Model save

README.md

@@ -0,0 +1,101 @@
+---
+license: apache-2.0
+base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
+tags:
+- generated_from_trainer
+datasets:
+- combined-train-distemist-dev-ner
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: output
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: combined-train-distemist-dev-ner
+      type: combined-train-distemist-dev-ner
+      config: CombinedTrainDisTEMISTDevNER
+      split: validation
+      args: CombinedTrainDisTEMISTDevNER
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.31002310289674784
+    - name: Recall
+      type: recall
+      value: 0.816331305568554
+    - name: F1
+      type: f1
+      value: 0.44938176197836166
+    - name: Accuracy
+      type: accuracy
+      value: 0.8498565092616749
+---
+
+<!-- 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 combined-train-distemist-dev-ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9384
+- Precision: 0.3100
+- Recall: 0.8163
+- F1: 0.4494
+- Accuracy: 0.8499
+
+## 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
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.9988 | 425  | 0.3834          | 0.2920    | 0.7819 | 0.4252 | 0.8517   |
+| 0.3349        | 2.0    | 851  | 0.5730          | 0.2681    | 0.8070 | 0.4025 | 0.8221   |
+| 0.1788        | 2.9988 | 1276 | 0.5796          | 0.2848    | 0.8009 | 0.4202 | 0.8338   |
+| 0.1227        | 4.0    | 1702 | 0.6591          | 0.2996    | 0.8109 | 0.4376 | 0.8388   |
+| 0.0856        | 4.9988 | 2127 | 0.6266          | 0.3220    | 0.8203 | 0.4624 | 0.8602   |
+| 0.0597        | 6.0    | 2553 | 0.7859          | 0.3075    | 0.8112 | 0.4460 | 0.8476   |
+| 0.0597        | 6.9988 | 2978 | 0.8297          | 0.3137    | 0.8166 | 0.4532 | 0.8508   |
+| 0.0458        | 8.0    | 3404 | 0.8468          | 0.3135    | 0.8205 | 0.4536 | 0.8532   |
+| 0.0343        | 8.9988 | 3829 | 0.9241          | 0.3085    | 0.8182 | 0.4481 | 0.8494   |
+| 0.0292        | 9.9882 | 4250 | 0.9384          | 0.3100    | 0.8163 | 0.4494 | 0.8499   |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee8406b24dd8ea93c5ad47e89c3c3618bb8d35ff5c4692b8e2ba58443735fd0
+oid sha256:0948f84443842f6cd934e63534288908b6139ed1c0d4f65942454302e5cb4afd
 size 496262556

tb/events.out.tfevents.1725046129.6b97e535edda.6370.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e95865b7fc16c5b5c206f58b587bfc4cf54ab941b4946ad9235d0c58e4547d2
-size 11327
+oid sha256:c9e94268d839c5a3c21781840b052643e729f1bd38c4ed1942a53d09ddd89bfc
+size 12153

train.log

@@ -1527,3 +1527,16 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|trainer.py:2621] 2024-08-30 19:48:54,756 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-2127 (score: 0.4624414693662204).
 
                                                   
 [INFO|trainer.py:4239] 2024-08-30 19:48:54,956 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+[INFO|trainer.py:3478] 2024-08-30 19:48:56,764 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-08-30 19:48:56,766 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2690] 2024-08-30 19:48:58,154 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 19:48:58,155 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 19:48:58,156 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+[INFO|trainer.py:3478] 2024-08-30 19:48:58,210 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-08-30 19:48:58,212 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2690] 2024-08-30 19:48:59,637 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 19:48:59,639 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 19:48:59,639 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+{'eval_loss': 0.938378632068634, 'eval_precision': 0.31002310289674784, 'eval_recall': 0.816331305568554, 'eval_f1': 0.44938176197836166, 'eval_accuracy': 0.8498565092616749, 'eval_runtime': 15.4697, 'eval_samples_per_second': 440.215, 'eval_steps_per_second': 55.075, 'epoch': 9.99}
+{'train_runtime': 1205.6346, 'train_samples_per_second': 225.848, 'train_steps_per_second': 3.525, 'train_loss': 0.10639642311544979, 'epoch': 9.99}
+