Model save
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [google/medsiglip-448](https://huggingface.co/google/medsiglip-448) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 1.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -44,23 +44,71 @@ The following hyperparameters were used during training:
|
|
| 44 |
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_steps: 5
|
| 47 |
-
- num_epochs:
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
-
| 2.
|
| 54 |
-
| 1.
|
| 55 |
-
| 1.
|
| 56 |
-
| 1.
|
| 57 |
-
| 1.
|
| 58 |
-
| 1.
|
| 59 |
-
| 1.
|
| 60 |
-
| 1.
|
| 61 |
-
| 1.
|
| 62 |
-
| 1.
|
| 63 |
-
| 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [google/medsiglip-448](https://huggingface.co/google/medsiglip-448) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.3957
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 44 |
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_steps: 5
|
| 47 |
+
- num_epochs: 10
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 2.0157 | 0.1696 | 50 | 1.3126 |
|
| 54 |
+
| 1.2948 | 0.3393 | 100 | 1.2470 |
|
| 55 |
+
| 1.2212 | 0.5089 | 150 | 1.2748 |
|
| 56 |
+
| 1.23 | 0.6785 | 200 | 1.2548 |
|
| 57 |
+
| 1.2481 | 0.8482 | 250 | 1.1919 |
|
| 58 |
+
| 1.2185 | 1.0170 | 300 | 1.1925 |
|
| 59 |
+
| 1.1155 | 1.1866 | 350 | 1.2026 |
|
| 60 |
+
| 1.1485 | 1.3562 | 400 | 1.1624 |
|
| 61 |
+
| 1.1534 | 1.5259 | 450 | 1.1593 |
|
| 62 |
+
| 1.1397 | 1.6955 | 500 | 1.1433 |
|
| 63 |
+
| 1.1196 | 1.8651 | 550 | 1.1361 |
|
| 64 |
+
| 1.0826 | 2.0339 | 600 | 1.1797 |
|
| 65 |
+
| 1.0308 | 2.2036 | 650 | 1.1511 |
|
| 66 |
+
| 1.0708 | 2.3732 | 700 | 1.1081 |
|
| 67 |
+
| 1.0575 | 2.5428 | 750 | 1.1451 |
|
| 68 |
+
| 1.0171 | 2.7125 | 800 | 1.1297 |
|
| 69 |
+
| 1.0203 | 2.8821 | 850 | 1.0809 |
|
| 70 |
+
| 1.0019 | 3.0509 | 900 | 1.0906 |
|
| 71 |
+
| 0.9815 | 3.2205 | 950 | 1.1364 |
|
| 72 |
+
| 0.941 | 3.3902 | 1000 | 1.0855 |
|
| 73 |
+
| 0.9998 | 3.5598 | 1050 | 1.0776 |
|
| 74 |
+
| 0.9542 | 3.7294 | 1100 | 1.0548 |
|
| 75 |
+
| 0.9459 | 3.8991 | 1150 | 1.1044 |
|
| 76 |
+
| 0.9768 | 4.0679 | 1200 | 1.0920 |
|
| 77 |
+
| 0.9572 | 4.2375 | 1250 | 1.1189 |
|
| 78 |
+
| 0.9052 | 4.4071 | 1300 | 1.1566 |
|
| 79 |
+
| 0.8447 | 4.5768 | 1350 | 1.1299 |
|
| 80 |
+
| 0.9008 | 4.7464 | 1400 | 1.0913 |
|
| 81 |
+
| 0.8784 | 4.9160 | 1450 | 1.1010 |
|
| 82 |
+
| 0.86 | 5.0848 | 1500 | 1.1310 |
|
| 83 |
+
| 0.8258 | 5.2545 | 1550 | 1.1896 |
|
| 84 |
+
| 0.84 | 5.4241 | 1600 | 1.2823 |
|
| 85 |
+
| 0.8637 | 5.5937 | 1650 | 1.2589 |
|
| 86 |
+
| 0.8488 | 5.7634 | 1700 | 1.1698 |
|
| 87 |
+
| 0.8298 | 5.9330 | 1750 | 1.2574 |
|
| 88 |
+
| 0.7697 | 6.1018 | 1800 | 1.2800 |
|
| 89 |
+
| 0.873 | 6.2714 | 1850 | 1.2326 |
|
| 90 |
+
| 0.7843 | 6.4411 | 1900 | 1.2283 |
|
| 91 |
+
| 0.8019 | 6.6107 | 1950 | 1.3048 |
|
| 92 |
+
| 0.7788 | 6.7803 | 2000 | 1.2452 |
|
| 93 |
+
| 0.7743 | 6.9500 | 2050 | 1.2635 |
|
| 94 |
+
| 0.7659 | 7.1187 | 2100 | 1.3144 |
|
| 95 |
+
| 0.8135 | 7.2884 | 2150 | 1.3114 |
|
| 96 |
+
| 0.7753 | 7.4580 | 2200 | 1.3197 |
|
| 97 |
+
| 0.7488 | 7.6277 | 2250 | 1.3256 |
|
| 98 |
+
| 0.7414 | 7.7973 | 2300 | 1.3678 |
|
| 99 |
+
| 0.7805 | 7.9669 | 2350 | 1.3413 |
|
| 100 |
+
| 0.7443 | 8.1357 | 2400 | 1.3732 |
|
| 101 |
+
| 0.7346 | 8.3053 | 2450 | 1.4000 |
|
| 102 |
+
| 0.7559 | 8.4750 | 2500 | 1.3945 |
|
| 103 |
+
| 0.7573 | 8.6446 | 2550 | 1.3864 |
|
| 104 |
+
| 0.7495 | 8.8142 | 2600 | 1.3861 |
|
| 105 |
+
| 0.6951 | 8.9839 | 2650 | 1.3784 |
|
| 106 |
+
| 0.7429 | 9.1527 | 2700 | 1.3987 |
|
| 107 |
+
| 0.7471 | 9.3223 | 2750 | 1.3968 |
|
| 108 |
+
| 0.7304 | 9.4919 | 2800 | 1.3966 |
|
| 109 |
+
| 0.778 | 9.6616 | 2850 | 1.3950 |
|
| 110 |
+
| 0.6908 | 9.8312 | 2900 | 1.3957 |
|
| 111 |
+
| 0.7074 | 10.0 | 2950 | 1.3957 |
|
| 112 |
|
| 113 |
|
| 114 |
### Framework versions
|