Upload 12 files

README.md

@@ -1,3 +1,62 @@
 ---
-license: apache-2.0
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: ner-bert-mini-conll2003
+  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. -->
+
+# ner-bert-mini-conll2003
+
+This model is a fine-tuned version of [prajjwal1/bert-mini](https://huggingface.co/prajjwal1/bert-mini) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1007
+- Precision: 0.8743
+- Recall: 0.8993
+- F1: 0.8866
+- Accuracy: 0.9745
+
+## 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: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.27.4
+- Pytorch 1.13.1+cu117
+- Datasets 2.10.1
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.97453909726637,
+    "eval_f1": 0.8866201859229748,
+    "eval_loss": 0.10066453367471695,
+    "eval_precision": 0.874283843509576,
+    "eval_recall": 0.8993096480889039,
+    "eval_runtime": 3.335,
+    "eval_samples": 3250,
+    "eval_samples_per_second": 974.504,
+    "eval_steps_per_second": 122.038,
+    "train_loss": 0.09602124729026151,
+    "train_runtime": 167.8929,
+    "train_samples": 14041,
+    "train_samples_per_second": 418.153,
+    "train_steps_per_second": 52.295
+}

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "prajjwal1/bert-mini",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.97453909726637,
+    "eval_f1": 0.8866201859229748,
+    "eval_loss": 0.10066453367471695,
+    "eval_precision": 0.874283843509576,
+    "eval_recall": 0.8993096480889039,
+    "eval_runtime": 3.335,
+    "eval_samples": 3250,
+    "eval_samples_per_second": 974.504,
+    "eval_steps_per_second": 122.038
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52013ba7b2fb5c53063af48d3ed8ff033380d78ac52cac960e1ac9a704d5711
+size 44456585

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 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.09602124729026151,
+    "train_runtime": 167.8929,
+    "train_samples": 14041,
+    "train_samples_per_second": 418.153,
+    "train_steps_per_second": 52.295
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 8780,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.715261958997722e-05,
+      "loss": 0.3945,
+      "step": 500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.4305239179954444e-05,
+      "loss": 0.1883,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.1457858769931665e-05,
+      "loss": 0.1584,
+      "step": 1500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.8610478359908886e-05,
+      "loss": 0.1311,
+      "step": 2000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.5763097949886106e-05,
+      "loss": 0.1052,
+      "step": 2500
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 3.291571753986333e-05,
+      "loss": 0.0989,
+      "step": 3000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 3.0068337129840545e-05,
+      "loss": 0.0868,
+      "step": 3500
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.722095671981777e-05,
+      "loss": 0.0687,
+      "step": 4000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 2.437357630979499e-05,
+      "loss": 0.0694,
+      "step": 4500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.152619589977221e-05,
+      "loss": 0.0594,
+      "step": 5000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 1.867881548974943e-05,
+      "loss": 0.0556,
+      "step": 5500
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 1.5831435079726652e-05,
+      "loss": 0.0498,
+      "step": 6000
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 1.2984054669703875e-05,
+      "loss": 0.0472,
+      "step": 6500
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 1.0136674259681094e-05,
+      "loss": 0.0439,
+      "step": 7000
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 7.289293849658315e-06,
+      "loss": 0.0373,
+      "step": 7500
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 4.4419134396355355e-06,
+      "loss": 0.0369,
+      "step": 8000
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 1.5945330296127566e-06,
+      "loss": 0.0369,
+      "step": 8500
+    },
+    {
+      "epoch": 5.0,
+      "step": 8780,
+      "total_flos": 55398132371610.0,
+      "train_loss": 0.09602124729026151,
+      "train_runtime": 167.8929,
+      "train_samples_per_second": 418.153,
+      "train_steps_per_second": 52.295
+    }
+  ],
+  "max_steps": 8780,
+  "num_train_epochs": 5,
+  "total_flos": 55398132371610.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d071c90bfa11743c96d026f25e28150fffeade69820d56bff1215f9ddbb9abe9
+size 3579