Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+license: mit
+base_model: openai-community/gpt2
+tags:
+- generated_from_keras_callback
+model-index:
+- name: kasrahabib/gpt2-finetuned-iso29148-sward-on-promise-km-labels-f-nf-cls
+  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-sward-on-promise-km-labels-f-nf-cls
+
+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: 0.0043
+- Validation Loss: 0.4534
+- Epoch: 14
+
+## 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': 61815, '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 |
+|:----------:|:---------------:|:-----:|
+| 0.4009     | 0.2523          | 0     |
+| 0.2466     | 0.2587          | 1     |
+| 0.1737     | 0.2424          | 2     |
+| 0.1156     | 0.2541          | 3     |
+| 0.0731     | 0.2580          | 4     |
+| 0.0488     | 0.3160          | 5     |
+| 0.0364     | 0.2907          | 6     |
+| 0.0268     | 0.3266          | 7     |
+| 0.0178     | 0.4484          | 8     |
+| 0.0162     | 0.3838          | 9     |
+| 0.0107     | 0.4148          | 10    |
+| 0.0073     | 0.4724          | 11    |
+| 0.0068     | 0.4474          | 12    |
+| 0.0041     | 0.4823          | 13    |
+| 0.0043     | 0.4534          | 14    |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- TensorFlow 2.15.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,47 @@
+{
+  "_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": "F",
+    "1": "NF"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "F": 0,
+    "NF": 1
+  },
+  "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": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

logs/train/events.out.tfevents.1734395837.iste.957649.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a2bc47220658c1436bfcb20aabdc27b0af3423861edf6e8b24d4c9d5cc1066
+size 2144975

logs/validation/events.out.tfevents.1734396029.iste.957649.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2347e96ce6dbe0269498b763cfb79fd9673489b0655eeb50943d70928e1bb9c9
+size 2428

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:c2ea1d52315c900c10f6f33202a0203e77cc44e512c640cab504f7e0c786a6e5
+size 497953264

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|>"
+}