Upload folder using huggingface_hub

README.md

@@ -0,0 +1,17 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- dshihk/llm-generated-essay
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+No validation metrics available

checkpoint-465/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "_num_labels": 2,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

checkpoint-465/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f57a94755d7ea9f7b7e2de2385c58b75715ac6fa1f1ea401714dd6a24982e89
+size 267832560

checkpoint-465/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca20bbccd5eaf5c099423746e0d8fb8676a41036ca0bffa5fbbb0906bff18fb
+size 535726853

checkpoint-465/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8223d367d168e9b8a141646903d507e3bc86be6a77bdd41a161c09636c124a5d
+size 14575

checkpoint-465/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20f9e764ede8e1fdc4169418d7b8a371325e2eec68e4d24bdaa184d16fb51d4
+size 627

checkpoint-465/trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.995169082125604,
+  "eval_steps": 500,
+  "global_step": 465,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.592916195656322e-05,
+      "loss": 0.2521,
+      "step": 124
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.650224885357251e-05,
+      "loss": 0.0304,
+      "step": 248
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 5.86231516774709e-06,
+      "loss": 0.0144,
+      "step": 372
+    }
+  ],
+  "logging_steps": 124,
+  "max_steps": 465,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3941964849205248.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-465/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ae4d124a5dedee4436a70238746c105dfbed02d8bb75a272895f6f74fb43d2
+size 4155

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "_num_labels": 2,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f57a94755d7ea9f7b7e2de2385c58b75715ac6fa1f1ea401714dd6a24982e89
+size 267832560

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 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ae4d124a5dedee4436a70238746c105dfbed02d8bb75a272895f6f74fb43d2
+size 4155

training_params.json

@@ -0,0 +1 @@
+{"data_path": "dshihk/llm-generated-essay", "model": "distilbert-base-uncased-finetuned-sst-2-english", "lr": 5e-05, "epochs": 3, "max_seq_length": 128, "batch_size": 64, "warmup_ratio": 0.1, "gradient_accumulation": 4, "optimizer": "adamw_torch", "scheduler": "cosine", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "train_split": "train", "valid_split": null, "text_column": "text", "target_column": "target", "logging_steps": -1, "project_name": "llm-essay-classifier", "auto_find_batch_size": false, "fp16": true, "save_total_limit": 1, "save_strategy": "epoch", "push_to_hub": true, "repo_id": "dshihk/llm-essay-classifier", "evaluation_strategy": "epoch", "username": null, "log": "wandb"}