Upload OSAE study results
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- README.md +299 -1
- configs/default.yaml +96 -0
- configs/fast.yaml +18 -0
- configs/kaggle.yaml +7 -0
- configs/kaggle_fast.yaml +14 -0
- configs/smoke.yaml +54 -0
- data_splits/splits.json +0 -0
- data_splits/splits_summary.md +16 -0
- data_splits/stats.json +13 -0
- downstream/C128_l0.01_clean/finetune/f0.1/s0/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f0.1/s0/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f0.1/s0/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/finetune/f0.1/s1/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f0.1/s1/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f0.1/s1/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/finetune/f0.1/s2/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f0.1/s2/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f0.1/s2/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/finetune/f0.25/s0/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f0.25/s0/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f0.25/s0/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/finetune/f0.25/s1/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f0.25/s1/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f0.25/s1/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/finetune/f0.25/s2/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f0.25/s2/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f0.25/s2/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/finetune/f0.5/s0/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f0.5/s0/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f0.5/s0/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/finetune/f0.5/s1/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f0.5/s1/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f0.5/s1/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/finetune/f0.5/s2/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f0.5/s2/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f0.5/s2/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/finetune/f1/s0/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f1/s0/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f1/s0/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/finetune/f1/s1/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f1/s1/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f1/s1/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/finetune/f1/s2/metrics.json +149 -0
- downstream/C128_l0.01_clean/finetune/f1/s2/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/finetune/f1/s2/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/frozen/f0.1/s0/metrics.json +149 -0
- downstream/C128_l0.01_clean/frozen/f0.1/s0/test_metrics.json +170 -0
- downstream/C128_l0.01_clean/frozen/f0.1/s0/test_predictions.npy +3 -0
- downstream/C128_l0.01_clean/frozen/f0.1/s1/metrics.json +149 -0
- downstream/C128_l0.01_clean/frozen/f0.1/s1/test_metrics.json +170 -0
README.md
CHANGED
|
@@ -1,3 +1,301 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
tags:
|
| 3 |
+
- autoencoder
|
| 4 |
+
- sparse-coding
|
| 5 |
+
- representation-learning
|
| 6 |
+
- self-supervised
|
| 7 |
+
- stl10
|
| 8 |
+
- resnet18
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
# Overcomplete Sparse Autoencoders for Visual Representation Learning (STL-10)
|
| 12 |
+
|
| 13 |
+
Controlled study of whether an **overcomplete, L1-sparse convolutional autoencoder** learns features that transfer
|
| 14 |
+
better to STL-10 classification than a **conventional undercomplete autoencoder**, against a **supervised
|
| 15 |
+
ResNet-18 trained from scratch**, at 10 / 25 / 50 / 100 % of the labelled data.
|
| 16 |
+
|
| 17 |
+
Code: https://github.com/0x-khalil/OSAE
|
| 18 |
+
|
| 19 |
+
* Shared feature extractor: ResNet-18 adapted to 96×96 (3×3/2 stem, no max-pool); identical downstream classifier for all models.
|
| 20 |
+
* Standard AE latent: 128×6×6 = 4,608 coefficients (0.17× input). Overcomplete AE latent: 2048×6×6 = 73,728 (2.67× input).
|
| 21 |
+
* Pre-training on the 100,000 unlabeled images; λ* = 0.01 (selected on validation).
|
| 22 |
+
* Downstream: full fine-tuning and frozen-encoder protocols, 3 seeds, identical stratified subsets,
|
| 23 |
+
validation-only model selection, test split used once for final evaluation.
|
| 24 |
+
|
| 25 |
+
## Files
|
| 26 |
+
|
| 27 |
+
| Path | Content |
|
| 28 |
+
|---|---|
|
| 29 |
+
| `results/RESULTS.md` | headline table, ablations, paired statistics, costs |
|
| 30 |
+
| `results/figures/` | label-efficiency curves, confusion matrices, per-class accuracy |
|
| 31 |
+
| `results/representation/` | sparsity, reconstruction, separability, PCA / t-SNE / UMAP, CKA |
|
| 32 |
+
| `encoders/<variant>/encoder.pt` | pre-trained ResNet-18 trunk (`torch.load(...)["encoder"]`) |
|
| 33 |
+
| `downstream/` | per-run metrics (and checkpoints if uploaded) |
|
| 34 |
+
| `configs/`, `data_splits/` | exact configuration and split indices |
|
| 35 |
+
|
| 36 |
+
Load a pre-trained trunk with the code from the repository:
|
| 37 |
+
|
| 38 |
+
```python
|
| 39 |
+
import torch
|
| 40 |
+
from osae.models import Classifier
|
| 41 |
+
clf = Classifier()
|
| 42 |
+
clf.encoder.load_state_dict(torch.load("encoders/oae_sparse/encoder.pt")["encoder"])
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
---
|
| 46 |
+
|
| 47 |
+
# Results
|
| 48 |
+
|
| 49 |
+
All numbers: mean ± std over seeds, in %. Test = official STL-10 test split (8,000 images); every choice below was made on the validation split.
|
| 50 |
+
|
| 51 |
+
## finetune — test_top1
|
| 52 |
+
|
| 53 |
+
| Model | variant | 10% | 25% | 50% | 100% |
|
| 54 |
+
|:-------------------|:--------------------|:-------------|:-------------|:-------------|:-------------|
|
| 55 |
+
| ResNet-18 baseline | scratch | 44.11 ± 0.62 | 54.44 ± 1.86 | 65.16 ± 0.97 | 72.77 ± 0.40 |
|
| 56 |
+
| Standard AE | C128_l0_clean | 49.19 ± 0.28 | 58.44 ± 0.29 | 65.80 ± 0.12 | 68.91 ± 0.64 |
|
| 57 |
+
| Sparse OAE | C2048_l0.01_mask0.5 | 49.55 ± 0.84 | 59.21 ± 0.54 | 67.40 ± 0.14 | 69.82 ± 4.37 |
|
| 58 |
+
|
| 59 |
+
## finetune — test_macro_f1
|
| 60 |
+
|
| 61 |
+
| Model | variant | 10% | 25% | 50% | 100% |
|
| 62 |
+
|:-------------------|:--------------------|:-------------|:-------------|:-------------|:-------------|
|
| 63 |
+
| ResNet-18 baseline | scratch | 44.00 ± 0.65 | 54.40 ± 1.93 | 65.21 ± 0.97 | 72.87 ± 0.39 |
|
| 64 |
+
| Standard AE | C128_l0_clean | 49.02 ± 0.28 | 58.46 ± 0.28 | 65.84 ± 0.16 | 68.81 ± 0.77 |
|
| 65 |
+
| Sparse OAE | C2048_l0.01_mask0.5 | 49.36 ± 0.82 | 59.16 ± 0.46 | 67.45 ± 0.15 | 69.76 ± 4.46 |
|
| 66 |
+
|
| 67 |
+
## finetune — val_top1
|
| 68 |
+
|
| 69 |
+
| Model | variant | 10% | 25% | 50% | 100% |
|
| 70 |
+
|:-------------------|:--------------------|:-------------|:-------------|:-------------|:-------------|
|
| 71 |
+
| ResNet-18 baseline | scratch | 47.47 ± 2.31 | 57.20 ± 1.22 | 64.40 ± 1.59 | 70.33 ± 1.10 |
|
| 72 |
+
| Standard AE | C128_l0_clean | 51.13 ± 0.42 | 57.07 ± 0.95 | 62.27 ± 1.50 | 64.33 ± 1.30 |
|
| 73 |
+
| Sparse OAE | C2048_l0.01_mask0.5 | 50.40 ± 1.83 | 59.33 ± 0.31 | 64.07 ± 0.70 | 66.80 ± 0.53 |
|
| 74 |
+
|
| 75 |
+
## finetune — all variants (test_top1)
|
| 76 |
+
|
| 77 |
+
| variant | latent | lambda | noise | 10% | 25% | 50% | 100% | val (all f) |
|
| 78 |
+
|:---------------------|:---------|:---------|:---------|:-------------|:-------------|:-------------|:-------------|--------------:|
|
| 79 |
+
| ae_sparse | 128 | 0.01 | none | 47.90 ± 0.87 | 57.55 ± 0.64 | 64.12 ± 0.63 | 67.90 ± 0.79 | 59.02 |
|
| 80 |
+
| ae_sparse_denoise | 128 | 0.01 | gaussian | 48.93 ± 0.15 | 57.14 ± 0.50 | 63.78 ± 0.94 | 68.45 ± 0.51 | 59 |
|
| 81 |
+
| ae | 128 | 0.0 | none | 49.19 ± 0.28 | 58.44 ± 0.29 | 65.80 ± 0.12 | 68.91 ± 0.64 | 58.7 |
|
| 82 |
+
| ae_denoise | 128 | 0.0 | gaussian | 48.88 ± 0.48 | 58.58 ± 0.24 | 65.35 ± 0.73 | 69.50 ± 0.35 | 59.17 |
|
| 83 |
+
| oae_l0.01/oae_sparse | 2048 | 0.01 | none | 49.22 ± 0.51 | 57.58 ± 0.64 | 64.71 ± 0.39 | 67.90 ± 0.99 | 57.92 |
|
| 84 |
+
| oae_sparse_denoise | 2048 | 0.01 | gaussian | 48.85 ± 0.66 | 57.60 ± 0.53 | 65.05 ± 0.52 | 69.51 ± 0.14 | 58.5 |
|
| 85 |
+
| oae_sparse_mask | 2048 | 0.01 | mask | 49.55 ± 0.84 | 59.21 ± 0.54 | 67.40 ± 0.14 | 69.82 ± 4.37 | 60.15 |
|
| 86 |
+
| oae | 2048 | 0.0 | none | 49.77 ± 0.46 | 55.69 ± 1.58 | 65.09 ± 0.33 | 69.55 ± 0.48 | 58.33 |
|
| 87 |
+
| oae_denoise | 2048 | 0.0 | gaussian | 48.93 ± 0.40 | 57.85 ± 0.46 | 65.55 ± 0.16 | 69.77 ± 0.21 | 59.35 |
|
| 88 |
+
| scratch | – | – | – | 44.11 ± 0.62 | 54.44 ± 1.86 | 65.16 ± 0.97 | 72.77 ± 0.40 | 59.85 |
|
| 89 |
+
|
| 90 |
+
## finetune — downstream training cost (mean over runs)
|
| 91 |
+
|
| 92 |
+
| canonical | train_time_s | peak_train_mem_mb | params_total | params_trainable |
|
| 93 |
+
|:---------------------|---------------:|--------------------:|---------------:|-------------------:|
|
| 94 |
+
| C128_l0.01_clean | 147.5 | 919.2 | 1.1174e+07 | 1.1174e+07 |
|
| 95 |
+
| C128_l0.01_gauss0.5 | 145.1 | 919.2 | 1.1174e+07 | 1.1174e+07 |
|
| 96 |
+
| C128_l0_clean | 153 | 919.2 | 1.1174e+07 | 1.1174e+07 |
|
| 97 |
+
| C128_l0_gauss0.5 | 149.9 | 919.2 | 1.1174e+07 | 1.1174e+07 |
|
| 98 |
+
| C2048_l0.01_clean | 148.4 | 919.2 | 1.1174e+07 | 1.1174e+07 |
|
| 99 |
+
| C2048_l0.01_gauss0.5 | 142 | 919.2 | 1.1174e+07 | 1.1174e+07 |
|
| 100 |
+
| C2048_l0.01_mask0.5 | 143.9 | 919.2 | 1.1174e+07 | 1.1174e+07 |
|
| 101 |
+
| C2048_l0_clean | 148.7 | 919.2 | 1.1174e+07 | 1.1174e+07 |
|
| 102 |
+
| C2048_l0_gauss0.5 | 147.4 | 919.2 | 1.1174e+07 | 1.1174e+07 |
|
| 103 |
+
| scratch | 151 | 919.2 | 1.1174e+07 | 1.1174e+07 |
|
| 104 |
+
|
| 105 |
+
## finetune — paired comparisons (test top-1, B − A in points)
|
| 106 |
+
|
| 107 |
+
| A | B | fraction | n_seeds | diff_B_minus_A | diff_std | p_paired_t | p_paired_t_holm | cohens_dz | p_mcnemar_max_over_seeds |
|
| 108 |
+
|:------------------|:---------------------|-----------:|----------:|-----------------:|-----------:|-------------:|------------------:|------------:|---------------------------:|
|
| 109 |
+
| scratch | C128_l0_clean | 0.1 | 3 | 5.083 | 0.719 | 0.006602 | 0.02641 | 7.07 | 2.226e-14 |
|
| 110 |
+
| scratch | C128_l0_clean | 0.25 | 3 | 4.004 | 2.073 | 0.07893 | 0.1579 | 1.931 | 0.002828 |
|
| 111 |
+
| scratch | C128_l0_clean | 0.5 | 3 | 0.6417 | 1.079 | 0.4112 | 0.4112 | 0.5947 | 0.3509 |
|
| 112 |
+
| scratch | C128_l0_clean | 1 | 3 | -3.858 | 0.5837 | 0.007542 | 0.02641 | -6.61 | 7.597e-11 |
|
| 113 |
+
| scratch | C2048_l0.01_mask0.5 | 0.1 | 3 | 5.438 | 0.9135 | 0.009278 | 0.03711 | 5.952 | 6.667e-17 |
|
| 114 |
+
| scratch | C2048_l0.01_mask0.5 | 0.25 | 3 | 4.775 | 1.338 | 0.0252 | 0.07559 | 3.568 | 2.118e-09 |
|
| 115 |
+
| scratch | C2048_l0.01_mask0.5 | 0.5 | 3 | 2.237 | 1.038 | 0.06488 | 0.1298 | 2.155 | 0.01869 |
|
| 116 |
+
| scratch | C2048_l0.01_mask0.5 | 1 | 3 | -2.95 | 4.179 | 0.346 | 0.346 | -0.7059 | 0.5993 |
|
| 117 |
+
| C128_l0_clean | C2048_l0.01_mask0.5 | 0.1 | 3 | 0.3542 | 1.122 | 0.6394 | 1 | 0.3157 | 0.3909 |
|
| 118 |
+
| C128_l0_clean | C2048_l0.01_mask0.5 | 0.25 | 3 | 0.7708 | 0.8079 | 0.2402 | 0.7207 | 0.9541 | 0.7619 |
|
| 119 |
+
| C128_l0_clean | C2048_l0.01_mask0.5 | 0.5 | 3 | 1.596 | 0.1938 | 0.004879 | 0.01952 | 8.235 | 0.004674 |
|
| 120 |
+
| C128_l0_clean | C2048_l0.01_mask0.5 | 1 | 3 | 0.9083 | 3.722 | 0.7136 | 1 | 0.244 | 4.28e-09 |
|
| 121 |
+
| C128_l0_clean | C2048_l0_clean | 0.1 | 3 | 0.5792 | 0.6411 | 0.2581 | 0.3788 | 0.9034 | 0.8093 |
|
| 122 |
+
