Upload 11 files

Browse files

Files changed (11) hide show

config.json +171 -0
optimizer.pt +3 -0
pytorch_model.bin +3 -0
rng_state.pth +3 -0
scheduler.pt +3 -0
special_tokens_map.json +1 -0
tokenizer.json +0 -0
tokenizer_config.json +1 -0
trainer_state.json +192 -0
training_args.bin +3 -0
vocab.txt +0 -0

config.json ADDED Viewed

	@@ -0,0 +1,171 @@

+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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"
+  },
+  "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_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bd98cdcfa1bea346140c781562c6f7459e873b4c23ffdd6e1f87aa0e70d5ffdb
+size 1418636517

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1d9f1ee166dfb395404d19da06543b15201b825819b99ca68a88843929f263
+size 709330993

rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:67e8699eb3e12aeca5f957a4c2d99b75f9a9b82c08ee2ddd08d65257965b16e9
+size 14503

scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3447daa87166d71e9c3b1a8f2a8e662e22e864d49f6304c158d388f9b42f32dd
+size 623

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@


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

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,192 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.731946144430845,
+  "global_step": 5500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.288129560420003e-05,
+      "loss": 0.6366,
+      "step": 500
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.89628166395538,
+      "eval_f1": 0.3185402661735773,
+      "eval_loss": 0.3915744125843048,
+      "eval_runtime": 10.4747,
+      "eval_samples_per_second": 314.091,
+      "eval_steps_per_second": 39.333,
+      "step": 500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 8.398291510945009e-05,
+      "loss": 0.3572,
+      "step": 1000
+    },
+    {
+      "epoch": 1.22,
+      "eval_accuracy": 0.908552172902626,
+      "eval_f1": 0.4301535570388646,
+      "eval_loss": 0.3250293731689453,
+      "eval_runtime": 10.4843,
+      "eval_samples_per_second": 313.802,
+      "eval_steps_per_second": 39.297,
+      "step": 1000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.508453461470013e-05,
+      "loss": 0.2839,
+      "step": 1500
+    },
+    {
+      "epoch": 1.84,
+      "eval_accuracy": 0.9177550546130606,
+      "eval_f1": 0.4733065481810558,
+      "eval_loss": 0.29356610774993896,
+      "eval_runtime": 10.3662,
+      "eval_samples_per_second": 317.379,
+      "eval_steps_per_second": 39.745,
+      "step": 1500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 6.618615411995017e-05,
+      "loss": 0.2231,
+      "step": 2000
+    },
+    {
+      "epoch": 2.45,
+      "eval_accuracy": 0.9202416918429003,
+      "eval_f1": 0.5303373844974727,
+      "eval_loss": 0.29578134417533875,
+      "eval_runtime": 10.3862,
+      "eval_samples_per_second": 316.768,
+      "eval_steps_per_second": 39.668,
+      "step": 2000
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 5.728777362520021e-05,
+      "loss": 0.1893,
+      "step": 2500
+    },
+    {
+      "epoch": 3.06,
+      "eval_accuracy": 0.9223100162677202,
+      "eval_f1": 0.5747956508031589,
+      "eval_loss": 0.32106420397758484,
+      "eval_runtime": 10.402,
+      "eval_samples_per_second": 316.284,
+      "eval_steps_per_second": 39.608,
+      "step": 2500
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 4.838939313045026e-05,
+      "loss": 0.1372,
+      "step": 3000
+    },
+    {
+      "epoch": 3.67,
+      "eval_accuracy": 0.9265628631187544,
+      "eval_f1": 0.5956050840740277,
+      "eval_loss": 0.2856525480747223,
+      "eval_runtime": 10.4359,
+      "eval_samples_per_second": 315.259,
+      "eval_steps_per_second": 39.479,
+      "step": 3000
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 3.9491012635700305e-05,
+      "loss": 0.1148,
+      "step": 3500
+    },
+    {
+      "epoch": 4.28,
+      "eval_accuracy": 0.9301417615617011,
+      "eval_f1": 0.6182402434709684,
+      "eval_loss": 0.2969909608364105,
+      "eval_runtime": 10.3712,
+      "eval_samples_per_second": 317.225,
+      "eval_steps_per_second": 39.725,
+      "step": 3500
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 3.059263214095035e-05,
+      "loss": 0.092,
+      "step": 4000
+    },
+    {
+      "epoch": 4.9,
+      "eval_accuracy": 0.932396002788752,
+      "eval_f1": 0.6418559187952009,
+      "eval_loss": 0.28680795431137085,
+      "eval_runtime": 10.3835,
+      "eval_samples_per_second": 316.85,
+      "eval_steps_per_second": 39.678,
+      "step": 4000
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 2.169425164620039e-05,
+      "loss": 0.0585,
+      "step": 4500
+    },
+    {
+      "epoch": 5.51,
+      "eval_accuracy": 0.932419242389031,
+      "eval_f1": 0.6322022976473333,
+      "eval_loss": 0.30797600746154785,
+      "eval_runtime": 10.3681,
+      "eval_samples_per_second": 317.319,
+      "eval_steps_per_second": 39.737,
+      "step": 4500
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 1.2795871151450436e-05,
+      "loss": 0.0492,
+      "step": 5000
+    },
+    {
+      "epoch": 6.12,
+      "eval_accuracy": 0.9329769927957239,
+      "eval_f1": 0.6370967443537814,
+      "eval_loss": 0.31786486506462097,
+      "eval_runtime": 10.4041,
+      "eval_samples_per_second": 316.22,
+      "eval_steps_per_second": 39.6,
+      "step": 5000
+    },
+    {
+      "epoch": 6.73,
+      "learning_rate": 3.897490656700481e-06,
+      "loss": 0.0295,
+      "step": 5500
+    },
+    {
+      "epoch": 6.73,
+      "eval_accuracy": 0.934278410411341,
+      "eval_f1": 0.6499060895478286,
+      "eval_loss": 0.3314834535121918,
+      "eval_runtime": 10.3769,
+      "eval_samples_per_second": 317.051,
+      "eval_steps_per_second": 39.704,
+      "step": 5500
+    }
+  ],
+  "max_steps": 5719,
+  "num_train_epochs": 7,
+  "total_flos": 1.1503917613056e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:af5bd9cdb2f90438ad9bbf82ba85e4e637c108051b33da1ca87448efbbe55288
+size 3247

vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff