Upload 10 files

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "C:\\Users\\Administrator\\Desktop\\NLP\\distilbert-question-detector\\checkpoint-5150",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12e07a10e6e39854a917ab909d634b5ae4b8c7ce5cf7bee9f343a47c2e462d0
+size 267832560

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c7a0ee0c9b0d89c4232b62978dacbc3671bf684ddbd0756132ed0e55c83c22
+size 535724410

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8181325e5e95bcf618839dcce24cadeaf5957e14e5842f1d42122506cfd82b5
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809a9de7163e05e3b8d05343016acfe15f45ee7f402a7dadbf60a94502b7ff96
+size 1064

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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]"
+}

trainer_state.json

@@ -0,0 +1,176 @@
+{
+  "best_metric": 0.02409563586115837,
+  "best_model_checkpoint": "./distilbert-question-detector\\checkpoint-3429",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3429,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17497812773403323,
+      "grad_norm": 0.427781343460083,
+      "learning_rate": 4.708369787109945e-05,
+      "loss": 0.0255,
+      "step": 200
+    },
+    {
+      "epoch": 0.34995625546806647,
+      "grad_norm": 0.400822252035141,
+      "learning_rate": 4.416739574219889e-05,
+      "loss": 0.0252,
+      "step": 400
+    },
+    {
+      "epoch": 0.5249343832020997,
+      "grad_norm": 0.5707641243934631,
+      "learning_rate": 4.125109361329834e-05,
+      "loss": 0.0274,
+      "step": 600
+    },
+    {
+      "epoch": 0.6999125109361329,
+      "grad_norm": 0.3984428346157074,
+      "learning_rate": 3.8334791484397786e-05,
+      "loss": 0.0258,
+      "step": 800
+    },
+    {
+      "epoch": 0.8748906386701663,
+      "grad_norm": 1.198236107826233,
+      "learning_rate": 3.541848935549723e-05,
+      "loss": 0.0262,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.024490611627697945,
+      "eval_runtime": 55.9659,
+      "eval_samples_per_second": 36.308,
+      "eval_steps_per_second": 2.269,
+      "step": 1143
+    },
+    {
+      "epoch": 1.0498687664041995,
+      "grad_norm": 0.8012853860855103,
+      "learning_rate": 3.2502187226596675e-05,
+      "loss": 0.0274,
+      "step": 1200
+    },
+    {
+      "epoch": 1.2248468941382327,
+      "grad_norm": 0.4337884187698364,
+      "learning_rate": 2.9585885097696126e-05,
+      "loss": 0.0183,
+      "step": 1400
+    },
+    {
+      "epoch": 1.399825021872266,
+      "grad_norm": 0.5056678652763367,
+      "learning_rate": 2.666958296879557e-05,
+      "loss": 0.0189,
+      "step": 1600
+    },
+    {
+      "epoch": 1.574803149606299,
+      "grad_norm": 0.5337983965873718,
+      "learning_rate": 2.3753280839895015e-05,
+      "loss": 0.0206,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7497812773403325,
+      "grad_norm": 0.26040902733802795,
+      "learning_rate": 2.083697871099446e-05,
+      "loss": 0.0186,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9247594050743657,
+      "grad_norm": 0.2849089205265045,
+      "learning_rate": 1.7920676582093906e-05,
+      "loss": 0.0184,
+      "step": 2200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.024468354880809784,
+      "eval_runtime": 59.7745,
+      "eval_samples_per_second": 33.994,
+      "eval_steps_per_second": 2.125,
+      "step": 2286
+    },
+    {
+      "epoch": 2.099737532808399,
+      "grad_norm": 0.21000386774539948,
+      "learning_rate": 1.500437445319335e-05,
+      "loss": 0.0164,
+      "step": 2400
+    },
+    {
+      "epoch": 2.2747156605424323,
+      "grad_norm": 0.2694750130176544,
+      "learning_rate": 1.2088072324292797e-05,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 2.4496937882764653,
+      "grad_norm": 0.12494825571775436,
+      "learning_rate": 9.171770195392243e-06,
+      "loss": 0.0154,
+      "step": 2800
+    },
+    {
+      "epoch": 2.6246719160104988,
+      "grad_norm": 0.21705402433872223,
+      "learning_rate": 6.255468066491689e-06,
+      "loss": 0.0143,
+      "step": 3000
+    },
+    {
+      "epoch": 2.799650043744532,
+      "grad_norm": 0.2746178209781647,
+      "learning_rate": 3.339165937591135e-06,
+      "loss": 0.0146,
+      "step": 3200
+    },
+    {
+      "epoch": 2.974628171478565,
+      "grad_norm": 0.2427779734134674,
+      "learning_rate": 4.2286380869058036e-07,
+      "loss": 0.0143,
+      "step": 3400
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.02409563586115837,
+      "eval_runtime": 62.7666,
+      "eval_samples_per_second": 32.374,
+      "eval_steps_per_second": 2.023,
+      "step": 3429
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 3429,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1816525437769728.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d3ae508f97ae7f5d0dbd0e18eb837936d9dd184c9249ff22a8f7745f1d1914
+size 5304