Training in progress epoch 0

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: vedantjumle/bert
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# vedantjumle/bert
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 2.2958
+- Validation Loss: 1.1168
+- Train Accuracy: 0.7712
+- Epoch: 0
+
+## 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:
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 23250, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Train Accuracy | Epoch |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 2.2958     | 1.1168          | 0.7712         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- TensorFlow 2.13.0
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,147 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "alarm_query": 15,
+    "alarm_remove": 14,
+    "alarm_set": 0,
+    "audio_volume_down": 23,
+    "audio_volume_mute": 1,
+    "audio_volume_other": 26,
+    "audio_volume_up": 28,
+    "calendar_query": 7,
+    "calendar_remove": 52,
+    "calendar_set": 38,
+    "cooking_query": 50,
+    "cooking_recipe": 35,
+    "datetime_convert": 12,
+    "datetime_query": 11,
+    "email_addcontact": 56,
+    "email_query": 48,
+    "email_querycontact": 54,
+    "email_sendemail": 43,
+    "general_greet": 10,
+    "general_joke": 24,
+    "general_quirky": 9,
+    "iot_cleaning": 6,
+    "iot_coffee": 27,
+    "iot_hue_lightchange": 2,
+    "iot_hue_lightdim": 5,
+    "iot_hue_lightoff": 3,
+    "iot_hue_lighton": 4,
+    "iot_hue_lightup": 19,
+    "iot_wemo_off": 30,
+    "iot_wemo_on": 29,
+    "lists_createoradd": 55,
+    "lists_query": 46,
+    "lists_remove": 53,
+    "music_dislikeness": 25,
+    "music_likeness": 17,
+    "music_query": 18,
+    "music_settings": 22,
+    "news_query": 16,
+    "play_audiobook": 39,
+    "play_game": 47,
+    "play_music": 8,
+    "play_podcasts": 40,
+    "play_radio": 32,
+    "qa_currency": 59,
+    "qa_definition": 51,
+    "qa_factoid": 36,
+    "qa_maths": 58,
+    "qa_stock": 31,
+    "recommendation_events": 37,
+    "recommendation_locations": 34,
+    "recommendation_movies": 45,
+    "social_post": 33,
+    "social_query": 41,
+    "takeaway_order": 20,
+    "takeaway_query": 13,
+    "transport_query": 42,
+    "transport_taxi": 57,
+    "transport_ticket": 44,
+    "transport_traffic": 49,
+    "weather_query": 21
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": "alarm_set",
+    "1": "audio_volume_mute",
+    "2": "iot_hue_lightchange",
+    "3": "iot_hue_lightoff",
+    "4": "iot_hue_lighton",
+    "5": "iot_hue_lightdim",
+    "6": "iot_cleaning",
+    "7": "calendar_query",
+    "8": "play_music",
+    "9": "general_quirky",
+    "10": "general_greet",
+    "11": "datetime_query",
+    "12": "datetime_convert",
+    "13": "takeaway_query",
+    "14": "alarm_remove",
+    "15": "alarm_query",
+    "16": "news_query",
+    "17": "music_likeness",
+    "18": "music_query",
+    "19": "iot_hue_lightup",
+    "20": "takeaway_order",
+    "21": "weather_query",
+    "22": "music_settings",
+    "23": "audio_volume_down",
+    "24": "general_joke",
+    "25": "music_dislikeness",
+    "26": "audio_volume_other",
+    "27": "iot_coffee",
+    "28": "audio_volume_up",
+    "29": "iot_wemo_on",
+    "30": "iot_wemo_off",
+    "31": "qa_stock",
+    "32": "play_radio",
+    "33": "social_post",
+    "34": "recommendation_locations",
+    "35": "cooking_recipe",
+    "36": "qa_factoid",
+    "37": "recommendation_events",
+    "38": "calendar_set",
+    "39": "play_audiobook",
+    "40": "play_podcasts",
+    "41": "social_query",
+    "42": "transport_query",
+    "43": "email_sendemail",
+    "44": "transport_ticket",
+    "45": "recommendation_movies",
+    "46": "lists_query",
+    "47": "play_game",
+    "48": "email_query",
+    "49": "transport_traffic",
+    "50": "cooking_query",
+    "51": "qa_definition",
+    "52": "calendar_remove",
+    "53": "lists_remove",
+    "54": "email_querycontact",
+    "55": "lists_createoradd",
+    "56": "email_addcontact",
+    "57": "transport_taxi",
+    "58": "qa_maths",
+    "59": "qa_currency"
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.33.2",
+  "vocab_size": 30522
+}

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7ad3ca43079aa0e9a3fbda0c079d56f96e2cb16065bf486dc66d009a0e5eae
+size 268129984

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "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]"
+}