Subida inicial del modelo entrenado

README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: PlanTL-GOB-ES/roberta-base-bne
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: PlanTL-GOB-ES-roberta-base-bne-ner
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# PlanTL-GOB-ES-roberta-base-bne-ner
+
+This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0827
+- Precision: 0.8648
+- Recall: 0.8696
+- F1: 0.8672
+- Accuracy: 0.9795
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.4.1+cpu
+- Datasets 3.5.1
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.9794575113808801,
+    "eval_f1": 0.8672074159907299,
+    "eval_loss": 0.08266742527484894,
+    "eval_precision": 0.8648024035128264,
+    "eval_recall": 0.8696258424355101,
+    "eval_runtime": 82.5256,
+    "eval_samples": 1915,
+    "eval_samples_per_second": 23.205,
+    "eval_steps_per_second": 2.908,
+    "total_flos": 381121355275344.0,
+    "train_loss": 0.1387540928705442,
+    "train_runtime": 1240.6431,
+    "train_samples": 8323,
+    "train_samples_per_second": 6.709,
+    "train_steps_per_second": 0.21
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "B-MISC",
+    "2": "B-ORG",
+    "3": "B-PER",
+    "4": "I-LOC",
+    "5": "I-MISC",
+    "6": "I-ORG",
+    "7": "I-PER",
+    "8": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 0,
+    "B-MISC": 1,
+    "B-ORG": 2,
+    "B-PER": 3,
+    "I-LOC": 4,
+    "I-MISC": 5,
+    "I-ORG": 6,
+    "I-PER": 7,
+    "O": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.9794575113808801,
+    "eval_f1": 0.8672074159907299,
+    "eval_loss": 0.08266742527484894,
+    "eval_precision": 0.8648024035128264,
+    "eval_recall": 0.8696258424355101,
+    "eval_runtime": 82.5256,
+    "eval_samples": 1915,
+    "eval_samples_per_second": 23.205,
+    "eval_steps_per_second": 2.908
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba01fc921ae2e16467617e104badd3fe6727d7e40136b0f8435a899a6d70377
+size 496262556

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 381121355275344.0,
+    "train_loss": 0.1387540928705442,
+    "train_runtime": 1240.6431,
+    "train_samples": 8323,
+    "train_samples_per_second": 6.709,
+    "train_steps_per_second": 0.21
+}

trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 261,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3831417624521073,
+      "grad_norm": 0.691992998123169,
+      "learning_rate": 3.103448275862069e-05,
+      "loss": 0.258,
+      "step": 100
+    },
+    {
+      "epoch": 0.7662835249042146,
+      "grad_norm": 1.280352234840393,
+      "learning_rate": 1.1877394636015327e-05,
+      "loss": 0.0693,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "step": 261,
+      "total_flos": 381121355275344.0,
+      "train_loss": 0.1387540928705442,
+      "train_runtime": 1240.6431,
+      "train_samples_per_second": 6.709,
+      "train_steps_per_second": 0.21
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 261,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 381121355275344.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7501c702bab1d084cf868dae04a963286d82313dfba02f235fb08143e26cf4
+size 5368