Hugging Face's logo

lombardata
/
drone-DinoVdeau-produttoria-probabilities-large-2024_11_04-batch-size64_freeze_probs

TensorBoard
Safetensors
English
dinov2
multilabel-image-classification
multilabel
Generated from Trainer
Model card Files Metrics Community
lombardata commited on
Commit
528b0b1
•
1 Parent(s): c42c931

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +176 -110
README.md CHANGED
@@ -1,131 +1,197 @@
 
1
  ---
2
- license: apache-2.0
3
- base_model: facebook/dinov2-large
 
4
  tags:
 
 
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: drone-DinoVdeau-produttoria-probabilities-large-2024_11_04-batch-size64_freeze_probs
8
  results: []
9
  ---
10
 
11
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
- should probably proofread and complete it, then remove this comment. -->
13
 
14
- # drone-DinoVdeau-produttoria-probabilities-large-2024_11_04-batch-size64_freeze_probs
15
 
16
- This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the None dataset.
17
- It achieves the following results on the evaluation set:
18
  - Loss: 0.3194
19
- - Rmse: 0.2405
20
- - Mae: 0.1536
21
- - R2: 0.4281
22
- - Explained Variance: 0.4294
23
- - Learning Rate: 0.0000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
 
25
- ## Model description
 
26
 
27
- More information needed
28
 
29
- ## Intended uses & limitations
30
 
31
- More information needed
 
 
 
 
 
32
 
33
- ## Training and evaluation data
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
 
35
- More information needed
36
 
37
- ## Training procedure
38
 
39
- ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 0.001
43
- - train_batch_size: 64
44
- - eval_batch_size: 64
45
- - seed: 42
46
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
- - lr_scheduler_type: linear
48
- - num_epochs: 150
49
- - mixed_precision_training: Native AMP
50
-
51
- ### Training results
52
-
53
- | Training Loss | Epoch | Step | Validation Loss | Rmse | Mae | R2 | Explained Variance | Rate |
54
- |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:------------------:|:------:|
55
- | No log | 1.0 | 181 | 0.3610 | 0.2645 | 0.1878 | 0.2818 | 0.3037 | 0.001 |
56
- | No log | 2.0 | 362 | 0.3465 | 0.2566 | 0.1778 | 0.3349 | 0.3479 | 0.001 |
57
- | 0.4149 | 3.0 | 543 | 0.3413 | 0.2532 | 0.1731 | 0.3536 | 0.3600 | 0.001 |
58
- | 0.4149 | 4.0 | 724 | 0.3406 | 0.2532 | 0.1743 | 0.3519 | 0.3591 | 0.001 |
59
- | 0.4149 | 5.0 | 905 | 0.3342 | 0.2496 | 0.1661 | 0.3702 | 0.3731 | 0.001 |
60
- | 0.3486 | 6.0 | 1086 | 0.3385 | 0.2512 | 0.1739 | 0.3651 | 0.3724 | 0.001 |
61
- | 0.3486 | 7.0 | 1267 | 0.3321 | 0.2476 | 0.1650 | 0.3836 | 0.3846 | 0.001 |
62
- | 0.3486 | 8.0 | 1448 | 0.3332 | 0.2484 | 0.1629 | 0.3802 | 0.3811 | 0.001 |
63
- | 0.3462 | 9.0 | 1629 | 0.3305 | 0.2468 | 0.1652 | 0.3859 | 0.3872 | 0.001 |
64
- | 0.3462 | 10.0 | 1810 | 0.3314 | 0.2476 | 0.1655 | 0.3827 | 0.3850 | 0.001 |
65
- | 0.3462 | 11.0 | 1991 | 0.3320 | 0.2474 | 0.1602 | 0.3840 | 0.3866 | 0.001 |
66
- | 0.3391 | 12.0 | 2172 | 0.3342 | 0.2494 | 0.1683 | 0.3761 | 0.3843 | 0.001 |
67
- | 0.3391 | 13.0 | 2353 | 0.3325 | 0.2480 | 0.1649 | 0.3821 | 0.3836 | 0.001 |
68
- | 0.3372 | 14.0 | 2534 | 0.3323 | 0.2472 | 0.1700 | 0.3878 | 0.3930 | 0.001 |
69
- | 0.3372 | 15.0 | 2715 | 0.3349 | 0.2493 | 0.1703 | 0.3749 | 0.3828 | 0.001 |
70
- | 0.3372 | 16.0 | 2896 | 0.3279 | 0.2448 | 0.1649 | 0.3983 | 0.4019 | 0.0001 |
71
- | 0.3343 | 17.0 | 3077 | 0.3279 | 0.2448 | 0.1648 | 0.3984 | 0.4041 | 0.0001 |
72
- | 0.3343 | 18.0 | 3258 | 0.3262 | 0.2440 | 0.1622 | 0.4025 | 0.4032 | 0.0001 |
73
- | 0.3343 | 19.0 | 3439 | 0.3247 | 0.2432 | 0.1588 | 0.4046 | 0.4051 | 0.0001 |
74
- | 0.3271 | 20.0 | 3620 | 0.3261 | 0.2433 | 0.1625 | 0.4059 | 0.4106 | 0.0001 |
75
- | 0.3271 | 21.0 | 3801 | 0.3241 | 0.2424 | 0.1606 | 0.4095 | 0.4119 | 0.0001 |
76
- | 0.3271 | 22.0 | 3982 | 0.3236 | 0.2422 | 0.1587 | 0.4111 | 0.4132 | 0.0001 |
77
- | 0.3275 | 23.0 | 4163 | 0.3242 | 0.2423 | 0.1601 | 0.4107 | 0.4134 | 0.0001 |
78
- | 0.3275 | 24.0 | 4344 | 0.3227 | 0.2414 | 0.1586 | 0.4150 | 0.4161 | 0.0001 |
79
- | 0.3247 | 25.0 | 4525 | 0.3224 | 0.2413 | 0.1587 | 0.4148 | 0.4162 | 0.0001 |
80
- | 0.3247 | 26.0 | 4706 | 0.3218 | 0.2413 | 0.1557 | 0.4143 | 0.4155 | 0.0001 |
81
- | 0.3247 | 27.0 | 4887 | 0.3227 | 0.2416 | 0.1603 | 0.4138 | 0.4154 | 0.0001 |
82
- | 0.3231 | 28.0 | 5068 | 0.3207 | 0.2405 | 0.1562 | 0.4186 | 0.4197 | 0.0001 |
83
- | 0.3231 | 29.0 | 5249 | 0.3221 | 0.2411 | 0.1597 | 0.4163 | 0.4175 | 0.0001 |
84
- | 0.3231 | 30.0 | 5430 | 0.3225 | 0.2413 | 0.1608 | 0.4164 | 0.4190 | 0.0001 |
85
- | 0.3215 | 31.0 | 5611 | 0.3224 | 0.2416 | 0.1535 | 0.4134 | 0.4164 | 0.0001 |
86
- | 0.3215 | 32.0 | 5792 | 0.3213 | 0.2408 | 0.1553 | 0.4180 | 0.4185 | 0.0001 |
87
- | 0.3215 | 33.0 | 5973 | 0.3216 | 0.2414 | 0.1583 | 0.4123 | 0.4142 | 0.0001 |
88
- | 0.3227 | 34.0 | 6154 | 0.3205 | 0.2406 | 0.1562 | 0.4172 | 0.4181 | 0.0001 |
89
- | 0.3227 | 35.0 | 6335 | 0.3198 | 0.2399 | 0.1535 | 0.4215 | 0.4224 | 0.0001 |
90
- | 0.3202 | 36.0 | 6516 | 0.3211 | 0.2406 | 0.1577 | 0.4187 | 0.4194 | 0.0001 |
91
- | 0.3202 | 37.0 | 6697 | 0.3204 | 0.2403 | 0.1520 | 0.4188 | 0.4203 | 0.0001 |
92
- | 0.3202 | 38.0 | 6878 | 0.3214 | 0.2409 | 0.1560 | 0.4170 | 0.4185 | 0.0001 |
93
- | 0.3195 | 39.0 | 7059 | 0.3195 | 0.2397 | 0.1520 | 0.4226 | 0.4232 | 0.0001 |
94
- | 0.3195 | 40.0 | 7240 | 0.3208 | 0.2404 | 0.1577 | 0.4204 | 0.4231 | 0.0001 |
95
- | 0.3195 | 41.0 | 7421 | 0.3198 | 0.2398 | 0.1547 | 0.4217 | 0.4233 | 0.0001 |
96
- | 0.3192 | 42.0 | 7602 | 0.3218 | 0.2410 | 0.1589 | 0.4174 | 0.4218 | 0.0001 |
97
- | 0.3192 | 43.0 | 7783 | 0.3190 | 0.2396 | 0.1544 | 0.4235 | 0.4254 | 0.0001 |
98
- | 0.3192 | 44.0 | 7964 | 0.3190 | 0.2396 | 0.1534 | 0.4230 | 0.4239 | 0.0001 |
99
- | 0.3178 | 45.0 | 8145 | 0.3198 | 0.2397 | 0.1566 | 0.4239 | 0.4260 | 0.0001 |
100
- | 0.3178 | 46.0 | 8326 | 0.3193 | 0.2398 | 0.1556 | 0.4213 | 0.4231 | 0.0001 |
101
- | 0.3175 | 47.0 | 8507 | 0.3190 | 0.2393 | 0.1524 | 0.4245 | 0.4257 | 0.0001 |
102
- | 0.3175 | 48.0 | 8688 | 0.3193 | 0.2398 | 0.1525 | 0.4215 | 0.4230 | 0.0001 |
103
- | 0.3175 | 49.0 | 8869 | 0.3207 | 0.2405 | 0.1558 | 0.4187 | 0.4196 | 0.0001 |
104
- | 0.3174 | 50.0 | 9050 | 0.3198 | 0.2400 | 0.1572 | 0.4218 | 0.4237 | 1e-05 |
105
- | 0.3174 | 51.0 | 9231 | 0.3244 | 0.2426 | 0.1602 | 0.4092 | 0.4173 | 1e-05 |
106
- | 0.3174 | 52.0 | 9412 | 0.3190 | 0.2396 | 0.1550 | 0.4227 | 0.4235 | 1e-05 |
107
- | 0.3152 | 53.0 | 9593 | 0.3189 | 0.2394 | 0.1552 | 0.4249 | 0.4270 | 1e-05 |
108
- | 0.3152 | 54.0 | 9774 | 0.3194 | 0.2396 | 0.1540 | 0.4227 | 0.4239 | 1e-05 |
109
- | 0.3152 | 55.0 | 9955 | 0.3185 | 0.2391 | 0.1539 | 0.4250 | 0.4258 | 1e-05 |
110
- | 0.317 | 56.0 | 10136 | 0.3181 | 0.2388 | 0.1527 | 0.4273 | 0.4281 | 1e-05 |
111
- | 0.317 | 57.0 | 10317 | 0.3187 | 0.2392 | 0.1532 | 0.4259 | 0.4274 | 1e-05 |
112
- | 0.317 | 58.0 | 10498 | 0.3201 | 0.2401 | 0.1567 | 0.4217 | 0.4259 | 1e-05 |
113
- | 0.314 | 59.0 | 10679 | 0.3181 | 0.2388 | 0.1528 | 0.4270 | 0.4282 | 1e-05 |
114
- | 0.314 | 60.0 | 10860 | 0.3182 | 0.2389 | 0.1534 | 0.4256 | 0.4268 | 1e-05 |
115
- | 0.314 | 61.0 | 11041 | 0.3186 | 0.2391 | 0.1510 | 0.4255 | 0.4266 | 1e-05 |
116
- | 0.314 | 62.0 | 11222 | 0.3203 | 0.2398 | 0.1596 | 0.4240 | 0.4262 | 1e-05 |
117
- | 0.314 | 63.0 | 11403 | 0.3196 | 0.2397 | 0.1570 | 0.4242 | 0.4276 | 1e-05 |
118
- | 0.3142 | 64.0 | 11584 | 0.3181 | 0.2391 | 0.1527 | 0.4244 | 0.4253 | 1e-05 |
119
- | 0.3142 | 65.0 | 11765 | 0.3185 | 0.2390 | 0.1550 | 0.4259 | 0.4264 | 1e-05 |
120
- | 0.3142 | 66.0 | 11946 | 0.3186 | 0.2389 | 0.1562 | 0.4278 | 0.4291 | 0.0000 |
121
- | 0.3131 | 67.0 | 12127 | 0.3181 | 0.2387 | 0.1526 | 0.4270 | 0.4279 | 0.0000 |
122
- | 0.3131 | 68.0 | 12308 | 0.3195 | 0.2397 | 0.1549 | 0.4221 | 0.4257 | 0.0000 |
123
- | 0.3131 | 69.0 | 12489 | 0.3183 | 0.2390 | 0.1540 | 0.4259 | 0.4275 | 0.0000 |
124
-
125
-
126
- ### Framework versions
127
-
128
- - Transformers 4.41.0
129
- - Pytorch 2.5.0+cu124
130
- - Datasets 3.0.2
131
- - Tokenizers 0.19.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
  ---
3
+ language:
4
+ - eng
5
+ license: cc0-1.0
6
  tags:
7
+ - multilabel-image-classification
8
+ - multilabel
9
  - generated_from_trainer
10
+ base_model: drone-DinoVdeau-produttoria-probabilities-large-2024_11_04-batch-size64_freeze_probs
11
  model-index:
12
  - name: drone-DinoVdeau-produttoria-probabilities-large-2024_11_04-batch-size64_freeze_probs
13
  results: []
14
  ---
15
 
