End of training

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
+tags:
+- token-classification
+- generated_from_trainer
+datasets:
+- Rodrigo1771/multi-train-distemist-dev-ner
+model-index:
+- name: output
+  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. -->
+
+# output
+
+This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the Rodrigo1771/multi-train-distemist-dev-ner dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 2.3735
+- eval_precision: 0.0045
+- eval_recall: 0.1273
+- eval_f1: 0.0088
+- eval_accuracy: 0.0187
+- eval_runtime: 16.9354
+- eval_samples_per_second: 401.939
+- eval_steps_per_second: 50.25
+- step: 0
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,19 @@
+{
+    "eval_accuracy": 0.018743434648577764,
+    "eval_f1": 0.008761828065230522,
+    "eval_loss": 2.3735408782958984,
+    "eval_precision": 0.004537076421380973,
+    "eval_recall": 0.1272812353766963,
+    "eval_runtime": 16.9354,
+    "eval_samples": 6807,
+    "eval_samples_per_second": 401.939,
+    "eval_steps_per_second": 50.25,
+    "predict_accuracy": 0.018743434648577764,
+    "predict_f1": 0.008761828065230522,
+    "predict_loss": 2.3735408782958984,
+    "predict_precision": 0.004537076421380973,
+    "predict_recall": 0.1272812353766963,
+    "predict_runtime": 16.1794,
+    "predict_samples_per_second": 420.719,
+    "predict_steps_per_second": 52.598
+}

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-ENFERMEDAD",
+    "2": "I-ENFERMEDAD",
+    "3": "B-PROCEDIMIENTO",
+    "4": "I-PROCEDIMIENTO",
+    "5": "B-SINTOMA",
+    "6": "I-SINTOMA",
+    "7": "B-FARMACO",
+    "8": "I-FARMACO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ENFERMEDAD": 1,
+    "B-FARMACO": 7,
+    "B-PROCEDIMIENTO": 3,
+    "B-SINTOMA": 5,
+    "I-ENFERMEDAD": 2,
+    "I-FARMACO": 8,
+    "I-PROCEDIMIENTO": 4,
+    "I-SINTOMA": 6,
+    "O": 0
+  },
+  "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": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "eval_accuracy": 0.018743434648577764,
+    "eval_f1": 0.008761828065230522,
+    "eval_loss": 2.3735408782958984,
+    "eval_precision": 0.004537076421380973,
+    "eval_recall": 0.1272812353766963,
+    "eval_runtime": 16.9354,
+    "eval_samples": 6807,
+    "eval_samples_per_second": 401.939,
+    "eval_steps_per_second": 50.25
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb8f27d656928c021399304ae37e82d147c80df5386c804b66e664424a60fee
+size 496262556

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_accuracy": 0.018743434648577764,
+    "predict_f1": 0.008761828065230522,
+    "predict_loss": 2.3735408782958984,
+    "predict_precision": 0.004537076421380973,
+    "predict_recall": 0.1272812353766963,
+    "predict_runtime": 16.1794,
+    "predict_samples_per_second": 420.719,
+    "predict_steps_per_second": 52.598
+}

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
+  }
+}

tb/events.out.tfevents.1715599919.dff07dfba241.4551.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f2d751e4f7bee8be430707a913556ed6397cb45dac39b8842fa2e13944d1ba
+size 486

tb/events.out.tfevents.1715600029.dff07dfba241.5135.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdbb0b41e4cdcc8831058dade865be672deae192e10b50a2f2aebc3a27db9443
+size 486

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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
+    },
+    "50261": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "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.log

@@ -0,0 +1,357 @@
+2024-05-13 11:33:22.284311: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
+2024-05-13 11:33:22.284357: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
