Upload TFDistilBertForSequenceClassification

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Regression_bert_10
+  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. -->
+
+# Regression_bert_10
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.0535
+- Train Mae: 0.2673
+- Train Mse: 0.1031
+- Train R2-score: 0.6896
+- Validation Loss: 0.1142
+- Validation Mae: 0.3549
+- Validation Mse: 0.1957
+- Validation R2-score: 0.9230
+- Epoch: 9
+
+## 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': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Mae | Train Mse | Train R2-score | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Epoch |
+|:----------:|:---------:|:---------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-----:|
+| 0.2988     | 0.4759    | 0.3361    | 0.6079         | 0.1967          | 0.3939         | 0.2542         | 0.9026              | 0     |
+| 0.1715     | 0.4010    | 0.2357    | 0.6812         | 0.1680          | 0.4014         | 0.2478         | 0.9049              | 1     |
+| 0.0903     | 0.3374    | 0.1532    | 0.8384         | 0.1354          | 0.3432         | 0.1971         | 0.9210              | 2     |
+| 0.0636     | 0.3139    | 0.1272    | 0.4117         | 0.1538          | 0.4066         | 0.2304         | 0.9034              | 3     |
+| 0.0746     | 0.3142    | 0.1294    | 0.9220         | 0.1184          | 0.3589         | 0.2015         | 0.9224              | 4     |
+| 0.0604     | 0.2837    | 0.1119    | 0.9439         | 0.1268          | 0.3450         | 0.1994         | 0.9209              | 5     |
+| 0.0556     | 0.2660    | 0.1049    | 0.6002         | 0.1193          | 0.3037         | 0.1704         | 0.9265              | 6     |
+| 0.0541     | 0.2581    | 0.1007    | 0.8081         | 0.1125          | 0.3350         | 0.1743         | 0.9229              | 7     |
+| 0.0532     | 0.2679    | 0.1044    | 0.8917         | 0.1109          | 0.3131         | 0.1757         | 0.9311              | 8     |
+| 0.0535     | 0.2673    | 0.1031    | 0.6896         | 0.1142          | 0.3549         | 0.1957         | 0.9230              | 9     |
+
+
+### Framework versions
+
+- Transformers 4.27.4
+- TensorFlow 2.12.0
+- Datasets 2.11.0
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.27.4",
+  "vocab_size": 30522
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab8b0c5ef7767beadbb5bfe7350db1dd91ea125f9ab621787415b1e0a167d76
+size 267948736