add model files

config.json

@@ -0,0 +1,24 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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 sha256:3b147b8c151bac4053c544dfe9276315b15be6ec44c070b5c0cdc96892ccbe63
+size 866620625

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4219adcc6844afd400ccf32dabd00a954a2593cedf78ca98c3d11de97d3d1f
+size 433336585

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a1ef680b075840373a88ed789cf8762c0adb180f3bc44bfd94c2bf45d7d77a9
+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 +1,146 @@
+{
+  "best_metric": 0.6329699372315825,
+  "best_model_checkpoint": "/scratch/ccc779/rtgender_opgender_annotations_model/checkpoint-9210",
+  "epoch": 2.0,
+  "global_step": 9210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.1520220054230351e-05,
+      "loss": 0.6943,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.085889858154204e-05,
+      "loss": 0.6774,
+      "step": 1000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.0197577108853733e-05,
+      "loss": 0.6879,
+      "step": 1500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.536255636165422e-06,
+      "loss": 0.6953,
+      "step": 2000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.874934163477113e-06,
+      "loss": 0.7215,
+      "step": 2500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.213612690788802e-06,
+      "loss": 0.6924,
+      "step": 3000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.552291218100494e-06,
+      "loss": 0.6984,
+      "step": 3500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.8909697454121845e-06,
+      "loss": 0.702,
+      "step": 4000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 6.2296482727238754e-06,
+      "loss": 0.6821,
+      "step": 4500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6304135460761967,
+      "eval_f1": 0.628963713631906,
+      "eval_loss": 0.7998125553131104,
+      "eval_precision": 0.6421895861148198,
+      "eval_recall": 0.6162716207559257,
+      "eval_runtime": 12.7284,
+      "eval_samples_per_second": 241.272,
+      "step": 4605
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 5.5683268000355656e-06,
+      "loss": 0.8274,
+      "step": 5000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 4.9070053273472565e-06,
+      "loss": 0.7584,
+      "step": 5500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 4.245683854658947e-06,
+      "loss": 0.7485,
+      "step": 6000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 3.5843623819706372e-06,
+      "loss": 0.8287,
+      "step": 6500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.923040909282328e-06,
+      "loss": 0.7596,
+      "step": 7000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.2617194365940184e-06,
+      "loss": 0.7292,
+      "step": 7500
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.600397963905709e-06,
+      "loss": 0.7779,
+      "step": 8000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 9.390764912173995e-07,
+      "loss": 0.7819,
+      "step": 8500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.7775501852908997e-07,
+      "loss": 0.7811,
+      "step": 9000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.638228590035819,
+      "eval_f1": 0.6329699372315825,
+      "eval_loss": 1.1031067371368408,
+      "eval_precision": 0.6534788540245566,
+      "eval_recall": 0.6137091607943626,
+      "eval_runtime": 12.7111,
+      "eval_samples_per_second": 241.6,
+      "step": 9210
+    }
+  ],
+  "max_steps": 9210,
+  "num_train_epochs": 2,
+  "total_flos": 434334690572400.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ffee4d478344979e2f30768ce00733d2003627cf5238efc28fb43e3455df09
+size 2351