add model files

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.5.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09949f2a85e9e31cc1564a90f9d2fdd017ff38b55e92c7f7ee6c02846a22f969
+size 866626769

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ea4394b800263adcb281ee255baca5ad23bf2294d918e960ab463461a0f348
+size 433339657

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6bcc514b090cf233fdc4f2aaef0b391d8f52e3c382a4aed98b3bc0477bb2d70
+size 623

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased"}

trainer_state.json

@@ -0,0 +1,158 @@
+{
+  "best_metric": 0.88268156424581,
+  "best_model_checkpoint": "/scratch/ccc779/md_gender_wizard_model/checkpoint-5225",
+  "epoch": 2.0,
+  "global_step": 10450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.1598692650032599e-05,
+      "loss": 0.8563,
+      "step": 500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.101584377314654e-05,
+      "loss": 0.7332,
+      "step": 1000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.043299489626048e-05,
+      "loss": 0.7972,
+      "step": 1500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.850146019374418e-06,
+      "loss": 0.7073,
+      "step": 2000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.267297142488359e-06,
+      "loss": 0.7096,
+      "step": 2500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.684448265602297e-06,
+      "loss": 0.6715,
+      "step": 3000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 8.101599388716238e-06,
+      "loss": 0.6625,
+      "step": 3500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.5187505118301775e-06,
+      "loss": 0.6198,
+      "step": 4000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.935901634944117e-06,
+      "loss": 0.6188,
+      "step": 4500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.353052758058057e-06,
+      "loss": 0.584,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.88268156424581,
+      "eval_f1": 0.88268156424581,
+      "eval_loss": 0.5398293733596802,
+      "eval_precision": 0.88268156424581,
+      "eval_recall": 0.88268156424581,
+      "eval_runtime": 2.2447,
+      "eval_samples_per_second": 239.226,
+      "step": 5225
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 5.770203881171996e-06,
+      "loss": 0.5129,
+      "step": 5500
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 5.187355004285937e-06,
+      "loss": 0.5021,
+      "step": 6000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 4.604506127399876e-06,
+      "loss": 0.3964,
+      "step": 6500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.021657250513816e-06,
+      "loss": 0.3348,
+      "step": 7000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.4388083736277554e-06,
+      "loss": 0.3628,
+      "step": 7500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.8559594967416954e-06,
+      "loss": 0.4128,
+      "step": 8000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.273110619855635e-06,
+      "loss": 0.4337,
+      "step": 8500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.690261742969575e-06,
+      "loss": 0.4487,
+      "step": 9000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.1074128660835145e-06,
+      "loss": 0.4398,
+      "step": 9500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 5.245639891974543e-07,
+      "loss": 0.3933,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8752327746741154,
+      "eval_f1": 0.8752327746741154,
+      "eval_loss": 0.6503844857215881,
+      "eval_precision": 0.8752327746741154,
+      "eval_recall": 0.8752327746741154,
+      "eval_runtime": 2.1459,
+      "eval_samples_per_second": 250.243,
+      "step": 10450
+    }
+  ],
+  "max_steps": 10450,
+  "num_train_epochs": 2,
+  "total_flos": 365447724671790.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c95edeecfb2f4300660552f977df41fe114f7cf61f62e2ee7b84159b1648ef
+size 2351