Upload folder using huggingface_hub

README.md

@@ -0,0 +1,83 @@
+---
+license: mit
+base_model: openai-community/gpt2
+tags:
+- generated_from_keras_callback
+model-index:
+- name: kasrahabib/gpt2-finetuned-iso29148-req-detector
+  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. -->
+
+# kasrahabib/gpt2-finetuned-iso29148-req-detector
+
+This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.1004
+- Validation Loss: 0.5468
+- Epoch: 29
+
+## 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3570, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 3.0225     | 2.8144          | 0     |
+| 2.7666     | 2.7501          | 1     |
+| 2.6971     | 2.6517          | 2     |
+| 2.6218     | 2.4804          | 3     |
+| 2.3698     | 2.0353          | 4     |
+| 1.8887     | 1.4317          | 5     |
+| 1.1104     | 0.8991          | 6     |
+| 0.7810     | 0.8057          | 7     |
+| 0.6463     | 0.6800          | 8     |
+| 0.5507     | 0.6747          | 9     |
+| 0.4679     | 0.6156          | 10    |
+| 0.4313     | 0.6102          | 11    |
+| 0.3696     | 0.5972          | 12    |
+| 0.3365     | 0.5437          | 13    |
+| 0.2866     | 0.5637          | 14    |
+| 0.2492     | 0.5682          | 15    |
+| 0.2392     | 0.5496          | 16    |
+| 0.2029     | 0.6076          | 17    |
+| 0.2062     | 0.5368          | 18    |
+| 0.1898     | 0.5434          | 19    |
+| 0.1670     | 0.5434          | 20    |
+| 0.1682     | 0.5403          | 21    |
+| 0.1650     | 0.5830          | 22    |
+| 0.1326     | 0.5400          | 23    |
+| 0.1366     | 0.5497          | 24    |
+| 0.1148     | 0.5432          | 25    |
+| 0.1263     | 0.5662          | 26    |
+| 0.1171     | 0.5591          | 27    |
+| 0.1075     | 0.5445          | 28    |
+| 0.1004     | 0.5468          | 29    |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- TensorFlow 2.15.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "openai-community/gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForSequenceClassification"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "may_signal_keyword_general_text",
+    "1": "may_signal_keyword_requirement",
+    "2": "may_signal_keyword_srs_text",
+    "3": "must_signal_keyword_general_text",
+    "4": "must_signal_keyword_requirement",
+    "5": "must_signal_keyword_srs_text",
+    "6": "no_signal_keyword_general_text",
+    "7": "no_signal_keyword_srs_text",
+    "8": "shall_signal_keyword_general_text",
+    "9": "shall_signal_keyword_requirement",
+    "10": "shall_signal_keyword_srs_text",
+    "11": "should_signal_keyword_general_text",
+    "12": "should_signal_keyword_requirement",
+    "13": "should_signal_keyword_srs_text",
+    "14": "will_signal_keyword_general_text",
+    "15": "will_signal_keyword_requirement",
+    "16": "will_signal_keyword_srs_text"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "may_signal_keyword_general_text": 0,
+    "may_signal_keyword_requirement": 1,
+    "may_signal_keyword_srs_text": 2,
+    "must_signal_keyword_general_text": 3,
+    "must_signal_keyword_requirement": 4,
+    "must_signal_keyword_srs_text": 5,
+    "no_signal_keyword_general_text": 6,
+    "no_signal_keyword_srs_text": 7,
+    "shall_signal_keyword_general_text": 8,
+    "shall_signal_keyword_requirement": 9,
+    "shall_signal_keyword_srs_text": 10,
+    "should_signal_keyword_general_text": 11,
+    "should_signal_keyword_requirement": 12,
+    "should_signal_keyword_srs_text": 13,
+    "will_signal_keyword_general_text": 14,
+    "will_signal_keyword_requirement": 15,
+    "will_signal_keyword_srs_text": 16
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

logs/train/events.out.tfevents.1715264632.iste.735681.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c437776db51741285f427ca952ac3ed3accc3375cb78cbd4ae05a90a43516728
+size 78

logs/train/events.out.tfevents.1715264715.iste.740663.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b31c654cbb678df8a428286b62fb3db471a0b31997057ce8bd08581cadfb0e
+size 78

logs/train/events.out.tfevents.1715264960.iste.740663.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055ee6ca1c4a560966022bfda107a3022841507805b93c8bb6cb6002509c0ea8
+size 78

logs/train/events.out.tfevents.1715265195.iste.740663.2.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0589403f4d259eca78a9e29861907a0c5a4ef972a13709a29d0d997d55adaac4
+size 78

logs/train/events.out.tfevents.1715265874.iste.746549.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e952971e19e9b1523d9aee4dda8ed08b4710debd41a29527d9145d0b453a6731
+size 78

logs/train/events.out.tfevents.1715265886.iste.746549.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10115068f6a645dfb825e1e69f27ee92437c20fa791067ee5474697f6345ec3c
+size 78

logs/train/events.out.tfevents.1715266154.iste.746549.2.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a37da4b206f8cd6510b1b23f2adffee15ec497dbe3f23bd353cb6af3d9fc58
+size 78

logs/train/events.out.tfevents.1715266268.iste.746549.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc084f2551a8944dc68efdbe467cd5407268e65212529d6c86eb27c89244e53
+size 78

logs/train/events.out.tfevents.1715266585.iste.746549.4.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a922a7777e81ab3fce4e1f85f9a313dba89447263c312ac1129606b37238694
+size 78

logs/train/events.out.tfevents.1715266792.iste.747601.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920eea06c7511697c9518c38702f069ccae869113d0dfe3e68bcc642a8ff0111
+size 78

logs/train/events.out.tfevents.1715266929.iste.748139.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0f234dd49ecd467261b507a8e0f7590245d7f3a01163357f09405a33a9779d
+size 78

logs/train/events.out.tfevents.1715267006.iste.748518.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84901a1c4eddad101e707364e60f7e5370b4c3ec629180e957ba1d92a6a19e7b
+size 2150825

logs/validation/events.out.tfevents.1715267040.iste.748518.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d0c31c9b591efb5184eefa7b4a203ea6f20ed3519546bf53778910dd453c47
+size 4755

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab7cc49e98dda84bfeabe4fcfd38e07f3e6d2786672098974ffa5c46ee51b45
+size 497999344

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}