16
+ drone-DinoVdeau-produttoria-probabilities is a fine-tuned version of [drone-DinoVdeau-produttoria-probabilities-large-2024_11_04-batch-size64_freeze_probs](https://huggingface.co/drone-DinoVdeau-produttoria-probabilities-large-2024_11_04-batch-size64_freeze_probs). It achieves the following results on the test set:
 
17
 
 
18
 
 
 
19
  - Loss: 0.3194
20
+ - F1 Micro: 0.8663
21
+ - F1 Macro: 0.8311
22
+ - Accuracy: 0.1799
23
+ - RMSE: 0.2404
24
+ - MAE: 0.1536
25
+ - R2: 0.4282
26
+
27
+ | Class | F1 per class |
28
+ |----------|-------|
29
+ | Acropore_branched | 0.8010 |
30
+ | Acropore_digitised | 0.7454 |
31
+ | Acropore_tabular | 0.6426 |
32
+ | Algae | 0.9852 |
33
+ | Dead_coral | 0.8448 |
34
+ | Fish | 0.7497 |
35
+ | Millepore | 0.6641 |
36
+ | No_acropore_encrusting | 0.7391 |
37
+ | No_acropore_massive | 0.8688 |
38
+ | No_acropore_sub_massive | 0.8137 |
39
+ | Rock | 0.9924 |
40
+ | Rubble | 0.9691 |
41
+ | Sand | 0.9888 |
42
+
43
+
44
+ ---
45
 
46
+ # Model description
47
+ drone-DinoVdeau-produttoria-probabilities is a model built on top of drone-DinoVdeau-produttoria-probabilities-large-2024_11_04-batch-size64_freeze_probs model for underwater multilabel image classification.The classification head is a combination of linear, ReLU, batch normalization, and dropout layers.
48
 
