Upload TFDistilBertForSequenceClassification

README.md

@@ -1,62 +1,63 @@
----
-library_name: transformers
-license: apache-2.0
-base_model: distilbert-base-uncased
-tags:
-- generated_from_keras_callback
-model-index:
-- name: tl-test-learn-prompt-classifier
-  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. -->
-
-# tl-test-learn-prompt-classifier
-
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the [reddgr/tl-test-learn-prompts](https://huggingface.co/datasets/reddgr/tl-test-learn-prompts) dataset.
-It achieves the following results on the evaluation set:
-- Train Loss: 0.0794
-- Train Accuracy: 1.0
-- Validation Loss: 0.2381
-- Validation Accuracy: 0.9444
-- Epoch: 5
-
-## 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-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
-- training_precision: float32
-
-### Training results
-
-| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
-|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.6829     | 0.5808         | 0.6541          | 0.7639              | 0     |
-| 0.6315     | 0.7784         | 0.5824          | 0.8472              | 1     |
-| 0.4975     | 0.9222         | 0.4382          | 0.8889              | 2     |
-| 0.3094     | 0.9521         | 0.3303          | 0.9028              | 3     |
-| 0.1684     | 0.9820         | 0.2741          | 0.9028              | 4     |
-| 0.0794     | 1.0            | 0.2381          | 0.9444              | 5     |
-
-
-### Framework versions
-
-- Transformers 4.46.2
-- TensorFlow 2.17.1
-- Datasets 3.1.0
-- Tokenizers 0.20.3
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: tl-test-learn-prompt-classifier
+  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. -->
+
+# tl-test-learn-prompt-classifier
+
+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: 0.2656
+- Train Accuracy: 0.9728
+- Validation Loss: 0.3730
+- Validation Accuracy: 0.8500
+- Epoch: 6
+
+## 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': 5e-06, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
+|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
+| 0.6956     | 0.4728         | 0.6850          | 0.625               | 0     |
+| 0.6722     | 0.6685         | 0.6670          | 0.75                | 1     |
+| 0.6520     | 0.7120         | 0.6367          | 0.6875              | 2     |
+| 0.6002     | 0.8261         | 0.5741          | 0.8000              | 3     |
+| 0.5079     | 0.875          | 0.4797          | 0.8875              | 4     |
+| 0.3805     | 0.9511         | 0.4118          | 0.8250              | 5     |
+| 0.2656     | 0.9728         | 0.3730          | 0.8500              | 6     |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- TensorFlow 2.18.0-dev20240717
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -1,23 +1,23 @@
-{
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
-  "architectures": [
-    "DistilBertForSequenceClassification"
-  ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
-  "initializer_range": 0.02,
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
-  "transformers_version": "4.46.2",
-  "vocab_size": 30522
-}
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.44.2",
+  "vocab_size": 30522
+}

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e00f7f05008e32a7560fa27e954419556dca7d9e562e8ab999922e4d6b9df0
+oid sha256:9341a2e684c8a723f5278c28604a0c759865d15ce9718dc7fcf272fad482f171
 size 267955144