Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: MoritzLaurer/mDeBERTa-v3-base-mnli-xnli
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 2.303269863128662
+
+f1_macro: 0.040508170738823165
+
+f1_micro: 0.3367965367965368
+
+f1_weighted: 0.2413478397672539
+
+precision_macro: 0.0434917012251169
+
+precision_micro: 0.3367965367965368
+
+precision_weighted: 0.21644678791353103
+
+recall_macro: 0.05803911531326899
+
+recall_micro: 0.3367965367965368
+
+recall_weighted: 0.3367965367965368
+
+accuracy: 0.3367965367965368

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 250101
+}

checkpoint-435/config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "MoritzLaurer/mDeBERTa-v3-base-mnli-xnli",
+  "_num_labels": 33,
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Actualizaciones Pol\u00edticas",
+    "1": "Billetera Electr\u00f3nica",
+    "2": "Clasificaciones",
+    "3": "Comercio Electr\u00f3nico",
+    "4": "Comercio exterior",
+    "5": "Contenido",
+    "6": "Convergencia Regulatoria",
+    "7": "Convergencia de Medios",
+    "8": "Criptoactivos",
+    "9": "Cuotas",
+    "10": "Defensa del Consumidor",
+    "11": "Etiquetado ",
+    "12": "Incentivos de Producci\u00f3n",
+    "13": "Inteligencia Artificial",
+    "14": "Lavado de Dinero",
+    "15": "Leyes de Medios",
+    "16": "Medicamentos de Venta Libre",
+    "17": "Nutrici\u00f3n",
+    "18": "OTT",
+    "19": "Operaciones Financieras de Consumo y Cr\u00e9dito",
+    "20": "Propiedad Intelectual",
+    "21": "Protecci\u00f3n de Datos",
+    "22": "Publicidad",
+    "23": "Registros de Medicamentos",
+    "24": "Regulaciones bancarias",
+    "25": "Regulaci\u00f3n Financiera",
+    "26": "Regulaci\u00f3n Laboral de Plataformas",
+    "27": "Sistemas de Pago Electr\u00f3nico",
+    "28": "Suplementos",
+    "29": "Tarjetas de Cr\u00e9dito o D\u00e9bito",
+    "30": "Tasas de Inter\u00e9s",
+    "31": "Tecnolog\u00edas Financieras",
+    "32": "Tributaci\u00f3n"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Actualizaciones Pol\u00edticas": 0,
+    "Billetera Electr\u00f3nica": 1,
+    "Clasificaciones": 2,
+    "Comercio Electr\u00f3nico": 3,
+    "Comercio exterior": 4,
+    "Contenido": 5,
+    "Convergencia Regulatoria": 6,
+    "Convergencia de Medios": 7,
+    "Criptoactivos": 8,
+    "Cuotas": 9,
+    "Defensa del Consumidor": 10,
+    "Etiquetado ": 11,
+    "Incentivos de Producci\u00f3n": 12,
+    "Inteligencia Artificial": 13,
+    "Lavado de Dinero": 14,
+    "Leyes de Medios": 15,
+    "Medicamentos de Venta Libre": 16,
+    "Nutrici\u00f3n": 17,
+    "OTT": 18,
+    "Operaciones Financieras de Consumo y Cr\u00e9dito": 19,
+    "Propiedad Intelectual": 20,
+    "Protecci\u00f3n de Datos": 21,
+    "Publicidad": 22,
+    "Registros de Medicamentos": 23,
+    "Regulaciones bancarias": 24,
+    "Regulaci\u00f3n Financiera": 25,
+    "Regulaci\u00f3n Laboral de Plataformas": 26,
+    "Sistemas de Pago Electr\u00f3nico": 27,
+    "Suplementos": 28,
+    "Tarjetas de Cr\u00e9dito o D\u00e9bito": 29,
+    "Tasas de Inter\u00e9s": 30,
+    "Tecnolog\u00edas Financieras": 31,
+    "Tributaci\u00f3n": 32
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

checkpoint-435/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e06ff32cfff3fb4744c369da31991a6e633886100a04f3311b70cef319aab4d
+size 1115363572

checkpoint-435/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d832e55ba50b308d02dcc66173606698bffd994401885c74810ee8b14e14b7b
+size 2230841082

checkpoint-435/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63db05e94907cd2505e2cdbde7c40373738908c73c83f76bbdc6fe03bddddb8f
+size 13990

checkpoint-435/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b3a2c068d7c24581fbd22dda89dd7be4336ba97e22c1eee7f130a54e893682
+size 1064

