shawhin/distilbert-base-uncased-lora-text-classification

README.md

@@ -0,0 +1,69 @@
+---
+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 an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8720
+- Accuracy: {'accuracy': 0.894}
+
+## 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: 0.001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy            |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------:|
+| No log        | 1.0   | 250  | 0.2692          | {'accuracy': 0.901} |
+| 0.4047        | 2.0   | 500  | 0.5088          | {'accuracy': 0.883} |
+| 0.4047        | 3.0   | 750  | 0.6266          | {'accuracy': 0.886} |
+| 0.2421        | 4.0   | 1000 | 0.6066          | {'accuracy': 0.895} |
+| 0.2421        | 5.0   | 1250 | 0.6501          | {'accuracy': 0.88}  |
+| 0.0951        | 6.0   | 1500 | 0.7872          | {'accuracy': 0.877} |
+| 0.0951        | 7.0   | 1750 | 0.8000          | {'accuracy': 0.891} |
+| 0.0231        | 8.0   | 2000 | 0.9661          | {'accuracy': 0.88}  |
+| 0.0231        | 9.0   | 2250 | 0.8709          | {'accuracy': 0.894} |
+| 0.0166        | 10.0  | 2500 | 0.8720          | {'accuracy': 0.894} |
+
+
+### Framework versions
+
+- Transformers 4.35.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.7
+- Tokenizers 0.14.1

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 sha256:15e586a4131cd054ef011fd607fa8094eeddc1814346932f830e752a73876cf1
+size 2518104

runs/Nov15_10-44-46_41567c771d91/events.out.tfevents.1700045123.41567c771d91.16896.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5207b00cd59e396931bceb0f92277bd70acc9ef9063c8fe4a4abd3fbb690c63
+size 8158

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:b5d1d55702fa7c19029a1108a4db737f853b0f06558a7d608c4b3cc87e35ef1f
+size 4664