Training in progress epoch 0

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: harsh4248/ai_vs_human_classification_2
+  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. -->
+
+# harsh4248/ai_vs_human_classification_2
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 1.3238
+- Validation Loss: 1.3084
+- Train Accuracy: 0.5420
+- Epoch: 0
+
+## 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': 70665, '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 | Train Accuracy | Epoch |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 1.3238     | 1.3084          | 0.5420         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- TensorFlow 2.15.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,153 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Bloom-7B",
+    "1": "Claude-Instant-v1",
+    "2": "Claude-v1",
+    "3": "Cohere-Command",
+    "4": "Dolphin-2.5-Mixtral-8x7B",
+    "5": "Dolphin-Mixtral-8x7B",
+    "6": "Falcon-180B",
+    "7": "Flan-T5-Base",
+    "8": "Flan-T5-Large",
+    "9": "Flan-T5-Small",
+    "10": "Flan-T5-XL",
+    "11": "Flan-T5-XXL",
+    "12": "GLM-130B",
+    "13": "GPT-3.5",
+    "14": "GPT-4",
+    "15": "GPT-J",
+    "16": "GPT-NeoX",
+    "17": "Gemini-Pro",
+    "18": "Goliath-120B",
+    "19": "Human",
+    "20": "LLaMA-13B",
+    "21": "LLaMA-2-70B",
+    "22": "LLaMA-2-7B",
+    "23": "LLaMA-30B",
+    "24": "LLaMA-65B",
+    "25": "LLaMA-7B",
+    "26": "LZLV-70B",
+    "27": "Mistral-7B",
+    "28": "Mistral-7B-OpenOrca",
+    "29": "Mixtral-8x7B",
+    "30": "MythoMax-L2-13B",
+    "31": "Neural-Chat-7B",
+    "32": "Noromaid-20B",
+    "33": "Nous-Capybara-34B",
+    "34": "Nous-Capybara-7B",
+    "35": "Nous-Hermes-LLaMA-2-13B",
+    "36": "Nous-Hermes-LLaMA-2-70B",
+    "37": "OPT-1.3B",
+    "38": "OPT-125M",
+    "39": "OPT-13B",
+    "40": "OPT-2.7B",
+    "41": "OPT-30B",
+    "42": "OPT-350M",
+    "43": "OPT-6.7B",
+    "44": "OpenChat-3.5",
+    "45": "OpenHermes-2-Mistral-7B",
+    "46": "OpenHermes-2.5-Mistral-7B",
+    "47": "PaLM-2",
+    "48": "Psyfighter-13B",
+    "49": "Psyfighter-2-13B",
+    "50": "RWKV-5-World-3B",
+    "51": "StripedHyena-Nous-7B",
+    "52": "T0-11B",
+    "53": "T0-3B",
+    "54": "Text-Ada-001",
+    "55": "Text-Babbage-001",
+    "56": "Text-Curie-001",
+    "57": "Text-Davinci-001",
+    "58": "Text-Davinci-002",
+    "59": "Text-Davinci-003",
+    "60": "Toppy-M-7B",
+    "61": "Unknown",
+    "62": "YI-34B"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Bloom-7B": 0,
+    "Claude-Instant-v1": 1,
+    "Claude-v1": 2,
+    "Cohere-Command": 3,
+    "Dolphin-2.5-Mixtral-8x7B": 4,
+    "Dolphin-Mixtral-8x7B": 5,
+    "Falcon-180B": 6,
+    "Flan-T5-Base": 7,
+    "Flan-T5-Large": 8,
+    "Flan-T5-Small": 9,
+    "Flan-T5-XL": 10,
+    "Flan-T5-XXL": 11,
+    "GLM-130B": 12,
+    "GPT-3.5": 13,
+    "GPT-4": 14,
+    "GPT-J": 15,
+    "GPT-NeoX": 16,
+    "Gemini-Pro": 17,
+    "Goliath-120B": 18,
+    "Human": 19,
+    "LLaMA-13B": 20,
+    "LLaMA-2-70B": 21,
+    "LLaMA-2-7B": 22,
+    "LLaMA-30B": 23,
+    "LLaMA-65B": 24,
+    "LLaMA-7B": 25,
+    "LZLV-70B": 26,
+    "Mistral-7B": 27,
+    "Mistral-7B-OpenOrca": 28,
+    "Mixtral-8x7B": 29,
+    "MythoMax-L2-13B": 30,
+    "Neural-Chat-7B": 31,
+    "Noromaid-20B": 32,
+    "Nous-Capybara-34B": 33,
+    "Nous-Capybara-7B": 34,
+    "Nous-Hermes-LLaMA-2-13B": 35,
+    "Nous-Hermes-LLaMA-2-70B": 36,
+    "OPT-1.3B": 37,
+    "OPT-125M": 38,
+    "OPT-13B": 39,
+    "OPT-2.7B": 40,
+    "OPT-30B": 41,
+    "OPT-350M": 42,
+    "OPT-6.7B": 43,
+    "OpenChat-3.5": 44,
+    "OpenHermes-2-Mistral-7B": 45,
+    "OpenHermes-2.5-Mistral-7B": 46,
+    "PaLM-2": 47,
+    "Psyfighter-13B": 48,
+    "Psyfighter-2-13B": 49,
+    "RWKV-5-World-3B": 50,
+    "StripedHyena-Nous-7B": 51,
+    "T0-11B": 52,
+    "T0-3B": 53,
+    "Text-Ada-001": 54,
+    "Text-Babbage-001": 55,
+    "Text-Curie-001": 56,
+    "Text-Davinci-001": 57,
+    "Text-Davinci-002": 58,
+    "Text-Davinci-003": 59,
+    "Toppy-M-7B": 60,
+    "Unknown": 61,
+    "YI-34B": 62
+  },
+  "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": "4.40.2",
+  "vocab_size": 30522
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec0bd5d0163e2c064159e92c382bc69c1993310c3ad5d0794786ae6226d29a3
+size 268139200

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}