Hugging Face's logo

ahmed792002
/
Finetuning_XLNET_Paraphrase_Classification

Text Classification
Transformers
TensorBoard
Safetensors
xlnet
Generated from Trainer
Model card Files Metrics Community
ahmed792002 commited on
Commit
b5944da
·
verified ·
1 Parent(s): 4581d8c

ahmed792002/Finetuning_XLNET_Paraphrase_Classification

Browse files
Files changed (11) hide show
  1. README.md +9 -9
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Dec05_20-04-57_d225dec885f9/events.out.tfevents.1733429098.d225dec885f9.784.0 +3 -0
  5. runs/Dec05_20-09-41_d225dec885f9/events.out.tfevents.1733429382.d225dec885f9.784.1 +3 -0
  6. runs/Dec05_20-12-18_d225dec885f9/events.out.tfevents.1733429539.d225dec885f9.784.2 +3 -0
  7. runs/Dec05_20-16-30_d225dec885f9/events.out.tfevents.1733429792.d225dec885f9.784.3 +3 -0
  8. runs/Dec05_20-20-39_d225dec885f9/events.out.tfevents.1733430041.d225dec885f9.784.4 +3 -0
  9. runs/Dec05_20-25-14_d225dec885f9/events.out.tfevents.1733430316.d225dec885f9.784.5 +3 -0
  10. runs/Dec05_20-26-01_d225dec885f9/events.out.tfevents.1733430361.d225dec885f9.784.6 +3 -0
  11. training_args.bin +1 -1
README.md CHANGED
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.7478
23
- - Accuracy: 0.8775
24
- - F1: 0.8777
25
 
26
  ## Model description
27
 
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
- | No log | 1.0 | 459 | 0.4274 | 0.8260 | 0.8126 |
56
- | 0.5099 | 2.0 | 918 | 0.3347 | 0.8578 | 0.8547 |
57
- | 0.3271 | 3.0 | 1377 | 0.5607 | 0.875 | 0.8710 |
58
- | 0.2297 | 4.0 | 1836 | 0.7238 | 0.8701 | 0.8702 |
59
- | 0.1346 | 5.0 | 2295 | 0.7478 | 0.8775 | 0.8777 |
60
 
61
 
62
  ### Framework versions
63
 
64
- - Transformers 4.46.2
65
  - Pytorch 2.5.1+cu121
66
  - Datasets 3.1.0
67
  - Tokenizers 0.20.3
 
19
 
20
  This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.9155
23
+ - Accuracy: 0.8701
24
+ - F1: 0.8671
25
 
26
  ## Model description
27
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
+ | 0.5517 | 1.0 | 619 | 0.3508 | 0.8529 | 0.8513 |
56
+ | 0.3345 | 2.0 | 1238 | 0.4829 | 0.8725 | 0.8711 |
57
+ | 0.2295 | 3.0 | 1857 | 0.9169 | 0.8627 | 0.8585 |
58
+ | 0.1313 | 4.0 | 2476 | 0.8408 | 0.8652 | 0.8624 |
59
+ | 0.0398 | 5.0 | 3095 | 0.9155 | 0.8701 | 0.8671 |
60
 
61
 
62
  ### Framework versions
63
 
64
+ - Transformers 4.46.3
65
  - Pytorch 2.5.1+cu121
66
  - Datasets 3.1.0
67
  - Tokenizers 0.20.3
config.json CHANGED
@@ -36,7 +36,7 @@
36
  }
37
  },
38
  "torch_dtype": "float32",
39
- "transformers_version": "4.46.2",
40
  "untie_r": true,
41
  "use_mems_eval": true,
42
  "use_mems_train": false,
 
36
  }
37
  },
38
  "torch_dtype": "float32",
39
+ "transformers_version": "4.46.3",
40
  "untie_r": true,
41
  "use_mems_eval": true,
42
  "use_mems_train": false,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa23fcc21e5114ac69b959ef1703973bd24ce59bc2aacb6607b0f13de9a78eeb
3
  size 469264592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa7ba42b482a7510bfef2d1d4a4c02e881475f6ecf6af72690a4e4c18a40665c
3
  size 469264592
runs/Dec05_20-04-57_d225dec885f9/events.out.tfevents.1733429098.d225dec885f9.784.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:782e13ead43a59b5bf08c1f0ff65ac3eff23c5b116ceac16af8b9895bd3b7e16
3
+ size 6545
runs/Dec05_20-09-41_d225dec885f9/events.out.tfevents.1733429382.d225dec885f9.784.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72313948092256a66fbdb69eeeb095004db0513cc9abdd36ea5f5e527fc32a15
3
+ size 5754
runs/Dec05_20-12-18_d225dec885f9/events.out.tfevents.1733429539.d225dec885f9.784.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8e4cbbee2bc96663a144bb9e3d4f1cc0e70c39da4eb03dda385cd4f5fe7011
3
+ size 5965
runs/Dec05_20-16-30_d225dec885f9/events.out.tfevents.1733429792.d225dec885f9.784.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc544ed7a2c008176b26e8c1a7f78beca2e359ec45f01b1ac15ee5b5a5c8864
3
+ size 5965
runs/Dec05_20-20-39_d225dec885f9/events.out.tfevents.1733430041.d225dec885f9.784.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704ea4198b6a421d3c613bf2f96a998a0ef242653886c7bef1aa3e7ed4e300b1
3
+ size 5965
runs/Dec05_20-25-14_d225dec885f9/events.out.tfevents.1733430316.d225dec885f9.784.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc03d8632f21ce465dd9755091311b637f62827d54e57ecae6a5a14912b1906
3
+ size 5385
runs/Dec05_20-26-01_d225dec885f9/events.out.tfevents.1733430361.d225dec885f9.784.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ef440c00806a64b963dc32545ba4b6f11b135652e6c5d5f065a972631f9cc6
3
+ size 8850
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa01fa8a20589df72b5ad7d14ef2398a7a54c41cb6ac21642392d35bbeff4738
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1e1857e1f99d8c1f968b3f8eb13991f344bfe0d9f623312a8840a0064bc11c
3
  size 5368