Training in progress epoch 0

README.md

@@ -0,0 +1,52 @@
+---
+tags:
+- generated_from_keras_callback
+model-index:
+- name: jabalov/MARBERT-finetuned-arabic-dialects-identification
+  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. -->
+
+# jabalov/MARBERT-finetuned-arabic-dialects-identification
+
+This model is a fine-tuned version of [UBC-NLP/MARBERT](https://huggingface.co/UBC-NLP/MARBERT) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 1.4599
+- Validation Loss: 1.0517
+- 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', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 64431, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 1.4599     | 1.0517          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.15.0
+- TensorFlow 2.6.2
+- Datasets 1.18.4
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "UBC-NLP/MARBERT",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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"
+  },
+  "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_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
+}

logs/train/events.out.tfevents.1646928932.f0feff400231.39.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78cdc908563e9b22a200dc82993d8bba07ff498799cf03f5afe99b4a1b4a0ad9
+size 2746220

logs/train/events.out.tfevents.1646928960.f0feff400231.profile-empty

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08bc3b7eaec73cba0ec39db43b82860a8f27dee0741d53220caa484ead766dc0
+size 40

logs/train/plugins/profile/2022_03_10_16_16_00/f0feff400231.input_pipeline.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62cb28195dcd59e5eedd8955fd4c13e0cf6f17fc05660502bdfcfd722e83fb63
+size 3066

logs/train/plugins/profile/2022_03_10_16_16_00/f0feff400231.kernel_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5cce8bc302c305d3326960e47355f42a1b921610520a73e78ec56906e3bfa2
+size 327917

logs/train/plugins/profile/2022_03_10_16_16_00/f0feff400231.memory_profile.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd030b80803dd5dc6fba4efa09a7bd66bee4be5703d92e0b2145339e0734aaba
+size 40338

logs/train/plugins/profile/2022_03_10_16_16_00/f0feff400231.overview_page.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5607a1a77b7371516bd24d904e63beacf6cb7fb519d57da5387fab7e0adc361f
+size 5386

logs/train/plugins/profile/2022_03_10_16_16_00/f0feff400231.tensorflow_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2dcfa04ce2ee7901ffd22b426a94707bc2fa7f941d6143e775b8085b3ad5843
+size 189081

logs/train/plugins/profile/2022_03_10_16_16_00/f0feff400231.trace.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142851932388a99d16b0c15a20602f42dc71243df00e01bc9127af8b457f857c
+size 273976

logs/train/plugins/profile/2022_03_10_16_16_00/f0feff400231.xplane.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17bdbdb5635f255759d180f1f5212b27d97661f7e2e321ffe3de81ed37404c36
+size 2140639

logs/validation/events.out.tfevents.1646932172.f0feff400231.39.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67eb7088c43c6bfcdf4c459fb6931fabfb6212446a902dcf720333381d97726e
+size 195

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd96a2e54e98f4b344220333f67ca545cd26964535fc077f2aaf6308744ea81
+size 651708824

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": null, "name_or_path": "UBC-NLP/MARBERT", "tokenizer_class": "BertTokenizer"}