| C128_l0_clean | C2048_l0_clean | 0.25 | 3 | -2.75 | 1.875 | 0.1263 | 0.3788 | -1.467 | 0.05449 |
|
| 123 |
+
| C128_l0_clean | C2048_l0_clean | 0.5 | 3 | -0.7125 | 0.219 | 0.03008 | 0.1203 | -3.253 | 0.2517 |
|
| 124 |
+
| C128_l0_clean | C2048_l0_clean | 1 | 3 | 0.6375 | 0.553 | 0.1839 | 0.3788 | 1.153 | 1 |
|
| 125 |
+
| C2048_l0_clean | C2048_l0.01_clean | 0.1 | 3 | -0.55 | 0.2382 | 0.05719 | 0.2288 | -2.309 | 0.3679 |
|
| 126 |
+
| C2048_l0_clean | C2048_l0.01_clean | 0.25 | 3 | 1.887 | 1.003 | 0.08257 | 0.2477 | 1.883 | 0.01547 |
|
| 127 |
+
| C2048_l0_clean | C2048_l0.01_clean | 0.5 | 3 | -0.3792 | 0.7142 | 0.4549 | 0.4549 | -0.5309 | 0.3409 |
|
| 128 |
+
| C2048_l0_clean | C2048_l0.01_clean | 1 | 3 | -1.646 | 1.06 | 0.1149 | 0.2477 | -1.553 | 0.1841 |
|
| 129 |
+
| C128_l0_clean | C128_l0.01_clean | 0.1 | 3 | -1.288 | 0.7253 | 0.0915 | 0.2745 | -1.775 | 0.1862 |
|
| 130 |
+
| C128_l0_clean | C128_l0.01_clean | 0.25 | 3 | -0.8917 | 0.7381 | 0.1715 | 0.343 | -1.208 | 0.7835 |
|
| 131 |
+
| C128_l0_clean | C128_l0.01_clean | 0.5 | 3 | -1.683 | 0.5693 | 0.03608 | 0.1443 | -2.957 | 0.01671 |
|
| 132 |
+
| C128_l0_clean | C128_l0.01_clean | 1 | 3 | -1.008 | 1.264 | 0.3012 | 0.343 | -0.7977 | 0.4219 |
|
| 133 |
+
| C2048_l0.01_clean | C2048_l0.01_gauss0.5 | 0.1 | 3 | -0.3708 | 0.4537 | 0.2925 | 0.8775 | -0.8174 | 0.824 |
|
| 134 |
+
| C2048_l0.01_clean | C2048_l0.01_gauss0.5 | 0.25 | 3 | 0.01667 | 1.096 | 0.9814 | 0.9814 | 0.01521 | 0.2753 |
|
| 135 |
+
| C2048_l0.01_clean | C2048_l0.01_gauss0.5 | 0.5 | 3 | 0.3417 | 0.6825 | 0.4773 | 0.9546 | 0.5006 | 0.6171 |
|
| 136 |
+
| C2048_l0.01_clean | C2048_l0.01_gauss0.5 | 1 | 3 | 1.613 | 0.8928 | 0.08878 | 0.3551 | 1.806 | 0.02627 |
|
| 137 |
+
| C128_l0_clean | C128_l0_gauss0.5 | 0.1 | 3 | -0.3167 | 0.3224 | 0.231 | 0.9241 | -0.9821 | 0.9317 |
|
| 138 |
+
| C128_l0_clean | C128_l0_gauss0.5 | 0.25 | 3 | 0.1417 | 0.4161 | 0.6152 | 0.9852 | 0.3404 | 0.4568 |
|
| 139 |
+
| C128_l0_clean | C128_l0_gauss0.5 | 0.5 | 3 | -0.4583 | 0.6193 | 0.3284 | 0.9852 | -0.7401 | 0.6854 |
|
| 140 |
+
| C128_l0_clean | C128_l0_gauss0.5 | 1 | 3 | 0.5917 | 0.9863 | 0.4079 | 0.9852 | 0.5999 | 0.5875 |
|
| 141 |
+
|
| 142 |
+
## frozen — test_top1
|
| 143 |
+
|
| 144 |
+
| Model | variant | 10% | 25% | 50% | 100% |
|
| 145 |
+
|:----------------------------------|:--------------------|:-------------|:-------------|:-------------|:-------------|
|
| 146 |
+
| Random frozen ResNet-18 (control) | random | 35.58 ± 0.28 | 39.48 ± 0.34 | 41.61 ± 0.72 | 42.82 ± 1.13 |
|
| 147 |
+
| Standard AE | C128_l0_clean | 43.90 ± 0.29 | 48.54 ± 1.39 | 50.90 ± 0.56 | 52.55 ± 0.21 |
|
| 148 |
+
| Sparse OAE | C2048_l0.01_mask0.5 | 45.72 ± 0.18 | 49.67 ± 1.44 | 53.93 ± 0.09 | 55.66 ± 0.30 |
|
| 149 |
+
|
| 150 |
+
## frozen — test_macro_f1
|
| 151 |
+
|
| 152 |
+
| Model | variant | 10% | 25% | 50% | 100% |
|
| 153 |
+
|:----------------------------------|:--------------------|:-------------|:-------------|:-------------|:-------------|
|
| 154 |
+
| Random frozen ResNet-18 (control) | random | 35.26 ± 0.24 | 39.22 ± 0.38 | 41.17 ± 0.66 | 42.36 ± 1.14 |
|
| 155 |
+
| Standard AE | C128_l0_clean | 43.83 ± 0.30 | 48.31 ± 1.34 | 50.68 ± 0.62 | 52.26 ± 0.26 |
|
| 156 |
+
| Sparse OAE | C2048_l0.01_mask0.5 | 45.50 ± 0.19 | 49.52 ± 1.48 | 53.86 ± 0.08 | 55.54 ± 0.33 |
|
| 157 |
+
|
| 158 |
+
## frozen — val_top1
|
| 159 |
+
|
| 160 |
+
| Model | variant | 10% | 25% | 50% | 100% |
|
| 161 |
+
|:----------------------------------|:--------------------|:-------------|:-------------|:-------------|:-------------|
|
| 162 |
+
| Random frozen ResNet-18 (control) | random | 37.20 ± 1.56 | 41.93 ± 1.01 | 42.80 ± 3.33 | 45.27 ± 2.34 |
|
| 163 |
+
| Standard AE | C128_l0_clean | 45.60 ± 0.20 | 50.27 ± 0.81 | 50.73 ± 1.14 | 52.33 ± 1.21 |
|
| 164 |
+
| Sparse OAE | C2048_l0.01_mask0.5 | 46.33 ± 0.50 | 51.20 ± 0.20 | 54.53 ± 0.83 | 56.60 ± 0.53 |
|
| 165 |
+
|
| 166 |
+
## frozen — all variants (test_top1)
|
| 167 |
+
|
| 168 |
+
| variant | latent | lambda | noise | 10% | 25% | 50% | 100% | val (all f) |
|
| 169 |
+
|:---------------------|:---------|:---------|:---------|:-------------|:-------------|:-------------|:-------------|--------------:|
|
| 170 |
+
| ae_sparse | 128 | 0.01 | none | 44.01 ± 0.35 | 48.34 ± 0.25 | 50.41 ± 0.13 | 51.15 ± 0.36 | 49 |
|
| 171 |
+
| ae_sparse_denoise | 128 | 0.01 | gaussian | 42.26 ± 0.89 | 47.79 ± 0.43 | 49.28 ± 0.30 | 50.71 ± 0.29 | 47.5 |
|
| 172 |
+
| ae | 128 | 0.0 | none | 43.90 ± 0.29 | 48.54 ± 1.39 | 50.90 ± 0.56 | 52.55 ± 0.21 | 49.73 |
|
| 173 |
+
| ae_denoise | 128 | 0.0 | gaussian | 42.89 ± 0.56 | 48.73 ± 0.47 | 51.08 ± 0.47 | 52.66 ± 0.31 | 48.43 |
|
| 174 |
+
| oae_l0.001 | 2048 | 0.001 | none | 44.61 | – | – | 53.02 | 48.3 |
|
| 175 |
+
| oae_l0.01/oae_sparse | 2048 | 0.01 | none | 42.94 ± 0.62 | 48.20 ± 0.14 | 50.65 ± 0.57 | 52.07 ± 0.42 | 49.72 |
|
| 176 |
+
| oae_sparse_denoise | 2048 | 0.01 | gaussian | 43.00 ± 0.61 | 48.59 ± 1.46 | 51.33 ± 0.41 | 52.85 ± 0.26 | 49.53 |
|
| 177 |
+
| oae_sparse_mask | 2048 | 0.01 | mask | 45.72 ± 0.18 | 49.67 ± 1.44 | 53.93 ± 0.09 | 55.66 ± 0.30 | 52.17 |
|
| 178 |
+
| oae_l0.1 | 2048 | 0.1 | none | 42.27 | – | – | 50.56 | 46.5 |
|
| 179 |
+
| oae | 2048 | 0.0 | none | 44.22 ± 0.91 | 49.39 ± 0.86 | 52.15 ± 0.20 | 52.88 ± 0.85 | 51.03 |
|
| 180 |
+
| oae_denoise | 2048 | 0.0 | gaussian | 44.13 ± 0.45 | 50.03 ± 0.24 | 52.55 ± 0.27 | 54.14 ± 0.10 | 50.67 |
|
| 181 |
+
| random | – | – | – | 35.58 ± 0.28 | 39.48 ± 0.34 | 41.61 ± 0.72 | 42.82 ± 1.13 | 41.8 |
|
| 182 |
+
|
| 183 |
+
## frozen — downstream training cost (mean over runs)
|
| 184 |
+
|
| 185 |
+
| canonical | train_time_s | peak_train_mem_mb | params_total | params_trainable |
|
| 186 |
+
|:---------------------|---------------:|--------------------:|---------------:|-------------------:|
|
| 187 |
+
| C128_l0.01_clean | 59.8 | 832.6 | 1.1174e+07 | 5130 |
|
| 188 |
+
| C128_l0.01_gauss0.5 | 57.3 | 832.6 | 1.1174e+07 | 5130 |
|
| 189 |
+
| C128_l0_clean | 56.6 | 832.6 | 1.1174e+07 | 5130 |
|
| 190 |
+
| C128_l0_gauss0.5 | 59.4 | 832.6 | 1.1174e+07 | 5130 |
|
| 191 |
+
| C2048_l0.001_clean | 64.2 | 832.6 | 1.1174e+07 | 5130 |
|
| 192 |
+
| C2048_l0.01_clean | 56.5 | 832.6 | 1.1174e+07 | 5130 |
|
| 193 |
+
| C2048_l0.01_gauss0.5 | 56.6 | 832.6 | 1.1174e+07 | 5130 |
|
| 194 |
+
| C2048_l0.01_mask0.5 | 57.9 | 832.6 | 1.1174e+07 | 5130 |
|
| 195 |
+
| C2048_l0.1_clean | 66.5 | 832.6 | 1.1174e+07 | 5130 |
|
| 196 |
+
| C2048_l0_clean | 61 | 832.6 | 1.1174e+07 | 5130 |
|
| 197 |
+
| C2048_l0_gauss0.5 | 56.5 | 832.6 | 1.1174e+07 | 5130 |
|
| 198 |
+
| random | 232.8 | 2418.4 | 1.1174e+07 | 5130 |
|
| 199 |
+
|
| 200 |
+
## frozen — paired comparisons (test top-1, B − A in points)
|
| 201 |
+
|
| 202 |
+
| A | B | fraction | n_seeds | diff_B_minus_A | diff_std | p_paired_t | p_paired_t_holm | cohens_dz | p_mcnemar_max_over_seeds |
|
| 203 |
+
|:------------------|:---------------------|-----------:|----------:|-----------------:|-----------:|-------------:|------------------:|------------:|---------------------------:|
|
| 204 |
+
| C128_l0_clean | C2048_l0.01_mask0.5 | 0.1 | 3 | 1.825 | 0.1146 | 0.001311 | 0.005244 | 15.93 | 0.0018 |
|
| 205 |
+
| C128_l0_clean | C2048_l0.01_mask0.5 | 0.25 | 3 | 1.133 | 2.788 | 0.5543 | 0.5543 | 0.4066 | 0.0002473 |
|
| 206 |
+
| C128_l0_clean | C2048_l0.01_mask0.5 | 0.5 | 3 | 3.029 | 0.5236 | 0.009812 | 0.02457 | 5.786 | 6.927e-06 |
|
| 207 |
+
| C128_l0_clean | C2048_l0.01_mask0.5 | 1 | 3 | 3.117 | 0.4915 | 0.00819 | 0.02457 | 6.341 | 9.169e-07 |
|
| 208 |
+
| C128_l0_clean | C2048_l0_clean | 0.1 | 3 | 0.3208 | 0.657 | 0.4867 | 1 | 0.4884 | 0.8107 |
|
| 209 |
+
| C128_l0_clean | C2048_l0_clean | 0.25 | 3 | 0.85 | 2.234 | 0.5776 | 1 | 0.3805 | 0.0009237 |
|
| 210 |
+
| C128_l0_clean | C2048_l0_clean | 0.5 | 3 | 1.242 | 0.5646 | 0.06253 | 0.2501 | 2.199 | 0.2492 |
|
| 211 |
+
| C128_l0_clean | C2048_l0_clean | 1 | 3 | 0.3333 | 0.7821 | 0.5372 | 1 | 0.4262 | 0.2995 |
|
| 212 |
+
| C2048_l0_clean | C2048_l0.01_clean | 0.1 | 3 | -1.279 | 0.8055 | 0.1107 | 0.332 | -1.588 | 0.4022 |
|
| 213 |
+
| C2048_l0_clean | C2048_l0.01_clean | 0.25 | 3 | -1.192 | 0.9306 | 0.1568 | 0.332 | -1.281 | 0.8221 |
|
| 214 |
+
| C2048_l0_clean | C2048_l0.01_clean | 0.5 | 3 | -1.496 | 0.6377 | 0.05557 | 0.2223 | -2.346 | 0.09288 |
|
| 215 |
+
| C2048_l0_clean | C2048_l0.01_clean | 1 | 3 | -0.8042 | 1.172 | 0.3567 | 0.3567 | -0.6861 | 0.3488 |
|
| 216 |
+
| C128_l0_clean | C128_l0.01_clean | 0.1 | 3 | 0.1125 | 0.5717 | 0.7657 | 1 | 0.1968 | 0.5233 |
|
| 217 |
+
| C128_l0_clean | C128_l0.01_clean | 0.25 | 3 | -0.2 | 1.61 | 0.8496 | 1 | -0.1242 | 0.2949 |
|
| 218 |
+
| C128_l0_clean | C128_l0.01_clean | 0.5 | 3 | -0.4958 | 0.6831 | 0.3356 | 1 | -0.7259 | 1 |
|
| 219 |
+
| C128_l0_clean | C128_l0.01_clean | 1 | 3 | -1.396 | 0.2306 | 0.008975 | 0.0359 | -6.053 | 0.01661 |
|
| 220 |
+
| C2048_l0.01_clean | C2048_l0.01_gauss0.5 | 0.1 | 3 | 0.0625 | 0.598 | 0.873 | 1 | 0.1045 | 0.5002 |
|
| 221 |
+
| C2048_l0.01_clean | C2048_l0.01_gauss0.5 | 0.25 | 3 | 0.3958 | 1.325 | 0.6564 | 1 | 0.2988 | 0.05433 |
|
| 222 |
+
| C2048_l0.01_clean | C2048_l0.01_gauss0.5 | 0.5 | 3 | 0.675 | 0.3356 | 0.07345 | 0.2938 | 2.011 | 0.5933 |
|
| 223 |
+
| C2048_l0.01_clean | C2048_l0.01_gauss0.5 | 1 | 3 | 0.7792 | 0.4661 | 0.1014 | 0.3043 | 1.672 | 0.5116 |
|
| 224 |
+
| C128_l0_clean | C128_l0_gauss0.5 | 0.1 | 3 | -1.008 | 0.593 | 0.09853 | 0.3941 | -1.7 | 0.5056 |
|
| 225 |
+
| C128_l0_clean | C128_l0_gauss0.5 | 0.25 | 3 | 0.1958 | 0.9284 | 0.7499 | 1 | 0.2109 | 0.203 |
|
| 226 |
+
| C128_l0_clean | C128_l0_gauss0.5 | 0.5 | 3 | 0.175 | 0.4265 | 0.5509 | 1 | 0.4103 | 0.9387 |
|
| 227 |
+
| C128_l0_clean | C128_l0_gauss0.5 | 1 | 3 | 0.1125 | 0.142 | 0.3036 | 0.9107 | 0.7924 | 0.9418 |
|
| 228 |
+
|
| 229 |
+
## Frozen vs fine-tuned (test_top1, mean over seeds)
|
| 230 |
+
|
| 231 |
+
| | finetune | frozen | finetune_minus_frozen |
|
| 232 |
+
|:-------------------------------|-----------:|---------:|------------------------:|
|
| 233 |
+
| ('C128_l0.01_clean', 0.1) | 47.9 | 44.01 | 3.9 |
|
| 234 |
+
| ('C128_l0.01_clean', 0.25) | 57.55 | 48.34 | 9.21 |
|
| 235 |
+
| ('C128_l0.01_clean', 0.5) | 64.12 | 50.41 | 13.71 |
|
| 236 |
+
| ('C128_l0.01_clean', 1.0) | 67.9 | 51.15 | 16.75 |
|
| 237 |
+
| ('C128_l0.01_gauss0.5', 0.1) | 48.93 | 42.26 | 6.67 |
|
| 238 |
+
| ('C128_l0.01_gauss0.5', 0.25) | 57.14 | 47.79 | 9.35 |
|
| 239 |
+
| ('C128_l0.01_gauss0.5', 0.5) | 63.78 | 49.28 | 14.5 |
|
| 240 |
+
| ('C128_l0.01_gauss0.5', 1.0) | 68.45 | 50.71 | 17.74 |
|
| 241 |
+
| ('C128_l0_clean', 0.1) | 49.19 | 43.9 | 5.3 |
|
| 242 |
+
| ('C128_l0_clean', 0.25) | 58.44 | 48.54 | 9.9 |
|
| 243 |
+
| ('C128_l0_clean', 0.5) | 65.8 | 50.9 | 14.9 |
|
| 244 |
+
| ('C128_l0_clean', 1.0) | 68.91 | 52.55 | 16.36 |
|
| 245 |
+
| ('C128_l0_gauss0.5', 0.1) | 48.88 | 42.89 | 5.99 |
|
| 246 |
+
| ('C128_l0_gauss0.5', 0.25) | 58.58 | 48.73 | 9.85 |
|
| 247 |
+
| ('C128_l0_gauss0.5', 0.5) | 65.35 | 51.08 | 14.27 |
|
| 248 |
+
| ('C128_l0_gauss0.5', 1.0) | 69.5 | 52.66 | 16.84 |
|
| 249 |
+
| ('C2048_l0.01_clean', 0.1) | 49.22 | 42.94 | 6.28 |
|
| 250 |
+
| ('C2048_l0.01_clean', 0.25) | 57.58 | 48.2 | 9.38 |
|
| 251 |
+
| ('C2048_l0.01_clean', 0.5) | 64.71 | 50.65 | 14.06 |
|
| 252 |
+
| ('C2048_l0.01_clean', 1.0) | 67.9 | 52.08 | 15.82 |
|
| 253 |
+
| ('C2048_l0.01_gauss0.5', 0.1) | 48.85 | 43 | 5.85 |
|
| 254 |
+
| ('C2048_l0.01_gauss0.5', 0.25) | 57.6 | 48.59 | 9 |
|
| 255 |
+
| ('C2048_l0.01_gauss0.5', 0.5) | 65.05 | 51.32 | 13.73 |
|
| 256 |
+
| ('C2048_l0.01_gauss0.5', 1.0) | 69.51 | 52.85 | 16.66 |
|
| 257 |
+
| ('C2048_l0.01_mask0.5', 0.1) | 49.55 | 45.72 | 3.83 |
|
| 258 |
+
