adding model finetuned on POS

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9804082866064533,
+    "eval_f1": 0.9784274595889044,
+    "eval_loss": 0.06875239312648773,
+    "eval_precision": 0.9776080714627532,
+    "eval_recall": 0.9792482224175122,
+    "eval_runtime": 2.17,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 762.206,
+    "eval_steps_per_second": 23.963,
+    "train_loss": 0.07637897772448403,
+    "train_runtime": 8322.2563,
+    "train_samples": 14305,
+    "train_samples_per_second": 6.876,
+    "train_steps_per_second": 0.215
+}

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "pos",
+  "gradient_checkpointing": false,
+  "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"
+  },
+  "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_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "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,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31002
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9804082866064533,
+    "eval_f1": 0.9784274595889044,
+    "eval_loss": 0.06875239312648773,
+    "eval_precision": 0.9776080714627532,
+    "eval_recall": 0.9792482224175122,
+    "eval_runtime": 2.17,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 762.206,
+    "eval_steps_per_second": 23.963
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780f0d5df7209cae48b6ec4963c48e10253a59acaee273d2f406a46b4b64caf8
+size 437179953

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": false, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/data/jcanete/cache/78141ed1e8dcc5ff370950397ca0d1c5c9da478f54ec14544187d8a93eff1a26.f982506b52498d4adb4bd491f593dc92b2ef6be61bfdbe9d30f53f963f9f5b66", "name_or_path": "dccuchile/bert-base-spanish-wwm-uncased", "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.07637897772448403,
+    "train_runtime": 8322.2563,
+    "train_samples": 14305,
+    "train_samples_per_second": 6.876,
+    "train_steps_per_second": 0.215
+}

trainer_state.json

@@ -0,0 +1,463 @@
+{
+  "best_metric": 0.06875239312648773,
+  "best_model_checkpoint": "/data/jcanete/all_results/pos/beto_uncased/epochs_4_bs_32_lr_5e-5/checkpoint-850",
+  "epoch": 4.0,
+  "global_step": 1792,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "eval_accuracy": 0.9416445623342176,
+      "eval_f1": 0.9315524877309181,
+      "eval_loss": 0.20549777150154114,
+      "eval_precision": 0.9304758488761358,
+      "eval_recall": 0.9326316209954462,
+      "eval_runtime": 2.2237,
+      "eval_samples_per_second": 743.792,
+      "eval_steps_per_second": 23.384,
+      "step": 50
+    },
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.9580969009166302,
+      "eval_f1": 0.9511250424261785,
+      "eval_loss": 0.14205431938171387,
+      "eval_precision": 0.9507643795154272,
+      "eval_recall": 0.9514859790684669,
+      "eval_runtime": 2.1719,
+      "eval_samples_per_second": 761.545,
+      "eval_steps_per_second": 23.942,
+      "step": 100
+    },
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.963922371822852,
+      "eval_f1": 0.9588180131287536,
+      "eval_loss": 0.12034180760383606,
+      "eval_precision": 0.9578433326689256,
+      "eval_recall": 0.9597946792362387,
+      "eval_runtime": 2.8499,
+      "eval_samples_per_second": 580.367,
+      "eval_steps_per_second": 18.246,
+      "step": 150
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.9677668468589464,
+      "eval_f1": 0.9631556392700891,
+      "eval_loss": 0.10953102260828018,
+      "eval_precision": 0.9611918922682156,
+      "eval_recall": 0.9651274266996884,
+      "eval_runtime": 3.0514,
+      "eval_samples_per_second": 542.046,
+      "eval_steps_per_second": 17.041,
+      "step": 200
+    },
+    {
+      "epoch": 0.56,
+      "eval_accuracy": 0.9704865191552228,
+      "eval_f1": 0.9662253768243082,
+      "eval_loss": 0.1019054427742958,
+      "eval_precision": 0.9645330785765465,
+      "eval_recall": 0.9679236238715347,
+      "eval_runtime": 3.1025,
+      "eval_samples_per_second": 533.122,
