 3.0   | 540  | 0.8143          | 0.8457   | 0.8382 |
+| 0.6883        | 4.0   | 720  | 0.7246          | 0.8601   | 0.8544 |
+| 0.583         | 5.0   | 900  | 0.6938          | 0.8638   | 0.8593 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

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": "alarm_query",
+    "1": "alarm_remove",
+    "2": "alarm_set",
+    "3": "audio_volume_down",
+    "4": "audio_volume_mute",
+    "5": "audio_volume_other",
+    "6": "audio_volume_up",
+    "7": "calendar_query",
+    "8": "calendar_remove",
+    "9": "calendar_set",
+    "10": "cooking_query",
+    "11": "cooking_recipe",
+    "12": "datetime_convert",
+    "13": "datetime_query",
+    "14": "email_addcontact",
+    "15": "email_query",
+    "16": "email_querycontact",
+    "17": "email_sendemail",
+    "18": "general_greet",
+    "19": "general_joke",
+    "20": "general_quirky",
+    "21": "iot_cleaning",
+    "22": "iot_coffee",
+    "23": "iot_hue_lightchange",
+    "24": "iot_hue_lightdim",
+    "25": "iot_hue_lightoff",
+    "26": "iot_hue_lighton",
+    "27": "iot_hue_lightup",
+    "28": "iot_wemo_off",
+    "29": "iot_wemo_on",
+    "30": "lists_createoradd",
+    "31": "lists_query",
+    "32": "lists_remove",
+    "33": "music_dislikeness",
+    "34": "music_likeness",
+    "35": "music_query",
+    "36": "music_settings",
+    "37": "news_query",
+    "38": "play_audiobook",
+    "39": "play_game",
+    "40": "play_music",
+    "41": "play_podcasts",
+    "42": "play_radio",
+    "43": "qa_currency",
+    "44": "qa_definition",
+    "45": "qa_factoid",
+    "46": "qa_maths",
+    "47": "qa_stock",
+    "48": "recommendation_events",
+    "49": "recommendation_locations",
+    "50": "recommendation_movies",
+    "51": "social_post",
+    "52": "social_query",
+    "53": "takeaway_order",
+    "54": "takeaway_query",
+    "55": "transport_query",
+    "56": "transport_taxi",
+    "57": "transport_ticket",
+    "58": "transport_traffic",
+    "59": "weather_query"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "alarm_query": 0,
+    "alarm_remove": 1,
+    "alarm_set": 2,
+    "audio_volume_down": 3,
+    "audio_volume_mute": 4,
+    "audio_volume_other": 5,
+    "audio_volume_up": 6,
+    "calendar_query": 7,
+    "calendar_remove": 8,
+    "calendar_set": 9,
+    "cooking_query": 10,
+    "cooking_recipe": 11,
+    "datetime_convert": 12,
+    "datetime_query": 13,
+    "email_addcontact": 14,
+    "email_query": 15,
+    "email_querycontact": 16,
+    "email_sendemail": 17,
+    "general_greet": 18,
+    "general_joke": 19,
+    "general_quirky": 20,
+    "iot_cleaning": 21,
+    "iot_coffee": 22,
+    "iot_hue_lightchange": 23,
+    "iot_hue_lightdim": 24,
+    "iot_hue_lightoff": 25,
+    "iot_hue_lighton": 26,
+    "iot_hue_lightup": 27,
+    "iot_wemo_off": 28,
+    "iot_wemo_on": 29,
+    "lists_createoradd": 30,
+    "lists_query": 31,
+    "lists_remove": 32,
+    "music_dislikeness": 33,
+    "music_likeness": 34,
+    "music_query": 35,
+    "music_settings": 36,
+    "news_query": 37,
+    "play_audiobook": 38,
+    "play_game": 39,
+    "play_music": 40,
+    "play_podcasts": 41,
+    "play_radio": 42,
+    "qa_currency": 43,
+    "qa_definition": 44,
+    "qa_factoid": 45,
+    "qa_maths": 46,
+    "qa_stock": 47,
+    "recommendation_events": 48,
+    "recommendation_locations": 49,
+    "recommendation_movies": 50,
+    "social_post": 51,
+    "social_query": 52,
+    "takeaway_order": 53,
+    "takeaway_query": 54,
+    "transport_query": 55,
+    "transport_taxi": 56,
+    "transport_ticket": 57,
+    "transport_traffic": 58,
+    "weather_query": 59
+  },
+  "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f944b2a8df7548d78b2aa5ee0407ac48af719d7c3d926f3cff180f96c994ad8a
+size 433449176

runs/Apr16_11-56-51_0a575836a554/events.out.tfevents.1713268636.0a575836a554.1166.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000d03fbabb37aa6a8191814a88db6eb50591586ec0dfe67349eec826a4ace4a
+size 11159

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 sha256:9f1fbfb9694d30155f9f3afaa711c9a8616d9649f2503545c5bd0dbef60c354f
+size 4984