Training in progress, step 2862

run-15/checkpoint-2862/config.json

@@ -0,0 +1,330 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "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",
+    "77": "LABEL_77",
+    "78": "LABEL_78",
+    "79": "LABEL_79",
+    "80": "LABEL_80",
+    "81": "LABEL_81",
+    "82": "LABEL_82",
+    "83": "LABEL_83",
+    "84": "LABEL_84",
+    "85": "LABEL_85",
+    "86": "LABEL_86",
+    "87": "LABEL_87",
+    "88": "LABEL_88",
+    "89": "LABEL_89",
+    "90": "LABEL_90",
+    "91": "LABEL_91",
+    "92": "LABEL_92",
+    "93": "LABEL_93",
+    "94": "LABEL_94",
+    "95": "LABEL_95",
+    "96": "LABEL_96",
+    "97": "LABEL_97",
+    "98": "LABEL_98",
+    "99": "LABEL_99",
+    "100": "LABEL_100",
+    "101": "LABEL_101",
+    "102": "LABEL_102",
+    "103": "LABEL_103",
+    "104": "LABEL_104",
+    "105": "LABEL_105",
+    "106": "LABEL_106",
+    "107": "LABEL_107",
+    "108": "LABEL_108",
+    "109": "LABEL_109",
+    "110": "LABEL_110",
+    "111": "LABEL_111",
+    "112": "LABEL_112",
+    "113": "LABEL_113",
+    "114": "LABEL_114",
+    "115": "LABEL_115",
+    "116": "LABEL_116",
+    "117": "LABEL_117",
+    "118": "LABEL_118",
+    "119": "LABEL_119",
+    "120": "LABEL_120",
+    "121": "LABEL_121",
+    "122": "LABEL_122",
+    "123": "LABEL_123",
+    "124": "LABEL_124",
+    "125": "LABEL_125",
+    "126": "LABEL_126",
+    "127": "LABEL_127",
+    "128": "LABEL_128",
+    "129": "LABEL_129",
+    "130": "LABEL_130",
+    "131": "LABEL_131",
+    "132": "LABEL_132",
+    "133": "LABEL_133",
+    "134": "LABEL_134",
+    "135": "LABEL_135",
+    "136": "LABEL_136",
+    "137": "LABEL_137",
+    "138": "LABEL_138",
+    "139": "LABEL_139",
+    "140": "LABEL_140",
+    "141": "LABEL_141",
+    "142": "LABEL_142",
+    "143": "LABEL_143",
+    "144": "LABEL_144",
+    "145": "LABEL_145",
+    "146": "LABEL_146",
+    "147": "LABEL_147",
+    "148": "LABEL_148",
+    "149": "LABEL_149",
+    "150": "LABEL_150"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_100": 100,
+    "LABEL_101": 101,
+    "LABEL_102": 102,
+    "LABEL_103": 103,
+    "LABEL_104": 104,
+    "LABEL_105": 105,
+    "LABEL_106": 106,
+    "LABEL_107": 107,
+    "LABEL_108": 108,
+    "LABEL_109": 109,
+    "LABEL_11": 11,
+    "LABEL_110": 110,
+    "LABEL_111": 111,
+    "LABEL_112": 112,
+    "LABEL_113": 113,
+    "LABEL_114": 114,
+    "LABEL_115": 115,
+    "LABEL_116": 116,
+    "LABEL_117": 117,
+    "LABEL_118": 118,
+    "LABEL_119": 119,
+    "LABEL_12": 12,
+    "LABEL_120": 120,
+    "LABEL_121": 121,
+    "LABEL_122": 122,
+    "LABEL_123": 123,
+    "LABEL_124": 124,
+    "LABEL_125": 125,
+    "LABEL_126": 126,
+    "LABEL_127": 127,
+    "LABEL_128": 128,
+    "LABEL_129": 129,
+    "LABEL_13": 13,
+    "LABEL_130": 130,
+    "LABEL_131": 131,
+    "LABEL_132": 132,
+    "LABEL_133": 133,
+    "LABEL_134": 134,
+    "LABEL_135": 135,
+    "LABEL_136": 136,
+    "LABEL_137": 137,
+    "LABEL_138": 138,
+    "LABEL_139": 139,
+    "LABEL_14": 14,
+    "LABEL_140": 140,
+    "LABEL_141": 141,
+    "LABEL_142": 142,
+    "LABEL_143": 143,
+    "LABEL_144": 144,
+    "LABEL_145": 145,
+    "LABEL_146": 146,
+    "LABEL_147": 147,
+    "LABEL_148": 148,
+    "LABEL_149": 149,
+    "LABEL_15": 15,
+    "LABEL_150": 150,
+    "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_77": 77,
+    "LABEL_78": 78,
+    "LABEL_79": 79,
+    "LABEL_8": 8,
+    "LABEL_80": 80,
+    "LABEL_81": 81,
+    "LABEL_82": 82,
+    "LABEL_83": 83,
+    "LABEL_84": 84,
+    "LABEL_85": 85,
+    "LABEL_86": 86,
+    "LABEL_87": 87,
+    "LABEL_88": 88,
+    "LABEL_89": 89,
+    "LABEL_9": 9,
+    "LABEL_90": 90,
+    "LABEL_91": 91,
+    "LABEL_92": 92,
+    "LABEL_93": 93,
+    "LABEL_94": 94,
+    "LABEL_95": 95,
+    "LABEL_96": 96,
+    "LABEL_97": 97,
+    "LABEL_98": 98,
+    "LABEL_99": 99
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.57.1",
+  "vocab_size": 30522
+}

