End of training

README.md

@@ -1,13 +1,12 @@
 ---
 license: mit
-base_model: austin/Austin-MeDeBERTa
+base_model: Amna100/PreTraining-MLM
 tags:
 - generated_from_trainer
 metrics:
 - precision
 - recall
 - f1
-- accuracy
 model-index:
 - name: fold_2
   results: []
@@ -16,15 +15,21 @@ model-index:
 <!-- 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. -->
 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amnasaeed100/FineTuning-ADE-change1/runs/94wgcdtp)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amnasaeed100/FineTuning-ADE-change1/runs/8g0cixov)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amnasaeed100/FineTuning-ADE-change1/runs/05nc4r5u)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amnasaeed100/FineTuning-ADE-change1/runs/2tfkcyde)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amnasaeed100/FineTuning-ADE-change1/runs/2zf1k4id)
 # fold_2
 
-This model is a fine-tuned version of [austin/Austin-MeDeBERTa](https://huggingface.co/austin/Austin-MeDeBERTa) on the None dataset.
+This model is a fine-tuned version of [Amna100/PreTraining-MLM](https://huggingface.co/Amna100/PreTraining-MLM) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0102
-- Precision: 0.6842
-- Recall: 0.7772
-- F1: 0.7277
-- Accuracy: 0.9969
+- Loss: 0.0123
+- Precision: 0.1834
+- Recall: 0.3042
+- F1: 0.5248
+- Pr Auc: 0.6254
+- Roc Auc: 0.9352
 
 ## Model description
 
@@ -43,26 +48,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 5e-05
 - train_batch_size: 5
 - eval_batch_size: 5
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0362        | 1.0   | 708  | 0.0109          | 0.6517    | 0.6304 | 0.6409 | 0.9963   |
-| 0.0087        | 2.0   | 1416 | 0.0092          | 0.6618    | 0.7337 | 0.6959 | 0.9968   |
-| 0.0029        | 3.0   | 2124 | 0.0102          | 0.6842    | 0.7772 | 0.7277 | 0.9969   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Pr Auc | Roc Auc |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:------:|:-------:|
+| 0.0324        | 1.0   | 630  | 0.0108          | 0.3745    | 0.9507 | 0.7320 | 0.5652 | 0.9573  |
+| 0.0101        | 2.0   | 1260 | 0.0101          | 0.5987    | 0.1560 | 0.1560 | 0.5987 | 0.9585  |
+| 0.0067        | 3.0   | 1890 | 0.0114          | 0.0581    | 0.8662 | 0.6011 | 0.6210 | 0.9303  |
+| 0.0015        | 4.0   | 2520 | 0.0110          | 0.7081    | 0.0206 | 0.9699 | 0.5885 | 0.9400  |
+| 0.0006        | 5.0   | 3150 | 0.0123          | 0.8324    | 0.2123 | 0.1818 | 0.6254 | 0.9352  |
 
 
 ### Framework versions
 
-- Transformers 4.39.0.dev0
-- Pytorch 2.1.0+cu121
-- Datasets 2.17.1
-- Tokenizers 0.15.2
+- Transformers 4.41.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "austin/Austin-MeDeBERTa",
+  "_name_or_path": "Amna100/PreTraining-MLM",
   "architectures": [
     "DebertaForTokenClassification"
   ],
@@ -40,7 +40,7 @@
   "position_biased_input": false,
   "relative_attention": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.0.dev0",
+  "transformers_version": "4.41.0.dev0",
   "type_vocab_size": 0,
   "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8096fb7cacdb000ca902526182e8227bb2f7287c165aa9f4d6266d5189bc51a5
+oid sha256:b7e927621be49f5325bbbcbba781a0d958b8da2b2567e51fbb70d617bf1eacf2
 size 554446244

runs/May12_08-15-19_aff77f7d1741/events.out.tfevents.1715501725.aff77f7d1741.6664.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f80a2dd7ff7bfcc6265f3fbe11b174e56eccc85091bcb6eb68bc259470a35c4
+size 9513

runs/May12_08-15-19_aff77f7d1741/events.out.tfevents.1715504529.aff77f7d1741.6664.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d310272b4aaf8024ff63b02d53fe29d395c4ea7d961f0b096bd465fb8bad922
+size 609

special_tokens_map.json

@@ -2,21 +2,21 @@
   "bos_token": {
     "content": "[CLS]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "cls_token": {
     "content": "[CLS]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "[SEP]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
@@ -30,21 +30,21 @@
   "pad_token": {
     "content": "[PAD]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
     "content": "[SEP]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -21,7 +21,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -30,7 +30,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -39,7 +39,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -48,7 +48,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     },
     {
@@ -112,13 +112,13 @@
       {
         "Sequence": {
           "id": "B",
-          "type_id": 0
+          "type_id": 1
         }
       },
       {
         "SpecialToken": {
           "id": "[SEP]",
-          "type_id": 0
+          "type_id": 1
         }
       }
     ],
@@ -157,6 +157,7 @@
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "[PAD]": 0,
       "[CLS]": 1,

tokenizer_config.json

@@ -1,10 +1,11 @@
 {
+  "add_bos_token": false,
   "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -12,7 +13,7 @@
     "1": {
       "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,7 +21,7 @@
     "2": {
       "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -28,7 +29,7 @@
     "3": {
       "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e03c22eb8086c922662b34eb48bd42506b0899784776c6fbaea7d494882b6fcf
-size 4920
+oid sha256:675daf4a4db5ac8ab29fb1dd3e2cd013acda585d43f185330ef12c07bfc1053e
+size 5176