add model

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: celera_relevance
+  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. -->
+
+# celera_relevance
+
+This model is a fine-tuned version of [hfl/chinese-roberta-wwm-ext](https://huggingface.co/hfl/chinese-roberta-wwm-ext) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.3072
+- Train Sparse Categorical Accuracy: 0.8813
+- Validation Loss: 0.4371
+- Validation Sparse Categorical Accuracy: 0.8295
+- Epoch: 2
+
+## 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-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
+|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
+| 0.4060     | 0.8274                            | 0.3665          | 0.8440                                 | 0     |
+| 0.3388     | 0.8594                            | 0.3639          | 0.8585                                 | 1     |
+| 0.3072     | 0.8813                            | 0.4371          | 0.8295                                 | 2     |
+
+
+### Framework versions
+
+- Transformers 4.16.0
+- TensorFlow 2.7.0
+- Datasets 1.18.1
+- Tokenizers 0.11.0

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "hfl/chinese-roberta-wwm-ext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "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": "4.16.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53ac5a060f6638f8bb0238ec4118725b02b36e5bf7860eb602d75e9258d3661
+size 409367900