| ('C2048_l0.01_mask0.5', 0.25) | 59.21 | 49.67 | 9.54 |
|
| 259 |
+
| ('C2048_l0.01_mask0.5', 0.5) | 67.4 | 53.93 | 13.47 |
|
| 260 |
+
| ('C2048_l0.01_mask0.5', 1.0) | 69.82 | 55.66 | 14.15 |
|
| 261 |
+
| ('C2048_l0_clean', 0.1) | 49.77 | 44.22 | 5.55 |
|
| 262 |
+
| ('C2048_l0_clean', 0.25) | 55.69 | 49.39 | 6.3 |
|
| 263 |
+
| ('C2048_l0_clean', 0.5) | 65.09 | 52.15 | 12.95 |
|
| 264 |
+
| ('C2048_l0_clean', 1.0) | 69.55 | 52.88 | 16.67 |
|
| 265 |
+
| ('C2048_l0_gauss0.5', 0.1) | 48.93 | 44.13 | 4.8 |
|
| 266 |
+
| ('C2048_l0_gauss0.5', 0.25) | 57.85 | 50.03 | 7.82 |
|
| 267 |
+
| ('C2048_l0_gauss0.5', 0.5) | 65.55 | 52.55 | 13.01 |
|
| 268 |
+
| ('C2048_l0_gauss0.5', 1.0) | 69.77 | 54.14 | 15.63 |
|
| 269 |
+
|
| 270 |
+
## Autoencoder pre-training
|
| 271 |
+
|
| 272 |
+
| variant | latent_dim | overcomplete_x | params_encoder | params_decoder | train_time_h | img_per_s | peak_mem_mb | holdout_psnr | frac_active |
|
| 273 |
+
|:-------------------|-------------:|-----------------:|-----------------:|-----------------:|---------------:|------------:|--------------:|---------------:|--------------:|
|
| 274 |
+
| oae_l0.001 | 73728 | 2.667 | 12219456 | 2617155 | 0.3322 | 818.7 | 2550 | 25.1 | 0.22 |
|
| 275 |
+
| oae_l0.01 | 73728 | 2.667 | 12219456 | 2617155 | 0.3115 | 873.3 | 2550 | 25.05 | 0.1399 |
|
| 276 |
+
| oae_l0.1 | 73728 | 2.667 | 12219456 | 2617155 | 0.3331 | 816.6 | 2550 | 24.79 | 0.05403 |
|
| 277 |
+
| ae | 4608 | 0.167 | 11234496 | 1634115 | 0.2988 | 910.4 | 2507 | 25.1 | 0.7798 |
|
| 278 |
+
| ae_sparse | 4608 | 0.167 | 11234496 | 1634115 | 0.317 | 858.2 | 2507 | 24.78 | 0.396 |
|
| 279 |
+
| ae_denoise | 4608 | 0.167 | 11234496 | 1634115 | 0.294 | 925.1 | 2674 | 24.74 | 0.7822 |
|
| 280 |
+
| ae_sparse_denoise | 4608 | 0.167 | 11234496 | 1634115 | 0.3021 | 900.3 | 2674 | 24.44 | 0.3752 |
|
| 281 |
+
| oae | 73728 | 2.667 | 12219456 | 2617155 | 0.313 | 869.1 | 2550 | 25.17 | 0.2507 |
|
| 282 |
+
| oae_sparse | 73728 | 2.667 | 12219456 | 2617155 | 0.3115 | 873.3 | 2550 | 25.05 | 0.1399 |
|
| 283 |
+
| oae_denoise | 73728 | 2.667 | 12219456 | 2617155 | 0.2901 | 937.7 | 2564 | 24.79 | 0.2423 |
|
| 284 |
+
| oae_sparse_denoise | 73728 | 2.667 | 12219456 | 2617155 | 0.2947 | 923.1 | 2564 | 24.73 | 0.1336 |
|
| 285 |
+
| oae_sparse_mask | 73728 | 2.667 | 12219456 | 2617155 | 0.2928 | 928.9 | 2564 | 24.01 | 0.08135 |
|
| 286 |
+
|
| 287 |
+
## Inference cost (identical downstream architecture for all models)
|
| 288 |
+
|
| 289 |
+
Parameters: 11,173,962
|
| 290 |
+
|
| 291 |
+
| | latency_ms_median | latency_ms_p90 | throughput_img_s | peak_gpu_mem_mb |
|
| 292 |
+
|:------|--------------------:|-----------------:|-------------------:|------------------:|
|
| 293 |
+
| bs1 | 3.06 | 3.21 | 326 | 76.4 |
|
| 294 |
+
| bs256 | 45 | 45.2 | 5.69e+03 | 442 |
|
| 295 |
+
|
| 296 |
+
## Selections (validation only)
|
| 297 |
+
|
| 298 |
+
```
|
| 299 |
+
{'finetune/ResNet-18 baseline': {'chosen': 'scratch', 'mean_val_top1': {'scratch': np.float64(0.5984999999999999)}}, 'finetune/Standard AE': {'chosen': 'C128_l0_clean', 'mean_val_top1': {'C128_l0_clean': np.float64(0.587)}}, 'finetune/Sparse OAE': {'chosen': 'C2048_l0.01_mask0.5', 'mean_val_top1': {'C2048_l0.01_clean': np.float64(0.5791666666666667), 'C2048_l0.01_gauss0.5': np.float64(0.585), 'C2048_l0.01_mask0.5': np.float64(0.6015)}}, 'frozen/Random frozen ResNet-18 (control)': {'chosen': 'random', 'mean_val_top1': {'random': np.float64(0.418)}}, 'frozen/Standard AE': {'chosen': 'C128_l0_clean', 'mean_val_top1': {'C128_l0_clean': np.float64(0.49733333333333346)}}, 'frozen/Sparse OAE': {'chosen': 'C2048_l0.01_mask0.5', 'mean_val_top1': {'C2048_l0.01_clean': np.float64(0.4971666666666666), 'C2048_l0.01_gauss0.5': np.float64(0.4953333333333334), 'C2048_l0.01_mask0.5': np.float64(0.5216666666666668)}}}
|
| 300 |
+
```
|
| 301 |
+
|
configs/default.yaml
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Full experimental protocol. Run with: python scripts/run_all.py --config configs/default.yaml
|
| 2 |
+
# Every setting that must be identical across experiments lives here, once.
|
| 3 |
+
|
| 4 |
+
data_dir: data/stl10
|
| 5 |
+
runs_dir: runs
|
| 6 |
+
results_dir: results
|
| 7 |
+
amp: auto # bf16 on Ampere+ (RTX 30xx-50xx, A100), fp16 + loss scaling on older GPUs (T4); "none" = fp32
|
| 8 |
+
|
| 9 |
+
# Jobs run concurrently on the one GPU. 1 = sequential (fine for an 8 GB laptop GPU).
|
| 10 |
+
# On a 24-32 GB GPU (RTX 4090 / 5090): downstream_jobs 4, pretrain_jobs 2. CLI: --jobs / --pretrain_jobs.
|
| 11 |
+
parallel:
|
| 12 |
+
downstream_jobs: 1
|
| 13 |
+
pretrain_jobs: 1
|
| 14 |
+
|
| 15 |
+
splits:
|
| 16 |
+
fractions: [0.1, 0.25, 0.5, 1.0] # of the 4,500-image labelled pool (after removing validation)
|
| 17 |
+
val_per_class: 50 # 500-image stratified validation split (model selection / early stopping)
|
| 18 |
+
split_seed: 0 # fixed -> identical subsets for every method and seed
|
| 19 |
+
unlabeled_holdout: 2000 # unlabeled images held out to monitor reconstruction
|
| 20 |
+
|
| 21 |
+
seeds: [0, 1, 2] # downstream seeds (init of head / scratch model, data order, augmentation)
|
| 22 |
+
pretrain_seeds: [0] # [0] = one AE per variant shared by all downstream seeds;
|
| 23 |
+
# [0, 1, 2] = downstream seed s uses AE pre-trained with seed s (3x cost)
|
| 24 |
+
|
| 25 |
+
# ---------------------------------------------------------------------------- AE pre-training
|
| 26 |
+
pretrain:
|
| 27 |
+
epochs: 20 # over 98,000 unlabeled images
|
| 28 |
+
batch_size: 128
|
| 29 |
+
lr: 0.001 # AdamW, linear warm-up then cosine decay
|
| 30 |
+
weight_decay: 0.0001
|
| 31 |
+
warmup_epochs: 1
|
| 32 |
+
noise_std: 0.5 # Gaussian denoising: std in normalised units
|
| 33 |
+
mask_ratio: 0.5 # masking denoising: fraction of 8x8 patches zeroed
|
| 34 |
+
mask_patch: 8
|
| 35 |
+
max_steps: null
|
| 36 |
+
|
| 37 |
+
# Stage 1: sparsity sweep on the overcomplete AE (clean inputs). lambda* = the lambda > 0 with the best
|
| 38 |
+
# mean *validation* accuracy of a frozen-encoder probe on the selection grid below.
|
| 39 |
+
lambda_sweep:
|
| 40 |
+
latent_channels: 2048
|
| 41 |
+
values: [0.001, 0.01, 0.1] # lambda = 0 (non-sparse OAE) is always trained as variant `oae`
|
| 42 |
+
selection:
|
| 43 |
+
protocol: frozen
|
| 44 |
+
fractions: [0.1, 1.0]
|
| 45 |
+
seeds: [0]
|
| 46 |
+
full_downstream_grid: false # true -> also run every protocol/fraction/seed for every sweep lambda
|
| 47 |
+
|
| 48 |
+
# Stage 2: factorial design {undercomplete, overcomplete} x {lambda=0, lambda*} x {clean, Gaussian}
|
| 49 |
+
# + masking-denoising OAE. `lambda_star` is resolved after stage 1.
|
| 50 |
+
variants:
|
| 51 |
+
ae: {latent_channels: 128, l1_lambda: 0.0, noise: none} # Experiment B
|
| 52 |
+
ae_sparse: {latent_channels: 128, l1_lambda: lambda_star, noise: none}
|
| 53 |
+
ae_denoise: {latent_channels: 128, l1_lambda: 0.0, noise: gaussian}
|
| 54 |
+
ae_sparse_denoise: {latent_channels: 128, l1_lambda: lambda_star, noise: gaussian}
|
| 55 |
+
oae: {latent_channels: 2048, l1_lambda: 0.0, noise: none}
|
| 56 |
+
oae_sparse: {latent_channels: 2048, l1_lambda: lambda_star, noise: none} # Experiment C
|
| 57 |
+
oae_denoise: {latent_channels: 2048, l1_lambda: 0.0, noise: gaussian}
|
| 58 |
+
oae_sparse_denoise: {latent_channels: 2048, l1_lambda: lambda_star, noise: gaussian} # Experiment C
|
| 59 |
+
oae_sparse_mask: {latent_channels: 2048, l1_lambda: lambda_star, noise: mask} # Experiment C
|
| 60 |
+
|
| 61 |
+
# Rows of the headline table. With several candidates, the one with the best mean validation accuracy wins.
|
| 62 |
+
main_table:
|
| 63 |
+
ResNet-18 baseline: [scratch]
|
| 64 |
+
Random frozen ResNet-18 (control): [random]
|
| 65 |
+
Standard AE: [ae]
|
| 66 |
+
Sparse OAE: [oae_sparse, oae_sparse_denoise, oae_sparse_mask]
|
| 67 |
+
|
| 68 |
+
# Paired statistical comparisons (A, B) -> reports B - A. Row names of main_table or variant names.
|
| 69 |
+
comparisons:
|
| 70 |
+
- [ResNet-18 baseline, Standard AE]
|
| 71 |
+
- [ResNet-18 baseline, Sparse OAE]
|
| 72 |
+
- [Standard AE, Sparse OAE]
|
| 73 |
+
- [ae, oae] # overcompleteness alone
|
| 74 |
+
- [oae, oae_sparse] # sparsity given overcompleteness
|
| 75 |
+
- [ae, ae_sparse] # sparsity given undercompleteness
|
| 76 |
+
- [oae_sparse, oae_sparse_denoise] # denoising given sparse OAE
|
| 77 |
+
- [ae, ae_denoise] # denoising given undercomplete AE
|
| 78 |
+
|
| 79 |
+
# ---------------------------------------------------------------------------- downstream
|
| 80 |
+
downstream:
|
| 81 |
+
protocols: [finetune, frozen]
|
| 82 |
+
common: # identical for every method, fraction and seed
|
| 83 |
+
steps: 2000 # fixed optimisation budget (batch 128 -> ~57 epochs at 100%, ~570 at 10%)
|
| 84 |
+
batch_size: 128
|
| 85 |
+
momentum: 0.9 # SGD + Nesterov, linear warm-up then cosine decay
|
| 86 |
+
warmup_steps: 100
|
| 87 |
+
eval_every: 100 # validation check; the best-validation checkpoint is kept (early stopping)
|
| 88 |
+
patience: 0
|
| 89 |
+
label_smoothing: 0.0
|
| 90 |
+
finetune: {lr: 0.05, weight_decay: 0.0005}
|
| 91 |
+
frozen: {lr: 0.1, weight_decay: 0.0}
|
| 92 |
+
|
| 93 |
+
analysis:
|
| 94 |
+
embed_samples: 2000 # points in t-SNE / UMAP plots
|
| 95 |
+
include_supervised_reference: true # add the 100%-label scratch model (seed 0) to the analysis
|
| 96 |
+
pairs: ["ae,oae_sparse", "ae,oae", "oae,oae_sparse", "scratch_100,oae_sparse"]
|
configs/fast.yaml
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Same protocol as default.yaml (all variants, both protocols, 4 fractions, 3 seeds) with a halved
|
| 2 |
+
# training budget: ~7-7.5 h on an RTX 3070 Laptop instead of ~16-17 h. Results go to separate folders
|
| 3 |
+
# so they never mix with a full-budget run.
|
| 4 |
+
base: default.yaml
|
| 5 |
+
|
| 6 |
+
runs_dir: runs_fast
|
| 7 |
+
results_dir: results_fast
|
| 8 |
+
|
| 9 |
+
parallel:
|
| 10 |
+
downstream_jobs: 2 # 2 concurrent downstream runs fit easily in 8 GB
|
| 11 |
+
pretrain_jobs: 1 # one AE pre-training (~4.5 GB) at a time on 8 GB
|
| 12 |
+
|
| 13 |
+
pretrain:
|
| 14 |
+
epochs: 10 # default: 20
|
| 15 |
+
|
| 16 |
+
downstream:
|
| 17 |
+
common:
|
| 18 |
+
steps: 1000 # default: 2000 (still ~28 epochs at 100% labels, ~280 at 10%)
|
configs/kaggle.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Kaggle free tier (2x Tesla T4, 12 h sessions). Same scientific protocol as default.yaml; only the
|
| 2 |
+
# infrastructure differs. Run with scripts/kaggle_session.py (see README, "Running on Kaggle").
|
| 3 |
+
base: default.yaml
|
| 4 |
+
|
| 5 |
+
data_dir: /tmp/stl10 # outside /kaggle/working (20 GB output limit); re-downloaded each session
|
| 6 |
+
delete_raw_data: true # drop the 2.6 GB archive after conversion
|
| 7 |
+
amp: auto # T4 has no bf16 -> fp16 with loss scaling (bf16 on Ampere+ GPUs)
|
configs/kaggle_fast.yaml
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Kaggle (2x T4) with the halved training budget: fits in ONE 12-hour session (~6-7.5 h estimated).
|
| 2 |
+
# Same design as the full study (all variants, both protocols, 4 fractions, 3 seeds); only
|
| 3 |
+
# pre-training epochs (20 -> 10) and downstream steps (2000 -> 1000) are halved.
|
| 4 |
+
base: kaggle.yaml
|
| 5 |
+
|
| 6 |
+
runs_dir: runs_fast
|
| 7 |
+
results_dir: results_fast
|
| 8 |
+
|
| 9 |
+
pretrain:
|
| 10 |
+
epochs: 10
|
| 11 |
+
|
| 12 |
+
downstream:
|
| 13 |
+
common:
|
| 14 |
+
steps: 1000
|
configs/smoke.yaml
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Tiny end-to-end check of the whole pipeline (minutes, not hours). Numbers are meaningless.