run-15/checkpoint-2862/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cefc7c04cefc59c706dd01e3589e97ef44250db349f7a9b60c3a12d427b4093
+size 268290900

run-15/checkpoint-2862/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c5030b3ea91c12e739dcfc9be3f9f7c7de597b4d2641f14827ca31205f9625
+size 536645835

run-15/checkpoint-2862/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ba0578b66134d94e8a9895f9e373cfaf43dc8dd0430a6d2b238ce3a5fb776c
+size 14645

run-15/checkpoint-2862/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d096fac789ed022e5bee1c20f0a12bd1365801b6087b9ba94b777b004aa708
+size 1465

run-15/checkpoint-2862/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-15/checkpoint-2862/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-15/checkpoint-2862/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 2862,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9968553459119497,
+      "grad_norm": 10.417920112609863,
+      "learning_rate": 1.7791754018169113e-05,
+      "loss": 24.3647,
+      "step": 317
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.0070967741935483875,
+      "eval_loss": 19.544130325317383,
+      "eval_runtime": 7.6696,
+      "eval_samples_per_second": 404.191,
+      "eval_steps_per_second": 8.475,
+      "step": 318
+    },
+    {
+      "epoch": 1.9937106918238994,
+      "grad_norm": 16.617650985717773,
+      "learning_rate": 1.557651991614256e-05,
+      "loss": 18.0272,
+      "step": 634
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.005161290322580645,
+      "eval_loss": 16.46693229675293,
+      "eval_runtime": 7.6645,
+      "eval_samples_per_second": 404.46,
+      "eval_steps_per_second": 8.481,
+      "step": 636
+    },
+    {
+      "epoch": 2.990566037735849,
+      "grad_norm": 56.44863510131836,
+      "learning_rate": 1.3361285814116003e-05,
+      "loss": 14.9204,
+      "step": 951
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.005161290322580645,
+      "eval_loss": 13.930508613586426,
+      "eval_runtime": 7.6133,
+      "eval_samples_per_second": 407.183,
+      "eval_steps_per_second": 8.538,
+      "step": 954
+    },
+    {
+      "epoch": 3.9874213836477987,
+      "grad_norm": 33.379825592041016,
+      "learning_rate": 1.114605171208945e-05,
+      "loss": 12.3664,
+      "step": 1268
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.005161290322580645,
+      "eval_loss": 12.059591293334961,
+      "eval_runtime": 7.6296,
+      "eval_samples_per_second": 406.314,
+      "eval_steps_per_second": 8.519,
+      "step": 1272
+    },
+    {
+      "epoch": 4.984276729559748,
+      "grad_norm": 51.79707717895508,
+      "learning_rate": 8.930817610062894e-06,
+      "loss": 10.721,
+      "step": 1585
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.005806451612903226,
+      "eval_loss": 11.096216201782227,
+      "eval_runtime": 7.6461,
+      "eval_samples_per_second": 405.435,
+      "eval_steps_per_second": 8.501,
+      "step": 1590
+    },
+    {
+      "epoch": 5.981132075471698,
+      "grad_norm": 54.033203125,
+      "learning_rate": 6.715583508036338e-06,
+      "loss": 9.6685,
+      "step": 1902
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.007741935483870968,
+      "eval_loss": 10.470527648925781,
+      "eval_runtime": 7.6592,
+      "eval_samples_per_second": 404.744,
+      "eval_steps_per_second": 8.487,
+      "step": 1908
+    },
+    {
+      "epoch": 6.977987421383648,
+      "grad_norm": 40.04940414428711,
+      "learning_rate": 4.500349406009784e-06,
+      "loss": 8.9602,
+      "step": 2219
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.007741935483870968,
+      "eval_loss": 10.081583023071289,
+      "eval_runtime": 7.6637,
+      "eval_samples_per_second": 404.506,
+      "eval_steps_per_second": 8.482,
+      "step": 2226
+    },
+    {
+      "epoch": 7.9748427672955975,
+      "grad_norm": 36.44171142578125,
+      "learning_rate": 2.2851153039832287e-06,
+      "loss": 8.4919,
+      "step": 2536
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.007741935483870968,
+      "eval_loss": 9.863218307495117,
+      "eval_runtime": 7.6408,
+      "eval_samples_per_second": 405.719,
+      "eval_steps_per_second": 8.507,
+      "step": 2544
+    },
+    {
+      "epoch": 8.971698113207546,
+      "grad_norm": 39.616554260253906,
+      "learning_rate": 6.988120195667366e-08,
+      "loss": 8.2453,
+      "step": 2853
+    }
+  ],
+  "logging_steps": 317,
+  "max_steps": 2862,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 1000000000.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 742838622388212.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9560685250081855,
+    "num_train_epochs": 9,
+    "temperature": 9
+  }
+}

run-15/checkpoint-2862/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b114a07d666a8525733be964bc20d05bb1b35f4d474ba8c3ca9211fe8fcdca
+size 5841