ahmed792002/Finetuning_XLNET_Paraphrase_Classification

README.md

@@ -4,9 +4,6 @@ license: mit
 base_model: xlnet-base-cased
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
-- f1
 model-index:
 - name: Finetuning_XLNET_Paraphrase_Classification
   results: []
@@ -18,10 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # Finetuning_XLNET_Paraphrase_Classification
 
 This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.9155
-- Accuracy: 0.8701
-- F1: 0.8671
 
 ## Model description
 
@@ -44,24 +37,17 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- 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: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.5517        | 1.0   | 619  | 0.3508          | 0.8529   | 0.8513 |
-| 0.3345        | 2.0   | 1238 | 0.4829          | 0.8725   | 0.8711 |
-| 0.2295        | 3.0   | 1857 | 0.9169          | 0.8627   | 0.8585 |
-| 0.1313        | 4.0   | 2476 | 0.8408          | 0.8652   | 0.8624 |
-| 0.0398        | 5.0   | 3095 | 0.9155          | 0.8701   | 0.8671 |
 
 
 ### Framework versions
 
-- Transformers 4.46.3
-- Pytorch 2.5.1+cu121
-- Datasets 3.1.0
-- Tokenizers 0.20.3
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "xlnet-base-cased",
   "architectures": [
     "XLNetForSequenceClassification"
   ],
@@ -36,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.51.3",
   "untie_r": true,
   "use_mems_eval": true,
   "use_mems_train": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7ba42b482a7510bfef2d1d4a4c02e881475f6ecf6af72690a4e4c18a40665c
+oid sha256:f8ad96335da3b4db1ba27710d9658b6ca50b2ab340fe189c2718d03a666ee4c9
 size 469264592

runs/Jun03_21-37-40_ea8e5d3258cc/events.out.tfevents.1748986662.ea8e5d3258cc.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a4af50a46b6f50e269c42bc8cd1a56da6c9a1cb0bb3541e00be9b4c587ee20
+size 6498

tokenizer_config.json

@@ -82,6 +82,7 @@
   "cls_token": "<cls>",
   "do_lower_case": false,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "keep_accents": false,
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1e1857e1f99d8c1f968b3f8eb13991f344bfe0d9f623312a8840a0064bc11c
+oid sha256:b9903d57b2418646e98ee5f1ca8dbd2556578e61f50055646a3800500a8d50ac
 size 5368