|
| 2 |
+
# python scripts/run_all.py --config configs/smoke.yaml
|
| 3 |
+
data_dir: data/stl10
|
| 4 |
+
runs_dir: runs_smoke
|
| 5 |
+
results_dir: results_smoke
|
| 6 |
+
amp: bf16
|
| 7 |
+
|
| 8 |
+
# Jobs run concurrently on the one GPU. 1 = sequential (fine for an 8 GB laptop GPU).
|
| 9 |
+
# On a 24-32 GB GPU (RTX 4090 / 5090): downstream_jobs 4, pretrain_jobs 2. CLI: --jobs / --pretrain_jobs.
|
| 10 |
+
parallel:
|
| 11 |
+
downstream_jobs: 1
|
| 12 |
+
pretrain_jobs: 1
|
| 13 |
+
|
| 14 |
+
splits: {fractions: [0.1, 0.25, 0.5, 1.0], val_per_class: 50, split_seed: 0, unlabeled_holdout: 2000}
|
| 15 |
+
seeds: [0, 1]
|
| 16 |
+
pretrain_seeds: [0]
|
| 17 |
+
|
| 18 |
+
pretrain: {epochs: 1, batch_size: 64, lr: 0.001, weight_decay: 0.0001, warmup_epochs: 1,
|
| 19 |
+
noise_std: 0.5, mask_ratio: 0.5, mask_patch: 8, max_steps: 30, holdout_max: 256}
|
| 20 |
+
|
| 21 |
+
lambda_sweep:
|
| 22 |
+
latent_channels: 2048
|
| 23 |
+
values: [0.01, 0.1]
|
| 24 |
+
selection: {protocol: frozen, fractions: [0.1], seeds: [0]}
|
| 25 |
+
full_downstream_grid: false
|
| 26 |
+
|
| 27 |
+
variants:
|
| 28 |
+
ae: {latent_channels: 128, l1_lambda: 0.0, noise: none}
|
| 29 |
+
oae: {latent_channels: 2048, l1_lambda: 0.0, noise: none}
|
| 30 |
+
oae_sparse: {latent_channels: 2048, l1_lambda: lambda_star, noise: none}
|
| 31 |
+
oae_sparse_mask: {latent_channels: 2048, l1_lambda: lambda_star, noise: mask}
|
| 32 |
+
|
| 33 |
+
main_table:
|
| 34 |
+
ResNet-18 baseline: [scratch]
|
| 35 |
+
Random frozen ResNet-18 (control): [random]
|
| 36 |
+
Standard AE: [ae]
|
| 37 |
+
Sparse OAE: [oae_sparse, oae_sparse_mask]
|
| 38 |
+
|
| 39 |
+
comparisons:
|
| 40 |
+
- [ResNet-18 baseline, Sparse OAE]
|
| 41 |
+
- [Standard AE, Sparse OAE]
|
| 42 |
+
- [ae, oae]
|
| 43 |
+
|
| 44 |
+
downstream:
|
| 45 |
+
protocols: [finetune, frozen]
|
| 46 |
+
common: {steps: 20, batch_size: 64, momentum: 0.9, warmup_steps: 5, eval_every: 10, patience: 0, label_smoothing: 0.0}
|
| 47 |
+
finetune: {lr: 0.05, weight_decay: 0.0005}
|
| 48 |
+
frozen: {lr: 0.1, weight_decay: 0.0}
|
| 49 |
+
|
| 50 |
+
analysis:
|
| 51 |
+
embed_samples: 300
|
| 52 |
+
max_pool: 500
|
| 53 |
+
include_supervised_reference: true
|
| 54 |
+
pairs: ["ae,oae_sparse"]
|
data_splits/splits.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
data_splits/splits_summary.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# STL-10 splits
|
| 2 |
+
|
| 3 |
+
split_seed = 0; validation = 50 images/class drawn from the official 5,000-image training split; the official 8,000-image test split is untouched.
|
| 4 |
+
|
| 5 |
+
| subset | images | airplane | bird | car | cat | deer | dog | horse | monkey | ship | truck |
|
| 6 |
+
|---|---|---|---|---|---|---|---|---|---|---|---|
|
| 7 |
+
| validation | 500 | 50 | 50 | 50 | 50 | 50 | 50 | 50 | 50 | 50 | 50 |
|
| 8 |
+
| train 10% | 450 | 45 | 45 | 45 | 45 | 45 | 45 | 45 | 45 | 45 | 45 |
|
| 9 |
+
| train 25% | 1120 | 112 | 112 | 112 | 112 | 112 | 112 | 112 | 112 | 112 | 112 |
|
| 10 |
+
| train 50% | 2250 | 225 | 225 | 225 | 225 | 225 | 225 | 225 | 225 | 225 | 225 |
|
| 11 |
+
| train 100% | 4500 | 450 | 450 | 450 | 450 | 450 | 450 | 450 | 450 | 450 | 450 |
|
| 12 |
+
|
| 13 |
+
Unlabeled: 98000 images for AE training, 2000 held out for reconstruction monitoring.
|
| 14 |
+
|
| 15 |
+
Labelled subsets are nested (10% ⊂ 25% ⊂ 50% ⊂ 100%) and identical for every method and seed.
|
| 16 |
+
Exact indices (into the official train / unlabeled arrays) are in `splits.json`.
|
data_splits/stats.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mean": [
|
| 3 |
+
0.44058638793147475,
|
| 4 |
+
0.42731113699108136,
|
| 5 |
+
0.38579501157407375
|
| 6 |
+
],
|
| 7 |
+
"std": [
|
| 8 |
+
0.2686545583839396,
|
| 9 |
+
0.2612521862515845,
|
| 10 |
+
0.26849920555418677
|
| 11 |
+
],
|
| 12 |
+
"computed_on": "unlabeled (100,000 images)"
|
| 13 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.1/s0/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f0.1/s0",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 0.1,
|
| 9 |
+
"seed": 0,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 450,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
45,
|
| 26 |
+
45,
|
| 27 |
+
45,
|
| 28 |
+
45,
|
| 29 |
+
45,
|
| 30 |
+
45,
|
| 31 |
+
45,
|
| 32 |
+
45,
|
| 33 |
+
45,
|
| 34 |
+
45
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.492,
|
| 38 |
+
"val_macro_f1": 0.4918337981398479,
|
| 39 |
+
"val_loss": 3.370607177734375,
|
| 40 |
+
"step": 700
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.1665714979171753,
|
| 46 |
+
"val_loss": 51.0107421875,
|
| 47 |
+
"val_top1": 0.214,
|
| 48 |
+
"val_macro_f1": 0.16285571706420549,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 18.63870734699958
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 0.2513880431652069,
|
| 55 |
+
"val_loss": 2.9067998046875,
|
| 56 |
+
"val_top1": 0.428,
|
| 57 |
+
"val_macro_f1": 0.4104706526137661,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 34.00254133699946
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 0.08250879496335983,
|
| 64 |
+
"val_loss": 3.075227294921875,
|
| 65 |
+
"val_top1": 0.486,
|
| 66 |
+
"val_macro_f1": 0.4797197036292201,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 49.588061432998984
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 0.013659990392625332,
|
| 73 |
+
"val_loss": 3.1420498046875,
|
| 74 |
+
"val_top1": 0.476,
|
| 75 |
+
"val_macro_f1": 0.47547102210778835,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 65.25845655399917
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.013041661120951176,
|
| 82 |
+
"val_loss": 3.532505859375,
|
| 83 |
+
"val_top1": 0.474,
|
| 84 |
+
"val_macro_f1": 0.47650066206638153,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 80.96726245599984
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.007182898931205273,
|
| 91 |
+
"val_loss": 3.29467431640625,
|
| 92 |
+
"val_top1": 0.474,
|
| 93 |
+
"val_macro_f1": 0.4742693909972022,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 96.76758273499945
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.00309723149985075,
|
| 100 |
+
"val_loss": 3.370607177734375,
|
| 101 |
+
"val_top1": 0.492,
|
| 102 |
+
"val_macro_f1": 0.4918337981398479,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 112.53901157199925
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.004616633057594299,
|
| 109 |
+
"val_loss": 3.354072265625,
|
| 110 |
+
"val_top1": 0.474,
|
| 111 |
+
"val_macro_f1": 0.4732649107774015,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 128.49585584799934
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.003953780047595501,
|
| 118 |
+
"val_loss": 3.34121728515625,
|
| 119 |
+
"val_top1": 0.48,
|
| 120 |
+
"val_macro_f1": 0.480697628964535,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 144.57307902999946
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.0033200725447386503,
|
| 127 |
+
"val_loss": 3.363711669921875,
|
| 128 |
+
"val_top1": 0.48,
|
| 129 |
+
"val_macro_f1": 0.47998055458343564,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 160.50339227699897
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 160.50344123299874,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.1/s0/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.4885,
|
| 3 |
+
"macro_f1": 0.4872389199270398,
|
| 4 |
+
"balanced_accuracy": 0.4885,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.55,
|
| 7 |
+
0.4,
|
| 8 |
+
0.65625,
|
| 9 |
+
0.4225,
|
| 10 |
+
0.39625,
|
| 11 |
+
0.28125,
|
| 12 |
+
0.545,
|
| 13 |
+
0.45,
|
| 14 |
+
0.665,
|
| 15 |
+
0.51875
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.6019151846785227,
|
| 19 |
+
0.4139715394566624,
|
| 20 |
+
0.6529850746268656,
|
| 21 |
+
0.37828763290430883,
|
| 22 |
+
0.41546526867627787,
|
| 23 |
+
0.3129346314325452,
|
| 24 |
+
0.5272067714631198,
|
| 25 |
+
0.4463732176069436,
|
| 26 |
+
0.6211325160537069,
|
| 27 |
+
0.5021173623714459
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
440,
|
| 32 |
+
34,
|
| 33 |
+
47,
|
| 34 |
+
13,
|
| 35 |
+
9,
|
| 36 |
+
9,
|
| 37 |
+
12,
|
| 38 |
+
9,
|
| 39 |
+
131,
|
| 40 |
+
96
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
51,
|
| 44 |
+
320,
|
| 45 |
+
26,
|
| 46 |
+
125,
|
| 47 |
+
62,
|
| 48 |
+
63,
|
| 49 |
+
43,
|
| 50 |
+
66,
|
| 51 |
+
29,
|
| 52 |
+
15
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
28,
|
| 56 |
+
2,
|
| 57 |
+
525,
|
| 58 |
+
8,
|
| 59 |
+
1,
|
| 60 |
+
11,
|
| 61 |
+
14,
|
| 62 |
+
3,
|
| 63 |
+
52,
|
| 64 |
+
156
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
6,
|
| 68 |
+
68,
|
| 69 |
+
17,
|
| 70 |
+
338,
|
| 71 |
+
85,
|
| 72 |
+
79,
|
| 73 |
+
51,
|
| 74 |
+
126,
|
| 75 |
+
12,
|
| 76 |
+
18
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
10,
|
| 80 |
+
75,
|
| 81 |
+
15,
|
| 82 |
+
153,
|
| 83 |
+
317,
|
| 84 |
+
60,
|
| 85 |
+
98,
|
| 86 |
+
57,
|
| 87 |
+
7,
|
| 88 |
+
8
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
16,
|
| 92 |
+
109,
|
| 93 |
+
6,
|
| 94 |
+
117,
|
| 95 |
+
68,
|
| 96 |
+
225,
|
| 97 |
+
121,
|
| 98 |
+
122,
|
| 99 |
+
6,
|
| 100 |
+
10
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
9,
|
| 104 |
+
36,
|
| 105 |
+
11,
|
| 106 |
+
27,
|
| 107 |
+
98,
|
| 108 |
+
103,
|
| 109 |
+
436,
|
| 110 |
+
56,
|
| 111 |
+
2,
|
| 112 |
+
22
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
2,
|
| 116 |
+
79,
|
| 117 |
+
2,
|
| 118 |
+
161,
|
| 119 |
+
61,
|
| 120 |
+
64,
|
| 121 |
+
56,
|
| 122 |
+
360,
|
| 123 |
+
4,
|
| 124 |
+
11
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
66,
|
| 128 |
+
10,
|
| 129 |
+
29,
|
| 130 |
+
27,
|
| 131 |
+
12,
|
| 132 |
+
12,
|
| 133 |
+
5,
|
| 134 |
+
5,
|
| 135 |
+
532,
|
| 136 |
+
102
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
34,
|
| 140 |
+
13,
|
| 141 |
+
130,
|
| 142 |
+
18,
|
| 143 |
+
13,
|
| 144 |
+
12,
|
| 145 |
+
18,
|
| 146 |
+
9,
|
| 147 |
+
138,
|
| 148 |
+
415
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.1/s0/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:417774b1e35f6ce811b45020658dc50208c6555e68e6547b2ba42f2cdaf81e85
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/finetune/f0.1/s1/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f0.1/s1",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 0.1,
|
| 9 |
+
"seed": 1,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 450,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
45,
|
| 26 |
+
45,
|
| 27 |
+
45,
|
| 28 |
+
45,
|
| 29 |
+
45,
|
| 30 |
+
45,
|
| 31 |
+
45,
|
| 32 |
+
45,
|
| 33 |
+
45,
|
| 34 |
+
45
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.494,
|
| 38 |
+
"val_macro_f1": 0.4925019110594578,
|
| 39 |
+
"val_loss": 3.339408203125,
|
| 40 |
+
"step": 500
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.0008782148361206,
|
| 46 |
+
"val_loss": 3.219765625,
|
| 47 |
+
"val_top1": 0.314,
|
| 48 |
+
"val_macro_f1": 0.27123795811247864,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 9.458997052000086
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 0.3748807907104492,
|
| 55 |
+
"val_loss": 2.83027099609375,
|
| 56 |
+
"val_top1": 0.42,
|
| 57 |
+
"val_macro_f1": 0.4127956873669282,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 24.474821982999856
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 0.08123943954706192,
|
| 64 |
+
"val_loss": 4.577466796875,
|
| 65 |
+
"val_top1": 0.42,
|
| 66 |
+
"val_macro_f1": 0.414446287034932,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 39.64488251399962
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 0.020724279806017876,
|
| 73 |
+
"val_loss": 3.254974609375,
|
| 74 |
+
"val_top1": 0.468,
|
| 75 |
+
"val_macro_f1": 0.46220013311116476,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 54.81532114699985
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.005773973651230335,
|
| 82 |
+
"val_loss": 3.339408203125,
|
| 83 |
+
"val_top1": 0.494,
|
| 84 |
+
"val_macro_f1": 0.4925019110594578,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 69.20235361400046
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.0073205092921853065,
|
| 91 |
+
"val_loss": 3.25009375,
|
| 92 |
+
"val_top1": 0.472,
|
| 93 |
+
"val_macro_f1": 0.47493385085967554,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 76.77247189599984
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.003716814797371626,
|
| 100 |
+
"val_loss": 3.264702880859375,
|
| 101 |
+
"val_top1": 0.482,
|
| 102 |
+
"val_macro_f1": 0.48445411821421186,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 92.00777965499947
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.002123554702848196,
|
| 109 |
+
"val_loss": 3.29340673828125,
|
| 110 |
+
"val_top1": 0.482,
|
| 111 |
+
"val_macro_f1": 0.4836453666089384,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 107.35191676900013
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.0037158969789743423,
|
| 118 |
+
"val_loss": 3.308322265625,
|
| 119 |
+
"val_top1": 0.472,
|
| 120 |
+
"val_macro_f1": 0.47600220747562594,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 123.05702766200011
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.0023842889349907637,
|
| 127 |
+
"val_loss": 3.309263671875,
|
| 128 |
+
"val_top1": 0.474,
|
| 129 |
+
"val_macro_f1": 0.47641109038895546,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 138.77393605400084
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 138.77395815300133,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.1/s1/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.47125,
|
| 3 |
+
"macro_f1": 0.46664404510136326,
|
| 4 |
+
"balanced_accuracy": 0.47125000000000006,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.56375,
|
| 7 |
+
0.3825,
|
| 8 |
+
0.7625,
|
| 9 |
+
0.3925,
|
| 10 |
+
0.4075,
|
| 11 |
+
0.2125,
|
| 12 |
+
0.50875,
|
| 13 |
+
0.42625,
|
| 14 |
+
0.6175,
|
| 15 |
+
0.43875
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.5957727873183619,
|
| 19 |
+
0.38107098381070986,
|
| 20 |
+
0.6479022835900159,
|
| 21 |
+
0.35182072829131655,
|
| 22 |
+
0.40471756672873993,
|
| 23 |
+
0.2607361963190184,
|
| 24 |
+
0.4990803188228081,
|
| 25 |
+
0.422029702970297,
|
| 26 |
+
0.627700127064803,
|
| 27 |
+
0.47560975609756095
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
451,
|
| 32 |
+
31,
|
| 33 |
+
71,
|
| 34 |
+
12,
|
| 35 |
+
17,
|
| 36 |
+
4,
|
| 37 |
+
6,
|
| 38 |
+
15,
|
| 39 |
+
109,
|
| 40 |
+
84
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
58,
|
| 44 |
+
306,
|
| 45 |
+
36,
|
| 46 |
+
120,
|
| 47 |
+
83,
|
| 48 |
+
50,
|
| 49 |
+
41,
|
| 50 |
+
69,
|
| 51 |
+
23,
|
| 52 |
+
14
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
27,
|
| 56 |
+
5,
|
| 57 |
+
610,
|
| 58 |
+
8,
|
| 59 |
+
5,
|
| 60 |
+
11,
|
| 61 |
+
12,
|
| 62 |
+
4,
|
| 63 |
+
28,
|
| 64 |
+
90
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
13,
|
| 68 |
+
75,
|
| 69 |
+
25,
|
| 70 |
+
314,
|
| 71 |
+
98,
|
| 72 |
+
64,
|
| 73 |
+
60,
|
| 74 |
+
128,