+2024-05-13 11:33:22.286270: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
+2024-05-13 11:33:23.400293: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
+05/13/2024 11:33:25 - WARNING - __main__ -   Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
+05/13/2024 11:33:25 - INFO - __main__ -   Training/evaluation parameters TrainingArguments(
+_n_gpu=1,
+accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None},
+adafactor=False,
+adam_beta1=0.9,
+adam_beta2=0.999,
+adam_epsilon=1e-08,
+auto_find_batch_size=False,
+bf16=False,
+bf16_full_eval=False,
+data_seed=None,
+dataloader_drop_last=False,
+dataloader_num_workers=0,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=True,
+dataloader_prefetch_factor=None,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=1800,
+debug=[],
+deepspeed=None,
+disable_tqdm=False,
+dispatch_batches=None,
+do_eval=True,
+do_predict=True,
+do_train=False,
+eval_accumulation_steps=None,
+eval_delay=0,
+eval_do_concat_batches=True,
+eval_steps=None,
+evaluation_strategy=epoch,
+fp16=False,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+fsdp=[],
+fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
+fsdp_min_num_params=0,
+fsdp_transformer_layer_cls_to_wrap=None,
+full_determinism=False,
+gradient_accumulation_steps=4,
+gradient_checkpointing=False,
+gradient_checkpointing_kwargs=None,
+greater_is_better=True,
+group_by_length=False,
+half_precision_backend=auto,
+hub_always_push=False,
+hub_model_id=None,
+hub_private_repo=False,
+hub_strategy=every_save,
+hub_token=<HUB_TOKEN>,
+ignore_data_skip=False,
+include_inputs_for_metrics=False,
+include_num_input_tokens_seen=False,
+include_tokens_per_second=False,
+jit_mode_eval=False,
+label_names=None,
+label_smoothing_factor=0.0,
+learning_rate=5e-05,
+length_column_name=length,
+load_best_model_at_end=True,
+local_rank=0,
+log_level=passive,
+log_level_replica=warning,
+log_on_each_node=True,
+logging_dir=/content/dissertation/scripts/ner/output/tb,
+logging_first_step=False,
+logging_nan_inf_filter=True,
+logging_steps=500,
+logging_strategy=steps,
+lr_scheduler_kwargs={},
+lr_scheduler_type=linear,
+max_grad_norm=1.0,
+max_steps=-1,
+metric_for_best_model=f1,
+mp_parameters=,
+neftune_noise_alpha=None,
+no_cuda=False,
+num_train_epochs=10.0,
+optim=adamw_torch,
+optim_args=None,
+optim_target_modules=None,
+output_dir=/content/dissertation/scripts/ner/output,
+overwrite_output_dir=True,
+past_index=-1,
+per_device_eval_batch_size=8,
+per_device_train_batch_size=4,
+prediction_loss_only=False,
+push_to_hub=True,
+push_to_hub_model_id=None,
+push_to_hub_organization=None,
+push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
+ray_scope=last,
+remove_unused_columns=True,
+report_to=['tensorboard'],
+resume_from_checkpoint=None,
+run_name=/content/dissertation/scripts/ner/output,
+save_on_each_node=False,
+save_only_model=False,
+save_safetensors=True,
+save_steps=500,
+save_strategy=epoch,
+save_total_limit=None,
+seed=42,
+skip_memory_metrics=True,
+split_batches=None,
+tf32=None,
+torch_compile=False,
+torch_compile_backend=None,
+torch_compile_mode=None,
+torchdynamo=None,
+tpu_metrics_debug=False,
+tpu_num_cores=None,
+use_cpu=False,
+use_ipex=False,
+use_legacy_prediction_loop=False,
+use_mps_device=False,
+warmup_ratio=0.0,
+warmup_steps=0,
+weight_decay=0.0,
+)
+/usr/local/lib/python3.10/dist-packages/datasets/load.py:1486: FutureWarning: The repository for Rodrigo1771/multi-train-distemist-dev-ner contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/Rodrigo1771/multi-train-distemist-dev-ner
+You can avoid this message in future by passing the argument `trust_remote_code=True`.
+Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`.