checkpoint-435/trainer_state.json

@@ -0,0 +1,215 @@
+{
+  "best_metric": 2.303269863128662,
+  "best_model_checkpoint": "autotrain-x03ts-qcf7e/checkpoint-435",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 435,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 6.1133551597595215,
+      "learning_rate": 2.8409090909090912e-05,
+      "loss": 3.4255,
+      "step": 25
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 8.178117752075195,
+      "learning_rate": 4.923273657289003e-05,
+      "loss": 3.0089,
+      "step": 50
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 6.662604808807373,
+      "learning_rate": 4.603580562659847e-05,
+      "loss": 2.825,
+      "step": 75
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 9.514023780822754,
+      "learning_rate": 4.283887468030691e-05,
+      "loss": 2.8092,
+      "step": 100
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 11.465914726257324,
+      "learning_rate": 3.964194373401535e-05,
+      "loss": 2.9111,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.28484848484848485,
+      "eval_f1_macro": 0.013436249285305889,
+      "eval_f1_micro": 0.28484848484848485,
+      "eval_f1_weighted": 0.12630074328187538,
+      "eval_loss": 2.676663398742676,
+      "eval_precision_macro": 0.008631772268135905,
+      "eval_precision_micro": 0.28484848484848485,
+      "eval_precision_weighted": 0.08113865932047751,
+      "eval_recall_macro": 0.030303030303030304,
+      "eval_recall_micro": 0.28484848484848485,
+      "eval_recall_weighted": 0.28484848484848485,
+      "eval_runtime": 255.7518,
+      "eval_samples_per_second": 4.516,
+      "eval_steps_per_second": 0.285,
+      "step": 145
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 6.465944766998291,
+      "learning_rate": 3.644501278772379e-05,
+      "loss": 2.5956,
+      "step": 150
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 8.603558540344238,
+      "learning_rate": 3.324808184143223e-05,
+      "loss": 2.6285,
+      "step": 175
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 8.11929702758789,
+      "learning_rate": 3.0051150895140666e-05,
+      "loss": 2.6964,
+      "step": 200
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 7.409820556640625,
+      "learning_rate": 2.6854219948849106e-05,
+      "loss": 2.7531,
+      "step": 225
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 7.499230861663818,
+      "learning_rate": 2.3657289002557546e-05,
+      "loss": 2.5273,
+      "step": 250
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 14.026644706726074,
+      "learning_rate": 2.0460358056265986e-05,
+      "loss": 2.5975,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3064935064935065,
+      "eval_f1_macro": 0.028228053192069863,
+      "eval_f1_micro": 0.3064935064935065,
+      "eval_f1_weighted": 0.23352329691937518,
+      "eval_loss": 2.477508544921875,
+      "eval_precision_macro": 0.02386167652983027,
+      "eval_precision_micro": 0.3064935064935065,
+      "eval_precision_weighted": 0.2057449099744913,
+      "eval_recall_macro": 0.04448079579994474,
+      "eval_recall_micro": 0.3064935064935065,
+      "eval_recall_weighted": 0.3064935064935065,
+      "eval_runtime": 256.8636,
+      "eval_samples_per_second": 4.497,
+      "eval_steps_per_second": 0.284,
+      "step": 290
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 8.43802547454834,
+      "learning_rate": 1.7263427109974426e-05,
+      "loss": 2.7131,
+      "step": 300
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 11.071104049682617,
+      "learning_rate": 1.4066496163682865e-05,
+      "loss": 2.4292,
+      "step": 325
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 7.782072067260742,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 2.3514,
+      "step": 350
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 12.599653244018555,
+      "learning_rate": 7.672634271099745e-06,
+      "loss": 2.4591,
+      "step": 375
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 8.950291633605957,
+      "learning_rate": 4.475703324808185e-06,
+      "loss": 2.3889,
+      "step": 400
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 8.916004180908203,
+      "learning_rate": 1.2787723785166241e-06,
+      "loss": 2.3493,
+      "step": 425
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3367965367965368,
+      "eval_f1_macro": 0.040508170738823165,
+      "eval_f1_micro": 0.3367965367965368,
+      "eval_f1_weighted": 0.2413478397672539,
+      "eval_loss": 2.303269863128662,
+      "eval_precision_macro": 0.0434917012251169,
+      "eval_precision_micro": 0.3367965367965368,
+      "eval_precision_weighted": 0.21644678791353103,
+      "eval_recall_macro": 0.05803911531326899,
+      "eval_recall_micro": 0.3367965367965368,
+      "eval_recall_weighted": 0.3367965367965368,
+      "eval_runtime": 261.9634,
+      "eval_samples_per_second": 4.409,
+      "eval_steps_per_second": 0.279,
+      "step": 435
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 435,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 227987477625600.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-435/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82be5e866644ace64f1453612eedbae31af120a0cda18525d26976ffc1d35e8
+size 5368

