update readme and add model weights

README.md

@@ -1,3 +1,4 @@
 ---
 license: afl-3.0
+inference: false
 ---

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "/mnt/beegfs/mc000051/CERPLES/Models/bio-bert-base-spanish-wwm-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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"
+  },
+  "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_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",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 38468
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f7ed6306ce2558c67241d43e75108ef5504d67223240c7cdc3c037e22af4dd
+size 924893085

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13199df00899bc172e4a71c8c8055064f5b667553461e2bafa89578e1e0bc393
+size 462459309

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3661d92c3c0d07b200452f1fd844a838ddd196d6a9c84c47e571efdde5b87954
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a4078fa2defe0274b0261f1ba356b0aa8e2ec3604b66663f1a29d151167f2a
+size 623

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": "/mnt/beegfs/mc000051/CERPLES/Models/bio-bert-base-spanish-wwm-uncased/special_tokens_map.json", "name_or_path": "/mnt/beegfs/mc000051/CERPLES/Models/bio-bert-base-spanish-wwm-uncased", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,336 @@
+{
+  "best_metric": 0.5951067347267447,
+  "best_model_checkpoint": "./CARES/checkpoints/bio-bert/checkpoint-8000",
+  "epoch": 56.737588652482266,
+  "global_step": 8000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.55,
+      "learning_rate": 4.822695035460993e-05,
+      "loss": 0.2147,
+      "step": 500
+    },
+    {
+      "epoch": 3.55,
+      "eval_loss": 0.18118813633918762,
+      "eval_macro_f1": 0.30207207042893824,
+      "eval_macro_precision": 0.5201644497890242,
+      "eval_macro_recall": 0.2643836699737847,
+      "eval_micro_f1": 0.6030504497457959,
+      "eval_micro_precision": 0.7529296875,
+      "eval_micro_recall": 0.50293542074364,
+      "eval_runtime": 2.8226,
+      "eval_samples_per_second": 342.243,
+      "eval_steps_per_second": 21.612,
+      "step": 500
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 4.645390070921986e-05,
+      "loss": 0.1141,
+      "step": 1000
+    },
+    {
+      "epoch": 7.09,
+      "eval_loss": 0.17683139443397522,
+      "eval_macro_f1": 0.4546518122185415,
+      "eval_macro_precision": 0.5858554608554609,
+      "eval_macro_recall": 0.3972024243991636,
+      "eval_micro_f1": 0.6614564831261102,
+      "eval_micro_precision": 0.7262090483619345,
+      "eval_micro_recall": 0.6073059360730594,
+      "eval_runtime": 8.8815,
+      "eval_samples_per_second": 108.765,
+      "eval_steps_per_second": 6.868,
+      "step": 1000
+    },
+    {
+      "epoch": 10.64,
+      "learning_rate": 4.468085106382979e-05,
+      "loss": 0.0644,
+      "step": 1500
+    },
+    {
+      "epoch": 10.64,
+      "eval_loss": 0.19797927141189575,
+      "eval_macro_f1": 0.49327845224918243,
+      "eval_macro_precision": 0.5767520501746984,
+      "eval_macro_recall": 0.45487076049782793,
+      "eval_micro_f1": 0.6739427012278308,
+      "eval_micro_precision": 0.7062187276626162,
+      "eval_micro_recall": 0.644487932159165,
+      "eval_runtime": 2.8151,
+      "eval_samples_per_second": 343.151,
+      "eval_steps_per_second": 21.669,
+      "step": 1500
+    },
+    {
+      "epoch": 14.18,
+      "learning_rate": 4.2907801418439716e-05,
+      "loss": 0.0352,
+      "step": 2000
+    },
+    {
+      "epoch": 14.18,
+      "eval_loss": 0.20916847884655,
+      "eval_macro_f1": 0.4970581008166056,
+      "eval_macro_precision": 0.5794598382601246,
+      "eval_macro_recall": 0.4507358136783414,
+      "eval_micro_f1": 0.6827225130890052,
+      "eval_micro_precision": 0.7342342342342343,
+      "eval_micro_recall": 0.6379647749510763,
+      "eval_runtime": 2.8186,