+  warnings.warn(
+/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
+  warnings.warn(
+[INFO|configuration_utils.py:726] 2024-05-13 11:33:29,256 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
+[INFO|configuration_utils.py:789] 2024-05-13 11:33:29,260 >> Model config RobertaConfig {
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-ENFERMEDAD",
+    "2": "I-ENFERMEDAD",
+    "3": "B-PROCEDIMIENTO",
+    "4": "I-PROCEDIMIENTO",
+    "5": "B-SINTOMA",
+    "6": "I-SINTOMA",
+    "7": "B-FARMACO",
+    "8": "I-FARMACO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ENFERMEDAD": 1,
+    "B-FARMACO": 7,
+    "B-PROCEDIMIENTO": 3,
+    "B-SINTOMA": 5,
+    "I-ENFERMEDAD": 2,
+    "I-FARMACO": 8,
+    "I-PROCEDIMIENTO": 4,
+    "I-SINTOMA": 6,
+    "O": 0
+  },
+  "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",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+[INFO|configuration_utils.py:726] 2024-05-13 11:33:29,519 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
+[INFO|configuration_utils.py:789] 2024-05-13 11:33:29,520 >> Model config RobertaConfig {
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+[INFO|tokenization_utils_base.py:2087] 2024-05-13 11:33:29,529 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/vocab.json
+[INFO|tokenization_utils_base.py:2087] 2024-05-13 11:33:29,529 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/merges.txt
+[INFO|tokenization_utils_base.py:2087] 2024-05-13 11:33:29,530 >> loading file tokenizer.json from cache at None
+[INFO|tokenization_utils_base.py:2087] 2024-05-13 11:33:29,530 >> loading file added_tokens.json from cache at None
+[INFO|tokenization_utils_base.py:2087] 2024-05-13 11:33:29,530 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/special_tokens_map.json
+[INFO|tokenization_utils_base.py:2087] 2024-05-13 11:33:29,530 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/tokenizer_config.json
+[INFO|configuration_utils.py:726] 2024-05-13 11:33:29,530 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
+[INFO|configuration_utils.py:789] 2024-05-13 11:33:29,531 >> Model config RobertaConfig {
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+[INFO|configuration_utils.py:726] 2024-05-13 11:33:29,608 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
+[INFO|configuration_utils.py:789] 2024-05-13 11:33:29,609 >> Model config RobertaConfig {
+  "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}
+
+[INFO|modeling_utils.py:3429] 2024-05-13 11:33:30,009 >> loading weights file pytorch_model.bin from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/pytorch_model.bin
+[INFO|modeling_utils.py:4160] 2024-05-13 11:33:30,135 >> Some weights of the model checkpoint at PlanTL-GOB-ES/bsc-bio-ehr-es were not used when initializing RobertaForTokenClassification: ['lm_head.bias', 'lm_head.decoder.bias', 'lm_head.decoder.weight', 'lm_head.dense.bias', 'lm_head.dense.weight', 'lm_head.layer_norm.bias', 'lm_head.layer_norm.weight']
+- This IS expected if you are initializing RobertaForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
+- This IS NOT expected if you are initializing RobertaForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
+[WARNING|modeling_utils.py:4172] 2024-05-13 11:33:30,135 >> Some weights of RobertaForTokenClassification were not initialized from the model checkpoint at PlanTL-GOB-ES/bsc-bio-ehr-es and are newly initialized: ['classifier.bias', 'classifier.weight']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+
+/content/dissertation/scripts/ner/run_ner.py:397: FutureWarning: load_metric is deprecated and will be removed in the next major version of datasets. Use 'evaluate.load' instead, from the new library 🤗 Evaluate: https://huggingface.co/docs/evaluate
+  metric = load_metric("seqeval")
+/usr/local/lib/python3.10/dist-packages/datasets/load.py:759: FutureWarning: The repository for seqeval contains custom code which must be executed to correctly load the metric. You can inspect the repository content at https://raw.githubusercontent.com/huggingface/datasets/2.19.1/metrics/seqeval/seqeval.py
+You can avoid this message in future by passing the argument `trust_remote_code=True`.
+Passing `trust_remote_code=True` will be mandatory to load this metric from the next major release of `datasets`.
