End of training

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: resume_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. -->
+
+# resume_model
+
+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: 0.9181
+- Accuracy: 0.8290
+
+## 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: 1
+- eval_batch_size: 1
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.2489        | 1.0   | 1987 | 0.9181          | 0.8290   |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.2.1
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,77 @@
+{
+  "_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": "HR",
+    "1": "DESIGNER",
+    "2": "INFORMATION-TECHNOLOGY",
+    "3": "TEACHER",
+    "4": "ADVOCATE",
+    "5": "BUSINESS-DEVELOPMENT",
+    "6": "HEALTHCARE",
+    "7": "FITNESS",
+    "8": "AGRICULTURE",
+    "9": "BPO",
+    "10": "SALES",
+    "11": "CONSULTANT",
+    "12": "DIGITAL-MEDIA",
+    "13": "AUTOMOBILE",
+    "14": "CHEF",
+    "15": "FINANCE",
+    "16": "APPAREL",
+    "17": "ENGINEERING",
+    "18": "ACCOUNTANT",
+    "19": "CONSTRUCTION",
+    "20": "PUBLIC-RELATIONS",
+    "21": "BANKING",
+    "22": "ARTS",
+    "23": "AVIATION"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "ACCOUNTANT": 18,
+    "ADVOCATE": 4,
+    "AGRICULTURE": 8,
+    "APPAREL": 16,
+    "ARTS": 22,
+    "AUTOMOBILE": 13,
+    "AVIATION": 23,
+    "BANKING": 21,
+    "BPO": 9,
+    "BUSINESS-DEVELOPMENT": 5,
+    "CHEF": 14,
+    "CONSTRUCTION": 19,
+    "CONSULTANT": 11,
+    "DESIGNER": 1,
+    "DIGITAL-MEDIA": 12,
+    "ENGINEERING": 17,
+    "FINANCE": 15,
+    "FITNESS": 7,
+    "HEALTHCARE": 6,
+    "HR": 0,
+    "INFORMATION-TECHNOLOGY": 2,
+    "PUBLIC-RELATIONS": 20,
+    "SALES": 10,
+    "TEACHER": 3
+  },
+  "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": "4.38.1",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77d31fc808bf4c09a3a97d184631a22c5b89db12b92e5cd1719cdfe81cf24d76
+size 267900240

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:aa63f7c8cbd4e82cc4bad0986f2087b85c501e775fa343d4444d27566678e4d8
+size 4856