Upload 9 files

config.json

@@ -1,10 +1,9 @@
 {
-  "_name_or_path": "/content/content/result/semeval-unsup-promcse-bert-base-uncased-semeval2014-restaurants",
+  "_name_or_path": "/content/result/semeval-unsup-promcse-bert-base-uncased-semeval2014-restaurants",
   "architectures": [
     "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -18,8 +17,8 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.2.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522
-}
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ebb43a9e5c5abcb35347fd7ac50afa920310ad7dedbff67e448c81bc007b8d
+size 7086823

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becfe44fbd3459bd89d25773ebd50a5e7e6003526564e9a4d6ff927e8e0574a6
+size 627

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": "YuxinJiang/unsup-promcse-bert-base-uncased", "do_basic_tokenize": true, "never_split": null}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 30.0
+train_runtime = 1516.7011
+train_samples_per_second = 1.899

trainer_state.json

@@ -0,0 +1,213 @@
+{
+  "best_metric": 0.8253311880533157,
+  "best_model_checkpoint": "/content/result/semeval-unsup-promcse-bert-base-uncased-semeval2014-restaurants",
+  "epoch": 30.0,
+  "global_step": 2880,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.3,
+      "eval_avg_sts": 0.7734256836656246,
+      "eval_sickr_spearman": 0.7301818685217797,
+      "eval_stsb_spearman": 0.8166694988094696,
+      "step": 125
+    },
+    {
+      "epoch": 2.6,
+      "eval_avg_sts": 0.7703746643952976,
+      "eval_sickr_spearman": 0.7321891362819799,
+      "eval_stsb_spearman": 0.8085601925086153,
+      "step": 250
+    },
+    {
+      "epoch": 3.91,
+      "eval_avg_sts": 0.7788971740918453,
+      "eval_sickr_spearman": 0.7471303631307394,
+      "eval_stsb_spearman": 0.8106639850529513,
+      "step": 375
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 0.024791666666666663,
+      "loss": 0.0007,
+      "step": 500
+    },
+    {
+      "epoch": 5.21,
+      "eval_avg_sts": 0.7773926482680351,
+      "eval_sickr_spearman": 0.7365530020031397,
+      "eval_stsb_spearman": 0.8182322945329304,
+      "step": 500
+    },
+    {
+      "epoch": 6.51,
+      "eval_avg_sts": 0.775445904944555,
+      "eval_sickr_spearman": 0.740137130823553,
+      "eval_stsb_spearman": 0.8107546790655571,
+      "step": 625
+    },
+    {
+      "epoch": 7.81,
+      "eval_avg_sts": 0.7784724629491336,
+      "eval_sickr_spearman": 0.7476811838020316,
+      "eval_stsb_spearman": 0.8092637420962356,
+      "step": 750
+    },
+    {
+      "epoch": 9.11,
+      "eval_avg_sts": 0.7813093219093801,
+      "eval_sickr_spearman": 0.7487985313147865,
+      "eval_stsb_spearman": 0.8138201125039736,
+      "step": 875
+    },
+    {
+      "epoch": 10.42,
+      "learning_rate": 0.019583333333333335,
+      "loss": 0.0006,
+      "step": 1000
+    },
+    {
+      "epoch": 10.42,
+      "eval_avg_sts": 0.7821698012287537,
+      "eval_sickr_spearman": 0.7488977155392563,
+      "eval_stsb_spearman": 0.8154418869182509,
+      "step": 1000
+    },
+    {
+      "epoch": 11.72,
+      "eval_avg_sts": 0.7816201340578361,
+      "eval_sickr_spearman": 0.7485443026948746,
+      "eval_stsb_spearman": 0.8146959654207976,
+      "step": 1125
+    },
+    {
+      "epoch": 13.02,
+      "eval_avg_sts": 0.7749666873628911,
+      "eval_sickr_spearman": 0.7446217467337283,
