Training complete

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: base2
+  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. -->
+
+# base2
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7291
+- Precision: 0.5945
+- Recall: 0.3128
+- F1: 0.4099
+- Accuracy: 0.9107
+
+## 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: 0.0001
+- 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.2254        | 1.0   | 976  | 0.3347          | 0.5725    | 0.3430 | 0.4290 | 0.9090   |
+| 0.1157        | 2.0   | 1952 | 0.3224          | 0.6249    | 0.3386 | 0.4392 | 0.9129   |
+| 0.0652        | 3.0   | 2928 | 0.5334          | 0.6116    | 0.2517 | 0.3567 | 0.9072   |
+| 0.0437        | 4.0   | 3904 | 0.4335          | 0.5189    | 0.2763 | 0.3606 | 0.9066   |
+| 0.0311        | 5.0   | 4880 | 0.5181          | 0.4966    | 0.3247 | 0.3927 | 0.9074   |
+| 0.0204        | 6.0   | 5856 | 0.7521          | 0.6343    | 0.2750 | 0.3837 | 0.9100   |
+| 0.0146        | 7.0   | 6832 | 0.5582          | 0.5241    | 0.3354 | 0.4091 | 0.9086   |
+| 0.0073        | 8.0   | 7808 | 0.7195          | 0.6151    | 0.2977 | 0.4012 | 0.9092   |
+| 0.0059        | 9.0   | 8784 | 0.6984          | 0.5773    | 0.2983 | 0.3934 | 0.9091   |
+| 0.0021        | 10.0  | 9760 | 0.7291          | 0.5945    | 0.3128 | 0.4099 | 0.9107   |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-location",
+    "2": "I-location",
+    "3": "B-group",
+    "4": "B-corporation",
+    "5": "B-person",
+    "6": "B-creative-work",
+    "7": "B-product",
+    "8": "I-person",
+    "9": "I-creative-work",
+    "10": "I-corporation",
+    "11": "I-group",
+    "12": "I-product"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-corporation": 4,
+    "B-creative-work": 6,
+    "B-group": 3,
+    "B-location": 1,
+    "B-person": 5,
+    "B-product": 7,
+    "I-corporation": 10,
+    "I-creative-work": 9,
+    "I-group": 11,
+    "I-location": 2,
+    "I-person": 8,
+    "I-product": 12,
+    "O": 0
+  },
+  "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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a48dea04adb81e8e8fd24ab3fbd235cecbf3d6fd9d863e752e4ff653ef979d
+size 430942044

runs/Nov07_21-31-19_de7b12349096/events.out.tfevents.1699392679.de7b12349096.31383.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:047f98e3706eaded60dfcb874aa6dcda14833648672d2f051c191593bf465f88
+size 7920

runs/Nov07_21-37-09_de7b12349096/events.out.tfevents.1699393031.de7b12349096.42749.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2a585bd4e6eee08815495e9bbccbeb2a08e4416e3911383a64b61255817206
+size 6348

runs/Nov07_21-40-41_de7b12349096/events.out.tfevents.1699393242.de7b12349096.42749.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b6589204e78fe7cbd77919fdf293d4d46ac4964c10541d1460916464952f657
+size 6349

runs/Nov07_21-44-00_de7b12349096/events.out.tfevents.1699393441.de7b12349096.42749.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1288cd1035f89a2b7174250dfcdb7c9d10908ecb2e5535ba35e099ea6455184f
+size 5719

runs/Nov07_21-45-58_de7b12349096/events.out.tfevents.1699393559.de7b12349096.42749.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e74c12ac7fcd2a705d0fb0f64d2bfcbd9eb7e3f0d82cde2e51be35467e076b2
+size 12834

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": false,
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf80eac97e43cddc082a4384df7a0150baf349f7a05638393b9193e8c0d35e0
+size 4536