+  warnings.warn(
+05/13/2024 11:33:32 - INFO - __main__ -   *** Evaluate ***
+[INFO|trainer.py:786] 2024-05-13 11:33:32,238 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, tokens, id. If ner_tags, tokens, id are not expected by `RobertaForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3614] 2024-05-13 11:33:32,243 >> ***** Running Evaluation *****
+[INFO|trainer.py:3616] 2024-05-13 11:33:32,243 >>   Num examples = 6807
+[INFO|trainer.py:3619] 2024-05-13 11:33:32,243 >>   Batch size = 8
+
  0%|          | 0/851 [00:00<?, ?it/s]
  1%|          | 7/851 [00:00<00:12, 69.99it/s]
  2%|▏         | 15/851 [00:00<00:11, 72.61it/s]
  3%|▎         | 23/851 [00:00<00:11, 71.79it/s]
  4%|▎         | 31/851 [00:00<00:11, 71.34it/s]
  5%|▍         | 39/851 [00:00<00:11, 73.33it/s]
  6%|▌         | 47/851 [00:00<00:10, 74.03it/s]
  6%|▋         | 55/851 [00:00<00:10, 75.21it/s]
  7%|▋         | 63/851 [00:00<00:10, 75.11it/s]
  8%|▊         | 71/851 [00:00<00:11, 70.20it/s]
  9%|▉         | 79/851 [00:01<00:10, 71.93it/s]
 10%|█         | 87/851 [00:01<00:10, 72.37it/s]
 11%|█         | 95/851 [00:01<00:10, 70.10it/s]
 12%|█▏        | 103/851 [00:01<00:10, 72.17it/s]
 13%|█▎        | 111/851 [00:01<00:10, 71.21it/s]
 14%|█▍        | 119/851 [00:01<00:10, 72.24it/s]
 15%|█▍        | 127/851 [00:01<00:10, 68.05it/s]
 16%|█▌        | 135/851 [00:01<00:10, 69.82it/s]
 17%|█▋        | 143/851 [00:02<00:10, 69.72it/s]
 18%|█▊        | 151/851 [00:02<00:10, 66.80it/s]
 19%|█▉        | 160/851 [00:02<00:09, 71.09it/s]
 20%|█▉        | 168/851 [00:02<00:09, 71.81it/s]
 21%|██        | 176/851 [00:02<00:09, 73.08it/s]
 22%|██▏       | 184/851 [00:02<00:09, 73.12it/s]
 23%|██▎       | 192/851 [00:02<00:08, 74.39it/s]
 24%|██▎       | 200/851 [00:02<00:08, 75.94it/s]
 24%|██▍       | 208/851 [00:02<00:08, 73.49it/s]
 25%|██▌       | 216/851 [00:03<00:08, 71.64it/s]
 26%|██▋       | 224/851 [00:03<00:08, 71.02it/s]
 27%|██▋       | 232/851 [00:03<00:08, 73.33it/s]
 28%|██▊       | 240/851 [00:03<00:08, 71.22it/s]
 29%|██▉       | 248/851 [00:03<00:08, 69.25it/s]
 30%|███       | 257/851 [00:03<00:08, 72.74it/s]
 31%|███▏      | 266/851 [00:03<00:07, 75.27it/s]
 32%|███▏      | 274/851 [00:03<00:07, 73.53it/s]
 33%|███▎      | 283/851 [00:03<00:07, 75.83it/s]
 34%|███▍      | 291/851 [00:04<00:07, 74.19it/s]
 35%|███▌      | 299/851 [00:04<00:07, 75.63it/s]
 36%|███▌      | 308/851 [00:04<00:07, 77.05it/s]
 37%|███▋      | 316/851 [00:04<00:07, 72.54it/s]
 38%|███▊      | 324/851 [00:04<00:07, 73.26it/s]
 39%|███▉      | 332/851 [00:04<00:07, 72.27it/s]
 40%|███▉      | 340/851 [00:04<00:06, 73.29it/s]
 41%|████      | 348/851 [00:04<00:06, 74.09it/s]
