Training in progress epoch 0

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: andriipasternak/my_model
+  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. -->
+
+# andriipasternak/my_model
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 4.9296
+- Validation Loss: 3.1682
+- Train Accuracy: 0.2764
+- 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': 2480, '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 |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 4.9296     | 3.1682          | 0.2764         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- TensorFlow 2.15.0
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,113 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "no_relation",
+    "1": "org:alternate_names",
+    "2": "org:city_of_headquarters",
+    "3": "org:country_of_headquarters",
+    "4": "org:dissolved",
+    "5": "org:founded",
+    "6": "org:founded_by",
+    "7": "org:member_of",
+    "8": "org:members",
+    "9": "org:number_of_employees/members",
+    "10": "org:parents",
+    "11": "org:political/religious_affiliation",
+    "12": "org:shareholders",
+    "13": "org:stateorprovince_of_headquarters",
+    "14": "org:subsidiaries",
+    "15": "org:top_members/employees",
+    "16": "org:website",
+    "17": "per:age",
+    "18": "per:alternate_names",
+    "19": "per:cause_of_death",
+    "20": "per:charges",
+    "21": "per:children",
+    "22": "per:cities_of_residence",
+    "23": "per:city_of_birth",
+    "24": "per:city_of_death",
+    "25": "per:countries_of_residence",
+    "26": "per:country_of_birth",
+    "27": "per:country_of_death",
+    "28": "per:date_of_birth",
+    "29": "per:date_of_death",
+    "30": "per:employee_of",
+    "31": "per:origin",
+    "32": "per:other_family",
+    "33": "per:parents",
+    "34": "per:religion",
+    "35": "per:schools_attended",
+    "36": "per:siblings",
+    "37": "per:spouse",
+    "38": "per:stateorprovince_of_birth",
+    "39": "per:stateorprovince_of_death",
+    "40": "per:stateorprovinces_of_residence",
+    "41": "per:title",
+    "42": "per:identity"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "no_relation": 0,
+    "org:alternate_names": 1,
+    "org:city_of_headquarters": 2,
+    "org:country_of_headquarters": 3,
+    "org:dissolved": 4,
+    "org:founded": 5,
+    "org:founded_by": 6,
+    "org:member_of": 7,
+    "org:members": 8,
+    "org:number_of_employees/members": 9,
+    "org:parents": 10,
+    "org:political/religious_affiliation": 11,
+    "org:shareholders": 12,
+    "org:stateorprovince_of_headquarters": 13,
+    "org:subsidiaries": 14,
+    "org:top_members/employees": 15,
+    "org:website": 16,
+    "per:age": 17,
+    "per:alternate_names": 18,
+    "per:cause_of_death": 19,
+    "per:charges": 20,
+    "per:children": 21,
+    "per:cities_of_residence": 22,
+    "per:city_of_birth": 23,
+    "per:city_of_death": 24,
+    "per:countries_of_residence": 25,
+    "per:country_of_birth": 26,
+    "per:country_of_death": 27,
+    "per:date_of_birth": 28,
+    "per:date_of_death": 29,
+    "per:employee_of": 30,
+    "per:identity": 42,
+    "per:origin": 31,
+    "per:other_family": 32,
+    "per:parents": 33,
+    "per:religion": 34,
+    "per:schools_attended": 35,
+    "per:siblings": 36,
+    "per:spouse": 37,
+    "per:stateorprovince_of_birth": 38,
+    "per:stateorprovince_of_death": 39,
+    "per:stateorprovinces_of_residence": 40,
+    "per:title": 41
+  },
+  "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": "4.38.1",
+  "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 sha256:8fe9a6e2453301234c1ae0525c47e4bd567160b5e33f4055452ee424553b72a6
+size 268077760

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": 128,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}