desdesmond/lora_training

README.md

@@ -1,11 +1,11 @@
 ---
-base_model: mnoukhov/gpt2-imdb-sentiment-classifier
 library_name: peft
-license: mit
-metrics:
-- accuracy
+license: apache-2.0
+base_model: ykacer/bert-base-cased-imdb-sequence-classification
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: lora_training
   results: []
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lora_training
 
-This model is a fine-tuned version of [mnoukhov/gpt2-imdb-sentiment-classifier](https://huggingface.co/mnoukhov/gpt2-imdb-sentiment-classifier) on an unknown dataset.
+This model is a fine-tuned version of [ykacer/bert-base-cased-imdb-sequence-classification](https://huggingface.co/ykacer/bert-base-cased-imdb-sequence-classification) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1823
-- Accuracy: 0.5481
+- Loss: 1.0969
+- Accuracy: 0.5975
 
 ## Model description
 
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use 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: 5
 
@@ -50,16 +50,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.9491        | 1.0   | 800  | 1.5683          | 0.3409   |
-| 1.4934        | 2.0   | 1600 | 1.4219          | 0.4922   |
-| 1.4128        | 3.0   | 2400 | 1.2784          | 0.5244   |
-| 1.2545        | 4.0   | 3200 | 1.2019          | 0.5441   |
-| 1.1988        | 5.0   | 4000 | 1.1823          | 0.5481   |
+| 1.6038        | 1.0   | 800  | 1.5082          | 0.4547   |
+| 1.305         | 2.0   | 1600 | 1.2096          | 0.5466   |
+| 1.1727        | 3.0   | 2400 | 1.1352          | 0.5775   |
+| 1.1199        | 4.0   | 3200 | 1.1062          | 0.5947   |
+| 1.0959        | 5.0   | 4000 | 1.0969          | 0.5975   |
 
 
 ### Framework versions
 
 - PEFT 0.13.2
-- Transformers 4.44.2
+- Transformers 4.46.2
 - Pytorch 2.5.0+cu121
-- Tokenizers 0.19.1
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mnoukhov/gpt2-imdb-sentiment-classifier",
+  "base_model_name_or_path": "ykacer/bert-base-cased-imdb-sequence-classification",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -23,7 +23,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_proj"
+    "query",
+    "value"
   ],
   "task_type": "TOKEN_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88860639b64eec2fbd7ff1e9225092efd27e8bdb4d8a6f44ff876e5145f0d037
-size 1056704
+oid sha256:553082f5bf6bb7fe5c1ba6d0027c7dc097595e6626a4c2fc08766989495ce553
+size 615128

special_tokens_map.json

@@ -1,30 +1,7 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,8 +1,39 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "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,
@@ -10,11 +41,17 @@
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 1024,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26dfbcc74eb94d53c0b93afd7c5b38640c092cb2e063fd48cd5f97363dcf0ad5
-size 5176
+oid sha256:506faaa3ff61fda901e71fb517d5a38902a1b769b1aa5caae878b69178ce37bf
+size 5240