Upload 7 files

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "promcse/bert_large_pytorch",
+  "architectures": [
+    "BertForCL"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.2.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0922971878d4d7de7a7291140ba26bd2bb11f625f9ac74c02cc1c2acb2da8d1c
+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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/home/work/chenming6/ee/text-similarity/promcse_zh/promcse/bert_large_pytorch", "do_basic_tokenize": true, "never_split": null}

trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4691358024691357,
+  "global_step": 2600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.8575498575498578e-05,
+      "loss": 1.0064,
+      "step": 500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.715099715099715e-05,
+      "loss": 0.7464,
+      "step": 1000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.572649572649573e-05,
+      "loss": 0.586,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.4301994301994302e-05,
+      "loss": 0.5616,
+      "step": 2000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.287749287749288e-05,
+      "loss": 0.4552,
+      "step": 2500
+    }
+  ],
+  "max_steps": 10530,
+  "num_train_epochs": 10,
+  "total_flos": 249833139915718656,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14fed4bc0536641a85391f74dbf1afb659b5987ac8c7e223e6c7a4fb551ae957
+size 2095