End of training

README.md

@@ -0,0 +1,74 @@
+---
+base_model: manucos/finetuned__roberta-base-bne__augmented-ultrasounds
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: test-finetuned__roberta-base-bne__augmented-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. -->
+
+# test-finetuned__roberta-base-bne__augmented-ultrasounds-ner
+
+This model is a fine-tuned version of [manucos/finetuned__roberta-base-bne__augmented-ultrasounds](https://huggingface.co/manucos/finetuned__roberta-base-bne__augmented-ultrasounds) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3332
+- Precision: 0.7926
+- Recall: 0.8856
+- F1: 0.8365
+- Accuracy: 0.9236
+
+## 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 206  | 0.2753          | 0.7460    | 0.8411 | 0.7907 | 0.9106   |
+| No log        | 2.0   | 412  | 0.2692          | 0.7770    | 0.8603 | 0.8165 | 0.9238   |
+| 0.2993        | 3.0   | 618  | 0.3276          | 0.7493    | 0.8472 | 0.7952 | 0.9087   |
+| 0.2993        | 4.0   | 824  | 0.2983          | 0.7847    | 0.8704 | 0.8253 | 0.9180   |
+| 0.054         | 5.0   | 1030 | 0.3066          | 0.7852    | 0.8806 | 0.8302 | 0.9221   |
+| 0.054         | 6.0   | 1236 | 0.3211          | 0.7652    | 0.8806 | 0.8188 | 0.9211   |
+| 0.054         | 7.0   | 1442 | 0.3314          | 0.7883    | 0.8704 | 0.8273 | 0.9189   |
+| 0.0205        | 8.0   | 1648 | 0.3245          | 0.7827    | 0.8785 | 0.8278 | 0.9224   |
+| 0.0205        | 9.0   | 1854 | 0.3306          | 0.7825    | 0.8846 | 0.8304 | 0.9235   |
+| 0.0128        | 10.0  | 2060 | 0.3332          | 0.7926    | 0.8856 | 0.8365 | 0.9236   |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "manucos/finetuned__roberta-base-bne__augmented-ultrasounds",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "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": "4.40.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be53f70b153db809330a7c5aa2390b5ba968c14703d1b8ee8f4b97ec55bdf739
+size 496293316

runs/Apr24_22-07-52_0cc9268148b9/events.out.tfevents.1713996473.0cc9268148b9.4208.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6c7a0adc47f83b1935c27e8561b82f05350b99dd1bdaf7ae351227e3af0795
+size 11845

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
+    },
+    "4": {
+      "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:dec6809c8439d40ae41b2c88515dd60ae967dfb212a41853950fa12f34e14a19
+size 5048