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

README.md

@@ -0,0 +1,82 @@
+---
+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-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/xlnet-base-cased-biored-finetuned
+
+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: 0.7341
+- Accuracy: 0.7714
+- Precision: 0.5341
+- Recall: 0.4169
+- F1: 0.4594
+- Weighted F1: 0.7495
+
+## 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   | 0.8831          | 0.7377   | 0.4536    | 0.2481 | 0.2822 | 0.6719      |
+| No log        | 2.0   | 50   | 0.8309          | 0.7542   | 0.6035    | 0.3177 | 0.3598 | 0.6933      |
+| No log        | 3.0   | 75   | 0.7695          | 0.7624   | 0.568     | 0.3566 | 0.409  | 0.7189      |
+| No log        | 4.0   | 100  | 0.7562          | 0.7676   | 0.5536    | 0.3886 | 0.4398 | 0.7343      |
+| No log        | 5.0   | 125  | 0.7540          | 0.7673   | 0.5711    | 0.4013 | 0.4474 | 0.7368      |
+| No log        | 6.0   | 150  | 0.7425          | 0.7754   | 0.5867    | 0.4398 | 0.4873 | 0.7514      |
+| No log        | 7.0   | 175  | 0.7806          | 0.7788   | 0.606     | 0.4235 | 0.473  | 0.7475      |
+| No log        | 8.0   | 200  | 0.7638          | 0.7785   | 0.558     | 0.4547 | 0.4871 | 0.7549      |
+
+
+### 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": "xlnet/xlnet-base-cased",
+  "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 sha256:157747fe28e768f795e2930a1cedcc49a6dd691b4b57bbc76e05dd19c89d93da
+size 466917412

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,94 @@
+{
+  "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>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "<sep>",
+  "tokenizer_class": "XLNetTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebb75ac95de2a10a5d5febe1159f0879323beaf7efb6880f6257bd18d2623ee
+size 4219