+      "eval_steps_per_second": 16.761,
+      "step": 250
+    },
+    {
+      "epoch": 0.67,
+      "eval_accuracy": 0.9732061914514992,
+      "eval_f1": 0.9694056641404069,
+      "eval_loss": 0.09022298455238342,
+      "eval_precision": 0.9680156137974986,
+      "eval_recall": 0.970799712391148,
+      "eval_runtime": 3.1303,
+      "eval_samples_per_second": 528.378,
+      "eval_steps_per_second": 16.612,
+      "step": 300
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.973928079777054,
+      "eval_f1": 0.9705615354688107,
+      "eval_loss": 0.08854629099369049,
+      "eval_precision": 0.9695266567015446,
+      "eval_recall": 0.9715986258688184,
+      "eval_runtime": 3.1649,
+      "eval_samples_per_second": 522.602,
+      "eval_steps_per_second": 16.43,
+      "step": 350
+    },
+    {
+      "epoch": 0.89,
+      "eval_accuracy": 0.9757579827418326,
+      "eval_f1": 0.9730894722662914,
+      "eval_loss": 0.08236456662416458,
+      "eval_precision": 0.972264869499332,
+      "eval_recall": 0.9739154749540625,
+      "eval_runtime": 3.2614,
+      "eval_samples_per_second": 507.147,
+      "eval_steps_per_second": 15.944,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9756908303394554,
+      "eval_f1": 0.9728064139767254,
+      "eval_loss": 0.08048809319734573,
+      "eval_precision": 0.9714018282118176,
+      "eval_recall": 0.9742150675081889,
+      "eval_runtime": 3.0696,
+      "eval_samples_per_second": 538.832,
+      "eval_steps_per_second": 16.94,
+      "step": 450
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.607700892857143e-05,
+      "loss": 0.1891,
+      "step": 500
+    },
+    {
+      "epoch": 1.12,
+      "eval_accuracy": 0.976681328274519,
+      "eval_f1": 0.9741610570929944,
+      "eval_loss": 0.08373625576496124,
+      "eval_precision": 0.9728125560180851,
+      "eval_recall": 0.9755133019094032,
+      "eval_runtime": 3.2499,
+      "eval_samples_per_second": 508.931,
+      "eval_steps_per_second": 16.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.23,
+      "eval_accuracy": 0.9778229191149314,
+      "eval_f1": 0.975405828768695,
+      "eval_loss": 0.08112843334674835,
+      "eval_precision": 0.9745210231463944,
+      "eval_recall": 0.9762922425501318,
+      "eval_runtime": 3.1199,
+      "eval_samples_per_second": 530.139,
+      "eval_steps_per_second": 16.667,
+      "step": 550
+    },
+    {
+      "epoch": 1.34,
+      "eval_accuracy": 0.9784944431387033,
+      "eval_f1": 0.9759250024932683,
+      "eval_loss": 0.07825577259063721,
+      "eval_precision": 0.974622524999004,
+      "eval_recall": 0.9772309658863945,
+      "eval_runtime": 3.0821,
+      "eval_samples_per_second": 536.646,
+      "eval_steps_per_second": 16.872,
+      "step": 600
+    },
+    {
+      "epoch": 1.45,
+      "eval_accuracy": 0.9782594097303831,
+      "eval_f1": 0.976126314948999,
+      "eval_loss": 0.07251805067062378,
+      "eval_precision": 0.9755615848062882,
+      "eval_recall": 0.976691699288967,
+      "eval_runtime": 3.0567,
+      "eval_samples_per_second": 541.099,
+      "eval_steps_per_second": 17.012,
+      "step": 650
+    },
+    {
+      "epoch": 1.56,
+      "eval_accuracy": 0.9793506362690125,
+      "eval_f1": 0.9770881149585869,
+      "eval_loss": 0.07318206131458282,
+      "eval_precision": 0.976367117386622,
+      "eval_recall": 0.9778101781577055,
+      "eval_runtime": 3.123,
+      "eval_samples_per_second": 529.611,
+      "eval_steps_per_second": 16.65,
+      "step": 700
+    },
+    {
+      "epoch": 1.67,
+      "eval_accuracy": 0.9792331195648525,
+      "eval_f1": 0.9769158636100637,
+      "eval_loss": 0.07212899625301361,
+      "eval_precision": 0.9758839239446725,
+      "eval_recall": 0.9779499880162978,
+      "eval_runtime": 3.1071,
+      "eval_samples_per_second": 532.328,
+      "eval_steps_per_second": 16.736,
+      "step": 750
+    },
+    {
+      "epoch": 1.79,
+      "eval_accuracy": 0.9795856696773327,
+      "eval_f1": 0.9771997366898726,
+      "eval_loss": 0.07169780880212784,
