Training in progress, step 200

checkpoint-1000/config.json

@@ -1,183 +0,0 @@
-{
-  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
-  "architectures": [
-    "MPNetTwoClassForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6",
-    "7": "LABEL_7",
-    "8": "LABEL_8",
-    "9": "LABEL_9",
-    "10": "LABEL_10",
-    "11": "LABEL_11",
-    "12": "LABEL_12",
-    "13": "LABEL_13",
-    "14": "LABEL_14",
-    "15": "LABEL_15",
-    "16": "LABEL_16",
-    "17": "LABEL_17",
-    "18": "LABEL_18",
-    "19": "LABEL_19",
-    "20": "LABEL_20",
-    "21": "LABEL_21",
-    "22": "LABEL_22",
-    "23": "LABEL_23",
-    "24": "LABEL_24",
-    "25": "LABEL_25",
-    "26": "LABEL_26",
-    "27": "LABEL_27",
-    "28": "LABEL_28",
-    "29": "LABEL_29",
-    "30": "LABEL_30",
-    "31": "LABEL_31",
-    "32": "LABEL_32",
-    "33": "LABEL_33",
-    "34": "LABEL_34",
-    "35": "LABEL_35",
-    "36": "LABEL_36",
-    "37": "LABEL_37",
-    "38": "LABEL_38",
-    "39": "LABEL_39",
-    "40": "LABEL_40",
-    "41": "LABEL_41",
-    "42": "LABEL_42",
-    "43": "LABEL_43",
-    "44": "LABEL_44",
-    "45": "LABEL_45",
-    "46": "LABEL_46",
-    "47": "LABEL_47",
-    "48": "LABEL_48",
-    "49": "LABEL_49",
-    "50": "LABEL_50",
-    "51": "LABEL_51",
-    "52": "LABEL_52",
-    "53": "LABEL_53",
-    "54": "LABEL_54",
-    "55": "LABEL_55",
-    "56": "LABEL_56",
-    "57": "LABEL_57",
-    "58": "LABEL_58",
-    "59": "LABEL_59",
-    "60": "LABEL_60",
-    "61": "LABEL_61",
-    "62": "LABEL_62",
-    "63": "LABEL_63",
-    "64": "LABEL_64",
-    "65": "LABEL_65",
-    "66": "LABEL_66",
-    "67": "LABEL_67",
-    "68": "LABEL_68",
-    "69": "LABEL_69",
-    "70": "LABEL_70",
-    "71": "LABEL_71",
-    "72": "LABEL_72",
-    "73": "LABEL_73",
-    "74": "LABEL_74",
-    "75": "LABEL_75",
-    "76": "LABEL_76"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_10": 10,
-    "LABEL_11": 11,
-    "LABEL_12": 12,
-    "LABEL_13": 13,
-    "LABEL_14": 14,
-    "LABEL_15": 15,
-    "LABEL_16": 16,
-    "LABEL_17": 17,
-    "LABEL_18": 18,
-    "LABEL_19": 19,
-    "LABEL_2": 2,
-    "LABEL_20": 20,
-    "LABEL_21": 21,
-    "LABEL_22": 22,
-    "LABEL_23": 23,
-    "LABEL_24": 24,
-    "LABEL_25": 25,
-    "LABEL_26": 26,
-    "LABEL_27": 27,
-    "LABEL_28": 28,
-    "LABEL_29": 29,
-    "LABEL_3": 3,
-    "LABEL_30": 30,
-    "LABEL_31": 31,
-    "LABEL_32": 32,
-    "LABEL_33": 33,
-    "LABEL_34": 34,
-    "LABEL_35": 35,
-    "LABEL_36": 36,
-    "LABEL_37": 37,
-    "LABEL_38": 38,
-    "LABEL_39": 39,
-    "LABEL_4": 4,
-    "LABEL_40": 40,
-    "LABEL_41": 41,
-    "LABEL_42": 42,
-    "LABEL_43": 43,
-    "LABEL_44": 44,
-    "LABEL_45": 45,
-    "LABEL_46": 46,
-    "LABEL_47": 47,
-    "LABEL_48": 48,
-    "LABEL_49": 49,
-    "LABEL_5": 5,
-    "LABEL_50": 50,
-    "LABEL_51": 51,
-    "LABEL_52": 52,
-    "LABEL_53": 53,
-    "LABEL_54": 54,
-    "LABEL_55": 55,
-    "LABEL_56": 56,
-    "LABEL_57": 57,
-    "LABEL_58": 58,
-    "LABEL_59": 59,
-    "LABEL_6": 6,
-    "LABEL_60": 60,
-    "LABEL_61": 61,
-    "LABEL_62": 62,
-    "LABEL_63": 63,
-    "LABEL_64": 64,
-    "LABEL_65": 65,
-    "LABEL_66": 66,
-    "LABEL_67": 67,
-    "LABEL_68": 68,
-    "LABEL_69": 69,
-    "LABEL_7": 7,
-    "LABEL_70": 70,
-    "LABEL_71": 71,
-    "LABEL_72": 72,
-    "LABEL_73": 73,
-    "LABEL_74": 74,
-    "LABEL_75": 75,
-    "LABEL_76": 76,
-    "LABEL_8": 8,
-    "LABEL_9": 9
-  },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "mpnet",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "problem_type": "single_label_classification",
-  "relative_attention_num_buckets": 32,
-  "torch_dtype": "float32",
-  "transformers_version": "4.15.0",
-  "vocab_size": 30527
-}

checkpoint-1000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:98806338b6152f321605c6e089c9f12905c40d4d6bd4590b153e84d3f955066e
-size 1762416361

checkpoint-1000/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:69140b4d7ee7b802871ebcb5864fe0c82ff7858aaaf0430a1ba8feb9efddc7f5
-size 440628841

checkpoint-1000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6eb238abce4321731ab41f2be485eedd1abfd0181edb4e56d5d5ae1026848d01
-size 15523

checkpoint-1000/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:400e768806545e7e40b83914ee0f9a3b90a3cc3eae099a06b3457f82488736cc
-size 623

checkpoint-1000/special_tokens_map.json

@@ -1 +0,0 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

checkpoint-1000/tokenizer_config.json

@@ -1 +0,0 @@
-{"do_lower_case": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "[UNK]", "pad_token": "<pad>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "sentence-transformers/all-mpnet-base-v2", "tokenizer_class": "MPNetTokenizer"}

checkpoint-1000/trainer_state.json

@@ -1,138 +0,0 @@
-{
-  "best_metric": 0.9337662337662338,
-  "best_model_checkpoint": "mpnet-metric/checkpoint-800",
-  "epoch": 18.181818181818183,
-  "global_step": 1000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.82,
-      "eval_accuracy": 0.7766233766233767,
-      "eval_f1": 0.7235739413582274,
-      "eval_loss": 1.8678635358810425,
-      "eval_matthews_correlation": 0.7744941020912063,
-      "eval_runtime": 12.4746,
-      "eval_samples_per_second": 246.901,
-      "eval_steps_per_second": 2.004,
-      "step": 100
-    },
-    {
-      "epoch": 3.64,
-      "eval_accuracy": 0.8633116883116884,
-      "eval_f1": 0.8279516467335359,
-      "eval_loss": 0.9851127862930298,
-      "eval_matthews_correlation": 0.8618599657600979,
-      "eval_runtime": 11.8588,
-      "eval_samples_per_second": 259.723,
-      "eval_steps_per_second": 2.108,
-      "step": 200
-    },
-    {
-      "epoch": 5.45,
-      "eval_accuracy": 0.9,
-      "eval_f1": 0.8874777454446199,
-      "eval_loss": 0.6038196682929993,
-      "eval_matthews_correlation": 0.8988080460356929,
-      "eval_runtime": 11.7845,
-      "eval_samples_per_second": 261.359,
-      "eval_steps_per_second": 2.121,
-      "step": 300
-    },
-    {
-      "epoch": 7.27,
-      "eval_accuracy": 0.9185064935064935,
-      "eval_f1": 0.9081076782008323,
-      "eval_loss": 0.42275315523147583,
-      "eval_matthews_correlation": 0.9174232607369284,
-      "eval_runtime": 11.9852,
-      "eval_samples_per_second": 256.983,
-      "eval_steps_per_second": 2.086,
-      "step": 400
-    },
-    {
-      "epoch": 9.09,
-      "learning_rate": 1.9318181818181818e-05,
-      "loss": 1.0552,
-      "step": 500
-    },
-    {
-      "epoch": 9.09,
-      "eval_accuracy": 0.9288961038961039,
-      "eval_f1": 0.9288248145286723,
-      "eval_loss": 0.3406440317630768,
-      "eval_matthews_correlation": 0.9279299978682313,
-      "eval_runtime": 11.8752,
-      "eval_samples_per_second": 259.363,
-      "eval_steps_per_second": 2.105,
-      "step": 500
-    },
-    {
-      "epoch": 10.91,
-      "eval_accuracy": 0.9279220779220779,
-      "eval_f1": 0.9286644401345681,
-      "eval_loss": 0.2898033559322357,
-      "eval_matthews_correlation": 0.9269395086148065,
-      "eval_runtime": 12.0212,
-      "eval_samples_per_second": 256.214,
-      "eval_steps_per_second": 2.08,
-      "step": 600
-    },
-    {
-      "epoch": 12.73,
-      "eval_accuracy": 0.9298701298701298,
-      "eval_f1": 0.9302893867424595,
-      "eval_loss": 0.26082128286361694,
-      "eval_matthews_correlation": 0.928906606647114,
-      "eval_runtime": 11.6947,
-      "eval_samples_per_second": 263.367,
-      "eval_steps_per_second": 2.138,
-      "step": 700
-    },
-    {
-      "epoch": 14.55,
-      "eval_accuracy": 0.9337662337662338,
-      "eval_f1": 0.9336908245424703,
-      "eval_loss": 0.25573107600212097,
-      "eval_matthews_correlation": 0.9328474614092904,
-      "eval_runtime": 12.1404,
-      "eval_samples_per_second": 253.699,
-      "eval_steps_per_second": 2.059,
-      "step": 800
-    },
-    {
-      "epoch": 16.36,
-      "eval_accuracy": 0.9340909090909091,
-      "eval_f1": 0.9341025795943668,
-      "eval_loss": 0.25437676906585693,
-      "eval_matthews_correlation": 0.9331859044314311,
-      "eval_runtime": 11.8917,
-      "eval_samples_per_second": 259.004,
-      "eval_steps_per_second": 2.102,
-      "step": 900
-    },
-    {
-      "epoch": 18.18,
-      "learning_rate": 1.3636363636363637e-05,
-      "loss": 0.0875,
-      "step": 1000
-    },
-    {
-      "epoch": 18.18,
-      "eval_accuracy": 0.9314935064935065,
-      "eval_f1": 0.9320089101075096,
-      "eval_loss": 0.253446489572525,
-      "eval_matthews_correlation": 0.930554683394419,
-      "eval_runtime": 12.2294,
-      "eval_samples_per_second": 251.853,
-      "eval_steps_per_second": 2.044,
-      "step": 1000
-    }
-  ],
-  "max_steps": 2200,
-  "num_train_epochs": 40,
-  "total_flos": 3951207219755796.0,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-1000/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:25b4dd4501c6028241dbafe254eb397a1ab407473a18a2c67e449038569d244d
-size 2927

