KrishGoyani/distilbert-movie-classification

README.md

@@ -0,0 +1,66 @@
+---
+base_model: distilbert-base-uncased
+library_name: peft
+license: apache-2.0
+metrics:
+- accuracy
+tags:
+- generated_from_trainer
+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: 0.2711
+- Accuracy: {'accuracy': 0.903}
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy            |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------:|
+| No log        | 1.0   | 16   | 0.3245          | {'accuracy': 0.886} |
+| No log        | 2.0   | 32   | 0.2693          | {'accuracy': 0.892} |
+| No log        | 3.0   | 48   | 0.2717          | {'accuracy': 0.887} |
+| No log        | 4.0   | 64   | 0.2650          | {'accuracy': 0.898} |
+| No log        | 5.0   | 80   | 0.2711          | {'accuracy': 0.903} |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "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": 64,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "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 sha256:032076ce224ee74147f280c6bc7c5e5cf60c5849a4523a4d4641bc4a0fc8f34e
+size 3550600

runs/Nov06_06-31-07_01127d0cd214/events.out.tfevents.1730874674.01127d0cd214.1329.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986e2976ee986f532d63eeba60c442c2e369609287477faf24244a78191f8ac9
+size 4184

runs/Nov06_06-35-20_01127d0cd214/events.out.tfevents.1730874925.01127d0cd214.4863.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f1d106f4afcd474c1ed8a2e392db588ce720658e1a8e6fb29c9bdc2926c1c9
+size 5018

runs/Nov06_06-36-31_01127d0cd214/events.out.tfevents.1730874995.01127d0cd214.4863.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4efb6c831d29547fa15eef353d6b9afc318c37d29e21712eb4b0c5a17d6523
+size 6397

runs/Nov06_06-45-42_01127d0cd214/events.out.tfevents.1730875546.01127d0cd214.4863.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7473ecaccd2ff711652f8b412c8f9aa67aae5a4de52424b86faee4ac8149f6c3
+size 6744

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:b1a4efd13a50f5dd57ea456e46dff25c1f12dabee4dadcca862d605563530db2
+size 5240