|
| 75 |
+
8,
|
| 76 |
+
15
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
15,
|
| 80 |
+
77,
|
| 81 |
+
16,
|
| 82 |
+
142,
|
| 83 |
+
326,
|
| 84 |
+
53,
|
| 85 |
+
100,
|
| 86 |
+
62,
|
| 87 |
+
4,
|
| 88 |
+
5
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
27,
|
| 92 |
+
139,
|
| 93 |
+
13,
|
| 94 |
+
132,
|
| 95 |
+
76,
|
| 96 |
+
170,
|
| 97 |
+
121,
|
| 98 |
+
110,
|
| 99 |
+
4,
|
| 100 |
+
8
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
14,
|
| 104 |
+
68,
|
| 105 |
+
20,
|
| 106 |
+
36,
|
| 107 |
+
105,
|
| 108 |
+
83,
|
| 109 |
+
407,
|
| 110 |
+
53,
|
| 111 |
+
1,
|
| 112 |
+
13
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
5,
|
| 116 |
+
84,
|
| 117 |
+
7,
|
| 118 |
+
174,
|
| 119 |
+
67,
|
| 120 |
+
50,
|
| 121 |
+
52,
|
| 122 |
+
341,
|
| 123 |
+
9,
|
| 124 |
+
11
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
72,
|
| 128 |
+
7,
|
| 129 |
+
59,
|
| 130 |
+
34,
|
| 131 |
+
19,
|
| 132 |
+
9,
|
| 133 |
+
6,
|
| 134 |
+
15,
|
| 135 |
+
494,
|
| 136 |
+
85
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
32,
|
| 140 |
+
14,
|
| 141 |
+
226,
|
| 142 |
+
13,
|
| 143 |
+
15,
|
| 144 |
+
10,
|
| 145 |
+
26,
|
| 146 |
+
19,
|
| 147 |
+
94,
|
| 148 |
+
351
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.1/s1/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86ce06debafe1e8d18a2c14bd5642f1b3b0476ea7e9be5e99526021e7c636cd6
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/finetune/f0.1/s2/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f0.1/s2",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 0.1,
|
| 9 |
+
"seed": 2,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 450,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
45,
|
| 26 |
+
45,
|
| 27 |
+
45,
|
| 28 |
+
45,
|
| 29 |
+
45,
|
| 30 |
+
45,
|
| 31 |
+
45,
|
| 32 |
+
45,
|
| 33 |
+
45,
|
| 34 |
+
45
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.502,
|
| 38 |
+
"val_macro_f1": 0.5025969863809201,
|
| 39 |
+
"val_loss": 3.207138671875,
|
| 40 |
+
"step": 500
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 0.7579313516616821,
|
| 46 |
+
"val_loss": 3.37785693359375,
|
| 47 |
+
"val_top1": 0.388,
|
| 48 |
+
"val_macro_f1": 0.36111624998462777,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 16.186432792000232
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 0.3175930380821228,
|
| 55 |
+
"val_loss": 2.66659375,
|
| 56 |
+
"val_top1": 0.46,
|
| 57 |
+
"val_macro_f1": 0.4578665785490942,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 31.47894563800037
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 0.07602322101593018,
|
| 64 |
+
"val_loss": 3.0446904296875,
|
| 65 |
+
"val_top1": 0.482,
|
| 66 |
+
"val_macro_f1": 0.4834471697652252,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 46.758263552000244
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 0.01683623716235161,
|
| 73 |
+
"val_loss": 3.111078125,
|
| 74 |
+
"val_top1": 0.484,
|
| 75 |
+
"val_macro_f1": 0.48789790249900805,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 62.06071158600025
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.007751318626105785,
|
| 82 |
+
"val_loss": 3.207138671875,
|
| 83 |
+
"val_top1": 0.502,
|
| 84 |
+
"val_macro_f1": 0.5025969863809201,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 69.53512524800044
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.0019714594818651676,
|
| 91 |
+
"val_loss": 3.3405,
|
| 92 |
+
"val_top1": 0.486,
|
| 93 |
+
"val_macro_f1": 0.4863927881096918,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 83.47451420899961
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.00385871808975935,
|
| 100 |
+
"val_loss": 3.23151806640625,
|
| 101 |
+
"val_top1": 0.49,
|
| 102 |
+
"val_macro_f1": 0.49309516734223086,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 98.8063177920003
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.002976941177621484,
|
| 109 |
+
"val_loss": 3.264876953125,
|
| 110 |
+
"val_top1": 0.502,
|
| 111 |
+
"val_macro_f1": 0.5028797205781366,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 114.13058873400041
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.0015659760683774948,
|
| 118 |
+
"val_loss": 3.25403173828125,
|
| 119 |
+
"val_top1": 0.5,
|
| 120 |
+
"val_macro_f1": 0.5015497467989943,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 129.4627581450004
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.003472910961136222,
|
| 127 |
+
"val_loss": 3.27770068359375,
|
| 128 |
+
"val_top1": 0.496,
|
| 129 |
+
"val_macro_f1": 0.4962385696368175,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 138.14243283400083
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 138.14245812100035,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.1/s2/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.477375,
|
| 3 |
+
"macro_f1": 0.4774554768330976,
|
| 4 |
+
"balanced_accuracy": 0.47737500000000005,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.48125,
|
| 7 |
+
0.3775,
|
| 8 |
+
0.64875,
|
| 9 |
+
0.495,
|
| 10 |
+
0.4375,
|
| 11 |
+
0.30375,
|
| 12 |
+
0.4225,
|
| 13 |
+
0.4075,
|
| 14 |
+
0.7325,
|
| 15 |
+
0.4675
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.5720653789004457,
|
| 19 |
+
0.4097693351424695,
|
| 20 |
+
0.6352509179926561,
|
| 21 |
+
0.3829787234042554,
|
| 22 |
+
0.41791044776119407,
|
| 23 |
+
0.32443257676902537,
|
| 24 |
+
0.48493543758967,
|
| 25 |
+
0.4343770819453697,
|
| 26 |
+
0.6318059299191374,
|
| 27 |
+
0.4810289389067524
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
385,
|
| 32 |
+
38,
|
| 33 |
+
39,
|
| 34 |
+
29,
|
| 35 |
+
10,
|
| 36 |
+
20,
|
| 37 |
+
10,
|
| 38 |
+
7,
|
| 39 |
+
172,
|
| 40 |
+
90
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
42,
|
| 44 |
+
302,
|
| 45 |
+
28,
|
| 46 |
+
165,
|
| 47 |
+
83,
|
| 48 |
+
58,
|
| 49 |
+
25,
|
| 50 |
+
59,
|
| 51 |
+
28,
|
| 52 |
+
10
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
25,
|
| 56 |
+
5,
|
| 57 |
+
519,
|
| 58 |
+
15,
|
| 59 |
+
3,
|
| 60 |
+
11,
|
| 61 |
+
10,
|
| 62 |
+
4,
|
| 63 |
+
59,
|
| 64 |
+
149
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
3,
|
| 68 |
+
57,
|
| 69 |
+
15,
|
| 70 |
+
396,
|
| 71 |
+
98,
|
| 72 |
+
76,
|
| 73 |
+
33,
|
| 74 |
+
93,
|
| 75 |
+
15,
|
| 76 |
+
14
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
8,
|
| 80 |
+
60,
|
| 81 |
+
10,
|
| 82 |
+
197,
|
| 83 |
+
350,
|
| 84 |
+
60,
|
| 85 |
+
53,
|
| 86 |
+
44,
|
| 87 |
+
9,
|
| 88 |
+
9
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
11,
|
| 92 |
+
86,
|
| 93 |
+
12,
|
| 94 |
+
155,
|
| 95 |
+
94,
|
| 96 |
+
243,
|
| 97 |
+
74,
|
| 98 |
+
105,
|
| 99 |
+
13,
|
| 100 |
+
7
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
9,
|
| 104 |
+
52,
|
| 105 |
+
22,
|
| 106 |
+
42,
|
| 107 |
+
140,
|
| 108 |
+
129,
|
| 109 |
+
338,
|
| 110 |
+
47,
|
| 111 |
+
4,
|
| 112 |
+
17
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
2,
|
| 116 |
+
60,
|
| 117 |
+
6,
|
| 118 |
+
219,
|
| 119 |
+
72,
|
| 120 |
+
66,
|
| 121 |
+
33,
|
| 122 |
+
326,
|
| 123 |
+
8,
|
| 124 |
+
8
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
41,
|
| 128 |
+
5,
|
| 129 |
+
22,
|
| 130 |
+
28,
|
| 131 |
+
14,
|
| 132 |
+
19,
|
| 133 |
+
3,
|
| 134 |
+
5,
|
| 135 |
+
586,
|
| 136 |
+
77
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
20,
|
| 140 |
+
9,
|
| 141 |
+
161,
|
| 142 |
+
22,
|
| 143 |
+
11,
|
| 144 |
+
16,
|
| 145 |
+
15,
|
| 146 |
+
11,
|
| 147 |
+
161,
|
| 148 |
+
374
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.1/s2/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e9a925c714ab9717c9ac08a0b096b55db92ec67019b1b3b8ed48d9e85069fdb
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/finetune/f0.25/s0/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f0.25/s0",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 0.25,
|
| 9 |
+
"seed": 0,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 1120,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
112,
|
| 26 |
+
112,
|
| 27 |
+
112,
|
| 28 |
+
112,
|
| 29 |
+
112,
|
| 30 |
+
112,
|
| 31 |
+
112,
|
| 32 |
+
112,
|
| 33 |
+
112,
|
| 34 |
+
112
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.598,
|
| 38 |
+
"val_macro_f1": 0.5998760388379384,
|
| 39 |
+
"val_loss": 2.135194091796875,
|
| 40 |
+
"step": 900
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.3392980098724365,
|
| 46 |
+
"val_loss": 1.75057177734375,
|
| 47 |
+
"val_top1": 0.398,
|
| 48 |
+
"val_macro_f1": 0.3794102903491342,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 13.875871758999892
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 1.141497015953064,
|
| 55 |
+
"val_loss": 2.776034423828125,
|
| 56 |
+
"val_top1": 0.382,
|
| 57 |
+
"val_macro_f1": 0.3463041778154979,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 25.42991890399935
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 0.6150950789451599,
|
| 64 |
+
"val_loss": 1.634187255859375,
|
| 65 |
+
"val_top1": 0.506,
|
| 66 |
+
"val_macro_f1": 0.5032138941121254,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 40.74091223599953
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 0.4763893485069275,
|
| 73 |
+
"val_loss": 1.925493896484375,
|
| 74 |
+
"val_top1": 0.526,
|
| 75 |
+
"val_macro_f1": 0.5218058229986063,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 56.03826060099982
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.1384853571653366,
|
| 82 |
+
"val_loss": 2.185093505859375,
|
| 83 |
+
"val_top1": 0.534,
|
| 84 |
+
"val_macro_f1": 0.5198918068124869,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 71.33629051300068
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.2182987630367279,
|
| 91 |
+
"val_loss": 2.2829892578125,
|
| 92 |
+
"val_top1": 0.542,
|
| 93 |
+
"val_macro_f1": 0.5419744408880669,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 83.29302232500049
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.054394371807575226,
|
| 100 |
+
"val_loss": 2.20001708984375,
|
| 101 |
+
"val_top1": 0.55,
|
| 102 |
+
"val_macro_f1": 0.5496483877837706,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 92.19104595200042
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.03407266363501549,
|
| 109 |
+
"val_loss": 2.110118896484375,
|
| 110 |
+
"val_top1": 0.596,
|
| 111 |
+
"val_macro_f1": 0.5987605662397861,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 107.32956836800076
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.07010406255722046,
|
| 118 |
+
"val_loss": 2.135194091796875,
|
| 119 |
+
"val_top1": 0.598,
|
| 120 |
+
"val_macro_f1": 0.5998760388379384,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 122.61886956000126
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.030658934265375137,
|
| 127 |
+
"val_loss": 2.15734375,
|
| 128 |
+
"val_top1": 0.596,
|
| 129 |
+
"val_macro_f1": 0.597947050769364,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 137.88322177400187
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 137.88325717200223,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.25/s0/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.580125,
|
| 3 |
+
"macro_f1": 0.5805694562484712,
|
| 4 |
+
"balanced_accuracy": 0.580125,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.6425,
|
| 7 |
+
0.54,
|
| 8 |
+
0.715,
|
| 9 |
+
0.43625,
|
| 10 |
+
0.52875,
|
| 11 |
+
0.40875,
|
| 12 |
+
0.63125,
|
| 13 |
+
0.49,
|
| 14 |
+
0.72875,
|
| 15 |
+
0.68
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.6844207723035952,
|
| 19 |
+
0.5356478611283324,
|
| 20 |
+
0.7333333333333333,
|
| 21 |
+
0.43327126008690253,
|
| 22 |
+
0.5121065375302664,
|
| 23 |
+
0.41603053435114506,
|
| 24 |
+
0.630461922596754,
|
| 25 |
+
0.501920614596671,
|
| 26 |
+
0.7255756067205975,
|
| 27 |
+
0.6329261198371147
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
514,
|
| 32 |
+
50,
|
| 33 |
+
46,
|
| 34 |
+
16,
|
| 35 |
+
6,
|
| 36 |
+
13,
|
| 37 |
+
6,
|
| 38 |
+
4,
|
| 39 |
+
83,
|
| 40 |
+
62
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
36,
|
| 44 |
+
432,
|
| 45 |
+
13,
|
| 46 |
+
101,
|
| 47 |
+
51,
|
| 48 |
+
55,
|
| 49 |
+
23,
|
| 50 |
+
68,
|
| 51 |
+
15,
|
| 52 |
+
6
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
22,
|
| 56 |
+
7,
|
| 57 |
+
572,
|
| 58 |
+
11,
|
| 59 |
+
5,
|
| 60 |
+
4,
|
| 61 |
+
4,
|
| 62 |
+
6,
|
| 63 |
+
17,
|
| 64 |
+
152
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
5,
|
| 68 |
+
65,
|
| 69 |
+
7,
|
| 70 |
+
349,
|
| 71 |
+
113,
|
| 72 |
+
95,
|
| 73 |
+
36,
|
| 74 |
+
100,
|
| 75 |
+
22,
|
| 76 |
+
8
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
7,
|
| 80 |
+
53,
|
| 81 |
+
5,
|
| 82 |
+
108,
|
| 83 |
+
423,
|
| 84 |
+
78,
|
| 85 |
+
71,
|
| 86 |
+
38,
|
| 87 |
+
3,
|
| 88 |
+
14
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
5,
|
| 92 |
+
63,
|
| 93 |
+
7,
|
| 94 |
+
89,
|
| 95 |
+
86,
|
| 96 |
+
327,
|
| 97 |
+
104,
|
| 98 |
+
101,
|
| 99 |
+
3,
|
| 100 |
+
15
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
5,
|
| 104 |
+
24,
|
| 105 |
+
11,
|
| 106 |
+
13,
|
| 107 |
+
87,
|
| 108 |
+
84,
|
| 109 |
+
505,
|
| 110 |
+
46,
|
| 111 |
+
0,
|
| 112 |
+
25
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
1,
|
| 116 |
+
105,
|
| 117 |
+
3,
|
| 118 |
+
104,
|
| 119 |
+
64,
|
| 120 |
+
91,
|
| 121 |
+
32,
|
| 122 |
+
392,
|
| 123 |
+
2,
|
| 124 |
+
6
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
82,
|
| 128 |
+
4,
|
| 129 |
+
13,
|
| 130 |
+
7,
|
| 131 |
+
10,
|
| 132 |
+
10,
|
| 133 |
+
3,
|
| 134 |
+
1,
|
| 135 |
+
583,
|
| 136 |
+
87
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
25,
|
| 140 |
+
10,
|
| 141 |
+
83,
|
| 142 |
+
13,
|
| 143 |
+
7,
|
| 144 |
+
15,
|
| 145 |
+
18,
|
| 146 |
+
6,
|
| 147 |
+
79,
|
| 148 |
+
544
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.25/s0/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:938ede000ef42c2bdd5a7bcba9a4e9be708361a332732c69947db49dd42d4ba7
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/finetune/f0.25/s1/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f0.25/s1",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 0.25,
|
| 9 |
+
"seed": 1,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 1120,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
112,
|
| 26 |
+
112,
|
| 27 |
+
112,
|
| 28 |
+
112,
|
| 29 |
+
112,
|
| 30 |
+
112,
|
| 31 |
+
112,
|
| 32 |
+
112,
|
| 33 |
+
112,
|
| 34 |
+
112
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.602,
|
| 38 |
+
"val_macro_f1": 0.6017251026935571,
|
| 39 |
+
"val_loss": 2.01970458984375,
|
| 40 |
+
"step": 600
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.4362108707427979,
|
| 46 |
+
"val_loss": 2.222216796875,
|
| 47 |
+
"val_top1": 0.374,
|
| 48 |
+
"val_macro_f1": 0.3358232953356814,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 19.609342612000546
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 1.1777256727218628,
|
| 55 |
+
"val_loss": 2.21171240234375,
|
| 56 |
+
"val_top1": 0.394,
|
| 57 |
+