+      "eval_samples_per_second": 342.721,
+      "eval_steps_per_second": 21.642,
+      "step": 2000
+    },
+    {
+      "epoch": 17.73,
+      "learning_rate": 4.1134751773049644e-05,
+      "loss": 0.0206,
+      "step": 2500
+    },
+    {
+      "epoch": 17.73,
+      "eval_loss": 0.2218163162469864,
+      "eval_macro_f1": 0.5259843138534941,
+      "eval_macro_precision": 0.6617788311276105,
+      "eval_macro_recall": 0.47650769040572616,
+      "eval_micro_f1": 0.7059634608755602,
+      "eval_micro_precision": 0.7485380116959064,
+      "eval_micro_recall": 0.6679712981082844,
+      "eval_runtime": 2.81,
+      "eval_samples_per_second": 343.773,
+      "eval_steps_per_second": 21.708,
+      "step": 2500
+    },
+    {
+      "epoch": 21.28,
+      "learning_rate": 3.936170212765958e-05,
+      "loss": 0.0122,
+      "step": 3000
+    },
+    {
+      "epoch": 21.28,
+      "eval_loss": 0.23995181918144226,
+      "eval_macro_f1": 0.5252080208777923,
+      "eval_macro_precision": 0.6447606443742053,
+      "eval_macro_recall": 0.4820232253204122,
+      "eval_micro_f1": 0.7052341597796142,
+      "eval_micro_precision": 0.7469000729394603,
+      "eval_micro_recall": 0.6679712981082844,
+      "eval_runtime": 2.8113,
+      "eval_samples_per_second": 343.611,
+      "eval_steps_per_second": 21.698,
+      "step": 3000
+    },
+    {
+      "epoch": 24.82,
+      "learning_rate": 3.75886524822695e-05,
+      "loss": 0.008,
+      "step": 3500
+    },
+    {
+      "epoch": 24.82,
+      "eval_loss": 0.25718826055526733,
+      "eval_macro_f1": 0.5539441017425312,
+      "eval_macro_precision": 0.7083242996515385,
+      "eval_macro_recall": 0.4999427418977689,
+      "eval_micro_f1": 0.7067209775967414,
+      "eval_micro_precision": 0.7367303609341825,
+      "eval_micro_recall": 0.6790606653620352,
+      "eval_runtime": 2.8104,
+      "eval_samples_per_second": 343.718,
+      "eval_steps_per_second": 21.705,
+      "step": 3500
+    },
+    {
+      "epoch": 28.37,
+      "learning_rate": 3.5815602836879437e-05,
+      "loss": 0.0057,
+      "step": 4000
+    },
+    {
+      "epoch": 28.37,
+      "eval_loss": 0.26836735010147095,
+      "eval_macro_f1": 0.5549375909054308,
+      "eval_macro_precision": 0.6742213004313782,
+      "eval_macro_recall": 0.517984206223687,
+      "eval_micro_f1": 0.6922293858160842,
+      "eval_micro_precision": 0.7213578500707214,
+      "eval_micro_recall": 0.6653620352250489,
+      "eval_runtime": 2.8131,
+      "eval_samples_per_second": 343.392,
+      "eval_steps_per_second": 21.684,
+      "step": 4000
+    },
+    {
+      "epoch": 31.91,
+      "learning_rate": 3.4042553191489365e-05,
+      "loss": 0.0044,
+      "step": 4500
+    },
+    {
+      "epoch": 31.91,
+      "eval_loss": 0.2778957784175873,
+      "eval_macro_f1": 0.5565319075579724,
+      "eval_macro_precision": 0.7103639870539683,
+      "eval_macro_recall": 0.4991815941846965,
+      "eval_micro_f1": 0.7065663474692202,
+      "eval_micro_precision": 0.7426312005751258,
+      "eval_micro_recall": 0.6738421395955643,
+      "eval_runtime": 2.8149,
+      "eval_samples_per_second": 343.169,
+      "eval_steps_per_second": 21.67,
+      "step": 4500
+    },
+    {
+      "epoch": 35.46,
+      "learning_rate": 3.226950354609929e-05,
+      "loss": 0.0031,
+      "step": 5000
+    },
+    {
+      "epoch": 35.46,
+      "eval_loss": 0.29447928071022034,
+      "eval_macro_f1": 0.5603530484048236,
+      "eval_macro_precision": 0.7069918743571822,
+      "eval_macro_recall": 0.5094178224183427,
+      "eval_micro_f1": 0.7012113055181696,
+      "eval_micro_precision": 0.7241139680333565,
+      "eval_micro_recall": 0.6797129810828441,
+      "eval_runtime": 2.8093,
+      "eval_samples_per_second": 343.853,
+      "eval_steps_per_second": 21.713,
+      "step": 5000
+    },
+    {
+      "epoch": 39.01,
+      "learning_rate": 3.0496453900709222e-05,
