Training in progress epoch 0

README.md

@@ -0,0 +1,54 @@
+---
+base_model: bert-base-chinese
+tags:
+- generated_from_keras_callback
+model-index:
+- name: AIYIYA/my_wr1
+  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. -->
+
+# AIYIYA/my_wr1
+
+This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 2.9423
+- Validation Loss: 2.5705
+- Train Accuracy: 0.1842
+- 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 30, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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 |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 2.9423     | 2.5705          | 0.1842         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- TensorFlow 2.12.0
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "bert-base-chinese",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\u5176\u4ed6",
+    "1": "\u59d3\u540d",
+    "2": "\u8eab\u4efd\u8bc1\u53f7",
+    "3": "\u624b\u673a\u53f7",
+    "4": "\u5730\u5740",
+    "5": "\u90ae\u7bb1",
+    "6": "QQ",
+    "7": "\u82f1\u6587\u59d3",
+    "8": "\u516c\u53f8\u540d\u79f0",
+    "9": "\u8054\u7cfb\u4eba\u59d3\u540d",
+    "10": "\u7edf\u4e00\u793e\u4f1a\u4fe1\u7528\u4ee3\u7801",
+    "11": "\u90ae\u7f16",
+    "12": "\u5b57\u6bcd",
+    "13": "\u6c49\u5b57",
+    "14": "\u786e\u8ba4\u5bc6\u7801",
+    "15": "\u7528\u6237\u540d",
+    "16": "\u5bc6\u7801",
+    "17": "\u524d\u7aef\u9a8c\u8bc1\u7801",
+    "18": "\u52a8\u6001\u9a8c\u8bc1\u7801",
+    "19": "\u4f20\u771f",
+    "20": "\u6635\u79f0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "QQ": 6,
+    "\u4f20\u771f": 19,
+    "\u516c\u53f8\u540d\u79f0": 8,
+    "\u5176\u4ed6": 0,
+    "\u524d\u7aef\u9a8c\u8bc1\u7801": 17,
+    "\u52a8\u6001\u9a8c\u8bc1\u7801": 18,
+    "\u5730\u5740": 4,
+    "\u59d3\u540d": 1,
+    "\u5b57\u6bcd": 12,
+    "\u5bc6\u7801": 16,
+    "\u624b\u673a\u53f7": 3,
+    "\u6635\u79f0": 20,
+    "\u6c49\u5b57": 13,
+    "\u7528\u6237\u540d": 15,
+    "\u786e\u8ba4\u5bc6\u7801": 14,
+    "\u7edf\u4e00\u793e\u4f1a\u4fe1\u7528\u4ee3\u7801": 10,
+    "\u8054\u7cfb\u4eba\u59d3\u540d": 9,
+    "\u82f1\u6587\u59d3": 7,
+    "\u8eab\u4efd\u8bc1\u53f7": 2,
+    "\u90ae\u7bb1": 5,
+    "\u90ae\u7f16": 11
+  },
+  "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": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

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:d69301950701e734a86070603fe8933538fe10b68e04c669cfb7fd4872ec8f5b
+size 409423204

tokenizer_config.json

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