49
+ The source code for training the model can be found in this [Git repository](https://github.com/SeatizenDOI/DinoVdeau).
50
 
51
+ - **Developed by:** [lombardata](https://huggingface.co/lombardata), credits to [César Leblanc](https://huggingface.co/CesarLeblanc) and [Victor Illien](https://huggingface.co/groderg)
52
 
53
+ ---
54
+
55
+ # Intended uses & limitations
56
+ You can use the raw model for classify diverse marine species, encompassing coral morphotypes classes taken from the Global Coral Reef Monitoring Network (GCRMN), habitats classes and seagrass species.
57
+
58
+ ---
59
 
60
+ # Training and evaluation data
61
+ Details on the estimated number of images for each class are given in the following table:
62
+ | Class | train | test | val | Total |
63
+ |:------------------------|--------:|-------:|------:|--------:|
64
+ | Acropore_branched | 2028 | 684 | 686 | 3398 |
65
+ | Acropore_digitised | 2006 | 735 | 717 | 3458 |
66
+ | Acropore_tabular | 1237 | 461 | 451 | 2149 |
67
+ | Algae | 11086 | 3671 | 3675 | 18432 |
68
+ | Dead_coral | 6354 | 2161 | 2147 | 10662 |
69
+ | Fish | 4032 | 1430 | 1430 | 6892 |
70
+ | Millepore | 1943 | 783 | 772 | 3498 |
71
+ | No_acropore_encrusting | 2663 | 986 | 957 | 4606 |
72
+ | No_acropore_massive | 6897 | 2375 | 2375 | 11647 |
73
+ | No_acropore_sub_massive | 5416 | 1988 | 1958 | 9362 |
74
+ | Rock | 11164 | 3726 | 3725 | 18615 |
75
+ | Rubble | 10687 | 3570 | 3572 | 17829 |
76
+ | Sand | 11151 | 3726 | 3723 | 18600 |
77
 