 42%|████▏     | 356/851 [00:04<00:06, 71.17it/s]
 43%|████▎     | 364/851 [00:05<00:06, 71.16it/s]
 44%|████▎     | 372/851 [00:05<00:06, 70.58it/s]
 45%|████▍     | 380/851 [00:05<00:06, 67.86it/s]
 46%|████▌     | 388/851 [00:05<00:06, 70.57it/s]
 47%|████▋     | 396/851 [00:05<00:06, 71.36it/s]
 47%|████▋     | 404/851 [00:05<00:06, 66.91it/s]
 48%|████▊     | 412/851 [00:05<00:06, 67.91it/s]
 49%|████▉     | 420/851 [00:05<00:06, 70.89it/s]
 50%|█████     | 428/851 [00:05<00:06, 69.31it/s]
 51%|█████     | 436/851 [00:06<00:05, 71.73it/s]
 52%|█████▏    | 444/851 [00:06<00:05, 72.78it/s]
 53%|█████▎    | 452/851 [00:06<00:05, 72.01it/s]
 54%|█████▍    | 460/851 [00:06<00:05, 71.19it/s]
 55%|█████▍    | 468/851 [00:06<00:05, 68.93it/s]
 56%|█████▌    | 475/851 [00:06<00:05, 64.78it/s]
 57%|█████▋    | 482/851 [00:06<00:05, 65.43it/s]
 57%|█████▋    | 489/851 [00:06<00:05, 66.13it/s]
 59%|█████▊    | 498/851 [00:06<00:04, 70.86it/s]
 59%|█████▉    | 506/851 [00:07<00:04, 73.13it/s]
 60%|██████    | 514/851 [00:07<00:04, 72.24it/s]
 61%|██████▏   | 522/851 [00:07<00:04, 67.88it/s]
 62%|██████▏   | 529/851 [00:07<00:04, 67.10it/s]
 63%|██████▎   | 537/851 [00:07<00:04, 69.73it/s]
 64%|██████▍   | 545/851 [00:07<00:04, 70.97it/s]
 65%|██████▍   | 553/851 [00:07<00:04, 68.72it/s]
 66%|██████▌   | 561/851 [00:07<00:04, 71.78it/s]
 67%|██████▋   | 569/851 [00:07<00:03, 73.74it/s]
 68%|██████▊   | 577/851 [00:08<00:03, 74.03it/s]
 69%|██████▊   | 585/851 [00:08<00:03, 69.31it/s]
 70%|██████▉   | 593/851 [00:08<00:03, 68.71it/s]
 71%|███████   | 601/851 [00:08<00:03, 69.53it/s]
 72%|███████▏  | 609/851 [00:08<00:03, 69.71it/s]
 73%|███████▎  | 617/851 [00:08<00:03, 65.18it/s]
 73%|███████▎  | 625/851 [00:08<00:03, 67.75it/s]
 74%|███████▍  | 632/851 [00:08<00:03, 66.40it/s]
 75%|███████▌  | 639/851 [00:09<00:03, 66.73it/s]
 76%|███████▌  | 646/851 [00:09<00:03, 64.45it/s]
 77%|███████▋  | 654/851 [00:09<00:02, 67.81it/s]
 78%|███████▊  | 662/851 [00:09<00:02, 69.27it/s]
 79%|███████▊  | 670/851 [00:09<00:02, 70.30it/s]
 80%|███████▉  | 678/851 [00:09<00:02, 70.89it/s]
 81%|████████  | 686/851 [00:09<00:02, 71.36it/s]
 82%|████████▏ | 694/851 [00:09<00:02, 73.14it/s]
 82%|████████▏ | 702/851 [00:09<00:01, 74.61it/s]
 83%|████████▎ | 710/851 [00:09<00:01, 76.06it/s]
 84%|████████▍ | 718/851 [00:10<00:01, 73.20it/s]
 85%|████████▌ | 726/851 [00:10<00:01, 74.44it/s]
 86%|████████▋ | 734/851 [00:10<00:01, 73.01it/s]
 87%|████████▋ | 742/851 [00:10<00:01, 74.39it/s]
 88%|████████▊ | 750/851 [00:10<00:01, 74.30it/s]
 89%|████████▉ | 758/851 [00:10<00:01, 74.83it/s]
 90%|█████████ | 766/851 [00:10<00:01, 71.22it/s]
 91%|█████████ | 774/851 [00:10<00:01, 71.36it/s]
