update

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "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": "4.30.2",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe6d44ed8eadd7b3fa298e0b516c01635f64e8d63cb962aecfd656af54bc9df
+size 535744069

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bea91ab55815e992847f99e4cfa09b525f0ae38062ae428c373962f2f6ff77c
+size 267877037

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30dbcef122e942f8a8df2b8e1c57b3ec194d344225213f40f2c328c6925c6d6
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf7f11b4a721200e4855c318b8001b95008046cba699011100f3bf012c01c546
+size 627

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 +1,13 @@
+{
+  "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]"
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.49603304266929626,
+  "best_model_checkpoint": "MD_SL_best_model/checkpoint-5276",
+  "epoch": 2.0,
+  "global_step": 5276,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.936820823856457e-05,
+      "loss": 1.0828,
+      "step": 500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.873641647712914e-05,
+      "loss": 0.7086,
+      "step": 1000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8104624715693708e-05,
+      "loss": 0.669,
+      "step": 1500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.747283295425828e-05,
+      "loss": 0.6264,
+      "step": 2000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6841041192822848e-05,
+      "loss": 0.5951,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_balanced accuracy": 0.6598598463994036,
+      "eval_f1": 0.6477315522294683,
+      "eval_loss": 0.5617039799690247,
+      "eval_precision": 0.6664522794774816,
+      "eval_recall": 0.6598598463994036,
+      "eval_runtime": 177.7279,
+      "eval_samples_per_second": 59.366,
+      "eval_steps_per_second": 3.714,
+      "step": 2638
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.6209249431387417e-05,
+      "loss": 0.5066,
+      "step": 3000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.5577457669951985e-05,
+      "loss": 0.475,
+      "step": 3500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.4945665908516554e-05,
+      "loss": 0.4635,
+      "step": 4000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.4313874147081124e-05,
+      "loss": 0.4546,
+      "step": 4500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.3682082385645691e-05,
+      "loss": 0.4428,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_balanced accuracy": 0.7034186400261718,
+      "eval_f1": 0.6980022981890632,
+      "eval_loss": 0.49603304266929626,
+      "eval_precision": 0.7144313872416078,
+      "eval_recall": 0.7034186400261718,
+      "eval_runtime": 177.7105,
+      "eval_samples_per_second": 59.372,
+      "eval_steps_per_second": 3.714,
+      "step": 5276
+    }
+  ],
+  "max_steps": 15828,
+  "num_train_epochs": 6,
+  "total_flos": 1.11816441335808e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca839a775bd188814fd1d454dfd76732fcd7c1f4521dc5b5f57416f583db5f0
+size 3963