78
+ ---
79
 
80
+ # Training procedure
81
 
82
+ ## Training hyperparameters
83
 
84
  The following hyperparameters were used during training:
85
+
86
+ - **Number of Epochs**: 69.0
87
+ - **Learning Rate**: 0.001
88
+ - **Train Batch Size**: 64
89
+ - **Eval Batch Size**: 64
90
+ - **Optimizer**: Adam
91
+ - **LR Scheduler Type**: ReduceLROnPlateau with a patience of 5 epochs and a factor of 0.1
92
+ - **Freeze Encoder**: Yes
93
+ - **Data Augmentation**: Yes
94
+
95
+
96
+ ## Data Augmentation
97
+ Data were augmented using the following transformations :
98
+
99
+ Train Transforms
100
+ - **PreProcess**: No additional parameters
101
+ - **Resize**: probability=1.00
102
+ - **RandomHorizontalFlip**: probability=0.25
103
+ - **RandomVerticalFlip**: probability=0.25
104
+ - **ColorJiggle**: probability=0.25
105
+ - **RandomPerspective**: probability=0.25
106
+ - **Normalize**: probability=1.00
107
+
108
+ Val Transforms
109
+ - **PreProcess**: No additional parameters
110
+ - **Resize**: probability=1.00
111
+ - **Normalize**: probability=1.00
112
+
113
+
114
+
115
+ ## Training results
116
+ Epoch | Validation Loss | MAE | RMSE | R2 | Learning Rate
117
+ --- | --- | --- | --- | --- | ---
118
+ 1 | 0.36101797223091125 | 0.1878 | 0.2645 | 0.2818 | 0.001
119
+ 2 | 0.3464529514312744 | 0.1778 | 0.2566 | 0.3349 | 0.001
120
+ 3 | 0.34133487939834595 | 0.1731 | 0.2532 | 0.3536 | 0.001
121
+ 4 | 0.3406243324279785 | 0.1743 | 0.2532 | 0.3519 | 0.001
122
+ 5 | 0.3341675400733948 | 0.1661 | 0.2496 | 0.3702 | 0.001
123
+ 6 | 0.33848145604133606 | 0.1739 | 0.2512 | 0.3651 | 0.001
124
+ 7 | 0.3320676386356354 | 0.1650 | 0.2476 | 0.3836 | 0.001
125
+ 8 | 0.3332081437110901 | 0.1629 | 0.2484 | 0.3802 | 0.001
126
+ 9 | 0.3305376172065735 | 0.1652 | 0.2468 | 0.3859 | 0.001
127
+ 10 | 0.33136793971061707 | 0.1655 | 0.2476 | 0.3827 | 0.001
128
+ 11 | 0.3319685757160187 | 0.1602 | 0.2474 | 0.3840 | 0.001
129
+ 12 | 0.3341500759124756 | 0.1683 | 0.2494 | 0.3761 | 0.001
130
+ 13 | 0.33248215913772583 | 0.1649 | 0.2480 | 0.3821 | 0.001
131
+ 14 | 0.33228376507759094 | 0.1700 | 0.2472 | 0.3878 | 0.001
132
+ 15 | 0.334873229265213 | 0.1703 | 0.2493 | 0.3749 | 0.001
133
+ 16 | 0.3279329538345337 | 0.1649 | 0.2448 | 0.3983 | 0.0001
134
+ 17 | 0.3279244005680084 | 0.1648 | 0.2448 | 0.3984 | 0.0001
135
+ 18 | 0.3262367248535156 | 0.1622 | 0.2440 | 0.4025 | 0.0001
136
+ 19 | 0.3247373402118683 | 0.1588 | 0.2432 | 0.4046 | 0.0001
137
+ 20 | 0.32612329721450806 | 0.1625 | 0.2433 | 0.4059 | 0.0001
138
+ 21 | 0.3241129517555237 | 0.1606 | 0.2424 | 0.4095 | 0.0001
139
+ 22 | 0.32355180382728577 | 0.1587 | 0.2422 | 0.4111 | 0.0001
140
+ 23 | 0.3242079019546509 | 0.1601 | 0.2423 | 0.4107 | 0.0001
141
+ 24 | 0.3227241337299347 | 0.1586 | 0.2414 | 0.4150 | 0.0001
142
+ 25 | 0.3223778307437897 | 0.1587 | 0.2413 | 0.4148 | 0.0001
143
+ 26 | 0.3217927813529968 | 0.1557 | 0.2413 | 0.4143 | 0.0001
144
+ 27 | 0.3227355182170868 | 0.1603 | 0.2416 | 0.4138 | 0.0001
145
