Upload 12 files

README.md

@@ -1,3 +1,64 @@
----
-license: mit
----
+---
+library_name: transformers
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: test-ner
+  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. -->
+
+# test-ner
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0201
+- Precision: 0.7977
+- Recall: 0.8532
+- F1: 0.8245
+- Accuracy: 0.9937
+
+## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.48.0.dev0
+- Pytorch 2.5.1
+- Datasets 3.1.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9936547895449831,
+    "eval_f1": 0.8245283018867925,
+    "eval_loss": 0.02005779556930065,
+    "eval_precision": 0.7976878612716763,
+    "eval_recall": 0.8532378782948259,
+    "eval_runtime": 31.1176,
+    "eval_samples": 620,
+    "eval_samples_per_second": 19.924,
+    "eval_steps_per_second": 2.507,
+    "total_flos": 3885346539712512.0,
+    "train_loss": 0.03023709866308397,
+    "train_runtime": 2355.393,
+    "train_samples": 4956,
+    "train_samples_per_second": 6.312,
+    "train_steps_per_second": 0.79
+}

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-Advisors.GENERIC_CONSULTING_COMPANY",
+    "1": "B-Advisors.LEGAL_CONSULTING_COMPANY",
+    "2": "B-Generic_Info.ANNUAL_REVENUES",
+    "3": "B-Parties.ACQUIRED_COMPANY",
+    "4": "B-Parties.BUYING_COMPANY",
+    "5": "B-Parties.SELLING_COMPANY",
+    "6": "I-Advisors.GENERIC_CONSULTING_COMPANY",
+    "7": "I-Advisors.LEGAL_CONSULTING_COMPANY",
+    "8": "I-Generic_Info.ANNUAL_REVENUES",
+    "9": "I-Parties.ACQUIRED_COMPANY",
+    "10": "I-Parties.BUYING_COMPANY",
+    "11": "I-Parties.SELLING_COMPANY",
+    "12": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Advisors.GENERIC_CONSULTING_COMPANY": 0,
+    "B-Advisors.LEGAL_CONSULTING_COMPANY": 1,
+    "B-Generic_Info.ANNUAL_REVENUES": 2,
+    "B-Parties.ACQUIRED_COMPANY": 3,
+    "B-Parties.BUYING_COMPANY": 4,
+    "B-Parties.SELLING_COMPANY": 5,
+    "I-Advisors.GENERIC_CONSULTING_COMPANY": 6,
+    "I-Advisors.LEGAL_CONSULTING_COMPANY": 7,
+    "I-Generic_Info.ANNUAL_REVENUES": 8,
+    "I-Parties.ACQUIRED_COMPANY": 9,
+    "I-Parties.BUYING_COMPANY": 10,
+    "I-Parties.SELLING_COMPANY": 11,
+    "O": 12
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9936547895449831,
+    "eval_f1": 0.8245283018867925,
+    "eval_loss": 0.02005779556930065,
+    "eval_precision": 0.7976878612716763,
+    "eval_recall": 0.8532378782948259,
+    "eval_runtime": 31.1176,
+    "eval_samples": 620,
+    "eval_samples_per_second": 19.924,
+    "eval_steps_per_second": 2.507
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ac9077113579cd934f7589850c727ca059bacf8f5c07e2c841274ef03a345c
+size 435629924

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 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3885346539712512.0,
+    "train_loss": 0.03023709866308397,
+    "train_runtime": 2355.393,
+    "train_samples": 4956,
+    "train_samples_per_second": 6.312,
+    "train_steps_per_second": 0.79
+}

trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1860,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 0.36054283380508423,
+      "learning_rate": 3.655913978494624e-05,
+      "loss": 0.0713,
+      "step": 500
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.2890476882457733,
+      "learning_rate": 2.3118279569892472e-05,
+      "loss": 0.0203,
+      "step": 1000
+    },
+    {
+      "epoch": 2.4193548387096775,
+      "grad_norm": 0.166881263256073,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 0.0136,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "step": 1860,
+      "total_flos": 3885346539712512.0,
+      "train_loss": 0.03023709866308397,
+      "train_runtime": 2355.393,
+      "train_samples_per_second": 6.312,
+      "train_steps_per_second": 0.79
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1860,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3885346539712512.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d168c9776b3531a8c6acde3dd9ef7333d7874da65f9004726acb9de825620ea
+size 5304