Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: dccuchile/bert-base-spanish-wwm-cased
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.41906410455703735
+
+f1: 0.8493150684931506
+
+precision: 0.8157894736842105
+
+recall: 0.8857142857142857
+
+auc: 0.9059649122807018
+
+accuracy: 0.835

checkpoint-100/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
+  "_num_labels": 2,
+  "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": "NONTOXIC",
+    "1": "TOXIC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NONTOXIC": 0,
+    "TOXIC": 1
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31002
+}

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911bd376efd40f4cff5484f0dc85ec7f956f1c9699751a7a36e11b9c3286b293
+size 439433208

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1327a5885c81d90287c85a9f2ee98b15f567b904190d554781baaf5069852afc
+size 878981882

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18960c194b39c1c762e07eaeaf2c6bd3d4e437ef57953721af826bd8bfce0b40
+size 13990

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d035e61f1c66cd4befda09e39359b5d11abe5b64d7c41726de679803569f208e
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.41906410455703735,
+  "best_model_checkpoint": "autotrain-f7fct-dx9rn/checkpoint-100",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.968233823776245,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.7162,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.004212856292725,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.702,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.395503520965576,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7072,
+      "step": 15
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.344860076904297,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.722,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.5571045875549316,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.6178,
+      "step": 25
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.521437644958496,
+      "learning_rate": 5e-05,
+      "loss": 0.6845,
+      "step": 30
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 5.477353096008301,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6131,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 11.997583389282227,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.7953,
+      "step": 40
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 6.525259017944336,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.7484,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 7.6074748039245605,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.7293,
+      "step": 50
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 6.682773590087891,
+      "learning_rate": 4.5370370370370374e-05,
+      "loss": 0.6188,
+      "step": 55
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.664694786071777,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.5287,
+      "step": 60
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 5.581724643707275,
+      "learning_rate": 4.351851851851852e-05,
+      "loss": 0.5358,
+      "step": 65
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 14.359504699707031,
+      "learning_rate": 4.259259259259259e-05,
+      "loss": 0.4202,
+      "step": 70
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 7.6025919914245605,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.5042,
+      "step": 75
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 16.40511703491211,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.4972,
+      "step": 80
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 7.792325973510742,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.8613,
+      "step": 85
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.322792053222656,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.4195,
+      "step": 90
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.8841655254364014,
+      "learning_rate": 3.7962962962962964e-05,
+      "loss": 0.3093,
+      "step": 95
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 17.78056526184082,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.426,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.835,
+      "eval_auc": 0.9059649122807018,
+      "eval_f1": 0.8493150684931506,
+      "eval_loss": 0.41906410455703735,
+      "eval_precision": 0.8157894736842105,
+      "eval_recall": 0.8857142857142857,
+      "eval_runtime": 32.1015,
+      "eval_samples_per_second": 6.23,
+      "eval_steps_per_second": 0.405,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 300,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 52622211072000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8081ca9a5609f7f25104da7581a3c3ae42b8f112159708d15fb47ba1f45a130a
+size 5240

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
+  "_num_labels": 2,
+  "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": "NONTOXIC",
+    "1": "TOXIC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NONTOXIC": 0,
+    "TOXIC": 1
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911bd376efd40f4cff5484f0dc85ec7f956f1c9699751a7a36e11b9c3286b293
+size 439433208

runs/Nov04_17-05-46_r-bgonzalezbustamante-autotrain-cpu-basic-5k2apkzj-6b3ec-0ktiq/events.out.tfevents.1730739948.r-bgonzalezbustamante-autotrain-cpu-basic-5k2apkzj-6b3ec-0ktiq.106.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177aa53810e05ed4c85c870370242d0385c430728dd9b4815cccd720d56ae745
-size 15373
+oid sha256:1b88fc2ad44ee0786528cf03a3c51b58cd1a44793e489e0f53d0a8e26053d9f4
+size 19622

runs/Nov04_17-05-46_r-bgonzalezbustamante-autotrain-cpu-basic-5k2apkzj-6b3ec-0ktiq/events.out.tfevents.1730741637.r-bgonzalezbustamante-autotrain-cpu-basic-5k2apkzj-6b3ec-0ktiq.106.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c885efe88003175df1ed86da717ae71186cc435f1d7d9a28f84a9a0a165f0d
+size 607

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8081ca9a5609f7f25104da7581a3c3ae42b8f112159708d15fb47ba1f45a130a
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-f7fct-dx9rn/autotrain-data",
+    "model": "dccuchile/bert-base-spanish-wwm-cased",
+    "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-f7fct-dx9rn",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "bgonzalezbustamante",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}