Upload 8 files

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/work/chenming6/ee/text-similarity/promcse_zh/promcse/bert_pytorch",
+  "architectures": [
+    "BertForCL"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "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,
+  "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
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1060bf5a7571e974fb14aeefc231a97f945fec46433872a4261aa1d7930e0cb6
+size 819736527

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c06124dd864ba1653ae6af47344021c0bfcf372fc5bf027cb4d823acf368bab
+size 409894665

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e4d7284d899f7c7f27e1085672b348fe55f61f90a387fd8f6e8cc68e62ba12
+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_pytorch", "do_basic_tokenize": true, "never_split": null}

trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7871017871017871,
+  "global_step": 2300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.8834498834498833e-05,
+      "loss": 0.5929,
+      "step": 500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.766899766899767e-05,
+      "loss": 0.4371,
+      "step": 1000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.6503496503496503e-05,
+      "loss": 0.3773,
+      "step": 1500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.5337995337995338e-05,
+      "loss": 0.3391,
+      "step": 2000
+    }
+  ],
+  "max_steps": 12870,
+  "num_train_epochs": 10,
+  "total_flos": 138962361110593536,
+  "trial_name": null,
+  "trial_params": null
+}