 92%|█████████▏| 782/851 [00:10<00:00, 69.72it/s]
 93%|█████████▎| 790/851 [00:11<00:00, 70.57it/s]
 94%|█████████▍| 798/851 [00:11<00:00, 71.35it/s]
 95%|█████████▍| 806/851 [00:11<00:00, 73.28it/s]
 96%|█████████▌| 814/851 [00:11<00:00, 69.76it/s]
 97%|█████████▋| 822/851 [00:11<00:00, 71.00it/s]
 98%|█████████▊| 830/851 [00:11<00:00, 71.19it/s]
 98%|█████████▊| 838/851 [00:11<00:00, 71.54it/s]
 99%|█████████▉| 846/851 [00:11<00:00, 67.56it/s]/usr/local/lib/python3.10/dist-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.
+  _warn_prf(average, modifier, msg_start, len(result))
+
+***** eval metrics *****
+  eval_accuracy           =     0.0187
+  eval_f1                 =     0.0088
+  eval_loss               =     2.3735
+  eval_precision          =     0.0045
+  eval_recall             =     0.1273
+  eval_runtime            = 0:00:16.93
+  eval_samples            =       6807
+  eval_samples_per_second =    401.939
+  eval_steps_per_second   =      50.25
+05/13/2024 11:33:49 - INFO - __main__ -   *** Predict ***
+[INFO|trainer.py:786] 2024-05-13 11:33:49,182 >> The following columns in the test set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, tokens, id. If ner_tags, tokens, id are not expected by `RobertaForTokenClassification.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3614] 2024-05-13 11:33:49,184 >> ***** Running Prediction *****
+[INFO|trainer.py:3616] 2024-05-13 11:33:49,185 >>   Num examples = 6807
+[INFO|trainer.py:3619] 2024-05-13 11:33:49,185 >>   Batch size = 8
+
  0%|          | 0/851 [00:00<?, ?it/s]
  1%|          | 10/851 [00:00<00:09, 93.41it/s]
  2%|▏         | 20/851 [00:00<00:10, 80.25it/s]
  3%|▎         | 29/851 [00:00<00:10, 77.17it/s]
  4%|▍         | 37/851 [00:00<00:10, 75.63it/s]
  5%|▌         | 45/851 [00:00<00:10, 75.87it/s]
  6%|▌         | 53/851 [00:00<00:10, 76.47it/s]
  7%|▋         | 62/851 [00:00<00:10, 77.26it/s]
  8%|▊         | 70/851 [00:00<00:10, 71.62it/s]
  9%|▉         | 78/851 [00:01<00:10, 71.87it/s]
 10%|█         | 86/851 [00:01<00:10, 72.52it/s]
 11%|█         | 94/851 [00:01<00:10, 70.09it/s]
 12%|█▏        | 102/851 [00:01<00:10, 71.95it/s]
 13%|█▎        | 110/851 [00:01<00:10, 71.06it/s]
 14%|█▍        | 118/851 [00:01<00:10, 72.15it/s]
 15%|█▍        | 126/851 [00:01<00:10, 68.63it/s]
 16%|█▌        | 133/851 [00:01<00:10, 68.94it/s]
 16%|█▋        | 140/851 [00:01<00:10, 68.78it/s]
 17%|█▋        | 148/851 [00:02<00:10, 67.78it/s]
 18%|█▊        | 156/851 [00:02<00:09, 70.02it/s]
 19%|█▉        | 164/851 [00:02<00:09, 70.66it/s]
 20%|██        | 172/851 [00:02<00:09, 72.98it/s]
 21%|██        | 180/851 [00:02<00:09, 73.53it/s]
