Upload TFBertForTokenClassification

README.md

@@ -0,0 +1,74 @@
+---
+license: cc-by-4.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: constituency-brackets-20
+  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. -->
+
+# constituency-brackets-20
+
+This model is a fine-tuned version of [allegro/herbert-base-cased](https://huggingface.co/allegro/herbert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.2020
+- Train Acc: 0.9356
+- Validation Loss: 0.2929
+- Validation Acc: 0.9120
+- Epoch: 19
+
+## 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': 5e-06, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Acc | Validation Loss | Validation Acc | Epoch |
+|:----------:|:---------:|:---------------:|:--------------:|:-----:|
+| 2.4703     | 0.3783    | 1.4719          | 0.5858         | 0     |
+| 1.2149     | 0.6600    | 0.8922          | 0.7269         | 1     |
+| 0.8721     | 0.7343    | 0.6914          | 0.7779         | 2     |
+| 0.7186     | 0.7715    | 0.6028          | 0.8037         | 3     |
+| 0.6239     | 0.7987    | 0.5427          | 0.8240         | 4     |
+| 0.5432     | 0.8342    | 0.4469          | 0.8677         | 5     |
+| 0.4521     | 0.8665    | 0.4092          | 0.8760         | 6     |
+| 0.4100     | 0.8761    | 0.3867          | 0.8819         | 7     |
+| 0.3792     | 0.8855    | 0.3761          | 0.8849         | 8     |
+| 0.3526     | 0.8926    | 0.3469          | 0.8938         | 9     |
+| 0.3304     | 0.8981    | 0.3433          | 0.8944         | 10    |
+| 0.3091     | 0.9049    | 0.3329          | 0.8977         | 11    |
+| 0.2935     | 0.9081    | 0.3178          | 0.9028         | 12    |
+| 0.2769     | 0.9138    | 0.3140          | 0.9032         | 13    |
+| 0.2614     | 0.9173    | 0.2994          | 0.9114         | 14    |
+| 0.2472     | 0.9213    | 0.2954          | 0.9128         | 15    |
+| 0.2344     | 0.9260    | 0.2899          | 0.9142         | 16    |
+| 0.2229     | 0.9292    | 0.2971          | 0.9092         | 17    |
+| 0.2136     | 0.9322    | 0.2872          | 0.9143         | 18    |
+| 0.2020     | 0.9356    | 0.2929          | 0.9120         | 19    |
+
+
+### Framework versions
+
+- Transformers 4.26.0
+- TensorFlow 2.9.2
+- Datasets 2.8.0
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,151 @@
+{
+  "_name_or_path": "allegro/herbert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59",
+    "60": "LABEL_60"
+  },
+  "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_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "HerbertTokenizerFast",
+  "transformers_version": "4.26.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1bd9a0ad0888cd183cafd1a4d3577d6a183660574a133c9e86469eb9b90959
+size 495870140