Upload 13 files

README.md

@@ -0,0 +1,83 @@
+---
+base_model: pucpr/biobertpt-all
+tags:
+- generated_from_trainer
+datasets:
+- adalbertojunior/substance_quantity
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: test-ner-4
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: adalbertojunior/substance_quantity
+      type: adalbertojunior/substance_quantity
+    metrics:
+    - name: Precision
+      type: precision
+      value: 1.0
+    - name: Recall
+      type: recall
+      value: 1.0
+    - name: F1
+      type: f1
+      value: 1.0
+    - name: Accuracy
+      type: accuracy
+      value: 1.0
+---
+
+<!-- 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-ner-4
+
+This model is a fine-tuned version of [pucpr/biobertpt-all](https://huggingface.co/pucpr/biobertpt-all) on the adalbertojunior/substance_quantity dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0001
+- Precision: 1.0
+- Recall: 1.0
+- F1: 1.0
+- Accuracy: 1.0
+
+## 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: 5e-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: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.11.0
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 1.0,
+    "eval_f1": 1.0,
+    "eval_loss": 5.960646376479417e-05,
+    "eval_precision": 1.0,
+    "eval_recall": 1.0,
+    "eval_runtime": 8.1734,
+    "eval_samples": 500,
+    "eval_samples_per_second": 61.174,
+    "eval_steps_per_second": 7.708,
+    "train_loss": 0.009698579121523807,
+    "train_runtime": 643.1965,
+    "train_samples": 7375,
+    "train_samples_per_second": 34.399,
+    "train_steps_per_second": 4.3
+}

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "pucpr/biobertpt-all",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_ids": null,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-ADMFORM",
+    "1": "B-DOSAGE",
+    "2": "B-MEDTYPE",
+    "3": "B-PACKAGINGTYPE",
+    "4": "B-QUANTITY",
+    "5": "B-SUBSTANCE",
+    "6": "I-DOSAGE",
+    "7": "I-MEDTYPE",
+    "8": "I-QUANTITY",
+    "9": "I-SUBSTANCE",
+    "10": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ADMFORM": 0,
+    "B-DOSAGE": 1,
+    "B-MEDTYPE": 2,
+    "B-PACKAGINGTYPE": 3,
+    "B-QUANTITY": 4,
+    "B-SUBSTANCE": 5,
+    "I-DOSAGE": 6,
+    "I-MEDTYPE": 7,
+    "I-QUANTITY": 8,
+    "I-SUBSTANCE": 9,
+    "O": 10
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": null,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 1.0,
+    "eval_f1": 1.0,
+    "eval_loss": 5.960646376479417e-05,
+    "eval_precision": 1.0,
+    "eval_recall": 1.0,
+    "eval_runtime": 8.1734,
+    "eval_samples": 500,
+    "eval_samples_per_second": 61.174,
+    "eval_steps_per_second": 7.708
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf2f8f3e73597f20dbebdfda987bf9a5200b96da60c13f8929c2e6df8b4abca
+size 709152937

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 +1,59 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.009698579121523807,
+    "train_runtime": 643.1965,
+    "train_samples": 7375,
+    "train_samples_per_second": 34.399,
+    "train_steps_per_second": 4.3
+}

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2766,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.096167751265365e-05,
+      "loss": 0.0465,
+      "step": 500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.192335502530731e-05,
+      "loss": 0.0003,
+      "step": 1000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.2885032537960955e-05,
+      "loss": 0.0054,
+      "step": 1500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.3846710050614606e-05,
+      "loss": 0.0012,
+      "step": 2000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.808387563268257e-06,
+      "loss": 0.0002,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "step": 2766,
+      "total_flos": 5781661149312000.0,
+      "train_loss": 0.009698579121523807,
+      "train_runtime": 643.1965,
+      "train_samples_per_second": 34.399,
+      "train_steps_per_second": 4.3
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2766,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 5781661149312000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7be351dad52ae38555c807b33e9ba864be6302c3616d6696c5bd7735b534441
+size 4091