Upload folder using huggingface_hub

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/electra-large-discriminator
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: deberta-v3-hybrid-detector
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# deberta-v3-hybrid-detector
+
+This model is a fine-tuned version of [google/electra-large-discriminator](https://huggingface.co/google/electra-large-discriminator) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0564
+- Accuracy: 0.9654
+
+## 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:
+- learning_rate: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0926        | 0.125 | 1000 | 0.0443          | 0.9446   |
+| 0.0565        | 0.25  | 2000 | 0.0480          | 0.9251   |
+| 0.0442        | 0.375 | 3000 | 0.2126          | 0.8871   |
+| 0.0383        | 0.5   | 4000 | 0.0716          | 0.9479   |
+| 0.0332        | 0.625 | 5000 | 0.2383          | 0.8774   |
+| 0.0253        | 0.75  | 6000 | 0.0347          | 0.9706   |
+| 0.0168        | 0.875 | 7000 | 0.0347          | 0.9795   |
+| 0.0117        | 1.0   | 8000 | 0.0564          | 0.9654   |
+
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.8.0+cu126
+- Datasets 4.4.2
+- Tokenizers 0.22.1

checkpoint-6000/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-6000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189a444d7d08fac053d0afdf579d15f2ce5c3b291fe2585a0a68aa06ac423125
+size 1340623936

checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1412909fafec55fdb0b545a055de004ce0fbb1c659bab1b641461c37ab1a06bd
+size 2681480830

checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8204224037896deef0f35c84f4577820f466f7fdc8392d7d9e2de6fbf7f54edd
+size 14645

checkpoint-6000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
+size 1383

checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea87eab7314030de6a681cdcf3c34a9f8132dae5f987b9ed0ac7d021ba4f0ee
+size 1465

checkpoint-6000/special_tokens_map.json

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

checkpoint-6000/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-6000/trainer_state.json

@@ -0,0 +1,172 @@
+{
+  "best_global_step": 6000,
+  "best_metric": 0.034662000834941864,
+  "best_model_checkpoint": "./training_output/checkpoint-6000",
+  "epoch": 0.75,
+  "eval_steps": 1000,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0625,
+      "grad_norm": 1.8642356395721436,
+      "learning_rate": 1.8752500000000004e-05,
+      "loss": 0.1279,
+      "step": 500
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 3.2498440742492676,
+      "learning_rate": 1.7502500000000004e-05,
+      "loss": 0.0926,
+      "step": 1000
+    },
+    {
+      "epoch": 0.125,
+      "eval_accuracy": 0.944625,
+      "eval_loss": 0.04429839178919792,
+      "eval_runtime": 500.554,
+      "eval_samples_per_second": 15.982,
+      "eval_steps_per_second": 0.999,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.005530397407710552,
+      "learning_rate": 1.62525e-05,
+      "loss": 0.0612,
+      "step": 1500
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.27407366037368774,
+      "learning_rate": 1.5002500000000002e-05,
+      "loss": 0.0565,
+      "step": 2000
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.925125,
+      "eval_loss": 0.04796064645051956,
+      "eval_runtime": 500.334,
+      "eval_samples_per_second": 15.989,
+      "eval_steps_per_second": 0.999,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.02653448097407818,
+      "learning_rate": 1.3752500000000003e-05,
+      "loss": 0.0527,
+      "step": 2500
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.2703651785850525,
+      "learning_rate": 1.2502500000000003e-05,
+      "loss": 0.0442,
+      "step": 3000
+    },
+    {
+      "epoch": 0.375,
+      "eval_accuracy": 0.887125,
+      "eval_loss": 0.21262305974960327,
+      "eval_runtime": 500.0079,
+      "eval_samples_per_second": 16.0,
+      "eval_steps_per_second": 1.0,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 0.08504923433065414,
+      "learning_rate": 1.1252500000000001e-05,
+      "loss": 0.0369,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.14933931827545166,
+      "learning_rate": 1.0002500000000001e-05,
+      "loss": 0.0383,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.947875,
+      "eval_loss": 0.071560338139534,
+      "eval_runtime": 499.5693,
+      "eval_samples_per_second": 16.014,
+      "eval_steps_per_second": 1.001,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 1.824542760848999,
+      "learning_rate": 8.7525e-06,
+      "loss": 0.0309,
+      "step": 4500
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.012093538418412209,
+      "learning_rate": 7.502500000000001e-06,
+      "loss": 0.0332,
+      "step": 5000
+    },
+    {
+      "epoch": 0.625,
+      "eval_accuracy": 0.877375,
+      "eval_loss": 0.23829498887062073,
+      "eval_runtime": 499.6395,
+      "eval_samples_per_second": 16.012,
+      "eval_steps_per_second": 1.001,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 0.006525672040879726,
+      "learning_rate": 6.2525e-06,
+      "loss": 0.0281,
+      "step": 5500
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.004029456060379744,
+      "learning_rate": 5.0025e-06,
+      "loss": 0.0253,
+      "step": 6000
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.970625,
+      "eval_loss": 0.034662000834941864,
+      "eval_runtime": 499.746,
+      "eval_samples_per_second": 16.008,
+      "eval_steps_per_second": 1.001,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2366352719872e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c2c378ae0a81e7a2579965f55102a37cebf57f8f379e3ae27d8b4f0db81465
+size 5841

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:189a444d7d08fac053d0afdf579d15f2ce5c3b291fe2585a0a68aa06ac423125
+size 1340623936

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c2c378ae0a81e7a2579965f55102a37cebf57f8f379e3ae27d8b4f0db81465
+size 5841