kadabengaran/distilbert-base-uncased-text-classification

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: distilbert-base-uncased-lora-text-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. -->
+
+# distilbert-base-uncased-lora-text-classification
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2489
+- Accuracy: {'accuracy': 0.9447222222222222}
+
+## 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: 15
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy                         |
+|:-------------:|:-----:|:-----:|:---------------:|:--------------------------------:|
+| 0.3734        | 1.0   | 1050  | 0.3066          | {'accuracy': 0.8947222222222222} |
+| 0.2802        | 2.0   | 2100  | 0.2840          | {'accuracy': 0.9144444444444444} |
+| 0.2562        | 3.0   | 3150  | 0.2413          | {'accuracy': 0.9277777777777778} |
+| 0.2291        | 4.0   | 4200  | 0.2327          | {'accuracy': 0.9291666666666667} |
+| 0.215         | 5.0   | 5250  | 0.2459          | {'accuracy': 0.9327777777777778} |
+| 0.1882        | 6.0   | 6300  | 0.2387          | {'accuracy': 0.9347222222222222} |
+| 0.1672        | 7.0   | 7350  | 0.2305          | {'accuracy': 0.9377777777777778} |
+| 0.1725        | 8.0   | 8400  | 0.2348          | {'accuracy': 0.9361111111111111} |
+| 0.163         | 9.0   | 9450  | 0.2419          | {'accuracy': 0.9388888888888889} |
+| 0.1553        | 10.0  | 10500 | 0.2430          | {'accuracy': 0.9405555555555556} |
+| 0.156         | 11.0  | 11550 | 0.2410          | {'accuracy': 0.9430555555555555} |
+| 0.1299        | 12.0  | 12600 | 0.2382          | {'accuracy': 0.9433333333333334} |
+| 0.1333        | 13.0  | 13650 | 0.2403          | {'accuracy': 0.9444444444444444} |
+| 0.1532        | 14.0  | 14700 | 0.2492          | {'accuracy': 0.9441666666666667} |
+| 0.1507        | 15.0  | 15750 | 0.2489          | {'accuracy': 0.9447222222222222} |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "distilbert-base-uncased",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.01,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_lin"
+  ],
+  "task_type": "SEQ_CLS"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9364dcf32d41746586c01fd53b7868bd8bb16f5487a5301e2eceaacb41151987
+size 2524256

runs/Dec03_21-54-55_0e01b6bac262/events.out.tfevents.1701640496.0e01b6bac262.1017.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ceb1852ab48afa75bc9f8f2ed3dd6e2691e9440374ef50b4b6adb91d23708e
+size 13724

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 +1,56 @@
+{
+  "add_prefix_space": true,
+  "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": 512,
+  "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:e04556cd7cc7dcf369aea70fdc9cde22b118a4c392a912178dd51b021f5b8a60
+size 4664