update

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "unrelated",
+    "1": "stereotype_gender",
+    "2": "anti-stereotype_gender",
+    "3": "stereotype_race",
+    "4": "anti-stereotype_race",
+    "5": "stereotype_profession",
+    "6": "anti-stereotype_profession",
+    "7": "stereotype_religion",
+    "8": "anti-stereotype_religion"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "anti-stereotype_gender": 2,
+    "anti-stereotype_profession": 6,
+    "anti-stereotype_race": 4,
+    "anti-stereotype_religion": 8,
+    "stereotype_gender": 1,
+    "stereotype_profession": 5,
+    "stereotype_race": 3,
+    "stereotype_religion": 7,
+    "unrelated": 0
+  },
+  "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": "4.30.2",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3a2ede176455f03fbb391b979ffdae699ee0b6a651038e4d30e81caf24615b
+size 175105008

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3f43365dd427813db2965cc9f4572fac706b40840d2b76126d8bea971329c1
+size 176815110

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d96600483ff85427d732ec69c81a43227d9090e71ba01297a2070e3b1e7a2276
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da5120f044f3bc98c066d6f08325e23bfcbf5fa4b3a593c660f74ac4cba240a
+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 +1,76 @@
+{
+  "best_metric": 0.06264707446098328,
+  "best_model_checkpoint": "token_level_model/best_model/checkpoint-1264",
+  "epoch": 4.0,
+  "global_step": 1264,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_balanced accuracy": 0.6290652713011048,
+      "eval_f1": 0.5903625610241477,
+      "eval_loss": 0.08535531163215637,
+      "eval_precision": 0.6673952462175068,
+      "eval_recall": 0.6290652713011048,
+      "eval_runtime": 1.1616,
+      "eval_samples_per_second": 1088.145,
+      "eval_steps_per_second": 68.009,
+      "step": 316
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.7362869198312237e-05,
+      "loss": 0.1826,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_balanced accuracy": 0.7368620541402373,
+      "eval_f1": 0.7319179038298047,
+      "eval_loss": 0.0663721114397049,
+      "eval_precision": 0.7513664045814622,
+      "eval_recall": 0.7368620541402373,
+      "eval_runtime": 1.1399,
+      "eval_samples_per_second": 1108.902,
+      "eval_steps_per_second": 69.306,
+      "step": 632
+    },
+    {
+      "epoch": 3.0,
+      "eval_balanced accuracy": 0.7154153135735104,
+      "eval_f1": 0.7058619488659976,
+      "eval_loss": 0.0662752017378807,
+      "eval_precision": 0.7270224611135597,
+      "eval_recall": 0.7154153135735104,
+      "eval_runtime": 1.1286,
+      "eval_samples_per_second": 1119.927,
+      "eval_steps_per_second": 69.995,
+      "step": 948
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 1.4725738396624474e-05,
+      "loss": 0.0568,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_balanced accuracy": 0.73742506900579,
+      "eval_f1": 0.7367887044772851,
+      "eval_loss": 0.06264707446098328,
+      "eval_precision": 0.7489761641718176,
+      "eval_recall": 0.73742506900579,
+      "eval_runtime": 1.1361,
+      "eval_samples_per_second": 1112.55,
+      "eval_steps_per_second": 69.534,
+      "step": 1264
+    }
+  ],
+  "max_steps": 3792,
+  "num_train_epochs": 12,
+  "total_flos": 100660027447476.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b8d0f901caec1b204fedf3a32dcc6d45c2a6f05439608359b93e904dccc26c
+size 3963