"val_macro_f1": 0.40102444484093347,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 35.735606671000824
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 0.7664592266082764,
|
| 64 |
+
"val_loss": 2.16381298828125,
|
| 65 |
+
"val_top1": 0.47,
|
| 66 |
+
"val_macro_f1": 0.4447068897383433,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 51.64684962100091
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 0.5216617584228516,
|
| 73 |
+
"val_loss": 2.150870361328125,
|
| 74 |
+
"val_top1": 0.512,
|
| 75 |
+
"val_macro_f1": 0.5091161011180149,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 64.02580361200125
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.21346740424633026,
|
| 82 |
+
"val_loss": 2.360287109375,
|
| 83 |
+
"val_top1": 0.534,
|
| 84 |
+
"val_macro_f1": 0.5242415770259976,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 72.45979360600177
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.0608561709523201,
|
| 91 |
+
"val_loss": 2.01970458984375,
|
| 92 |
+
"val_top1": 0.602,
|
| 93 |
+
"val_macro_f1": 0.6017251026935571,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 88.30734562800171
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.05216239392757416,
|
| 100 |
+
"val_loss": 2.07039013671875,
|
| 101 |
+
"val_top1": 0.6,
|
| 102 |
+
"val_macro_f1": 0.5994901439895515,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 104.1786659820018
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.035959575325250626,
|
| 109 |
+
"val_loss": 2.081227294921875,
|
| 110 |
+
"val_top1": 0.592,
|
| 111 |
+
"val_macro_f1": 0.592498126589047,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 120.04553574000147
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.02596161514520645,
|
| 118 |
+
"val_loss": 2.0930361328125,
|
| 119 |
+
"val_top1": 0.596,
|
| 120 |
+
"val_macro_f1": 0.597218874943765,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 135.95104919500136
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.034508608281612396,
|
| 127 |
+
"val_loss": 2.121373291015625,
|
| 128 |
+
"val_top1": 0.592,
|
| 129 |
+
"val_macro_f1": 0.5928969586654399,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 151.83161901300082
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 151.83164037400093,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.25/s1/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.56825,
|
| 3 |
+
"macro_f1": 0.5683876344620022,
|
| 4 |
+
"balanced_accuracy": 0.56825,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.68,
|
| 7 |
+
0.51625,
|
| 8 |
+
0.75875,
|
| 9 |
+
0.4475,
|
| 10 |
+
0.52625,
|
| 11 |
+
0.3275,
|
| 12 |
+
0.625,
|
| 13 |
+
0.53875,
|
| 14 |
+
0.665,
|
| 15 |
+
0.5975
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.6695384615384616,
|
| 19 |
+
0.5452145214521453,
|
| 20 |
+
0.74845869297164,
|
| 21 |
+
0.4264443120905301,
|
| 22 |
+
0.4915353181552831,
|
| 23 |
+
0.3692741367159972,
|
| 24 |
+
0.6134969325153374,
|
| 25 |
+
0.49341728677733254,
|
| 26 |
+
0.711705685618729,
|
| 27 |
+
0.614790996784566
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
544,
|
| 32 |
+
35,
|
| 33 |
+
47,
|
| 34 |
+
16,
|
| 35 |
+
10,
|
| 36 |
+
6,
|
| 37 |
+
9,
|
| 38 |
+
7,
|
| 39 |
+
63,
|
| 40 |
+
63
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
49,
|
| 44 |
+
413,
|
| 45 |
+
7,
|
| 46 |
+
103,
|
| 47 |
+
65,
|
| 48 |
+
43,
|
| 49 |
+
23,
|
| 50 |
+
86,
|
| 51 |
+
9,
|
| 52 |
+
2
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
32,
|
| 56 |
+
7,
|
| 57 |
+
607,
|
| 58 |
+
13,
|
| 59 |
+
11,
|
| 60 |
+
8,
|
| 61 |
+
12,
|
| 62 |
+
11,
|
| 63 |
+
13,
|
| 64 |
+
86
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
7,
|
| 68 |
+
52,
|
| 69 |
+
6,
|
| 70 |
+
358,
|
| 71 |
+
122,
|
| 72 |
+
89,
|
| 73 |
+
26,
|
| 74 |
+
121,
|
| 75 |
+
9,
|
| 76 |
+
10
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
17,
|
| 80 |
+
46,
|
| 81 |
+
4,
|
| 82 |
+
122,
|
| 83 |
+
421,
|
| 84 |
+
47,
|
| 85 |
+
71,
|
| 86 |
+
65,
|
| 87 |
+
1,
|
| 88 |
+
6
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
10,
|
| 92 |
+
64,
|
| 93 |
+
8,
|
| 94 |
+
106,
|
| 95 |
+
73,
|
| 96 |
+
262,
|
| 97 |
+
121,
|
| 98 |
+
148,
|
| 99 |
+
1,
|
| 100 |
+
7
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
3,
|
| 104 |
+
16,
|
| 105 |
+
6,
|
| 106 |
+
24,
|
| 107 |
+
109,
|
| 108 |
+
70,
|
| 109 |
+
500,
|
| 110 |
+
57,
|
| 111 |
+
0,
|
| 112 |
+
15
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
2,
|
| 116 |
+
72,
|
| 117 |
+
2,
|
| 118 |
+
105,
|
| 119 |
+
71,
|
| 120 |
+
74,
|
| 121 |
+
40,
|
| 122 |
+
431,
|
| 123 |
+
2,
|
| 124 |
+
1
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
122,
|
| 128 |
+
3,
|
| 129 |
+
14,
|
| 130 |
+
13,
|
| 131 |
+
13,
|
| 132 |
+
12,
|
| 133 |
+
1,
|
| 134 |
+
3,
|
| 135 |
+
532,
|
| 136 |
+
87
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
39,
|
| 140 |
+
7,
|
| 141 |
+
121,
|
| 142 |
+
19,
|
| 143 |
+
18,
|
| 144 |
+
8,
|
| 145 |
+
27,
|
| 146 |
+
18,
|
| 147 |
+
65,
|
| 148 |
+
478
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.25/s1/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07c91a4d4f39297ee8bf9eee884c42d8cf78a49c1ac220aff6ff612b69b25823
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/finetune/f0.25/s2/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f0.25/s2",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 0.25,
|
| 9 |
+
"seed": 2,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 1120,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
112,
|
| 26 |
+
112,
|
| 27 |
+
112,
|
| 28 |
+
112,
|
| 29 |
+
112,
|
| 30 |
+
112,
|
| 31 |
+
112,
|
| 32 |
+
112,
|
| 33 |
+
112,
|
| 34 |
+
112
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.576,
|
| 38 |
+
"val_macro_f1": 0.5786520195765992,
|
| 39 |
+
"val_loss": 2.20154296875,
|
| 40 |
+
"step": 900
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.5442334413528442,
|
| 46 |
+
"val_loss": 2.61542822265625,
|
| 47 |
+
"val_top1": 0.372,
|
| 48 |
+
"val_macro_f1": 0.3621421685829033,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 19.220177342999705
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 1.0383472442626953,
|
| 55 |
+
"val_loss": 1.725662109375,
|
| 56 |
+
"val_top1": 0.47,
|
| 57 |
+
"val_macro_f1": 0.45914562498902856,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 34.93146596000042
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 0.6199432611465454,
|
| 64 |
+
"val_loss": 1.765404541015625,
|
| 65 |
+
"val_top1": 0.516,
|
| 66 |
+
"val_macro_f1": 0.5139317854460306,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 50.825228142000014
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 0.43570783734321594,
|
| 73 |
+
"val_loss": 2.000652587890625,
|
| 74 |
+
"val_top1": 0.492,
|
| 75 |
+
"val_macro_f1": 0.4891188032747644,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 60.61319253200054
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.16606317460536957,
|
| 82 |
+
"val_loss": 2.2829853515625,
|
| 83 |
+
"val_top1": 0.524,
|
| 84 |
+
"val_macro_f1": 0.5210168060562163,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 72.15283780900063
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.12014079093933105,
|
| 91 |
+
"val_loss": 2.1225771484375,
|
| 92 |
+
"val_top1": 0.558,
|
| 93 |
+
"val_macro_f1": 0.5623607846461238,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 87.47775533500135
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.060131266713142395,
|
| 100 |
+
"val_loss": 2.18406494140625,
|
| 101 |
+
"val_top1": 0.552,
|
| 102 |
+
"val_macro_f1": 0.55113508985014,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 103.10129001400128
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.03902437537908554,
|
| 109 |
+
"val_loss": 2.187182373046875,
|
| 110 |
+
"val_top1": 0.574,
|
| 111 |
+
"val_macro_f1": 0.5763493399156965,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 118.72207301100116
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.03008311055600643,
|
| 118 |
+
"val_loss": 2.20154296875,
|
| 119 |
+
"val_top1": 0.576,
|
| 120 |
+
"val_macro_f1": 0.5786520195765992,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 134.41589049400136
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.030429497361183167,
|
| 127 |
+
"val_loss": 2.2016474609375,
|
| 128 |
+
"val_top1": 0.574,
|
| 129 |
+
"val_macro_f1": 0.5762061342129027,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 150.2329307300015
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 150.23295239800154,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.25/s2/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.578125,
|
| 3 |
+
"macro_f1": 0.5772926766495662,
|
| 4 |
+
"balanced_accuracy": 0.578125,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.68,
|
| 7 |
+
0.5,
|
| 8 |
+
0.7375,
|
| 9 |
+
0.4325,
|
| 10 |
+
0.55875,
|
| 11 |
+
0.35375,
|
| 12 |
+
0.62125,
|
| 13 |
+
0.505,
|
| 14 |
+
0.725,
|
| 15 |
+
0.6675
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.6992287917737788,
|
| 19 |
+
0.5298013245033112,
|
| 20 |
+
0.73888541014402,
|
| 21 |
+
0.43277048155096937,
|
| 22 |
+
0.5293072824156305,
|
| 23 |
+
0.36516129032258066,
|
| 24 |
+
0.6132017273288094,
|
| 25 |
+
0.5091367359798361,
|
| 26 |
+
0.7178217821782179,
|
| 27 |
+
0.6376119402985074
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
544,
|
| 32 |
+
36,
|
| 33 |
+
54,
|
| 34 |
+
13,
|
| 35 |
+
9,
|
| 36 |
+
7,
|
| 37 |
+
4,
|
| 38 |
+
2,
|
| 39 |
+
71,
|
| 40 |
+
60
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
49,
|
| 44 |
+
400,
|
| 45 |
+
14,
|
| 46 |
+
92,
|
| 47 |
+
61,
|
| 48 |
+
66,
|
| 49 |
+
25,
|
| 50 |
+
71,
|
| 51 |
+
14,
|
| 52 |
+
8
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
23,
|
| 56 |
+
6,
|
| 57 |
+
590,
|
| 58 |
+
5,
|
| 59 |
+
7,
|
| 60 |
+
7,
|
| 61 |
+
13,
|
| 62 |
+
4,
|
| 63 |
+
21,
|
| 64 |
+
124
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
4,
|
| 68 |
+
52,
|
| 69 |
+
11,
|
| 70 |
+
346,
|
| 71 |
+
114,
|
| 72 |
+
102,
|
| 73 |
+
29,
|
| 74 |
+
107,
|
| 75 |
+
18,
|
| 76 |
+
17
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
10,
|
| 80 |
+
37,
|
| 81 |
+
7,
|
| 82 |
+
86,
|
| 83 |
+
447,
|
| 84 |
+
75,
|
| 85 |
+
77,
|
| 86 |
+
49,
|
| 87 |
+
3,
|
| 88 |
+
9
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
9,
|
| 92 |
+
60,
|
| 93 |
+
6,
|
| 94 |
+
123,
|
| 95 |
+
88,
|
| 96 |
+
283,
|
| 97 |
+
120,
|
| 98 |
+
95,
|
| 99 |
+
6,
|
| 100 |
+
10
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
5,
|
| 104 |
+
23,
|
| 105 |
+
7,
|
| 106 |
+
19,
|
| 107 |
+
74,
|
| 108 |
+
101,
|
| 109 |
+
497,
|
| 110 |
+
44,
|
| 111 |
+
6,
|
| 112 |
+
24
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
2,
|
| 116 |
+
88,
|
| 117 |
+
3,
|
| 118 |
+
97,
|
| 119 |
+
72,
|
| 120 |
+
84,
|
| 121 |
+
41,
|
| 122 |
+
404,
|
| 123 |
+
3,
|
| 124 |
+
6
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
95,
|
| 128 |
+
1,
|
| 129 |
+
11,
|
| 130 |
+
6,
|
| 131 |
+
9,
|
| 132 |
+
13,
|
| 133 |
+
0,
|
| 134 |
+
2,
|
| 135 |
+
580,
|
| 136 |
+
83
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
15,
|
| 140 |
+
7,
|
| 141 |
+
94,
|
| 142 |
+
12,
|
| 143 |
+
8,
|
| 144 |
+
12,
|
| 145 |
+
15,
|
| 146 |
+
9,
|
| 147 |
+
94,
|
| 148 |
+
534
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.25/s2/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38c54a64fee7f29fcd31d7a982d80f0bd47f1181aa4ebb5f7238fd820af507d3
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/finetune/f0.5/s0/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f0.5/s0",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 0.5,
|
| 9 |
+
"seed": 0,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 2250,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
225,
|
| 26 |
+
225,
|
| 27 |
+
225,
|
| 28 |
+
225,
|
| 29 |
+
225,
|
| 30 |
+
225,
|
| 31 |
+
225,
|
| 32 |
+
225,
|
| 33 |
+
225,
|
| 34 |
+
225
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.622,
|
| 38 |
+
"val_macro_f1": 0.6221782460581855,
|
| 39 |
+
"val_loss": 1.4661429443359375,
|
| 40 |
+
"step": 900
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.664527177810669,
|
| 46 |
+
"val_loss": 2.424224853515625,
|
| 47 |
+
"val_top1": 0.356,
|
| 48 |
+
"val_macro_f1": 0.3157327227925132,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 13.696915329999683
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 1.5986084938049316,
|
| 55 |
+
"val_loss": 2.0173961181640623,
|
| 56 |
+
"val_top1": 0.462,
|
| 57 |
+
"val_macro_f1": 0.45025898459899505,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 26.329687538000144
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 1.1938261985778809,
|
| 64 |
+
"val_loss": 1.327635986328125,
|
| 65 |
+
"val_top1": 0.566,
|
| 66 |
+
"val_macro_f1": 0.5651982959513828,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 41.73735346399917
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 0.82810378074646,
|
| 73 |
+
"val_loss": 1.659606689453125,
|
| 74 |
+
"val_top1": 0.558,
|
| 75 |
+
"val_macro_f1": 0.5471666373938,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 57.16610283099908
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.6535406112670898,
|
| 82 |
+
"val_loss": 1.462862548828125,
|
| 83 |
+
"val_top1": 0.564,
|
| 84 |
+
"val_macro_f1": 0.5654383710369502,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 72.5963499319987
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.5393353700637817,
|
| 91 |
+
"val_loss": 1.3466689453125,
|
| 92 |
+
"val_top1": 0.604,
|
| 93 |
+
"val_macro_f1": 0.6025902562435809,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 83.5285831809997
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.3642338514328003,
|
| 100 |
+
"val_loss": 1.458321533203125,
|
| 101 |
+
"val_top1": 0.604,
|
| 102 |
+
"val_macro_f1": 0.6021349547539999,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 94.85576707600012
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.2942779064178467,
|
| 109 |
+
"val_loss": 1.4757919921875,
|
| 110 |
+
"val_top1": 0.608,
|
| 111 |
+
"val_macro_f1": 0.608161160305464,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 110.15946771900053
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.22133029997348785,
|
| 118 |
+
"val_loss": 1.4661429443359375,
|
| 119 |
+
"val_top1": 0.622,
|
| 120 |
+
"val_macro_f1": 0.6221782460581855,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 125.53320325899949
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.27174630761146545,
|
| 127 |
+
"val_loss": 1.4711282958984375,
|
| 128 |
+
"val_top1": 0.616,
|
| 129 |
+
"val_macro_f1": 0.6158800037264107,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 140.93479338399993
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 140.9348156470005,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.5/s0/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.637625,
|
| 3 |
+
"macro_f1": 0.6380527603646357,
|
| 4 |
+
"balanced_accuracy": 0.637625,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.76,