+      "eval_precision": 0.9759732238913017,
+      "eval_recall": 0.9784293361029001,
+      "eval_runtime": 3.1916,
+      "eval_samples_per_second": 518.234,
+      "eval_steps_per_second": 16.293,
+      "step": 800
+    },
+    {
+      "epoch": 1.9,
+      "eval_accuracy": 0.9804082866064533,
+      "eval_f1": 0.9784274595889044,
+      "eval_loss": 0.06875239312648773,
+      "eval_precision": 0.9776080714627532,
+      "eval_recall": 0.9792482224175122,
+      "eval_runtime": 3.2127,
+      "eval_samples_per_second": 514.836,
+      "eval_steps_per_second": 16.186,
+      "step": 850
+    },
+    {
+      "epoch": 2.01,
+      "eval_accuracy": 0.9791995433636639,
+      "eval_f1": 0.977885114366692,
+      "eval_loss": 0.07294180244207382,
+      "eval_precision": 0.9772219562789214,
+      "eval_recall": 0.9785491731245506,
+      "eval_runtime": 3.0782,
+      "eval_samples_per_second": 537.322,
+      "eval_steps_per_second": 16.893,
+      "step": 900
+    },
+    {
+      "epoch": 2.12,
+      "eval_accuracy": 0.9806097438135849,
+      "eval_f1": 0.9782331112086509,
+      "eval_loss": 0.0767468586564064,
+      "eval_precision": 0.977180325255102,
+      "eval_recall": 0.9792881680913957,
+      "eval_runtime": 3.1248,
+      "eval_samples_per_second": 529.314,
+      "eval_steps_per_second": 16.641,
+      "step": 950
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 2.2126116071428573e-05,
+      "loss": 0.049,
+      "step": 1000
+    },
+    {
+      "epoch": 2.23,
+      "eval_accuracy": 0.9794177886713897,
+      "eval_f1": 0.9773666247530087,
+      "eval_loss": 0.07647667080163956,
+      "eval_precision": 0.9766843511907136,
+      "eval_recall": 0.9780498522010066,
+      "eval_runtime": 3.0978,
+      "eval_samples_per_second": 533.936,
+      "eval_steps_per_second": 16.786,
+      "step": 1000
+    },
+    {
+      "epoch": 2.34,
+      "eval_accuracy": 0.97977033878387,
+      "eval_f1": 0.9773353018634531,
+      "eval_loss": 0.07652360200881958,
+      "eval_precision": 0.9762834821428571,
+      "eval_recall": 0.9783893904290165,
+      "eval_runtime": 3.0494,
+      "eval_samples_per_second": 542.399,
+      "eval_steps_per_second": 17.052,
+      "step": 1050
+    },
+    {
+      "epoch": 2.46,
+      "eval_accuracy": 0.9807272605177451,
+      "eval_f1": 0.9790142798694754,
+      "eval_loss": 0.07351543754339218,
+      "eval_precision": 0.9782821131563728,
+      "eval_recall": 0.9797475433410562,
+      "eval_runtime": 2.1592,
+      "eval_samples_per_second": 766.034,
+      "eval_steps_per_second": 24.083,
+      "step": 1100
+    },
+    {
+      "epoch": 2.57,
+      "eval_accuracy": 0.9812812678373569,
+      "eval_f1": 0.9792086517548935,
+      "eval_loss": 0.07407119125127792,
+      "eval_precision": 0.9782522026870789,
+      "eval_recall": 0.9801669729168331,
+      "eval_runtime": 2.3144,
+      "eval_samples_per_second": 714.646,
+      "eval_steps_per_second": 22.468,
+      "step": 1150
+    },
+    {
+      "epoch": 2.68,
+      "eval_accuracy": 0.9805761676123963,
+      "eval_f1": 0.9790627120673825,
+      "eval_loss": 0.07566250115633011,
+      "eval_precision": 0.9783987553853518,
+      "eval_recall": 0.9797275705041144,
+      "eval_runtime": 2.157,
+      "eval_samples_per_second": 766.796,
+      "eval_steps_per_second": 24.107,
+      "step": 1200
+    },
+    {
+      "epoch": 2.79,
+      "eval_accuracy": 0.9812141154349797,
+      "eval_f1": 0.9793385543971667,
+      "eval_loss": 0.0741068422794342,
+      "eval_precision": 0.978372236729324,
+      "eval_recall": 0.9803067827754254,
+      "eval_runtime": 2.1422,
+      "eval_samples_per_second": 772.1,
+      "eval_steps_per_second": 24.274,
+      "step": 1250
+    },
+    {
+      "epoch": 2.9,
+      "eval_accuracy": 0.9809287177248766,
+      "eval_f1": 0.9787904786607873,
+      "eval_loss": 0.07299875468015671,
+      "eval_precision": 0.9777954953159258,
+      "eval_recall": 0.9797874890149397,
+      "eval_runtime": 2.1492,
+      "eval_samples_per_second": 769.58,
