Training in progress, epoch 2

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: shibing624/text2vec-base-chinese
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ch_text_001
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# ch_text_001
+
+This model is a fine-tuned version of [shibing624/text2vec-base-chinese](https://huggingface.co/shibing624/text2vec-base-chinese) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0765
+- Accuracy: 0.9867
+
+## 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:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0733        | 1.0   | 2125 | 0.0785          | 0.9848   |
+| 0.0533        | 2.0   | 4250 | 0.0765          | 0.9867   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cpu
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "shibing624/text2vec-base-chinese",
+  "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": "\u8fdd\u6cd5\u60ac\u6302\u5e7f\u544a\u724c\u533e",
+    "1": "\u5e7f\u544a\u62db\u724c\u7834\u635f",
+    "2": "\u975e\u6cd5\u6d82\u5199\u5f20\u8d34\u5c0f\u5e7f\u544a",
+    "3": "\u9053\u8def\u7834\u635f",
+    "4": "\u4ea4\u901a\u62a4\u680f",
+    "5": "\u673a\u52a8\u8f66\u4e71\u505c\u653e",
+    "6": "\u8def\u706f",
+    "7": "\u5176\u5b83\u8857\u9762\u79e9\u5e8f\u95ee\u9898",
+    "8": "\u8fdd\u6cd5\u5360\u9053\u5e7f\u544a\u724c",
+    "9": "\u65bd\u5de5\u5360\u9053(\u65bd\u5de5\u7ef4\u62a4\u810f\u4e71\u5dee)",
+    "10": "\u5e97\u5916\u7ecf\u8425",
+    "11": "\u64c5\u81ea\u9972\u517b\u5bb6\u79bd\u5bb6\u755c",
+    "12": "\u65bd\u5de5\u5e9f\u5f03\u6599",
+    "13": "\u65e0\u7167\u7ecf\u8425\u6e38\u5546",
+    "14": "\u6cbf\u8857\u667e\u6302",
+    "15": "\u66b4\u9732\u5783\u573e",
+    "16": "\u4e71\u5806\u7269\u5806\u6599"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u4e71\u5806\u7269\u5806\u6599": 16,
+    "\u4ea4\u901a\u62a4\u680f": 4,
+    "\u5176\u5b83\u8857\u9762\u79e9\u5e8f\u95ee\u9898": 7,
+    "\u5e7f\u544a\u62db\u724c\u7834\u635f": 1,
+    "\u5e97\u5916\u7ecf\u8425": 10,
+    "\u64c5\u81ea\u9972\u517b\u5bb6\u79bd\u5bb6\u755c": 11,
+    "\u65bd\u5de5\u5360\u9053(\u65bd\u5de5\u7ef4\u62a4\u810f\u4e71\u5dee)": 9,
+    "\u65bd\u5de5\u5e9f\u5f03\u6599": 12,
+    "\u65e0\u7167\u7ecf\u8425\u6e38\u5546": 13,
+    "\u66b4\u9732\u5783\u573e": 15,
+    "\u673a\u52a8\u8f66\u4e71\u505c\u653e": 5,
+    "\u6cbf\u8857\u667e\u6302": 14,
+    "\u8def\u706f": 6,
+    "\u8fdd\u6cd5\u5360\u9053\u5e7f\u544a\u724c": 8,
+    "\u8fdd\u6cd5\u60ac\u6302\u5e7f\u544a\u724c\u533e": 0,
+    "\u9053\u8def\u7834\u635f": 3,
+    "\u975e\u6cd5\u6d82\u5199\u5f20\u8d34\u5c0f\u5e7f\u544a": 2
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f720c97725329014da2abb4bc0aa3a635379beaa3debf94362cd9107609059b
+size 409146380

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e265f413731753501560e6ab85bfd3382558114f8e6a5574b7dce9e7e0568044
+size 4728