|
| 7 |
+
0.59875,
|
| 8 |
+
0.8225,
|
| 9 |
+
0.48125,
|
| 10 |
+
0.56125,
|
| 11 |
+
0.46,
|
| 12 |
+
0.65375,
|
| 13 |
+
0.55,
|
| 14 |
+
0.7875,
|
| 15 |
+
0.70125
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.7755102040816326,
|
| 19 |
+
0.5998747651847213,
|
| 20 |
+
0.8058787507654622,
|
| 21 |
+
0.47648514851485146,
|
| 22 |
+
0.5647798742138365,
|
| 23 |
+
0.45885286783042395,
|
| 24 |
+
0.6492861576660459,
|
| 25 |
+
0.5422057917436846,
|
| 26 |
+
0.7875,
|
| 27 |
+
0.7201540436456997
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
608,
|
| 32 |
+
41,
|
| 33 |
+
34,
|
| 34 |
+
11,
|
| 35 |
+
5,
|
| 36 |
+
7,
|
| 37 |
+
5,
|
| 38 |
+
4,
|
| 39 |
+
51,
|
| 40 |
+
34
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
37,
|
| 44 |
+
479,
|
| 45 |
+
5,
|
| 46 |
+
70,
|
| 47 |
+
42,
|
| 48 |
+
59,
|
| 49 |
+
8,
|
| 50 |
+
88,
|
| 51 |
+
10,
|
| 52 |
+
2
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
27,
|
| 56 |
+
5,
|
| 57 |
+
658,
|
| 58 |
+
8,
|
| 59 |
+
4,
|
| 60 |
+
2,
|
| 61 |
+
11,
|
| 62 |
+
3,
|
| 63 |
+
12,
|
| 64 |
+
70
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
0,
|
| 68 |
+
65,
|
| 69 |
+
5,
|
| 70 |
+
385,
|
| 71 |
+
98,
|
| 72 |
+
114,
|
| 73 |
+
29,
|
| 74 |
+
85,
|
| 75 |
+
13,
|
| 76 |
+
6
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
4,
|
| 80 |
+
45,
|
| 81 |
+
6,
|
| 82 |
+
84,
|
| 83 |
+
449,
|
| 84 |
+
56,
|
| 85 |
+
96,
|
| 86 |
+
54,
|
| 87 |
+
2,
|
| 88 |
+
4
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
5,
|
| 92 |
+
56,
|
| 93 |
+
5,
|
| 94 |
+
96,
|
| 95 |
+
69,
|
| 96 |
+
368,
|
| 97 |
+
95,
|
| 98 |
+
102,
|
| 99 |
+
0,
|
| 100 |
+
4
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
7,
|
| 104 |
+
18,
|
| 105 |
+
11,
|
| 106 |
+
33,
|
| 107 |
+
58,
|
| 108 |
+
95,
|
| 109 |
+
523,
|
| 110 |
+
41,
|
| 111 |
+
1,
|
| 112 |
+
13
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
1,
|
| 116 |
+
77,
|
| 117 |
+
1,
|
| 118 |
+
99,
|
| 119 |
+
51,
|
| 120 |
+
93,
|
| 121 |
+
30,
|
| 122 |
+
440,
|
| 123 |
+
5,
|
| 124 |
+
3
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
57,
|
| 128 |
+
3,
|
| 129 |
+
24,
|
| 130 |
+
11,
|
| 131 |
+
6,
|
| 132 |
+
6,
|
| 133 |
+
2,
|
| 134 |
+
0,
|
| 135 |
+
630,
|
| 136 |
+
61
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
22,
|
| 140 |
+
8,
|
| 141 |
+
84,
|
| 142 |
+
19,
|
| 143 |
+
8,
|
| 144 |
+
4,
|
| 145 |
+
12,
|
| 146 |
+
6,
|
| 147 |
+
76,
|
| 148 |
+
561
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.5/s0/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31f206cf3c6b09fa712902c87a6948e3d41231bda09a60b0c9f8a5bea1327582
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/finetune/f0.5/s1/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f0.5/s1",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 0.5,
|
| 9 |
+
"seed": 1,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 2250,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
225,
|
| 26 |
+
225,
|
| 27 |
+
225,
|
| 28 |
+
225,
|
| 29 |
+
225,
|
| 30 |
+
225,
|
| 31 |
+
225,
|
| 32 |
+
225,
|
| 33 |
+
225,
|
| 34 |
+
225
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.628,
|
| 38 |
+
"val_macro_f1": 0.6290187976498306,
|
| 39 |
+
"val_loss": 1.4078359375,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.5371099710464478,
|
| 46 |
+
"val_loss": 1.9343111572265625,
|
| 47 |
+
"val_top1": 0.38,
|
| 48 |
+
"val_macro_f1": 0.34719261175023763,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 17.724598741999216
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 1.4742543697357178,
|
| 55 |
+
"val_loss": 2.013494384765625,
|
| 56 |
+
"val_top1": 0.398,
|
| 57 |
+
"val_macro_f1": 0.38683685463967044,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 33.16876373800005
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 1.1212689876556396,
|
| 64 |
+
"val_loss": 2.0129852294921875,
|
| 65 |
+
"val_top1": 0.496,
|
| 66 |
+
"val_macro_f1": 0.4750149901623363,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 48.674035547999665
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 1.0422449111938477,
|
| 73 |
+
"val_loss": 1.465039306640625,
|
| 74 |
+
"val_top1": 0.55,
|
| 75 |
+
"val_macro_f1": 0.5492188153620395,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 63.14872954599923
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.6011922359466553,
|
| 82 |
+
"val_loss": 1.606311279296875,
|
| 83 |
+
"val_top1": 0.556,
|
| 84 |
+
"val_macro_f1": 0.5525847675468278,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 71.42782198299938
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.4771849811077118,
|
| 91 |
+
"val_loss": 1.453379150390625,
|
| 92 |
+
"val_top1": 0.614,
|
| 93 |
+
"val_macro_f1": 0.6147878781222331,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 86.53574524399846
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.31056541204452515,
|
| 100 |
+
"val_loss": 1.4402371826171876,
|
| 101 |
+
"val_top1": 0.61,
|
| 102 |
+
"val_macro_f1": 0.6097286753865624,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 101.8722211159984
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.3110702633857727,
|
| 109 |
+
"val_loss": 1.4650087890625,
|
| 110 |
+
"val_top1": 0.614,
|
| 111 |
+
"val_macro_f1": 0.6126294338684682,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 117.23309545699885
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.19435670971870422,
|
| 118 |
+
"val_loss": 1.410713134765625,
|
| 119 |
+
"val_top1": 0.626,
|
| 120 |
+
"val_macro_f1": 0.6278351080382449,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 132.58969802799948
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.2845712900161743,
|
| 127 |
+
"val_loss": 1.4078359375,
|
| 128 |
+
"val_top1": 0.628,
|
| 129 |
+
"val_macro_f1": 0.6290187976498306,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 139.95889154199904
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 139.95896696899945,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.5/s1/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.6485,
|
| 3 |
+
"macro_f1": 0.6498532055749948,
|
| 4 |
+
"balanced_accuracy": 0.6485000000000001,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.75,
|
| 7 |
+
0.595,
|
| 8 |
+
0.79625,
|
| 9 |
+
0.4925,
|
| 10 |
+
0.59875,
|
| 11 |
+
0.5075,
|
| 12 |
+
0.65625,
|
| 13 |
+
0.54875,
|
| 14 |
+
0.79375,
|
| 15 |
+
0.74625
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.7766990291262137,
|
| 19 |
+
0.6002522068095838,
|
| 20 |
+
0.8125000000000001,
|
| 21 |
+
0.4876237623762376,
|
| 22 |
+
0.59875,
|
| 23 |
+
0.4839094159713945,
|
| 24 |
+
0.6649778340721976,
|
| 25 |
+
0.5567533291058973,
|
| 26 |
+
0.7947434292866082,
|
| 27 |
+
0.7223230490018149
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
600,
|
| 32 |
+
45,
|
| 33 |
+
29,
|
| 34 |
+
10,
|
| 35 |
+
6,
|
| 36 |
+
3,
|
| 37 |
+
5,
|
| 38 |
+
1,
|
| 39 |
+
54,
|
| 40 |
+
47
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
38,
|
| 44 |
+
476,
|
| 45 |
+
4,
|
| 46 |
+
75,
|
| 47 |
+
44,
|
| 48 |
+
56,
|
| 49 |
+
18,
|
| 50 |
+
78,
|
| 51 |
+
5,
|
| 52 |
+
6
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
20,
|
| 56 |
+
8,
|
| 57 |
+
637,
|
| 58 |
+
9,
|
| 59 |
+
6,
|
| 60 |
+
5,
|
| 61 |
+
7,
|
| 62 |
+
2,
|
| 63 |
+
18,
|
| 64 |
+
88
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
2,
|
| 68 |
+
57,
|
| 69 |
+
3,
|
| 70 |
+
394,
|
| 71 |
+
95,
|
| 72 |
+
117,
|
| 73 |
+
24,
|
| 74 |
+
90,
|
| 75 |
+
8,
|
| 76 |
+
10
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
5,
|
| 80 |
+
43,
|
| 81 |
+
4,
|
| 82 |
+
77,
|
| 83 |
+
479,
|
| 84 |
+
62,
|
| 85 |
+
74,
|
| 86 |
+
45,
|
| 87 |
+
4,
|
| 88 |
+
7
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
4,
|
| 92 |
+
52,
|
| 93 |
+
3,
|
| 94 |
+
104,
|
| 95 |
+
54,
|
| 96 |
+
406,
|
| 97 |
+
81,
|
| 98 |
+
88,
|
| 99 |
+
1,
|
| 100 |
+
7
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
4,
|
| 104 |
+
13,
|
| 105 |
+
10,
|
| 106 |
+
34,
|
| 107 |
+
58,
|
| 108 |
+
111,
|
| 109 |
+
525,
|
| 110 |
+
30,
|
| 111 |
+
2,
|
| 112 |
+
13
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
1,
|
| 116 |
+
82,
|
| 117 |
+
0,
|
| 118 |
+
86,
|
| 119 |
+
42,
|
| 120 |
+
106,
|
| 121 |
+
34,
|
| 122 |
+
439,
|
| 123 |
+
3,
|
| 124 |
+
7
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
49,
|
| 128 |
+
5,
|
| 129 |
+
15,
|
| 130 |
+
12,
|
| 131 |
+
6,
|
| 132 |
+
5,
|
| 133 |
+
2,
|
| 134 |
+
0,
|
| 135 |
+
635,
|
| 136 |
+
71
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
22,
|
| 140 |
+
5,
|
| 141 |
+
63,
|
| 142 |
+
15,
|
| 143 |
+
10,
|
| 144 |
+
7,
|
| 145 |
+
9,
|
| 146 |
+
4,
|
| 147 |
+
68,
|
| 148 |
+
597
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.5/s1/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cb71928ae9b9001a2cf580177d03b08c11439b91f6a2ed48ab3876e10a7cb43
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/finetune/f0.5/s2/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f0.5/s2",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 0.5,
|
| 9 |
+
"seed": 2,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 2250,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
225,
|
| 26 |
+
225,
|
| 27 |
+
225,
|
| 28 |
+
225,
|
| 29 |
+
225,
|
| 30 |
+
225,
|
| 31 |
+
225,
|
| 32 |
+
225,
|
| 33 |
+
225,
|
| 34 |
+
225
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.626,
|
| 38 |
+
"val_macro_f1": 0.6276225599970873,
|
| 39 |
+
"val_loss": 1.3873631591796876,
|
| 40 |
+
"step": 900
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.3954614400863647,
|
| 46 |
+
"val_loss": 11.521220703125,
|
| 47 |
+
"val_top1": 0.228,
|
| 48 |
+
"val_macro_f1": 0.1732283469704522,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 19.041560211000615
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 1.3203586339950562,
|
| 55 |
+
"val_loss": 1.5385164794921875,
|
| 56 |
+
"val_top1": 0.472,
|
| 57 |
+
"val_macro_f1": 0.4589835647364133,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 34.76120481599901
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 1.2003684043884277,
|
| 64 |
+
"val_loss": 1.5034833984375,
|
| 65 |
+
"val_top1": 0.506,
|
| 66 |
+
"val_macro_f1": 0.5040322670482625,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 50.47000436499911
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 0.8662247061729431,
|
| 73 |
+
"val_loss": 1.551482177734375,
|
| 74 |
+
"val_top1": 0.546,
|
| 75 |
+
"val_macro_f1": 0.5403759746792641,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 66.18782085699786
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.7043923139572144,
|
| 82 |
+
"val_loss": 1.3412440185546874,
|
| 83 |
+
"val_top1": 0.602,
|
| 84 |
+
"val_macro_f1": 0.6002351284074914,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 81.75911541899768
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.5357675552368164,
|
| 91 |
+
"val_loss": 1.3644307861328124,
|
| 92 |
+
"val_top1": 0.604,
|
| 93 |
+
"val_macro_f1": 0.6020021276453285,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 97.51658064399817
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.4202096164226532,
|
| 100 |
+
"val_loss": 1.408474365234375,
|
| 101 |
+
"val_top1": 0.618,
|
| 102 |
+
"val_macro_f1": 0.6235743879997069,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 113.302075976997
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.3027457594871521,
|
| 109 |
+
"val_loss": 1.46721044921875,
|
| 110 |
+
"val_top1": 0.594,
|
| 111 |
+
"val_macro_f1": 0.5913408386008079,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 129.11843697699624
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.18171077966690063,
|
| 118 |
+
"val_loss": 1.3873631591796876,
|
| 119 |
+
"val_top1": 0.626,
|
| 120 |
+
"val_macro_f1": 0.6276225599970873,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 144.9325570669953
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.2305491864681244,
|
| 127 |
+
"val_loss": 1.37533984375,
|
| 128 |
+
"val_top1": 0.622,
|
| 129 |
+
"val_macro_f1": 0.6238061395799843,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 160.6571598759947
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 160.65719096399516,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.5/s2/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.6375,
|
| 3 |
+
"macro_f1": 0.6388758991094365,
|
| 4 |
+
"balanced_accuracy": 0.6375000000000001,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.7425,
|
| 7 |
+
0.59,
|
| 8 |
+
0.7875,
|
| 9 |
+
0.505,
|
| 10 |
+
0.545,
|
| 11 |
+
0.48625,
|
| 12 |
+
0.66,
|
| 13 |
+
0.5425,
|
| 14 |
+
0.78875,
|
| 15 |
+
0.7275
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.7754569190600522,
|
| 19 |
+
0.5940843297671492,
|
| 20 |
+
0.7989854153455929,
|
| 21 |
+
0.4867469879518072,
|
| 22 |
+
0.5647668393782385,
|
| 23 |
+
0.4669867947178871,
|
| 24 |
+
0.6579439252336449,
|
| 25 |
+
0.5521628498727735,
|
| 26 |
+
0.7853142501555693,
|
| 27 |
+
0.7063106796116505
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
594,
|
| 32 |
+
35,
|
| 33 |
+
32,
|
| 34 |
+
12,
|
| 35 |
+
7,
|
| 36 |
+
4,
|
| 37 |
+
1,
|
| 38 |
+
4,
|
| 39 |
+
61,
|
| 40 |
+
50
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
34,
|
| 44 |
+
472,
|
| 45 |
+
5,
|
| 46 |
+
79,
|
| 47 |
+
39,
|
| 48 |
+
61,
|
| 49 |
+
17,
|
| 50 |
+
78,
|
| 51 |
+
12,
|
| 52 |
+
3
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
21,
|
| 56 |
+
9,
|
| 57 |
+
630,
|
| 58 |
+
8,
|
| 59 |
+
3,
|
| 60 |
+
7,
|
| 61 |
+
7,
|
| 62 |
+
5,
|
| 63 |
+
21,
|
| 64 |
+
89
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
1,
|
| 68 |
+
59,
|
| 69 |
+
3,
|
| 70 |
+
404,
|
| 71 |
+
89,
|
| 72 |
+
121,
|
| 73 |
+
29,
|
| 74 |
+
77,
|
| 75 |
+
7,
|
| 76 |
+
10
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
4,
|
| 80 |
+
54,
|
| 81 |
+
5,
|
| 82 |
+
87,
|
| 83 |
+
436,
|
| 84 |
+
65,
|
| 85 |
+
95,
|
| 86 |
+
43,
|
| 87 |
+
1,
|
| 88 |
+
10
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
3,
|
| 92 |
+
48,
|
| 93 |
+
5,
|
| 94 |
+
120,
|
| 95 |
+
58,
|
| 96 |
+
389,
|
| 97 |
+
85,
|
| 98 |
+
89,
|
| 99 |
+
0,
|
| 100 |
+
3
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
2,
|
| 104 |
+
16,
|
| 105 |
+
4,
|
| 106 |
+
33,
|
| 107 |
+
50,
|
| 108 |
+
110,
|
| 109 |
+
528,
|
| 110 |
+
35,
|
| 111 |
+
3,
|
| 112 |
+
19
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
1,
|
| 116 |
+
83,
|
| 117 |
+
4,
|
| 118 |
+
95,
|
| 119 |
+
46,
|
| 120 |
+
92,
|
| 121 |
+
36,
|
| 122 |
+
434,
|
| 123 |
+
1,
|
| 124 |
+
8
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
58,
|
| 128 |
+
4,
|
| 129 |
+
12,
|
| 130 |
+
8,
|
| 131 |
+
5,
|
| 132 |
+
7,
|
| 133 |
+
1,
|
| 134 |
+
0,
|
| 135 |
+
631,
|
| 136 |
+
74
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
14,
|
| 140 |
+
9,
|
| 141 |
+
77,
|
| 142 |
+
14,
|
| 143 |
+
11,
|
| 144 |
+
10,
|
| 145 |
+
6,
|
| 146 |
+
7,
|
| 147 |
+
70,
|
| 148 |
+
582
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f0.5/s2/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cc424b0ec4e3abe939358fae155cb32455b99473538ef78d9ddd8d5f1da8ca2
