paraskohli096/distilbert-base-uncased-lora-constructive-text-classification

README.md

@@ -0,0 +1,77 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+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: 2.1159
+- Accuracy: 0.8148
+- F1: 0.8147
+- Precision: 0.8148
+- Recall: 0.8148
+
+## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 81   | 1.3621          | 0.8148   | 0.8137 | 0.8189    | 0.8148 |
+| No log        | 2.0   | 162  | 0.9435          | 0.8272   | 0.8272 | 0.8283    | 0.8272 |
+| No log        | 3.0   | 243  | 1.3333          | 0.7778   | 0.7778 | 0.7789    | 0.7778 |
+| No log        | 4.0   | 324  | 1.4928          | 0.8395   | 0.8388 | 0.8509    | 0.8395 |
+| No log        | 5.0   | 405  | 1.7831          | 0.8025   | 0.8022 | 0.8028    | 0.8025 |
+| No log        | 6.0   | 486  | 2.2104          | 0.8148   | 0.8137 | 0.8189    | 0.8148 |
+| 0.1214        | 7.0   | 567  | 1.9896          | 0.8025   | 0.8022 | 0.8028    | 0.8025 |
+| 0.1214        | 8.0   | 648  | 2.0504          | 0.8148   | 0.8147 | 0.8148    | 0.8148 |
+| 0.1214        | 9.0   | 729  | 2.1091          | 0.8148   | 0.8147 | 0.8148    | 0.8148 |
+| 0.1214        | 10.0  | 810  | 2.1159          | 0.8148   | 0.8147 | 0.8148    | 0.8148 |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "distilbert-base-uncased",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_lin"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67e4a97cfc4a30f5884b483ea98b14cfbc7b3951333022413dc1f5ee13953b0f
+size 2518104

runs/Feb16_12-27-21_519ed2b4f75a/events.out.tfevents.1739708988.519ed2b4f75a.1307.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:917330302be3a3db955e070809a83a7206766fb93a7b0078097e1d0614200cf1
+size 5179

runs/Feb16_12-27-21_519ed2b4f75a/events.out.tfevents.1739709539.519ed2b4f75a.1307.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744e277bd9ef28f675c8c3541635e1fa0be9b14697dffee91ca220ae909594cf
+size 5228

runs/Feb16_12-27-21_519ed2b4f75a/events.out.tfevents.1739709653.519ed2b4f75a.1307.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5e061d201c0d71f52a3c0117cecca8ed06668673bd7149b46d96a57b724eed
+size 5228

runs/Feb16_12-27-21_519ed2b4f75a/events.out.tfevents.1739709776.519ed2b4f75a.1307.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26be213684f701b71ae7a21245b9794041e4dd3bcc9179d7e6d22595ad851c4b
+size 10504

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 +1,57 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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:dcf76b721d84dd47ad88b7bba5c43756232086544f90d14f5fd260ce88d3a02c
+size 5432