Push ../models/xlnet/xlnet-base-cased/biored-augmentations-only/ trained on biored-original_splits.pt

README.md

@@ -0,0 +1,78 @@
+---
+language:
+- en
+license: mit
+base_model: xlnet-base-cased
+tags:
+- low-resource NER
+- token_classification
+- biomedicine
+- medical NER
+- generated_from_trainer
+datasets:
+- medicine
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: Dagobert42/xlnet-base-cased-biored-augmented
+ 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/xlnet-base-cased-biored-augmented
+
+This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the bigbio/biored dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3178
+- Accuracy: 0.8937
+- Precision: 0.7458
+- Recall: 0.7607
+- F1: 0.752
+- Weighted F1: 0.893
+
+## 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 | 0.3320 | 0.889 | 0.8379 | 0.7151 | 0.7626 | 0.8852 |
+| No log | 2.0 | 50 | 0.3163 | 0.8984 | 0.789 | 0.7973 | 0.7921 | 0.8975 |
+| No log | 3.0 | 75 | 0.3176 | 0.9032 | 0.8098 | 0.8013 | 0.8045 | 0.902 |
+| No log | 4.0 | 100 | 0.3312 | 0.9001 | 0.7749 | 0.8266 | 0.7968 | 0.9007 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,61 @@
+{
+ "_name_or_path": "../models/xlnet/xlnet-base-cased/biored-augmentations-only/",
+ "architectures": [
+ "XLNetForTokenClassification"
+ ],
+ "attn_type": "bi",
+ "bi_data": false,
+ "bos_token_id": 1,
+ "clamp_len": -1,
+ "d_head": 64,
+ "d_inner": 3072,
+ "d_model": 768,
+ "dropout": 0.1,
+ "end_n_top": 5,
+ "eos_token_id": 2,
+ "ff_activation": "gelu",
+ "id2label": {
+ "0": "null",
+ "1": "GeneOrGeneProduct",
+ "2": "DiseaseOrPhenotypicFeature",
+ "3": "ChemicalEntity",
+ "4": "OrganismTaxon",
+ "5": "SequenceVariant",
+ "6": "CellLine"
+ },
+ "initializer_range": 0.02,
+ "label2id": {
+ "CellLine": 6,
+ "ChemicalEntity": 3,
+ "DiseaseOrPhenotypicFeature": 2,
+ "GeneOrGeneProduct": 1,
+ "OrganismTaxon": 4,
+ "SequenceVariant": 5,
+ "null": 0
+ },
+ "layer_norm_eps": 1e-12,
+ "mem_len": null,
+ "model_type": "xlnet",
+ "n_head": 12,
+ "n_layer": 12,
+ "pad_token_id": 5,
+ "reuse_len": null,
+ "same_length": false,
+ "start_n_top": 5,
+ "summary_activation": "tanh",
+ "summary_last_dropout": 0.1,
+ "summary_type": "last",
+ "summary_use_proj": true,
+ "task_specific_params": {
+ "text-generation": {
+ "do_sample": true,
+ "max_length": 250
+ }
+ },
+ "torch_dtype": "float32",
+ "transformers_version": "4.35.2",
+ "untie_r": true,
+ "use_mems_eval": true,
+ "use_mems_train": false,
+ "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36422d0dd6f8f36f3f55877e25fd17bf7b1724a735c35cc761fad0894601d8d
+size 466917412

special_tokens_map.json

@@ -0,0 +1,55 @@
+{
+ "additional_special_tokens": [
+ "<eop>",
+ "<eod>"
+ ],
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "cls_token": {
+ "content": "<cls>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "mask_token": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "sep_token": {
+ "content": "<sep>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,101 @@
+{
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "<cls>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "content": "<sep>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "5": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "6": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "7": {
+ "content": "<eod>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "8": {
+ "content": "<eop>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ "<eop>",
+ "<eod>"
+ ],
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "<cls>",
+ "do_lower_case": false,
+ "eos_token": "</s>",
+ "keep_accents": false,
+ "mask_token": "<mask>",
+ "max_length": 512,
+ "model_max_length": 512,
+ "pad_to_multiple_of": null,
+ "pad_token": "<pad>",
+ "pad_token_type_id": 3,
+ "padding_side": "left",
+ "remove_space": true,
+ "sep_token": "<sep>",
+ "stride": 0,
+ "tokenizer_class": "XLNetTokenizer",
+ "truncation_side": "right",
+ "truncation_strategy": "longest_first",
+ "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d0030a725c69060b8447774a2330418d30fe93135173359a2e8eb2d0a85d8d
+size 4219