Training in progress, epoch 1

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: distil-bert-fintuned-issues-cfpb-complaints
+  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. -->
+
+# distil-bert-fintuned-issues-cfpb-complaints
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7196
+- Accuracy: 0.7450
+- Precision: 0.5763
+- Recall: 0.5233
+- F1: 0.5371
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.7281        | 1.0   | 11603 | 0.7196          | 0.7450   | 0.5763    | 0.5233 | 0.5371 |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.2.0
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Account Operations and Unauthorized Transaction Issues",
+    "1": "Attempts to collect debt not owed",
+    "2": "Closing an account",
+    "3": "Closing your account",
+    "4": "Credit Report and Monitoring Issues",
+    "5": "Dealing with your lender or servicer",
+    "6": "Disputes and Misrepresentations",
+    "7": "Improper use of your report",
+    "8": "Incorrect information on your report",
+    "9": "Legal and Threat Actions",
+    "10": "Managing an account",
+    "11": "Payment and Funds Management",
+    "12": "Problem with a company's investigation into an existing issue",
+    "13": "Problem with a company's investigation into an existing problem",
+    "14": "Problem with a credit reporting company's investigation into an existing problem",
+    "15": "Problem with a purchase shown on your statement",
+    "16": "Written notification about debt"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Account Operations and Unauthorized Transaction Issues": 0,
+    "Attempts to collect debt not owed": 1,
+    "Closing an account": 2,
+    "Closing your account": 3,
+    "Credit Report and Monitoring Issues": 4,
+    "Dealing with your lender or servicer": 5,
+    "Disputes and Misrepresentations": 6,
+    "Improper use of your report": 7,
+    "Incorrect information on your report": 8,
+    "Legal and Threat Actions": 9,
+    "Managing an account": 10,
+    "Payment and Funds Management": 11,
+    "Problem with a company's investigation into an existing issue": 12,
+    "Problem with a company's investigation into an existing problem": 13,
+    "Problem with a credit reporting company's investigation into an existing problem": 14,
+    "Problem with a purchase shown on your statement": 15,
+    "Written notification about debt": 16
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c1858294df47b24072c932b6341cb0791a566421a29df04dbe0ea77b14bb80
+size 267878708

runs/Mar31_00-10-44_d1026/events.out.tfevents.1711858247.d1026

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11c87dd88256783494361e1aacbdde1e2344b96c1fefc998a1ae4037f0cc01a
+size 10456

runs/Mar31_01-35-36_d1026/events.out.tfevents.1711863338.d1026

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7d7d57eaaafb2932c19f852301a505251a379d3dd319359d8d08c49931d4a4
+size 9630

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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab92b4eaa43f951a436c810b0973f0b78ad0ba2ba68a6ceb8353b7c912ccc9b6
+size 4728