Hugging Face's logo

poglicious
/
algae-detr-dinov3

Object Detection
Transformers
Safetensors
detr
Generated from Trainer
Model card Files
xet
Community
poglicious commited on
Commit
be99405
·
verified ·
1 Parent(s): 414dc42

End of training

Browse files
Files changed (2) hide show
  1. README.md +30 -21
  2. model.safetensors +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 7.4529
18
 
19
  ## Model description
20
 
@@ -34,34 +34,43 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 1e-05
37
- - train_batch_size: 8
38
- - eval_batch_size: 8
39
  - seed: 42
40
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: linear
42
  - lr_scheduler_warmup_steps: 125
43
- - num_epochs: 8
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
48
- | Training Loss | Epoch | Step | Validation Loss |
49
- |:-------------:|:------:|:----:|:---------------:|
50
- | No log | 0.5165 | 125 | 9.1431 |
51
- | No log | 1.0331 | 250 | 8.3860 |
52
- | No log | 1.5496 | 375 | 7.6765 |
53
- | 8.1567 | 2.0661 | 500 | 7.7696 |
54
- | 8.1567 | 2.5826 | 625 | 7.4655 |
55
- | 8.1567 | 3.0992 | 750 | 7.5308 |
56
- | 8.1567 | 3.6157 | 875 | 7.5974 |
57
- | 5.6677 | 4.1322 | 1000 | 7.5934 |
58
- | 5.6677 | 4.6488 | 1125 | 7.4380 |
59
- | 5.6677 | 5.1653 | 1250 | 7.4757 |
60
- | 5.6677 | 5.6818 | 1375 | 7.5004 |
61
- | 4.9214 | 6.1983 | 1500 | 7.5878 |
62
- | 4.9214 | 6.7149 | 1625 | 7.4298 |
63
- | 4.9214 | 7.2314 | 1750 | 7.4569 |
64
- | 4.9214 | 7.7479 | 1875 | 7.4529 |
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 7.1502
18
 
19
  ## Model description
20
 
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 1e-05
37
+ - train_batch_size: 32
38
+ - eval_batch_size: 32
39
  - seed: 42
40
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: linear
42
  - lr_scheduler_warmup_steps: 125
43
+ - num_epochs: 50
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-------:|:----:|:---------------:|
50
+ | No log | 2.0492 | 125 | 9.0295 |
51
+ | No log | 4.0984 | 250 | 8.3572 |
52
+ | No log | 6.1475 | 375 | 7.9395 |
53
+ | 7.7729 | 8.1967 | 500 | 7.5209 |
54
+ | 7.7729 | 10.2459 | 625 | 7.3253 |
55
+ | 7.7729 | 12.2951 | 750 | 7.4211 |
56
+ | 7.7729 | 14.3443 | 875 | 7.4970 |
57
+ | 4.8593 | 16.3934 | 1000 | 7.3769 |
58
+ | 4.8593 | 18.4426 | 1125 | 7.3811 |
59
+ | 4.8593 | 20.4918 | 1250 | 7.3434 |
60
+ | 4.8593 | 22.5410 | 1375 | 7.3463 |
61
+ | 3.9879 | 24.5902 | 1500 | 7.4509 |
62
+ | 3.9879 | 26.6393 | 1625 | 7.3332 |
63
+ | 3.9879 | 28.6885 | 1750 | 7.2705 |
64
+ | 3.9879 | 30.7377 | 1875 | 7.1949 |
65
+ | 3.7833 | 32.7869 | 2000 | 7.3268 |
66
+ | 3.7833 | 34.8361 | 2125 | 7.2636 |
67
+ | 3.7833 | 36.8852 | 2250 | 7.2168 |
68
+ | 3.7833 | 38.9344 | 2375 | 7.2514 |
69
+ | 3.6853 | 40.9836 | 2500 | 7.1643 |
70
+ | 3.6853 | 43.0328 | 2625 | 7.2198 |
71
+ | 3.6853 | 45.0820 | 2750 | 7.1966 |
72
+ | 3.6853 | 47.1311 | 2875 | 7.1910 |
73
+ | 3.6303 | 49.1803 | 3000 | 7.1502 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dc3d0ee03fc918dc8f066379a1f28a37a3ed027ea76e8023c2486b36556f3f8
3
  size 856668688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304ff624dbe7c87a9b0b97f00fc9514f368aaeb93f031924c475dc0b5bef3e72
3
  size 856668688