checkpoint-200/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8633116883116884,
+  "best_metric": 0.8512987012987013,
   "best_model_checkpoint": "mpnet-metric/checkpoint-200",
   "epoch": 3.6363636363636362,
   "global_step": 200,
@@ -9,24 +9,24 @@
   "log_history": [
     {
       "epoch": 1.82,
-      "eval_accuracy": 0.7766233766233767,
-      "eval_f1": 0.7235739413582274,
-      "eval_loss": 1.8678635358810425,
-      "eval_matthews_correlation": 0.7744941020912063,
-      "eval_runtime": 12.4746,
-      "eval_samples_per_second": 246.901,
-      "eval_steps_per_second": 2.004,
+      "eval_accuracy": 0.7512987012987012,
+      "eval_f1": 0.7179602512079534,
+      "eval_loss": 1.8811957836151123,
+      "eval_matthews_correlation": 0.7494129786005829,
+      "eval_runtime": 10.5835,
+      "eval_samples_per_second": 291.02,
+      "eval_steps_per_second": 2.362,
       "step": 100
     },
     {
       "epoch": 3.64,
-      "eval_accuracy": 0.8633116883116884,
-      "eval_f1": 0.8279516467335359,
-      "eval_loss": 0.9851127862930298,
-      "eval_matthews_correlation": 0.8618599657600979,
-      "eval_runtime": 11.8588,
-      "eval_samples_per_second": 259.723,
-      "eval_steps_per_second": 2.108,
+      "eval_accuracy": 0.8512987012987013,
+      "eval_f1": 0.8329100165761718,
+      "eval_loss": 1.014992594718933,
+      "eval_matthews_correlation": 0.8501032826673115,
+      "eval_runtime": 10.1867,
+      "eval_samples_per_second": 302.355,
+      "eval_steps_per_second": 2.454,
       "step": 200
     }
   ],

checkpoint-200/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25b4dd4501c6028241dbafe254eb397a1ab407473a18a2c67e449038569d244d
+oid sha256:cdb3aaaf3a9ec1e810889c6c997c0310091ccf4b24a2b614da01b305925e2c65
 size 2927

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cd9b4ce061cca007cad04d4bb6c1f567c16e113b530b72408c52034ca3103ab
+oid sha256:004bd0ebd1ae2ffd37a03a0a16a2ce3ff5c9c4db406958b8eeb17cbc7dfaa0c8
 size 440628841

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25b4dd4501c6028241dbafe254eb397a1ab407473a18a2c67e449038569d244d
+oid sha256:cdb3aaaf3a9ec1e810889c6c997c0310091ccf4b24a2b614da01b305925e2c65
 size 2927