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "MoritzLaurer/mDeBERTa-v3-base-mnli-xnli",
+  "_num_labels": 33,
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Actualizaciones Pol\u00edticas",
+    "1": "Billetera Electr\u00f3nica",
+    "2": "Clasificaciones",
+    "3": "Comercio Electr\u00f3nico",
+    "4": "Comercio exterior",
+    "5": "Contenido",
+    "6": "Convergencia Regulatoria",
+    "7": "Convergencia de Medios",
+    "8": "Criptoactivos",
+    "9": "Cuotas",
+    "10": "Defensa del Consumidor",
+    "11": "Etiquetado ",
+    "12": "Incentivos de Producci\u00f3n",
+    "13": "Inteligencia Artificial",
+    "14": "Lavado de Dinero",
+    "15": "Leyes de Medios",
+    "16": "Medicamentos de Venta Libre",
+    "17": "Nutrici\u00f3n",
+    "18": "OTT",
+    "19": "Operaciones Financieras de Consumo y Cr\u00e9dito",
+    "20": "Propiedad Intelectual",
+    "21": "Protecci\u00f3n de Datos",
+    "22": "Publicidad",
+    "23": "Registros de Medicamentos",
+    "24": "Regulaciones bancarias",
+    "25": "Regulaci\u00f3n Financiera",
+    "26": "Regulaci\u00f3n Laboral de Plataformas",
+    "27": "Sistemas de Pago Electr\u00f3nico",
+    "28": "Suplementos",
+    "29": "Tarjetas de Cr\u00e9dito o D\u00e9bito",
+    "30": "Tasas de Inter\u00e9s",
+    "31": "Tecnolog\u00edas Financieras",
+    "32": "Tributaci\u00f3n"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Actualizaciones Pol\u00edticas": 0,
+    "Billetera Electr\u00f3nica": 1,
+    "Clasificaciones": 2,
+    "Comercio Electr\u00f3nico": 3,
+    "Comercio exterior": 4,
+    "Contenido": 5,
+    "Convergencia Regulatoria": 6,
+    "Convergencia de Medios": 7,
+    "Criptoactivos": 8,
+    "Cuotas": 9,
+    "Defensa del Consumidor": 10,
+    "Etiquetado ": 11,
+    "Incentivos de Producci\u00f3n": 12,
+    "Inteligencia Artificial": 13,
+    "Lavado de Dinero": 14,
+    "Leyes de Medios": 15,
+    "Medicamentos de Venta Libre": 16,
+    "Nutrici\u00f3n": 17,
+    "OTT": 18,
+    "Operaciones Financieras de Consumo y Cr\u00e9dito": 19,
+    "Propiedad Intelectual": 20,
+    "Protecci\u00f3n de Datos": 21,
+    "Publicidad": 22,
+    "Registros de Medicamentos": 23,
+    "Regulaciones bancarias": 24,
+    "Regulaci\u00f3n Financiera": 25,
+    "Regulaci\u00f3n Laboral de Plataformas": 26,
+    "Sistemas de Pago Electr\u00f3nico": 27,
+    "Suplementos": 28,
+    "Tarjetas de Cr\u00e9dito o D\u00e9bito": 29,
+    "Tasas de Inter\u00e9s": 30,
+    "Tecnolog\u00edas Financieras": 31,
+    "Tributaci\u00f3n": 32
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e06ff32cfff3fb4744c369da31991a6e633886100a04f3311b70cef319aab4d
+size 1115363572

runs/Jan02_20-12-21_r-metoledo-thematic-classification-dl-z5flmkvb-bf87e-7tpj2/events.out.tfevents.1735848743.r-metoledo-thematic-classification-dl-z5flmkvb-bf87e-7tpj2.106.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb842d40dbedcd42ac92e97bcaf2add19331cad880970433a1a4fd63a2788e5
-size 12284
+oid sha256:c3cf9f2d4d9415a9070fb24cb591c801545e4ddb714333b8846af78da1ad0b14
+size 14104

runs/Jan02_20-12-21_r-metoledo-thematic-classification-dl-z5flmkvb-bf87e-7tpj2/events.out.tfevents.1735853768.r-metoledo-thematic-classification-dl-z5flmkvb-bf87e-7tpj2.106.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e7889859872e9f4b18122dceec7bd7320e62abec0a04716d749051de6014ce
+size 921

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
+size 4305025

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07bf017c59c05b71d2f3de3ca420eeae57572049bc2903e829a041e6a1a25df9
+size 16316391

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250101": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82be5e866644ace64f1453612eedbae31af120a0cda18525d26976ffc1d35e8
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-x03ts-qcf7e/autotrain-data",
+    "model": "MoritzLaurer/mDeBERTa-v3-base-mnli-xnli",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "autotrain-x03ts-qcf7e",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "metoledo",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}