Hugging Face's logo

Shaer-AI
/
ARBERT-base-submeter-classifier

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
NourFakih commited on
Commit
6523e6c
·
verified ·
1 Parent(s): bcc35e4

Save final ARBERT sub-meter model

Browse files
Files changed (6) hide show
  1. README.md +37 -37
  2. all_results.json +4 -4
  3. model.safetensors +1 -1
  4. train_results.json +4 -4
  5. trainer_state.json +4 -4
  6. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [UBC-NLP/ARBERT](https://huggingface.co/UBC-NLP/ARBERT) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1113
21
  - Accuracy: 0.9709
 
22
  - Macro F1: 0.6021
23
  - Weighted F1: 0.9654
24
 
@@ -52,42 +52,42 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 |
56
- |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|:-----------:|
57
- | 1.2986 | 0.0865 | 500 | 0.7567 | 0.7652 | 0.2987 | 0.7566 |
58
- | 0.5963 | 0.1730 | 1000 | 0.4073 | 0.8766 | 0.4198 | 0.8677 |
59
- | 0.3789 | 0.2594 | 1500 | 0.2946 | 0.9137 | 0.4782 | 0.9067 |
60
- | 0.2838 | 0.3459 | 2000 | 0.2346 | 0.9315 | 0.5072 | 0.9263 |
61
- | 0.2401 | 0.4324 | 2500 | 0.2036 | 0.9422 | 0.5251 | 0.9357 |
62
- | 0.2168 | 0.5189 | 3000 | 0.1820 | 0.9480 | 0.5299 | 0.9418 |
63
- | 0.1955 | 0.6054 | 3500 | 0.1703 | 0.9519 | 0.5376 | 0.9455 |
64
- | 0.1782 | 0.6919 | 4000 | 0.1578 | 0.9557 | 0.5499 | 0.9496 |
65
- | 0.1699 | 0.7783 | 4500 | 0.1534 | 0.9571 | 0.5466 | 0.9508 |
66
- | 0.1622 | 0.8648 | 5000 | 0.1496 | 0.9585 | 0.5579 | 0.9523 |
67
- | 0.1569 | 0.9513 | 5500 | 0.1450 | 0.9602 | 0.5472 | 0.9537 |
68
- | 0.1422 | 1.0377 | 6000 | 0.1469 | 0.9593 | 0.5690 | 0.9533 |
69
- | 0.1251 | 1.1242 | 6500 | 0.1369 | 0.9628 | 0.5801 | 0.9568 |
70
- | 0.123 | 1.2107 | 7000 | 0.1349 | 0.9632 | 0.5686 | 0.9571 |
71
- | 0.1208 | 1.2972 | 7500 | 0.1337 | 0.9639 | 0.5747 | 0.9577 |
72
- | 0.1188 | 1.3836 | 8000 | 0.1307 | 0.9645 | 0.5725 | 0.9581 |
73
- | 0.1201 | 1.4701 | 8500 | 0.1295 | 0.9651 | 0.5705 | 0.9588 |
74
- | 0.118 | 1.5566 | 9000 | 0.1271 | 0.9657 | 0.5692 | 0.9594 |
75
- | 0.1167 | 1.6431 | 9500 | 0.1259 | 0.9662 | 0.5795 | 0.9600 |
76
- | 0.1133 | 1.7296 | 10000 | 0.1220 | 0.9671 | 0.5803 | 0.9609 |
77
- | 0.1116 | 1.8161 | 10500 | 0.1210 | 0.9674 | 0.5835 | 0.9612 |
78
- | 0.1103 | 1.9025 | 11000 | 0.1165 | 0.9685 | 0.5836 | 0.9623 |
79
- | 0.1093 | 1.9890 | 11500 | 0.1172 | 0.9683 | 0.5835 | 0.9623 |
80
- | 0.0899 | 2.0754 | 12000 | 0.1174 | 0.9689 | 0.5972 | 0.9632 |
81
- | 0.0851 | 2.1619 | 12500 | 0.1171 | 0.9692 | 0.5858 | 0.9632 |
82
- | 0.0862 | 2.2484 | 13000 | 0.1172 | 0.9688 | 0.5902 | 0.9635 |
83
- | 0.0835 | 2.3349 | 13500 | 0.1162 | 0.9696 | 0.5970 | 0.9638 |
84
- | 0.0854 | 2.4213 | 14000 | 0.1159 | 0.9694 | 0.5925 | 0.9639 |
85
- | 0.0797 | 2.5078 | 14500 | 0.1157 | 0.9698 | 0.5934 | 0.9640 |
86
- | 0.0819 | 2.5943 | 15000 | 0.1152 | 0.9698 | 0.6004 | 0.9643 |
87
- | 0.0813 | 2.6808 | 15500 | 0.1135 | 0.9703 | 0.5964 | 0.9646 |
88
- | 0.0792 | 2.7673 | 16000 | 0.1120 | 0.9706 | 0.6000 | 0.9649 |
89
- | 0.0786 | 2.8538 | 16500 | 0.1116 | 0.9707 | 0.6010 | 0.9653 |
90
- | 0.0789 | 2.9402 | 17000 | 0.1113 | 0.9709 | 0.6021 | 0.9654 |
91
 
92
 
93
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [UBC-NLP/ARBERT](https://huggingface.co/UBC-NLP/ARBERT) on the None dataset.
19
  It achieves the following results on the evaluation set:
 
20
  - Accuracy: 0.9709
21
+ - Loss: 0.1113
22
  - Macro F1: 0.6021
23
  - Weighted F1: 0.9654
24
 
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss | Macro F1 | Weighted F1 |
56
+ |:-------------:|:------:|:-----:|:--------:|:---------------:|:--------:|:-----------:|
57
+ | 1.2986 | 0.0865 | 500 | 0.7652 | 0.7567 | 0.2987 | 0.7566 |
58
+ | 0.5963 | 0.1730 | 1000 | 0.8766 | 0.4073 | 0.4198 | 0.8677 |
59
+ | 0.3789 | 0.2594 | 1500 | 0.9137 | 0.2946 | 0.4782 | 0.9067 |
60
+ | 0.2838 | 0.3459 | 2000 | 0.9315 | 0.2346 | 0.5072 | 0.9263 |
61
+ | 0.2401 | 0.4324 | 2500 | 0.9422 | 0.2036 | 0.5251 | 0.9357 |
62
+ | 0.2168 | 0.5189 | 3000 | 0.9480 | 0.1820 | 0.5299 | 0.9418 |
63
+ | 0.1955 | 0.6054 | 3500 | 0.9519 | 0.1703 | 0.5376 | 0.9455 |
64
+ | 0.1782 | 0.6919 | 4000 | 0.9557 | 0.1578 | 0.5499 | 0.9496 |
65
+ | 0.1699 | 0.7783 | 4500 | 0.9571 | 0.1534 | 0.5466 | 0.9508 |
66
+ | 0.1622 | 0.8648 | 5000 | 0.9585 | 0.1496 | 0.5579 | 0.9523 |
67
+ | 0.1569 | 0.9513 | 5500 | 0.9602 | 0.1450 | 0.5472 | 0.9537 |
68
+ | 0.1422 | 1.0377 | 6000 | 0.9593 | 0.1469 | 0.5690 | 0.9533 |
69
+ | 0.1251 | 1.1242 | 6500 | 0.9628 | 0.1369 | 0.5801 | 0.9568 |
70
+ | 0.123 | 1.2107 | 7000 | 0.9632 | 0.1349 | 0.5686 | 0.9571 |
71
+ | 0.1208 | 1.2972 | 7500 | 0.9639 | 0.1337 | 0.5747 | 0.9577 |
72
+ | 0.1188 | 1.3836 | 8000 | 0.9645 | 0.1307 | 0.5725 | 0.9581 |
73
+ | 0.1201 | 1.4701 | 8500 | 0.9651 | 0.1295 | 0.5705 | 0.9588 |
74
+ | 0.118 | 1.5566 | 9000 | 0.9657 | 0.1271 | 0.5692 | 0.9594 |
75
+ | 0.1167 | 1.6431 | 9500 | 0.9662 | 0.1259 | 0.5795 | 0.9600 |
76
+ | 0.1133 | 1.7296 | 10000 | 0.9671 | 0.1220 | 0.5803 | 0.9609 |
77
+ | 0.1116 | 1.8161 | 10500 | 0.9674 | 0.1210 | 0.5835 | 0.9612 |
78
+ | 0.1103 | 1.9025 | 11000 | 0.9685 | 0.1165 | 0.5836 | 0.9623 |
79
+ | 0.1093 | 1.9890 | 11500 | 0.9683 | 0.1172 | 0.5835 | 0.9623 |
80
+ | 0.0899 | 2.0754 | 12000 | 0.9689 | 0.1174 | 0.5972 | 0.9632 |
81
+ | 0.0851 | 2.1619 | 12500 | 0.9692 | 0.1171 | 0.5858 | 0.9632 |
82
+ | 0.0862 | 2.2484 | 13000 | 0.9688 | 0.1172 | 0.5902 | 0.9635 |
83
+ | 0.0835 | 2.3349 | 13500 | 0.9696 | 0.1162 | 0.5970 | 0.9638 |
84
+ | 0.0854 | 2.4213 | 14000 | 0.9694 | 0.1159 | 0.5925 | 0.9639 |
85
+ | 0.0797 | 2.5078 | 14500 | 0.9698 | 0.1157 | 0.5934 | 0.9640 |
86
+ | 0.0819 | 2.5943 | 15000 | 0.9698 | 0.1152 | 0.6004 | 0.9643 |
87
+ | 0.0813 | 2.6808 | 15500 | 0.9703 | 0.1135 | 0.5964 | 0.9646 |
88
+ | 0.0792 | 2.7673 | 16000 | 0.9706 | 0.1120 | 0.6000 | 0.9649 |
89
+ | 0.0786 | 2.8538 | 16500 | 0.9707 | 0.1116 | 0.6010 | 0.9653 |
90
+ | 0.0789 | 2.9402 | 17000 | 0.9709 | 0.1113 | 0.6021 | 0.9654 |
91
 