+      "loss": 0.0031,
+      "step": 5500
+    },
+    {
+      "epoch": 39.01,
+      "eval_loss": 0.30334585905075073,
+      "eval_macro_f1": 0.5559562958714916,
+      "eval_macro_precision": 0.6802693513173442,
+      "eval_macro_recall": 0.5132993305341865,
+      "eval_micro_f1": 0.7078189300411522,
+      "eval_micro_precision": 0.7462039045553145,
+      "eval_micro_recall": 0.6731898238747553,
+      "eval_runtime": 2.814,
+      "eval_samples_per_second": 343.285,
+      "eval_steps_per_second": 21.677,
+      "step": 5500
+    },
+    {
+      "epoch": 42.55,
+      "learning_rate": 2.8723404255319154e-05,
+      "loss": 0.0023,
+      "step": 6000
+    },
+    {
+      "epoch": 42.55,
+      "eval_loss": 0.3123699724674225,
+      "eval_macro_f1": 0.5623581591291773,
+      "eval_macro_precision": 0.7164115784901167,
+      "eval_macro_recall": 0.5082951108653608,
+      "eval_micro_f1": 0.701129750085587,
+      "eval_micro_precision": 0.7377521613832853,
+      "eval_micro_recall": 0.6679712981082844,
+      "eval_runtime": 2.8076,
+      "eval_samples_per_second": 344.062,
+      "eval_steps_per_second": 21.726,
+      "step": 6000
+    },
+    {
+      "epoch": 46.1,
+      "learning_rate": 2.695035460992908e-05,
+      "loss": 0.0024,
+      "step": 6500
+    },
+    {
+      "epoch": 46.1,
+      "eval_loss": 0.315276563167572,
+      "eval_macro_f1": 0.5844872930041309,
+      "eval_macro_precision": 0.6789210155524211,
+      "eval_macro_recall": 0.5412028544350216,
+      "eval_micro_f1": 0.7022849462365591,
+      "eval_micro_precision": 0.7241857241857241,
+      "eval_micro_recall": 0.6816699282452707,
+      "eval_runtime": 2.8361,
+      "eval_samples_per_second": 340.607,
+      "eval_steps_per_second": 21.508,
+      "step": 6500
+    },
+    {
+      "epoch": 49.65,
+      "learning_rate": 2.5177304964539007e-05,
+      "loss": 0.002,
+      "step": 7000
+    },
+    {
+      "epoch": 49.65,
+      "eval_loss": 0.3173142075538635,
+      "eval_macro_f1": 0.5797973374509848,
+      "eval_macro_precision": 0.7081281214068704,
+      "eval_macro_recall": 0.5234036689357117,
+      "eval_micro_f1": 0.7121682178559119,
+      "eval_micro_precision": 0.7551169590643275,
+      "eval_micro_recall": 0.6738421395955643,
+      "eval_runtime": 2.818,
+      "eval_samples_per_second": 342.802,
+      "eval_steps_per_second": 21.647,
+      "step": 7000
+    },
+    {
+      "epoch": 53.19,
+      "learning_rate": 2.340425531914894e-05,
+      "loss": 0.0016,
+      "step": 7500
+    },
+    {
+      "epoch": 53.19,
+      "eval_loss": 0.3481275737285614,
+      "eval_macro_f1": 0.5715812887434382,
+      "eval_macro_precision": 0.7237539680214637,
+      "eval_macro_recall": 0.5104648237002123,
+      "eval_micro_f1": 0.703448275862069,
+      "eval_micro_precision": 0.7461594732991953,
+      "eval_micro_recall": 0.6653620352250489,
+      "eval_runtime": 2.8127,
+      "eval_samples_per_second": 343.438,
+      "eval_steps_per_second": 21.687,
+      "step": 7500
+    },
+    {
+      "epoch": 56.74,
+      "learning_rate": 2.1631205673758867e-05,
+      "loss": 0.0012,
+      "step": 8000
+    },
+    {
+      "epoch": 56.74,
+      "eval_loss": 0.34702157974243164,
+      "eval_macro_f1": 0.5951067347267447,
+      "eval_macro_precision": 0.7516773928626448,
+      "eval_macro_recall": 0.5430089368236234,
+      "eval_micro_f1": 0.6986486486486487,
+      "eval_micro_precision": 0.7245970567624387,
+      "eval_micro_recall": 0.6744944553163731,
+      "eval_runtime": 2.8072,
+      "eval_samples_per_second": 344.113,
+      "eval_steps_per_second": 21.73,
+      "step": 8000
+    }
+  ],
+  "max_steps": 14100,
+  "num_train_epochs": 100,
+  "total_flos": 3.1977769947832704e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28a2c5a1f7f8d2b224f6418522014d5e9f8cb50c87f0b69e1be2aaaa0e7c9d7
+size 3247