 22%|██▏       | 188/851 [00:02<00:08, 74.03it/s]
 23%|██▎       | 196/851 [00:02<00:08, 75.22it/s]
 24%|██▍       | 204/851 [00:02<00:08, 76.42it/s]
 25%|██▍       | 212/851 [00:02<00:08, 71.76it/s]
 26%|██▌       | 220/851 [00:03<00:08, 70.32it/s]
 27%|██▋       | 228/851 [00:03<00:08, 71.73it/s]
 28%|██▊       | 236/851 [00:03<00:08, 71.56it/s]
 29%|██▊       | 244/851 [00:03<00:08, 67.69it/s]
 30%|██▉       | 253/851 [00:03<00:08, 71.63it/s]
 31%|███       | 262/851 [00:03<00:07, 74.49it/s]
 32%|███▏      | 270/851 [00:03<00:07, 72.98it/s]
 33%|███▎      | 279/851 [00:03<00:07, 75.66it/s]
 34%|███▎      | 287/851 [00:03<00:07, 74.53it/s]
 35%|███▍      | 295/851 [00:04<00:07, 74.21it/s]
 36%|███▌      | 304/851 [00:04<00:07, 76.50it/s]
 37%|███▋      | 312/851 [00:04<00:07, 72.50it/s]
 38%|███▊      | 321/851 [00:04<00:06, 75.74it/s]
 39%|███▊      | 329/851 [00:04<00:07, 74.05it/s]
 40%|███▉      | 337/851 [00:04<00:06, 73.96it/s]
 41%|████      | 346/851 [00:04<00:06, 74.14it/s]
 42%|████▏     | 354/851 [00:04<00:06, 71.38it/s]
 43%|████▎     | 362/851 [00:04<00:06, 70.84it/s]
 43%|████▎     | 370/851 [00:05<00:06, 70.89it/s]
 44%|████▍     | 378/851 [00:05<00:06, 70.69it/s]
 45%|████▌     | 386/851 [00:05<00:06, 70.06it/s]
 46%|████▋     | 394/851 [00:05<00:06, 70.15it/s]
 47%|████▋     | 402/851 [00:05<00:06, 70.60it/s]
 48%|████▊     | 410/851 [00:05<00:06, 67.26it/s]
 49%|████▉     | 418/851 [00:05<00:06, 69.32it/s]
 50%|████▉     | 425/851 [00:05<00:06, 67.83it/s]
 51%|█████     | 433/851 [00:05<00:05, 70.62it/s]
 52%|█████▏    | 441/851 [00:06<00:05, 72.80it/s]
 53%|█████▎    | 449/851 [00:06<00:05, 71.68it/s]
 54%|█████▎    | 457/851 [00:06<00:05, 72.72it/s]
 55%|█████▍    | 465/851 [00:06<00:05, 69.67it/s]
 56%|█████▌    | 473/851 [00:06<00:05, 63.94it/s]
 57%|█████▋    | 481/851 [00:06<00:05, 65.25it/s]
 57%|█████▋    | 489/851 [00:06<00:05, 66.10it/s]
 59%|█████▊    | 498/851 [00:06<00:04, 70.83it/s]
 59%|█████▉    | 506/851 [00:07<00:04, 73.00it/s]
 60%|██████    | 514/851 [00:07<00:04, 72.47it/s]
 61%|██████▏   | 522/851 [00:07<00:04, 68.53it/s]
 62%|██████▏   | 529/851 [00:07<00:04, 67.57it/s]
 63%|██████▎   | 537/851 [00:07<00:04, 69.88it/s]
 64%|██████▍   | 545/851 [00:07<00:04, 70.84it/s]
 65%|██████▍   | 553/851 [00:07<00:04, 68.71it/s]
 66%|██████▌   | 562/851 [00:07<00:03, 72.27it/s]
 67%|██████▋   | 570/851 [00:07<00:03, 73.35it/s]
 68%|██████▊   | 578/851 [00:08<00:03, 71.63it/s]
 69%|██████▉   | 586/851 [00:08<00:03, 69.61it/s]
 70%|██████▉   | 593/851 [00:08<00:03, 69.40it/s]
 71%|███████   | 601/851 [00:08<00:03, 70.17it/s]
 72%|███████▏  | 609/851 [00:08<00:03, 70.14it/s]
 73%|███████▎  | 617/851 [00:08<00:03, 65.67it/s]