+      "eval_stsb_spearman": 0.8053116279920538,
+      "step": 1250
+    },
+    {
+      "epoch": 14.32,
+      "eval_avg_sts": 0.7836477830344395,
+      "eval_sickr_spearman": 0.7419643780155633,
+      "eval_stsb_spearman": 0.8253311880533157,
+      "step": 1375
+    },
+    {
+      "epoch": 15.62,
+      "learning_rate": 0.014375,
+      "loss": 0.0006,
+      "step": 1500
+    },
+    {
+      "epoch": 15.62,
+      "eval_avg_sts": 0.7843268448693694,
+      "eval_sickr_spearman": 0.744167948887341,
+      "eval_stsb_spearman": 0.824485740851398,
+      "step": 1500
+    },
+    {
+      "epoch": 16.93,
+      "eval_avg_sts": 0.7833021826430621,
+      "eval_sickr_spearman": 0.7446480677773164,
+      "eval_stsb_spearman": 0.8219562975088077,
+      "step": 1625
+    },
+    {
+      "epoch": 18.23,
+      "eval_avg_sts": 0.7763940328282399,
+      "eval_sickr_spearman": 0.7362944505840984,
+      "eval_stsb_spearman": 0.8164936150723816,
+      "step": 1750
+    },
+    {
+      "epoch": 19.53,
+      "eval_avg_sts": 0.7798534729613469,
+      "eval_sickr_spearman": 0.7372460427657902,
+      "eval_stsb_spearman": 0.8224609031569036,
+      "step": 1875
+    },
+    {
+      "epoch": 20.83,
+      "learning_rate": 0.009166666666666667,
+      "loss": 0.0005,
+      "step": 2000
+    },
+    {
+      "epoch": 20.83,
+      "eval_avg_sts": 0.7800079514190481,
+      "eval_sickr_spearman": 0.7419313806488752,
+      "eval_stsb_spearman": 0.8180845221892211,
+      "step": 2000
+    },
+    {
+      "epoch": 22.14,
+      "eval_avg_sts": 0.775204360127723,
+      "eval_sickr_spearman": 0.7362090993168428,
+      "eval_stsb_spearman": 0.8141996209386033,
+      "step": 2125
+    },
+    {
+      "epoch": 23.44,
+      "eval_avg_sts": 0.7765059369521707,
+      "eval_sickr_spearman": 0.737198107726555,
+      "eval_stsb_spearman": 0.8158137661777864,
+      "step": 2250
+    },
+    {
+      "epoch": 24.74,
+      "eval_avg_sts": 0.7762751811566875,
+      "eval_sickr_spearman": 0.7387870245932292,
+      "eval_stsb_spearman": 0.8137633377201456,
+      "step": 2375
+    },
+    {
+      "epoch": 26.04,
+      "learning_rate": 0.003958333333333334,
+      "loss": 0.0004,
+      "step": 2500
+    },
+    {
+      "epoch": 26.04,
+      "eval_avg_sts": 0.7760480299115587,
+      "eval_sickr_spearman": 0.7409553886676528,
+      "eval_stsb_spearman": 0.8111406711554647,
+      "step": 2500
+    },
+    {
+      "epoch": 27.34,
+      "eval_avg_sts": 0.7772760835199366,
+      "eval_sickr_spearman": 0.7415818102926086,
+      "eval_stsb_spearman": 0.8129703567472646,
+      "step": 2625
+    },
+    {
+      "epoch": 28.65,
+      "eval_avg_sts": 0.7773403818371579,
+      "eval_sickr_spearman": 0.7416166328411512,
+      "eval_stsb_spearman": 0.8130641308331646,
+      "step": 2750
+    },
+    {
+      "epoch": 29.95,
+      "eval_avg_sts": 0.7772868899414305,
+      "eval_sickr_spearman": 0.7413437859462035,
+      "eval_stsb_spearman": 0.8132299939366575,
+      "step": 2875
+    },
+    {
+      "epoch": 30.0,
+      "step": 2880,
+      "train_runtime": 1516.7011,
+      "train_samples_per_second": 1.899
+    }
+  ],
+  "max_steps": 2880,
+  "num_train_epochs": 30,
+  "total_flos": 3837671792925696,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247902bef5ea1090ba0bc27182e6799820174bf65be968546a9a310f73d7d5b0
+size 2107