92
 
93
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
  "total_flos": 7.302829698913882e+16,
4
- "train_loss": 0.18075496944522934,
5
- "train_runtime": 31524.4633,
6
- "train_samples_per_second": 140.843,
7
- "train_steps_per_second": 0.55
8
  }
 
1
  {
2
  "epoch": 3.0,
3
  "total_flos": 7.302829698913882e+16,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 0.002,
6
+ "train_samples_per_second": 2234275296.242,
7
+ "train_steps_per_second": 8728781.906
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a50330db4c30408b0d667e66275ea8ddd76919ff801ccbdb36b76b7033c822f
3
  size 651465828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6ea42b8596bdc3b3a4c8bbfa837860af880198764fa18657a4ac3e03262efb
3
  size 651465828
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
  "total_flos": 7.302829698913882e+16,
4
- "train_loss": 0.18075496944522934,
5
- "train_runtime": 31524.4633,
6
- "train_samples_per_second": 140.843,
7
- "train_steps_per_second": 0.55
8
  }
 
1
  {
2
  "epoch": 3.0,
3
  "total_flos": 7.302829698913882e+16,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 0.002,
6
+ "train_samples_per_second": 2234275296.242,
7
+ "train_steps_per_second": 8728781.906
8
  }
trainer_state.json CHANGED
@@ -625,10 +625,10 @@
625
  "epoch": 3.0,
626
  "step": 17346,
627
  "total_flos": 7.302829698913882e+16,
628
- "train_loss": 0.18075496944522934,
629
- "train_runtime": 31524.4633,
630
- "train_samples_per_second": 140.843,
631
- "train_steps_per_second": 0.55
632
  }
633
  ],
634
  "logging_steps": 500,
 
625
  "epoch": 3.0,
626
  "step": 17346,
627
  "total_flos": 7.302829698913882e+16,
628
+ "train_loss": 0.0,
629
+ "train_runtime": 0.002,
630
+ "train_samples_per_second": 2234275296.242,
631
+ "train_steps_per_second": 8728781.906
632
  }
633
  ],
634
  "logging_steps": 500,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b72ba77cf4a8bdc54f108081b7aa5eea8cd135da46fb18b1892aa6c935c428c2
3
  size 5969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd1e711bf5c5676e5079793d4b83df07f7c1dd73186da85b6f4a1c312c1dda78
3
  size 5969