adediu25/distilbert-base-uncased-implicit-distilbert-all

README.md

@@ -1,10 +1,11 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-uncased
+library_name: peft
 tags:
 - generated_from_trainer
 metrics:
 - accuracy
+base_model: distilbert-base-uncased
 model-index:
 - name: trainer
   results: []
@@ -17,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.6671
-- Accuracy: {'accuracy': 0.6136936111747194}
+- Loss: 0.6720
+- Accuracy: {'accuracy': 0.7188000915960614}
 
 ## Model description
 
@@ -38,32 +39,27 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy                         |
 |:-------------:|:-----:|:-----:|:---------------:|:--------------------------------:|
-| 0.6652        | 1.0   | 5096  | 0.6672          | {'accuracy': 0.6136936111747194} |
-| 0.6621        | 2.0   | 10192 | 0.6675          | {'accuracy': 0.6136936111747194} |
-| 0.6702        | 3.0   | 15288 | 0.6711          | {'accuracy': 0.6136936111747194} |
-| 0.6748        | 4.0   | 20384 | 0.6705          | {'accuracy': 0.6136936111747194} |
-| 0.6693        | 5.0   | 25480 | 0.6674          | {'accuracy': 0.6136936111747194} |
-| 0.6594        | 6.0   | 30576 | 0.6672          | {'accuracy': 0.6136936111747194} |
-| 0.6663        | 7.0   | 35672 | 0.6682          | {'accuracy': 0.6136936111747194} |
-| 0.6738        | 8.0   | 40768 | 0.6671          | {'accuracy': 0.6136936111747194} |
-| 0.6669        | 9.0   | 45864 | 0.6671          | {'accuracy': 0.6136936111747194} |
-| 0.6654        | 10.0  | 50960 | 0.6671          | {'accuracy': 0.6136936111747194} |
+| 0.5412        | 1.0   | 2772  | 0.7622          | {'accuracy': 0.6675062972292192} |
+| 0.487         | 2.0   | 5544  | 0.7221          | {'accuracy': 0.6936111747194871} |
+| 0.4486        | 3.0   | 8316  | 0.6913          | {'accuracy': 0.7105564460728189} |
+| 0.4463        | 4.0   | 11088 | 0.6720          | {'accuracy': 0.7188000915960614} |
 
 
 ### Framework versions
 
+- PEFT 0.10.0
 - Transformers 4.38.2
 - Pytorch 2.2.1+cu121
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "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": 32,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "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 sha256:6d424fe6766c67c4dd10cd3fd38e39a5785b36a33f08513614fef4bbec25875b
+size 2669460

runs/Apr16_22-57-15_0dafd0179a67/events.out.tfevents.1713308235.0dafd0179a67.1311.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8044498bb2cf32b85f5be410d3b35e6a644dd3e0ec7845e8f8905d2593f76a
+size 7219

runs/Apr16_23-20-35_0dafd0179a67/events.out.tfevents.1713309638.0dafd0179a67.1311.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b6bb7447451e8969a7d2fe482c3a5e7298ec8065c0da8df20f609697f53ee8
+size 10704

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "[PAD]",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f45f383e3b1da361a15121b490e02caa99a2b967bb73ff04564be82e106b11
+oid sha256:65ce3a7a97684427bc85f4d0111668fb23ab0e9c616537d6875f075dabe150c7
 size 4856