Push google/mobilebert-uncased trained on biored-original_splits.pt

README.md

@@ -0,0 +1,90 @@
+---
+language:
+- en
+license: mit
+base_model: mobilebert-uncased
+tags:
+- low-resource NER
+- token_classification
+- biomedicine
+- medical NER
+- generated_from_trainer
+datasets:
+- medicine
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: Dagobert42/mobilebert-uncased-biored-finetuned
+  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. -->
+
+# Dagobert42/mobilebert-uncased-biored-finetuned
+
+This model is a fine-tuned version of [mobilebert-uncased](https://huggingface.co/mobilebert-uncased) on the bigbio/biored dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7686
+- Accuracy: 0.7387
+- Precision: 0.2041
+- Recall: 0.2219
+- F1: 0.1908
+- Weighted F1: 0.683
+
+## 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: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Weighted F1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------:|
+| No log        | 1.0   | 25   | 1.2311          | 0.7114   | 0.1016    | 0.1429 | 0.1188 | 0.5914      |
+| No log        | 2.0   | 50   | 1.0356          | 0.7114   | 0.1016    | 0.1429 | 0.1188 | 0.5914      |
+| No log        | 3.0   | 75   | 1.0300          | 0.7114   | 0.1016    | 0.1429 | 0.1188 | 0.5914      |
+| No log        | 4.0   | 100  | 1.0246          | 0.7114   | 0.1016    | 0.1429 | 0.1188 | 0.5914      |
+| No log        | 5.0   | 125  | 1.0162          | 0.7114   | 0.1016    | 0.1429 | 0.1188 | 0.5914      |
+| No log        | 6.0   | 150  | 1.0039          | 0.7114   | 0.1016    | 0.1429 | 0.1188 | 0.5914      |
+| No log        | 7.0   | 175  | 0.9806          | 0.7114   | 0.1016    | 0.1429 | 0.1188 | 0.5914      |
+| No log        | 8.0   | 200  | 0.9148          | 0.7114   | 0.1016    | 0.1429 | 0.1188 | 0.5914      |
+| No log        | 9.0   | 225  | 0.8715          | 0.7187   | 0.2116    | 0.1604 | 0.1484 | 0.6172      |
+| No log        | 10.0  | 250  | 0.8303          | 0.7261   | 0.1555    | 0.1972 | 0.1737 | 0.6508      |
+| No log        | 11.0  | 275  | 0.8216          | 0.7292   | 0.1572    | 0.2018 | 0.1764 | 0.6554      |
+| No log        | 12.0  | 300  | 0.8044          | 0.7299   | 0.2295    | 0.2081 | 0.1786 | 0.6605      |
+| No log        | 13.0  | 325  | 0.8108          | 0.732    | 0.2304    | 0.2091 | 0.1797 | 0.662       |
+| No log        | 14.0  | 350  | 0.7920          | 0.7306   | 0.2062    | 0.22   | 0.1877 | 0.6711      |
+| No log        | 15.0  | 375  | 0.8025          | 0.7332   | 0.2164    | 0.2153 | 0.1836 | 0.6674      |
+| No log        | 16.0  | 400  | 0.7937          | 0.7335   | 0.1982    | 0.2248 | 0.2039 | 0.6813      |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "google/mobilebert-uncased",
+  "architectures": [
+    "MobileBertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "null",
+    "1": "GeneOrGeneProduct",
+    "2": "DiseaseOrPhenotypicFeature",
+    "3": "ChemicalEntity",
+    "4": "OrganismTaxon",
+    "5": "SequenceVariant",
+    "6": "CellLine"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
+  "label2id": {
+    "CellLine": 6,
+    "ChemicalEntity": 3,
+    "DiseaseOrPhenotypicFeature": 2,
+    "GeneOrGeneProduct": 1,
+    "OrganismTaxon": 4,
+    "SequenceVariant": 5,
+    "null": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "trigram_input": true,
+  "true_hidden_size": 128,
+  "type_vocab_size": 2,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96fb4143c4d20903757eeceec5b505268946dbb173fdfb2b520ad4ecde10729
+size 98480380

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MobileBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c46b669772226cd7bce858b7531b3b0ac2681805b2bd702e5228fed1a203250
+size 4219