+      "eval_steps_per_second": 24.195,
+      "step": 1300
+    },
+    {
+      "epoch": 3.01,
+      "eval_accuracy": 0.9813652083403284,
+      "eval_f1": 0.9792876384316073,
+      "eval_loss": 0.07347211241722107,
+      "eval_precision": 0.9783700809377617,
+      "eval_recall": 0.9802069185907166,
+      "eval_runtime": 2.1559,
+      "eval_samples_per_second": 767.204,
+      "eval_steps_per_second": 24.12,
+      "step": 1350
+    },
+    {
+      "epoch": 3.12,
+      "eval_accuracy": 0.9818856394587516,
+      "eval_f1": 0.9799355463098764,
+      "eval_loss": 0.07577352970838547,
+      "eval_precision": 0.9790466317111585,
+      "eval_recall": 0.9808260765359111,
+      "eval_runtime": 2.1533,
+      "eval_samples_per_second": 768.11,
+      "eval_steps_per_second": 24.149,
+      "step": 1400
+    },
+    {
+      "epoch": 3.24,
+      "eval_accuracy": 0.98168418225162,
+      "eval_f1": 0.9799245674602383,
+      "eval_loss": 0.07578457146883011,
+      "eval_precision": 0.9790844199864418,
+      "eval_recall": 0.9807661580250859,
+      "eval_runtime": 2.1906,
+      "eval_samples_per_second": 755.058,
+      "eval_steps_per_second": 23.738,
+      "step": 1450
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 8.175223214285714e-06,
+      "loss": 0.0257,
+      "step": 1500
+    },
+    {
+      "epoch": 3.35,
+      "eval_accuracy": 0.9813316321391398,
+      "eval_f1": 0.9794737209743247,
+      "eval_loss": 0.07658305764198303,
+      "eval_precision": 0.9787217070495563,
+      "eval_recall": 0.9802268914276584,
+      "eval_runtime": 2.1425,
+      "eval_samples_per_second": 771.995,
+      "eval_steps_per_second": 24.271,
+      "step": 1500
+    },
+    {
+      "epoch": 3.46,
+      "eval_accuracy": 0.9814659369438942,
+      "eval_f1": 0.9793369052251389,
+      "eval_loss": 0.07673583924770355,
+      "eval_precision": 0.9784485336629518,
+      "eval_recall": 0.9802268914276584,
+      "eval_runtime": 2.137,
+      "eval_samples_per_second": 773.994,
+      "eval_steps_per_second": 24.334,
+      "step": 1550
+    },
+    {
+      "epoch": 3.57,
+      "eval_accuracy": 0.9814323607427056,
+      "eval_f1": 0.9795576307204215,
+      "eval_loss": 0.07736379653215408,
+      "eval_precision": 0.9786105850692715,
+      "eval_recall": 0.980506511144843,
+      "eval_runtime": 2.2904,
+      "eval_samples_per_second": 722.158,
+      "eval_steps_per_second": 22.704,
+      "step": 1600
+    },
+    {
+      "epoch": 3.68,
+      "eval_accuracy": 0.98168418225162,
+      "eval_f1": 0.9797461787125354,
+      "eval_loss": 0.07633356750011444,
+      "eval_precision": 0.978847687400319,
+      "eval_recall": 0.9806463210034353,
+      "eval_runtime": 2.1499,
+      "eval_samples_per_second": 769.338,
+      "eval_steps_per_second": 24.187,
+      "step": 1650
+    },
+    {
+      "epoch": 3.79,
+      "eval_accuracy": 0.9814995131450828,
+      "eval_f1": 0.9798431356896241,
+      "eval_loss": 0.07660035789012909,
+      "eval_precision": 0.9790810832369481,
+      "eval_recall": 0.9806063753295519,
+      "eval_runtime": 2.1514,
+      "eval_samples_per_second": 768.802,
+      "eval_steps_per_second": 24.17,
+      "step": 1700
+    },
+    {
+      "epoch": 3.91,
+      "eval_accuracy": 0.9819192156599402,
+      "eval_f1": 0.9799660780205528,
+      "eval_loss": 0.07586053013801575,
+      "eval_precision": 0.979047884853076,
+      "eval_recall": 0.9808859950467365,
+      "eval_runtime": 2.182,
+      "eval_samples_per_second": 758.038,
+      "eval_steps_per_second": 23.832,
+      "step": 1750
+    },
+    {
+      "epoch": 4.0,
+      "step": 1792,
+      "total_flos": 2508921974905632.0,
+      "train_loss": 0.07637897772448403,
+      "train_runtime": 8322.2563,
+      "train_samples_per_second": 6.876,
+      "train_steps_per_second": 0.215
+    }
+  ],
+  "max_steps": 1792,
+  "num_train_epochs": 4,
+  "total_flos": 2508921974905632.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5c1bf6d555ffb3f2c712590a2a672cfa9f70e0b96da6d0e4364d82e67b00ff
+size 2863