djsull/ner_insurence_roberta

README.md

@@ -0,0 +1,72 @@
+---
+base_model: klue/roberta-small
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: binary_classification
+  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. -->
+
+# binary_classification
+
+This model is a fine-tuned version of [klue/roberta-small](https://huggingface.co/klue/roberta-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0151
+- 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| No log        | 1.0   | 9    | 0.0151          | 1.0       | 1.0    | 1.0 | 1.0      |
+| No log        | 2.0   | 18   | 0.0038          | 1.0       | 1.0    | 1.0 | 1.0      |
+| No log        | 3.0   | 27   | 0.0018          | 1.0       | 1.0    | 1.0 | 1.0      |
+| No log        | 4.0   | 36   | 0.0014          | 1.0       | 1.0    | 1.0 | 1.0      |
+| No log        | 5.0   | 45   | 0.0015          | 1.0       | 1.0    | 1.0 | 1.0      |
+| No log        | 6.0   | 54   | 0.0017          | 1.0       | 1.0    | 1.0 | 1.0      |
+| No log        | 7.0   | 63   | 0.0020          | 1.0       | 1.0    | 1.0 | 1.0      |
+| No log        | 8.0   | 72   | 0.0023          | 1.0       | 1.0    | 1.0 | 1.0      |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.0.1
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "klue/roberta-small",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c636d05fd68d181ab16685036b9c6f61bc9dca9346f7226dcb8a20a1a390eb6
+size 272382200

runs/May31_08-00-22_129-146-79-76/events.out.tfevents.1717142423.129-146-79-76.3851210.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008e0804f6a2b7208f4001f0031ad0c2a37d2eaad63b3a19210d02278bfbb835
+size 8892

runs/May31_08-00-22_129-146-79-76/events.out.tfevents.1717142474.129-146-79-76.3851210.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db48b16a5e5fd74c686d8a98554155836d1b9d2876b7234156d5af679f24613
+size 551

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f021c0522504bb630bd001fe72fe20e7abf97500240f362c9212088dcd1e3e
+size 4603