End of training

README.md

@@ -0,0 +1,50 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+model-index:
+- name: ner_model
+  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_model
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
+
+## 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
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9877146528561972,
+    "eval_f1": 0.9397145256087323,
+    "eval_loss": 0.055851779878139496,
+    "eval_precision": 0.9376675603217158,
+    "eval_recall": 0.9417704476607203,
+    "eval_runtime": 7.0625,
+    "eval_samples": 3250,
+    "eval_samples_per_second": 460.177,
+    "eval_steps_per_second": 57.628,
+    "train_loss": 0.044327347904964204,
+    "train_runtime": 311.2643,
+    "train_samples": 14041,
+    "train_samples_per_second": 135.329,
+    "train_steps_per_second": 16.925
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "ner",
+  "hidden_dim": 3072,
+  "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,
+  "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
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9877146528561972,
+    "eval_f1": 0.9397145256087323,
+    "eval_loss": 0.055851779878139496,
+    "eval_precision": 0.9376675603217158,
+    "eval_recall": 0.9417704476607203,
+    "eval_runtime": 7.0625,
+    "eval_samples": 3250,
+    "eval_samples_per_second": 460.177,
+    "eval_steps_per_second": 57.628
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b49b372a7d4625a2ad7b5422e68f321560e0c5187572781660f59e92250f5c
+size 265491548

runs/Dec04_10-18-50_1261423ab883/events.out.tfevents.1701685157.1261423ab883.2501.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7976538e51c739926823f6bf5a334d5c4746654a2d29ae369c48de489d03c758
+size 6515

runs/Dec04_10-18-50_1261423ab883/events.out.tfevents.1701685476.1261423ab883.2501.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c455c5f9960a9949417678d0668861d4a1057b4457a520ac3a98b211e7fa1dc
+size 560

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 +1,55 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.044327347904964204,
+    "train_runtime": 311.2643,
+    "train_samples": 14041,
+    "train_samples_per_second": 135.329,
+    "train_steps_per_second": 16.925
+}

trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 5268,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.525436598329537e-05,
+      "loss": 0.1662,
+      "step": 500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.050873196659074e-05,
+      "loss": 0.0736,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.5763097949886106e-05,
+      "loss": 0.0629,
+      "step": 1500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.1017463933181475e-05,
+      "loss": 0.042,
+      "step": 2000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.6271829916476843e-05,
+      "loss": 0.028,
+      "step": 2500
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.152619589977221e-05,
+      "loss": 0.0283,
+      "step": 3000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.678056188306758e-05,
+      "loss": 0.0244,
+      "step": 3500
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.2034927866362947e-05,
+      "loss": 0.012,
+      "step": 4000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.289293849658315e-06,
+      "loss": 0.0112,
+      "step": 4500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.5436598329536827e-06,
+      "loss": 0.0135,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "step": 5268,
+      "total_flos": 445788652997016.0,
+      "train_loss": 0.044327347904964204,
+      "train_runtime": 311.2643,
+      "train_samples_per_second": 135.329,
+      "train_steps_per_second": 16.925
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 445788652997016.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a07260d95fd4eb5e3b6cd7b3391b25472cfa0b15a613ca8e828a9e11bbcd89d
+size 4728