+ 28 | 0.32067713141441345 | 0.1562 | 0.2405 | 0.4186 | 0.0001
146
+ 29 | 0.32205939292907715 | 0.1597 | 0.2411 | 0.4163 | 0.0001
147
+ 30 | 0.32246074080467224 | 0.1608 | 0.2413 | 0.4164 | 0.0001
148
+ 31 | 0.3223503530025482 | 0.1535 | 0.2416 | 0.4134 | 0.0001
149
+ 32 | 0.3212696313858032 | 0.1553 | 0.2408 | 0.4180 | 0.0001
150
+ 33 | 0.32156360149383545 | 0.1583 | 0.2414 | 0.4123 | 0.0001
151
+ 34 | 0.3205103278160095 | 0.1562 | 0.2406 | 0.4172 | 0.0001
152
+ 35 | 0.3197581171989441 | 0.1535 | 0.2399 | 0.4215 | 0.0001
153
+ 36 | 0.3211075961589813 | 0.1577 | 0.2406 | 0.4187 | 0.0001
154
+ 37 | 0.3203599154949188 | 0.1520 | 0.2403 | 0.4188 | 0.0001
155
+ 38 | 0.32143038511276245 | 0.1560 | 0.2409 | 0.4170 | 0.0001
156
+ 39 | 0.3195198178291321 | 0.1520 | 0.2397 | 0.4226 | 0.0001
157
+ 40 | 0.3207896649837494 | 0.1577 | 0.2404 | 0.4204 | 0.0001
158
+ 41 | 0.3197501003742218 | 0.1547 | 0.2398 | 0.4217 | 0.0001
159
+ 42 | 0.32175716757774353 | 0.1589 | 0.2410 | 0.4174 | 0.0001
160
+ 43 | 0.3189575970172882 | 0.1544 | 0.2396 | 0.4235 | 0.0001
161
+ 44 | 0.31898385286331177 | 0.1534 | 0.2396 | 0.4230 | 0.0001
162
+ 45 | 0.31977778673171997 | 0.1566 | 0.2397 | 0.4239 | 0.0001
163
+ 46 | 0.3193351626396179 | 0.1556 | 0.2398 | 0.4213 | 0.0001
164
+ 47 | 0.31895366311073303 | 0.1524 | 0.2393 | 0.4245 | 0.0001
165
+ 48 | 0.3192996680736542 | 0.1525 | 0.2398 | 0.4215 | 0.0001
166
+ 49 | 0.32073548436164856 | 0.1558 | 0.2405 | 0.4187 | 0.0001
167
+ 50 | 0.3198453485965729 | 0.1572 | 0.2400 | 0.4218 | 1e-05
168
+ 51 | 0.32436585426330566 | 0.1602 | 0.2426 | 0.4092 | 1e-05
169
+ 52 | 0.31899821758270264 | 0.1550 | 0.2396 | 0.4227 | 1e-05
170
+ 53 | 0.31892043352127075 | 0.1552 | 0.2394 | 0.4249 | 1e-05
171
+ 54 | 0.3194037675857544 | 0.1540 | 0.2396 | 0.4227 | 1e-05
172
+ 55 | 0.3184601366519928 | 0.1539 | 0.2391 | 0.4250 | 1e-05
173
+ 56 | 0.318115234375 | 0.1527 | 0.2388 | 0.4273 | 1e-05
174
+ 57 | 0.31871330738067627 | 0.1532 | 0.2392 | 0.4259 | 1e-05
175
+ 58 | 0.32010164856910706 | 0.1567 | 0.2401 | 0.4217 | 1e-05
176
+ 59 | 0.31807705760002136 | 0.1528 | 0.2388 | 0.4270 | 1e-05
177
+ 60 | 0.3181913495063782 | 0.1534 | 0.2389 | 0.4256 | 1e-05
178
+ 61 | 0.3185857832431793 | 0.1510 | 0.2391 | 0.4255 | 1e-05
179
+ 62 | 0.32031872868537903 | 0.1596 | 0.2398 | 0.4240 | 1e-05
180
+ 63 | 0.31964218616485596 | 0.1570 | 0.2397 | 0.4242 | 1e-05
181
+ 64 | 0.31808170676231384 | 0.1527 | 0.2391 | 0.4244 | 1e-05
182
+ 65 | 0.31850185990333557 | 0.1550 | 0.2390 | 0.4259 | 1e-05
183
+ 66 | 0.3186076879501343 | 0.1562 | 0.2389 | 0.4278 | 1.0000000000000002e-06
184
+ 67 | 0.3181016743183136 | 0.1526 | 0.2387 | 0.4270 | 1.0000000000000002e-06
185
+ 68 | 0.3194774389266968 | 0.1549 | 0.2397 | 0.4221 | 1.0000000000000002e-06
186
+ 69 | 0.3183264136314392 | 0.1540 | 0.2390 | 0.4259 | 1.0000000000000002e-06
187
+
188
+
189
+ ---
190
+
191
+ # Framework Versions
192
+
193
+ - **Transformers**: 4.41.0
194
+ - **Pytorch**: 2.5.0+cu124
195
+ - **Datasets**: 3.0.2
196
+ - **Tokenizers**: 0.19.1
197
+