Model save

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/roberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: clarioscope-insurance-v1
+  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. -->
+
+# clarioscope-insurance-v1
+
+This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0312
+- Macro F1: 0.9571
+- Weighted F1: 0.9706
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 16
+- 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: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Weighted F1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|
+| 0.0304        | 1.0   | 1011 | 0.0343          | 0.9486   | 0.9624      |
+| 0.0147        | 2.0   | 2022 | 0.0345          | 0.9537   | 0.9682      |
+| 0.0223        | 3.0   | 3033 | 0.0312          | 0.9571   | 0.9706      |
+| 0.0082        | 4.0   | 4044 | 0.0325          | 0.9562   | 0.9704      |
+| 0.0152        | 5.0   | 5055 | 0.0328          | 0.9563   | 0.9706      |
+
+
+### Framework versions
+
+- Transformers 5.8.0
+- Pytorch 2.11.0+cu130
+- Datasets 4.8.5
+- Tokenizers 0.22.2

final/config.json

@@ -0,0 +1,82 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-CARRIER",
+    "2": "B-PLAN_TYPE",
+    "3": "B-MEMBER_ID",
+    "4": "B-GROUP_NUMBER",
+    "5": "B-POLICY_NUMBER",
+    "6": "B-SUBSCRIBER_NAME",
+    "7": "B-RELATIONSHIP",
+    "8": "B-CLAIM_ID",
+    "9": "B-AUTH_NUMBER",
+    "10": "B-COPAY",
+    "11": "B-DEDUCTIBLE",
+    "12": "B-BILLED_AMOUNT",
+    "13": "I-CARRIER",
+    "14": "I-PLAN_TYPE",
+    "15": "I-MEMBER_ID",
+    "16": "I-GROUP_NUMBER",
+    "17": "I-POLICY_NUMBER",
+    "18": "I-SUBSCRIBER_NAME",
+    "19": "I-RELATIONSHIP",
+    "20": "I-CLAIM_ID",
+    "21": "I-AUTH_NUMBER",
+    "22": "I-COPAY",
+    "23": "I-DEDUCTIBLE",
+    "24": "I-BILLED_AMOUNT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "B-AUTH_NUMBER": 9,
+    "B-BILLED_AMOUNT": 12,
+    "B-CARRIER": 1,
+    "B-CLAIM_ID": 8,
+    "B-COPAY": 10,
+    "B-DEDUCTIBLE": 11,
+    "B-GROUP_NUMBER": 4,
+    "B-MEMBER_ID": 3,
+    "B-PLAN_TYPE": 2,
+    "B-POLICY_NUMBER": 5,
+    "B-RELATIONSHIP": 7,
+    "B-SUBSCRIBER_NAME": 6,
+    "I-AUTH_NUMBER": 21,
+    "I-BILLED_AMOUNT": 24,
+    "I-CARRIER": 13,
+    "I-CLAIM_ID": 20,
+    "I-COPAY": 22,
+    "I-DEDUCTIBLE": 23,
+    "I-GROUP_NUMBER": 16,
+    "I-MEMBER_ID": 15,
+    "I-PLAN_TYPE": 14,
+    "I-POLICY_NUMBER": 17,
+    "I-RELATIONSHIP": 19,
+    "I-SUBSCRIBER_NAME": 18,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

final/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea758073f7312aadaf6569f2eb59f25d4e7e1ee922018d3e7592bc6ab696bcb
+size 496320996

final/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

final/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ff8539bec4c8e05f5fa584b6cdcda5caec68fa2b38b87e5cd38c8c660f362e
+size 5329

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c586f7eebc43e8cfe20642da5cee8b08ff9b8fc60a0144edf6ffb079c1223299
+oid sha256:0ea758073f7312aadaf6569f2eb59f25d4e7e1ee922018d3e7592bc6ab696bcb
 size 496320996