Hugging Face's logo

ucla-nb-project
/
electra-finetuned

Fill-Mask
Transformers
Safetensors
electra
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
tejaskamtam commited on
Commit
bd2c029
•
1 Parent(s): 4dfadab

Model save

Browse files
Files changed (2) hide show
  1. README.md +103 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/electra-base-generator
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: electra-base-finetuned-xe_ey_fae
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # electra-base-finetuned-xe_ey_fae
17
+
18
+ This model is a fine-tuned version of [google/electra-base-generator](https://huggingface.co/google/electra-base-generator) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.7175
21
+ - Accuracy: 0.6678
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 100
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 16
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 3.0
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
55
+ | 2.5359 | 0.06 | 500 | 2.0696 | 0.6228 |
56
+ | 2.1807 | 0.13 | 1000 | 1.9677 | 0.6352 |
57
+ | 2.1028 | 0.19 | 1500 | 1.9192 | 0.6415 |
58
+ | 2.0658 | 0.26 | 2000 | 1.8923 | 0.6451 |
59
+ | 2.0426 | 0.32 | 2500 | 1.8699 | 0.6478 |
60
+ | 2.0133 | 0.39 | 3000 | 1.8580 | 0.6490 |
61
+ | 1.9978 | 0.45 | 3500 | 1.8411 | 0.6507 |
62
+ | 1.9862 | 0.52 | 4000 | 1.8297 | 0.6524 |
63
+ | 1.9745 | 0.58 | 4500 | 1.8154 | 0.6545 |
64
+ | 1.9606 | 0.64 | 5000 | 1.8056 | 0.6557 |
65
+ | 1.9486 | 0.71 | 5500 | 1.8033 | 0.6560 |
66
+ | 1.9416 | 0.77 | 6000 | 1.7894 | 0.6581 |
67
+ | 1.9279 | 0.84 | 6500 | 1.7848 | 0.6582 |
68
+ | 1.9196 | 0.9 | 7000 | 1.7786 | 0.6593 |
69
+ | 1.9168 | 0.97 | 7500 | 1.7762 | 0.6592 |
70
+ | 1.9123 | 1.03 | 8000 | 1.7744 | 0.6597 |
71
+ | 1.8942 | 1.1 | 8500 | 1.7625 | 0.6611 |
72
+ | 1.9053 | 1.16 | 9000 | 1.7576 | 0.6623 |
73
+ | 1.898 | 1.22 | 9500 | 1.7588 | 0.6620 |
74
+ | 1.8896 | 1.29 | 10000 | 1.7518 | 0.6625 |
75
+ | 1.8796 | 1.35 | 10500 | 1.7557 | 0.6619 |
76
+ | 1.8838 | 1.42 | 11000 | 1.7511 | 0.6628 |
77
+ | 1.8869 | 1.48 | 11500 | 1.7437 | 0.6640 |
78
+ | 1.8756 | 1.55 | 12000 | 1.7425 | 0.6641 |
79
+ | 1.8775 | 1.61 | 12500 | 1.7409 | 0.6641 |
80
+ | 1.8757 | 1.68 | 13000 | 1.7372 | 0.6649 |
81
+ | 1.8616 | 1.74 | 13500 | 1.7387 | 0.6646 |
82
+ | 1.8675 | 1.8 | 14000 | 1.7335 | 0.6648 |
83
+ | 1.8725 | 1.87 | 14500 | 1.7288 | 0.6660 |
84
+ | 1.8678 | 1.93 | 15000 | 1.7305 | 0.6659 |
85
+ | 1.8611 | 2.0 | 15500 | 1.7256 | 0.6666 |
86
+ | 1.853 | 2.06 | 16000 | 1.7286 | 0.6661 |
87
+ | 1.8487 | 2.13 | 16500 | 1.7285 | 0.6659 |
88
+ | 1.8543 | 2.19 | 17000 | 1.7229 | 0.6668 |
89
+ | 1.8519 | 2.26 | 17500 | 1.7240 | 0.6670 |
90
+ | 1.851 | 2.32 | 18000 | 1.7275 | 0.6662 |
91
+ | 1.8547 | 2.38 | 18500 | 1.7197 | 0.6673 |
92
+ | 1.8476 | 2.45 | 19000 | 1.7164 | 0.6675 |
93
+ | 1.8444 | 2.51 | 19500 | 1.7214 | 0.6676 |
94
+ | 1.8544 | 2.58 | 20000 | 1.7217 | 0.6668 |
95
+ | 1.8491 | 2.64 | 20500 | 1.7175 | 0.6678 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.36.2
101
+ - Pytorch 2.2.0+cu121
102
+ - Datasets 2.17.0
103
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92aa68c633f92abff125968da3bf34bdc4e9799df7b3b14c505cc48b2cc7d610
3
  size 134986856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a2f41fa975d2a66243cf70d44738cb6926ec4c04f82448058f18d9afc85d359
3
  size 134986856