add model weights

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "/mnt/beegfs/mc000051/CERPLES/Models/bert-base-spanish-wwm-cased",
+  "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": 31002
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d31a759ec106786b7d14b9db5903a8d1fc4094c5aba3dfa09c784b33bcb11b8
+size 879021981

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2df4b7c392b8d623f36a4e2ef75af9a85e57170bab256fcca5ab95d80e9cf7
+size 439523757

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01fef0c59d4860e25106e718f35edb1ef106ebaa4b62dfd95f8e7e4cf4e146e
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392a982a9ac8e9d0e956548d877a9d8bcc8f61fbe896d0a05495f841534dd993
+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": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "name_or_path": "/mnt/beegfs/mc000051/CERPLES/Models/bert-base-spanish-wwm-cased", "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/mnt/beegfs/mc000051/CERPLES/Models/bert-base-spanish-wwm-cased/special_tokens_map.json", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_metric": 0.6235998688300035,
+  "best_model_checkpoint": "./CARES/checkpoints/bert-bas/checkpoint-3500",
+  "epoch": 24.822695035460992,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.55,
+      "learning_rate": 2.8936170212765956e-05,
+      "loss": 0.2014,
+      "step": 500
+    },
+    {
+      "epoch": 3.55,
+      "eval_loss": 0.15534088015556335,
+      "eval_macro_f1": 0.34191398087233876,
+      "eval_macro_precision": 0.4575725498723576,
+      "eval_macro_recall": 0.32634682637580636,
+      "eval_micro_f1": 0.7120380534211489,
+      "eval_micro_precision": 0.8108333333333333,
+      "eval_micro_recall": 0.634703196347032,
+      "eval_runtime": 2.9867,
+      "eval_samples_per_second": 323.432,
+      "eval_steps_per_second": 20.424,
+      "step": 500
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 2.7872340425531914e-05,
+      "loss": 0.0909,
+      "step": 1000
+    },
+    {
+      "epoch": 7.09,
+      "eval_loss": 0.14328321814537048,
+      "eval_macro_f1": 0.5216600519885811,
+      "eval_macro_precision": 0.6582415980876382,
+      "eval_macro_recall": 0.45829582028075544,
+      "eval_micro_f1": 0.7527932960893854,
+      "eval_micro_precision": 0.8099173553719008,
+      "eval_micro_recall": 0.7031963470319634,
+      "eval_runtime": 2.9852,
+      "eval_samples_per_second": 323.592,
+      "eval_steps_per_second": 20.434,
+      "step": 1000
+    },
+    {
+      "epoch": 10.64,
+      "learning_rate": 2.6808510638297873e-05,
+      "loss": 0.0428,
+      "step": 1500
+    },
+    {
+      "epoch": 10.64,
+      "eval_loss": 0.1534910351037979,
+      "eval_macro_f1": 0.5762696837727688,
+      "eval_macro_precision": 0.6633765574994241,
+      "eval_macro_recall": 0.5217654870639399,
+      "eval_micro_f1": 0.7763426240652617,
+      "eval_micro_precision": 0.8105039034776437,
+      "eval_micro_recall": 0.7449445531637312,
+      "eval_runtime": 2.9874,
+      "eval_samples_per_second": 323.358,
+      "eval_steps_per_second": 20.419,
+      "step": 1500
+    },
+    {
+      "epoch": 14.18,
+      "learning_rate": 2.574468085106383e-05,
+      "loss": 0.0231,
+      "step": 2000
+    },
+    {
+      "epoch": 14.18,
+      "eval_loss": 0.15115897357463837,
+      "eval_macro_f1": 0.5809807709622608,
+      "eval_macro_precision": 0.6166814111331129,
+      "eval_macro_recall": 0.5608937720056061,
+      "eval_micro_f1": 0.7775925308436145,
+      "eval_micro_precision": 0.7953615279672579,
+      "eval_micro_recall": 0.7606001304631441,
+      "eval_runtime": 2.985,
+      "eval_samples_per_second": 323.621,
+      "eval_steps_per_second": 20.436,
+      "step": 2000
+    },
+    {
+      "epoch": 17.73,
+      "learning_rate": 2.4680851063829786e-05,
+      "loss": 0.0137,
+      "step": 2500
+    },
+    {
+      "epoch": 17.73,
+      "eval_loss": 0.16502933204174042,
+      "eval_macro_f1": 0.5991629446392395,
+      "eval_macro_precision": 0.6221331811310129,
+      "eval_macro_recall": 0.5815882875339234,
+      "eval_micro_f1": 0.7877187190491911,
+      "eval_micro_precision": 0.7974598930481284,
+      "eval_micro_recall": 0.7782126549249837,
+      "eval_runtime": 2.9854,
+      "eval_samples_per_second": 323.576,
+      "eval_steps_per_second": 20.433,
+      "step": 2500
+    },
+    {
+      "epoch": 21.28,
+      "learning_rate": 2.3617021276595744e-05,
+      "loss": 0.0087,
+      "step": 3000
+    },
+    {
+      "epoch": 21.28,
+      "eval_loss": 0.1669953465461731,
+      "eval_macro_f1": 0.6173151275498924,
+      "eval_macro_precision": 0.6814989884732782,
+      "eval_macro_recall": 0.5992296363093449,
+      "eval_micro_f1": 0.7861842105263159,
+      "eval_micro_precision": 0.7929661579296616,
+      "eval_micro_recall": 0.7795172863666014,
+      "eval_runtime": 2.9877,
+      "eval_samples_per_second": 323.321,
+      "eval_steps_per_second": 20.417,
+      "step": 3000
+    },
+    {
+      "epoch": 24.82,
+      "learning_rate": 2.2553191489361703e-05,
+      "loss": 0.0063,
+      "step": 3500
+    },
+    {
+      "epoch": 24.82,
+      "eval_loss": 0.18081951141357422,
+      "eval_macro_f1": 0.6235998688300035,
+      "eval_macro_precision": 0.6667425956441049,
+      "eval_macro_recall": 0.5993735670848622,
+      "eval_micro_f1": 0.7835120643431636,
+      "eval_micro_precision": 0.8056512749827704,
+      "eval_micro_recall": 0.7625570776255708,
+      "eval_runtime": 2.9803,
+      "eval_samples_per_second": 324.127,
+      "eval_steps_per_second": 20.468,
+      "step": 3500
+    }
+  ],
+  "max_steps": 14100,
+  "num_train_epochs": 100,
+  "total_flos": 1.4624642507081568e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32d80d5d5dce67c9a2a11756aa0d57c15b20ca460c1ef2d87c1f7b006d31804
+size 3247