 73%|███████▎  | 625/851 [00:08<00:03, 68.06it/s]
 74%|███████▍  | 632/851 [00:08<00:03, 65.68it/s]
 75%|███████▌  | 639/851 [00:08<00:03, 66.01it/s]
 76%|███████▌  | 646/851 [00:09<00:03, 63.53it/s]
 77%|███████▋  | 654/851 [00:09<00:02, 67.46it/s]
 78%|███████▊  | 662/851 [00:09<00:02, 68.21it/s]
 79%|███████▊  | 670/851 [00:09<00:02, 69.59it/s]
 80%|███████▉  | 678/851 [00:09<00:02, 70.67it/s]
 81%|████████  | 686/851 [00:09<00:02, 71.63it/s]
 82%|████████▏ | 694/851 [00:09<00:02, 73.38it/s]
 82%|████████▏ | 702/851 [00:09<00:01, 74.51it/s]
 83%|████████▎ | 710/851 [00:09<00:01, 75.85it/s]
 84%|████████▍ | 718/851 [00:10<00:01, 73.42it/s]
 85%|████████▌ | 726/851 [00:10<00:01, 74.64it/s]
 86%|████████▋ | 734/851 [00:10<00:01, 75.67it/s]
 87%|████████▋ | 742/851 [00:10<00:01, 75.71it/s]
 88%|████████▊ | 750/851 [00:10<00:01, 75.06it/s]
 89%|████████▉ | 758/851 [00:10<00:01, 75.32it/s]
 90%|█████████ | 766/851 [00:10<00:01, 71.14it/s]
 91%|█████████ | 774/851 [00:10<00:01, 71.13it/s]
 92%|█████████▏| 782/851 [00:10<00:00, 69.77it/s]
 93%|█████████▎| 790/851 [00:11<00:00, 70.89it/s]
 94%|█████████▍| 798/851 [00:11<00:00, 71.65it/s]
 95%|█████████▍| 807/851 [00:11<00:00, 74.32it/s]
 96%|█████████▌| 815/851 [00:11<00:00, 71.09it/s]
 97%|█████████▋| 823/851 [00:11<00:00, 71.28it/s]
 98%|█████████▊| 831/851 [00:11<00:00, 71.56it/s]
 99%|█████████▊| 839/851 [00:11<00:00, 70.65it/s]
+[INFO|trainer.py:3305] 2024-05-13 11:34:05,686 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:471] 2024-05-13 11:34:05,688 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2590] 2024-05-13 11:34:06,653 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2488] 2024-05-13 11:34:06,654 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-05-13 11:34:06,655 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+[INFO|modelcard.py:450] 2024-05-13 11:34:06,959 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Token Classification', 'type': 'token-classification'}, 'dataset': {'name': 'Rodrigo1771/multi-train-distemist-dev-ner', 'type': 'Rodrigo1771/multi-train-distemist-dev-ner', 'config': 'MultiTrainDisTEMISTDevNER', 'split': 'validation', 'args': 'MultiTrainDisTEMISTDevNER'}}
+***** predict metrics *****
+  predict_accuracy           =     0.0187
+  predict_f1                 =     0.0088
+  predict_loss               =     2.3735
+  predict_precision          =     0.0045
+  predict_recall             =     0.1273
+  predict_runtime            = 0:00:16.17
+  predict_samples_per_second =    420.719
+  predict_steps_per_second   =     52.598
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18cce49dc172023921a8c234d2d643afeaa0b4f8f209fd2e1d76d267cbbe3c95
+size 5048