Hugging Face's logo

jamesngai
/
xlm-roberta-xl-final-lora500

Safetensors
Generated from Trainer
Model card Files Community
jamesngai commited on
Commit
0679321
•
1 Parent(s): 7e4550f

End of training

Browse files
Files changed (1) hide show
  1. README.md +109 -0
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: facebook/xlm-roberta-xl
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: xlm-roberta-xl-final-lora500
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # xlm-roberta-xl-final-lora500
20
+
21
+ This model is a fine-tuned version of [facebook/xlm-roberta-xl](https://huggingface.co/facebook/xlm-roberta-xl) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.5378
24
+ - Precision: 0.9334
25
+ - Recall: 0.9341
26
+ - F1: 0.9337
27
+ - Accuracy: 0.9421
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 0.0001
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 16
49
+ - seed: 42
50
+ - distributed_type: multi-GPU
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_steps: 40
54
+ - num_epochs: 40
55
+ - mixed_precision_training: Native AMP
56
+ - label_smoothing_factor: 0.2
57
+
58
+ ### Training results
59
+
60
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
61
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
62
+ | 2.6949 | 1.0 | 250 | 1.9846 | 0.7571 | 0.8198 | 0.7872 | 0.8265 |
63
+ | 1.8141 | 2.0 | 500 | 1.6856 | 0.8709 | 0.8824 | 0.8766 | 0.8938 |
64
+ | 1.6277 | 3.0 | 750 | 1.6081 | 0.8881 | 0.9011 | 0.8945 | 0.9122 |
65
+ | 1.5464 | 4.0 | 1000 | 1.5735 | 0.9004 | 0.9064 | 0.9034 | 0.9201 |
66
+ | 1.4908 | 5.0 | 1250 | 1.5482 | 0.9111 | 0.9145 | 0.9128 | 0.9274 |
67
+ | 1.4599 | 6.0 | 1500 | 1.5386 | 0.9096 | 0.9175 | 0.9135 | 0.9282 |
68
+ | 1.4382 | 7.0 | 1750 | 1.5396 | 0.9175 | 0.9204 | 0.9189 | 0.9292 |
69
+ | 1.422 | 8.0 | 2000 | 1.5394 | 0.9163 | 0.9212 | 0.9188 | 0.9305 |
70
+ | 1.4053 | 9.0 | 2250 | 1.5354 | 0.9240 | 0.9223 | 0.9231 | 0.9335 |
71
+ | 1.3949 | 10.0 | 2500 | 1.5424 | 0.9155 | 0.9230 | 0.9192 | 0.9308 |
72
+ | 1.3858 | 11.0 | 2750 | 1.5405 | 0.9202 | 0.9248 | 0.9225 | 0.9313 |
73
+ | 1.379 | 12.0 | 3000 | 1.5364 | 0.9186 | 0.9263 | 0.9224 | 0.9339 |
74
+ | 1.3715 | 13.0 | 3250 | 1.5310 | 0.9263 | 0.9275 | 0.9269 | 0.9373 |
75
+ | 1.3647 | 14.0 | 3500 | 1.5321 | 0.9221 | 0.9273 | 0.9247 | 0.9355 |
76
+ | 1.3592 | 15.0 | 3750 | 1.5347 | 0.9277 | 0.9261 | 0.9269 | 0.9372 |
77
+ | 1.3564 | 16.0 | 4000 | 1.5323 | 0.9229 | 0.9269 | 0.9249 | 0.9371 |
78
+ | 1.3524 | 17.0 | 4250 | 1.5339 | 0.9232 | 0.9248 | 0.9240 | 0.9347 |
79
+ | 1.3512 | 18.0 | 4500 | 1.5425 | 0.9262 | 0.9284 | 0.9273 | 0.9370 |
80
+ | 1.3482 | 19.0 | 4750 | 1.5387 | 0.9238 | 0.9299 | 0.9268 | 0.9362 |
81
+ | 1.3437 | 20.0 | 5000 | 1.5334 | 0.9267 | 0.9324 | 0.9295 | 0.9389 |
82
+ | 1.3414 | 21.0 | 5250 | 1.5379 | 0.9302 | 0.9283 | 0.9292 | 0.9394 |
83
+ | 1.3408 | 22.0 | 5500 | 1.5394 | 0.9256 | 0.9291 | 0.9273 | 0.9381 |
84
+ | 1.3401 | 23.0 | 5750 | 1.5376 | 0.9320 | 0.9301 | 0.9310 | 0.9391 |
85
+ | 1.3388 | 24.0 | 6000 | 1.5381 | 0.9300 | 0.9300 | 0.9300 | 0.9383 |
86
+ | 1.3379 | 25.0 | 6250 | 1.5402 | 0.9247 | 0.9309 | 0.9278 | 0.9380 |
87
+ | 1.3361 | 26.0 | 6500 | 1.5415 | 0.9303 | 0.9275 | 0.9289 | 0.9383 |
88
+ | 1.3349 | 27.0 | 6750 | 1.5391 | 0.9305 | 0.9300 | 0.9302 | 0.9402 |
89
+ | 1.3338 | 28.0 | 7000 | 1.5379 | 0.9296 | 0.9290 | 0.9293 | 0.9392 |
90
+ | 1.3337 | 29.0 | 7250 | 1.5438 | 0.9286 | 0.9309 | 0.9297 | 0.9388 |
91
+ | 1.3329 | 30.0 | 7500 | 1.5388 | 0.9325 | 0.9310 | 0.9318 | 0.9410 |
92
+ | 1.3321 | 31.0 | 7750 | 1.5443 | 0.9319 | 0.9314 | 0.9317 | 0.9408 |
93
+ | 1.3319 | 32.0 | 8000 | 1.5413 | 0.9317 | 0.9334 | 0.9325 | 0.9415 |
94
+ | 1.3313 | 33.0 | 8250 | 1.5428 | 0.9329 | 0.9332 | 0.9331 | 0.9413 |
95
+ | 1.3309 | 34.0 | 8500 | 1.5452 | 0.9288 | 0.9317 | 0.9302 | 0.9396 |
96
+ | 1.3308 | 35.0 | 8750 | 1.5382 | 0.9307 | 0.9324 | 0.9315 | 0.9410 |
97
+ | 1.3307 | 36.0 | 9000 | 1.5370 | 0.9314 | 0.9334 | 0.9324 | 0.9413 |
98
+ | 1.33 | 37.0 | 9250 | 1.5391 | 0.9321 | 0.9328 | 0.9325 | 0.9414 |
99
+ | 1.3297 | 38.0 | 9500 | 1.5386 | 0.9330 | 0.9335 | 0.9333 | 0.9414 |
100
+ | 1.3293 | 39.0 | 9750 | 1.5378 | 0.9336 | 0.9343 | 0.9340 | 0.9420 |
101
+ | 1.3294 | 40.0 | 10000 | 1.5378 | 0.9334 | 0.9341 | 0.9337 | 0.9421 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.35.2
107
+ - Pytorch 2.0.1+cu118
108
+ - Datasets 2.15.0
109
+ - Tokenizers 0.15.0