End of training

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: manucos/final-ft__roberta-base-biomedical-clinical-es__70k-ultrasounds
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: final-ft__roberta-base-biomedical-clinical-es__70k-ultrasounds-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. -->
+
+# final-ft__roberta-base-biomedical-clinical-es__70k-ultrasounds-ner
+
+This model is a fine-tuned version of [manucos/final-ft__roberta-base-biomedical-clinical-es__70k-ultrasounds](https://huggingface.co/manucos/final-ft__roberta-base-biomedical-clinical-es__70k-ultrasounds) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3564
+- Precision: 0.8743
+- Recall: 0.8963
+- F1: 0.8851
+- Accuracy: 0.9405
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 280  | 0.2918          | 0.8036    | 0.8548 | 0.8284 | 0.9271   |
+| 0.3032        | 2.0   | 560  | 0.2601          | 0.8136    | 0.8859 | 0.8482 | 0.9346   |
+| 0.3032        | 3.0   | 840  | 0.2412          | 0.8573    | 0.8815 | 0.8692 | 0.9366   |
+| 0.1275        | 4.0   | 1120 | 0.2480          | 0.8487    | 0.8978 | 0.8726 | 0.9425   |
+| 0.1275        | 5.0   | 1400 | 0.2934          | 0.8457    | 0.8933 | 0.8689 | 0.9335   |
+| 0.0739        | 6.0   | 1680 | 0.2979          | 0.8660    | 0.9096 | 0.8873 | 0.9408   |
+| 0.0739        | 7.0   | 1960 | 0.3159          | 0.8651    | 0.8933 | 0.8790 | 0.9338   |
+| 0.042         | 8.0   | 2240 | 0.3255          | 0.8669    | 0.8874 | 0.8770 | 0.9374   |
+| 0.0308        | 9.0   | 2520 | 0.3467          | 0.8541    | 0.8933 | 0.8733 | 0.9391   |
+| 0.0308        | 10.0  | 2800 | 0.3228          | 0.8651    | 0.8933 | 0.8790 | 0.9383   |
+| 0.024         | 11.0  | 3080 | 0.3498          | 0.8699    | 0.8919 | 0.8808 | 0.9346   |
+| 0.024         | 12.0  | 3360 | 0.3465          | 0.8792    | 0.8948 | 0.8869 | 0.9419   |
+| 0.019         | 13.0  | 3640 | 0.3596          | 0.8705    | 0.8963 | 0.8832 | 0.9363   |
+| 0.019         | 14.0  | 3920 | 0.3557          | 0.8693    | 0.8963 | 0.8826 | 0.9386   |
+| 0.0157        | 15.0  | 4200 | 0.3564          | 0.8743    | 0.8963 | 0.8851 | 0.9405   |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "manucos/final-ft__roberta-base-biomedical-clinical-es__70k-ultrasounds",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "O",
+    "1": "B-Anatomical_Entity",
+    "10": "I-Location",
+    "11": "B-Type_of_measure",
+    "12": "I-Type_of_measure",
+    "13": "B-Measure",
+    "14": "I-Measure",
+    "15": "B-Degree",
+    "16": "I-Degree",
+    "17": "B-ConditionalTemporal",
+    "18": "I-ConditionalTemporal",
+    "2": "I-Anatomical_Entity",
+    "3": "B-Finding",
+    "4": "I-Finding",
+    "5": "B-Uncertainty",
+    "6": "I-Uncertainty",
+    "7": "B-Negation",
+    "8": "I-Negation",
+    "9": "B-Location"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Anatomical_Entity": "1",
+    "B-ConditionalTemporal": "17",
+    "B-Degree": "15",
+    "B-Finding": "3",
+    "B-Location": "9",
+    "B-Measure": "13",
+    "B-Negation": "7",
+    "B-Type_of_measure": "11",
+    "B-Uncertainty": "5",
+    "I-Anatomical_Entity": "2",
+    "I-ConditionalTemporal": "18",
+    "I-Degree": "16",
+    "I-Finding": "4",
+    "I-Location": "10",
+    "I-Measure": "14",
+    "I-Negation": "8",
+    "I-Type_of_measure": "12",
+    "I-Uncertainty": "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": "4.41.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef33851ea4d31914c7957e3e7c52f8c0b1da893fddfddd02f2ac38ce49067c3
+size 501632452

runs/May31_12-39-35_79f7b5ce56c8/events.out.tfevents.1717159199.79f7b5ce56c8.7876.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f13bc7991fa848414cc5aaf5b6085b62f63f995515a4b5bb25cdd255059c47
+size 6099

runs/May31_12-49-00_79f7b5ce56c8/events.out.tfevents.1717159747.79f7b5ce56c8.12094.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e0b411db27e829efcbae96b4602f0132bf0e5b730254788734e3007a02b05b
+size 6099

runs/May31_12-49-30_79f7b5ce56c8/events.out.tfevents.1717159771.79f7b5ce56c8.12094.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1812b58ea035a25581f10a474ddc5510a8a8187ba1cccfe7a8357fc28c3eb259
+size 15221

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 +1,58 @@
+{
+  "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
+    },
+    "51999": {
+      "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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3487e6b5a2ad251bc60ee52ffe579728d6e9ab7c220425a0cd2cfdb53199492
+size 5240