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/finetune/f1/s0/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f1/s0",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 1.0,
|
| 9 |
+
"seed": 0,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 4500,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
450,
|
| 26 |
+
450,
|
| 27 |
+
450,
|
| 28 |
+
450,
|
| 29 |
+
450,
|
| 30 |
+
450,
|
| 31 |
+
450,
|
| 32 |
+
450,
|
| 33 |
+
450,
|
| 34 |
+
450
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.646,
|
| 38 |
+
"val_macro_f1": 0.6431995595043855,
|
| 39 |
+
"val_loss": 1.113109619140625,
|
| 40 |
+
"step": 800
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.4402191638946533,
|
| 46 |
+
"val_loss": 48.434125,
|
| 47 |
+
"val_top1": 0.262,
|
| 48 |
+
"val_macro_f1": 0.231486794513879,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 19.595666684999742
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 1.2260222434997559,
|
| 55 |
+
"val_loss": 1.630965087890625,
|
| 56 |
+
"val_top1": 0.466,
|
| 57 |
+
"val_macro_f1": 0.44737279290425763,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 35.5338824570008
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 1.4344639778137207,
|
| 64 |
+
"val_loss": 2.4450634765625,
|
| 65 |
+
"val_top1": 0.444,
|
| 66 |
+
"val_macro_f1": 0.44565782839920426,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 48.08675563500037
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 1.1334424018859863,
|
| 73 |
+
"val_loss": 1.74398583984375,
|
| 74 |
+
"val_top1": 0.464,
|
| 75 |
+
"val_macro_f1": 0.4501137889652932,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 57.57589853300124
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 1.0889031887054443,
|
| 82 |
+
"val_loss": 1.6507138671875,
|
| 83 |
+
"val_top1": 0.55,
|
| 84 |
+
"val_macro_f1": 0.5460326036460827,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 73.21386474400242
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.842443585395813,
|
| 91 |
+
"val_loss": 1.354664306640625,
|
| 92 |
+
"val_top1": 0.582,
|
| 93 |
+
"val_macro_f1": 0.579455241868269,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 89.11956499400185
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.7784000039100647,
|
| 100 |
+
"val_loss": 1.1626893310546875,
|
| 101 |
+
"val_top1": 0.624,
|
| 102 |
+
"val_macro_f1": 0.6217312015547114,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 105.07884173900129
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.503559410572052,
|
| 109 |
+
"val_loss": 1.113109619140625,
|
| 110 |
+
"val_top1": 0.646,
|
| 111 |
+
"val_macro_f1": 0.6431995595043855,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 121.17437448900091
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.6135572195053101,
|
| 118 |
+
"val_loss": 1.0885562744140624,
|
| 119 |
+
"val_top1": 0.646,
|
| 120 |
+
"val_macro_f1": 0.6467807014854703,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 137.24749545600025
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.6150004863739014,
|
| 127 |
+
"val_loss": 1.0763377685546875,
|
| 128 |
+
"val_top1": 0.636,
|
| 129 |
+
"val_macro_f1": 0.6373144693143017,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 153.18861528900015
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 153.18864026600022,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f1/s0/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.670125,
|
| 3 |
+
"macro_f1": 0.6650833752104608,
|
| 4 |
+
"balanced_accuracy": 0.6701250000000001,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.81375,
|
| 7 |
+
0.6575,
|
| 8 |
+
0.85,
|
| 9 |
+
0.4375,
|
| 10 |
+
0.62625,
|
| 11 |
+
0.4325,
|
| 12 |
+
0.75875,
|
| 13 |
+
0.605,
|
| 14 |
+
0.8475,
|
| 15 |
+
0.6725
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.7871825876662635,
|
| 19 |
+
0.6162858816637375,
|
| 20 |
+
0.8104886769964244,
|
| 21 |
+
0.4946996466431095,
|
| 22 |
+
0.6317780580075663,
|
| 23 |
+
0.4890459363957597,
|
| 24 |
+
0.6949055523755009,
|
| 25 |
+
0.587378640776699,
|
| 26 |
+
0.8085867620751341,
|
| 27 |
+
0.7304820095044127
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
651,
|
| 32 |
+
27,
|
| 33 |
+
41,
|
| 34 |
+
2,
|
| 35 |
+
3,
|
| 36 |
+
0,
|
| 37 |
+
4,
|
| 38 |
+
1,
|
| 39 |
+
57,
|
| 40 |
+
14
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
53,
|
| 44 |
+
526,
|
| 45 |
+
10,
|
| 46 |
+
54,
|
| 47 |
+
36,
|
| 48 |
+
25,
|
| 49 |
+
17,
|
| 50 |
+
72,
|
| 51 |
+
5,
|
| 52 |
+
2
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
30,
|
| 56 |
+
5,
|
| 57 |
+
680,
|
| 58 |
+
4,
|
| 59 |
+
5,
|
| 60 |
+
1,
|
| 61 |
+
4,
|
| 62 |
+
3,
|
| 63 |
+
11,
|
| 64 |
+
57
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
3,
|
| 68 |
+
96,
|
| 69 |
+
8,
|
| 70 |
+
350,
|
| 71 |
+
107,
|
| 72 |
+
75,
|
| 73 |
+
37,
|
| 74 |
+
104,
|
| 75 |
+
15,
|
| 76 |
+
5
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
5,
|
| 80 |
+
46,
|
| 81 |
+
5,
|
| 82 |
+
50,
|
| 83 |
+
501,
|
| 84 |
+
34,
|
| 85 |
+
100,
|
| 86 |
+
52,
|
| 87 |
+
4,
|
| 88 |
+
3
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
9,
|
| 92 |
+
87,
|
| 93 |
+
4,
|
| 94 |
+
69,
|
| 95 |
+
50,
|
| 96 |
+
346,
|
| 97 |
+
133,
|
| 98 |
+
95,
|
| 99 |
+
2,
|
| 100 |
+
5
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
10,
|
| 104 |
+
15,
|
| 105 |
+
15,
|
| 106 |
+
11,
|
| 107 |
+
33,
|
| 108 |
+
59,
|
| 109 |
+
607,
|
| 110 |
+
33,
|
| 111 |
+
4,
|
| 112 |
+
13
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
2,
|
| 116 |
+
91,
|
| 117 |
+
3,
|
| 118 |
+
58,
|
| 119 |
+
47,
|
| 120 |
+
71,
|
| 121 |
+
35,
|
| 122 |
+
484,
|
| 123 |
+
4,
|
| 124 |
+
5
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
58,
|
| 128 |
+
4,
|
| 129 |
+
20,
|
| 130 |
+
6,
|
| 131 |
+
1,
|
| 132 |
+
1,
|
| 133 |
+
0,
|
| 134 |
+
1,
|
| 135 |
+
678,
|
| 136 |
+
31
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
33,
|
| 140 |
+
10,
|
| 141 |
+
92,
|
| 142 |
+
11,
|
| 143 |
+
3,
|
| 144 |
+
3,
|
| 145 |
+
10,
|
| 146 |
+
3,
|
| 147 |
+
97,
|
| 148 |
+
538
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f1/s0/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e047749c7aa2d64fa91ff4972086f796c9bdab14faf90e170aca429f37a6371
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/finetune/f1/s1/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f1/s1",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 1.0,
|
| 9 |
+
"seed": 1,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 4500,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
450,
|
| 26 |
+
450,
|
| 27 |
+
450,
|
| 28 |
+
450,
|
| 29 |
+
450,
|
| 30 |
+
450,
|
| 31 |
+
450,
|
| 32 |
+
450,
|
| 33 |
+
450,
|
| 34 |
+
450
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.642,
|
| 38 |
+
"val_macro_f1": 0.6426350724197716,
|
| 39 |
+
"val_loss": 1.2152886962890626,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.6809144020080566,
|
| 46 |
+
"val_loss": 3.02781201171875,
|
| 47 |
+
"val_top1": 0.432,
|
| 48 |
+
"val_macro_f1": 0.4200789625529183,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 13.070318083999155
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 1.3151838779449463,
|
| 55 |
+
"val_loss": 1.76627294921875,
|
| 56 |
+
"val_top1": 0.418,
|
| 57 |
+
"val_macro_f1": 0.40380787884380676,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 28.248113009000008
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 1.5031670331954956,
|
| 64 |
+
"val_loss": 1.421893798828125,
|
| 65 |
+
"val_top1": 0.514,
|
| 66 |
+
"val_macro_f1": 0.512205624776953,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 43.45445638899946
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 1.0106605291366577,
|
| 73 |
+
"val_loss": 1.6025562744140625,
|
| 74 |
+
"val_top1": 0.492,
|
| 75 |
+
"val_macro_f1": 0.48392156936379677,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 58.65733413899943
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.9204467535018921,
|
| 82 |
+
"val_loss": 1.7309908447265625,
|
| 83 |
+
"val_top1": 0.558,
|
| 84 |
+
"val_macro_f1": 0.554980999984315,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 69.13762343000053
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.821257472038269,
|
| 91 |
+
"val_loss": 1.3000107421875,
|
| 92 |
+
"val_top1": 0.602,
|
| 93 |
+
"val_macro_f1": 0.598506191312312,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 80.36585809700046
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.8413910269737244,
|
| 100 |
+
"val_loss": 1.399740234375,
|
| 101 |
+
"val_top1": 0.6,
|
| 102 |
+
"val_macro_f1": 0.5977736028782317,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 95.57113237200065
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.6839640736579895,
|
| 109 |
+
"val_loss": 1.21922119140625,
|
| 110 |
+
"val_top1": 0.632,
|
| 111 |
+
"val_macro_f1": 0.6320365787142193,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 110.78489923300003
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.5734846591949463,
|
| 118 |
+
"val_loss": 1.227885009765625,
|
| 119 |
+
"val_top1": 0.634,
|
| 120 |
+
"val_macro_f1": 0.6355198963290737,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 125.99263506399984
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.4888577461242676,
|
| 127 |
+
"val_loss": 1.2152886962890626,
|
| 128 |
+
"val_top1": 0.642,
|
| 129 |
+
"val_macro_f1": 0.6426350724197716,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 137.19366119000006
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 137.19369314100004,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f1/s1/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.68525,
|
| 3 |
+
"macro_f1": 0.6856048905682238,
|
| 4 |
+
"balanced_accuracy": 0.6852500000000001,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.79375,
|
| 7 |
+
0.63875,
|
| 8 |
+
0.80625,
|
| 9 |
+
0.52125,
|
| 10 |
+
0.6425,
|
| 11 |
+
0.50625,
|
| 12 |
+
0.7125,
|
| 13 |
+
0.63,
|
| 14 |
+
0.8375,
|
| 15 |
+
0.76375
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.8017676767676769,
|
| 19 |
+
0.6666666666666667,
|
| 20 |
+
0.8258642765685019,
|
| 21 |
+
0.5258511979823455,
|
| 22 |
+
0.638112973308504,
|
| 23 |
+
0.5049875311720697,
|
| 24 |
+
0.7201516108654453,
|
| 25 |
+
0.6021505376344086,
|
| 26 |
+
0.8230958230958232,
|
| 27 |
+
0.7474006116207952
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
635,
|
| 32 |
+
27,
|
| 33 |
+
28,
|
| 34 |
+
6,
|
| 35 |
+
8,
|
| 36 |
+
2,
|
| 37 |
+
4,
|
| 38 |
+
1,
|
| 39 |
+
58,
|
| 40 |
+
31
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
38,
|
| 44 |
+
511,
|
| 45 |
+
6,
|
| 46 |
+
69,
|
| 47 |
+
33,
|
| 48 |
+
46,
|
| 49 |
+
14,
|
| 50 |
+
74,
|
| 51 |
+
4,
|
| 52 |
+
5
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
19,
|
| 56 |
+
10,
|
| 57 |
+
645,
|
| 58 |
+
8,
|
| 59 |
+
5,
|
| 60 |
+
9,
|
| 61 |
+
3,
|
| 62 |
+
4,
|
| 63 |
+
10,
|
| 64 |
+
87
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
4,
|
| 68 |
+
47,
|
| 69 |
+
2,
|
| 70 |
+
417,
|
| 71 |
+
98,
|
| 72 |
+
97,
|
| 73 |
+
15,
|
| 74 |
+
101,
|
| 75 |
+
11,
|
| 76 |
+
8
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
7,
|
| 80 |
+
29,
|
| 81 |
+
3,
|
| 82 |
+
64,
|
| 83 |
+
514,
|
| 84 |
+
52,
|
| 85 |
+
69,
|
| 86 |
+
49,
|
| 87 |
+
5,
|
| 88 |
+
8
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
4,
|
| 92 |
+
41,
|
| 93 |
+
2,
|
| 94 |
+
99,
|
| 95 |
+
55,
|
| 96 |
+
405,
|
| 97 |
+
84,
|
| 98 |
+
103,
|
| 99 |
+
0,
|
| 100 |
+
7
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
5,
|
| 104 |
+
5,
|
| 105 |
+
5,
|
| 106 |
+
24,
|
| 107 |
+
47,
|
| 108 |
+
90,
|
| 109 |
+
570,
|
| 110 |
+
34,
|
| 111 |
+
1,
|
| 112 |
+
19
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
1,
|
| 116 |
+
51,
|
| 117 |
+
0,
|
| 118 |
+
84,
|
| 119 |
+
42,
|
| 120 |
+
94,
|
| 121 |
+
16,
|
| 122 |
+
504,
|
| 123 |
+
1,
|
| 124 |
+
7
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
45,
|
| 128 |
+
5,
|
| 129 |
+
13,
|
| 130 |
+
8,
|
| 131 |
+
3,
|
| 132 |
+
4,
|
| 133 |
+
0,
|
| 134 |
+
0,
|
| 135 |
+
670,
|
| 136 |
+
52
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
26,
|
| 140 |
+
7,
|
| 141 |
+
58,
|
| 142 |
+
7,
|
| 143 |
+
6,
|
| 144 |
+
5,
|
| 145 |
+
8,
|
| 146 |
+
4,
|
| 147 |
+
68,
|
| 148 |
+
611
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f1/s1/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff52c6215405eec245b1a676867ca5650220925db76ca941b7459aa1508963dd
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/finetune/f1/s2/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/finetune/f1/s2",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "finetune",
|
| 8 |
+
"fraction": 1.0,
|
| 9 |
+
"seed": 2,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.05,
|
| 13 |
+
"weight_decay": 0.0005,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 4500,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
450,
|
| 26 |
+
450,
|
| 27 |
+
450,
|
| 28 |
+
450,
|
| 29 |
+
450,
|
| 30 |
+
450,
|
| 31 |
+
450,
|
| 32 |
+
450,
|
| 33 |
+
450,
|
| 34 |
+
450
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.654,
|
| 38 |
+
"val_macro_f1": 0.6561774190023232,
|
| 39 |
+
"val_loss": 1.059621337890625,
|
| 40 |
+
"step": 900
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.9473944902420044,
|
| 46 |
+
"val_loss": 1.667942138671875,
|
| 47 |
+
"val_top1": 0.404,
|
| 48 |
+
"val_macro_f1": 0.3820966213343172,
|
| 49 |
+
"lr": 0.05,
|
| 50 |
+
"train_time_s": 19.184310279000783
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 1.2435941696166992,
|
| 55 |
+
"val_loss": 1.682259765625,
|
| 56 |
+
"val_top1": 0.446,
|
| 57 |
+
"val_macro_f1": 0.43524970170722366,
|
| 58 |
+
"lr": 0.04852201922385564,
|
| 59 |
+
"train_time_s": 34.93623902900072
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 1.1772289276123047,
|
| 64 |
+
"val_loss": 1.382130126953125,
|
| 65 |
+
"val_top1": 0.522,
|
| 66 |
+
"val_macro_f1": 0.5141435742222427,
|
| 67 |
+
"lr": 0.04420708808983809,
|
| 68 |
+
"train_time_s": 50.70281876199988
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 1.0206830501556396,
|
| 73 |
+
"val_loss": 1.425110595703125,
|
| 74 |
+
"val_top1": 0.52,
|
| 75 |
+
"val_macro_f1": 0.5193152477283001,
|
| 76 |
+
"lr": 0.03757549866575588,
|
| 77 |
+
"train_time_s": 66.33444605299883
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.8035917282104492,
|
| 82 |
+
"val_loss": 1.31982373046875,
|
| 83 |
+
"val_top1": 0.546,
|
| 84 |
+
"val_macro_f1": 0.5512592005581908,
|
| 85 |
+
"lr": 0.029427118507989587,
|
| 86 |
+
"train_time_s": 82.10266869699808
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.9900924563407898,
|
| 91 |
+
"val_loss": 1.175665283203125,
|
| 92 |
+
"val_top1": 0.606,
|
| 93 |
+
"val_macro_f1": 0.6087787723079152,
|
| 94 |
+
"lr": 0.020744762520849194,
|
| 95 |
+
"train_time_s": 97.8688987209971
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.731718897819519,
|
| 100 |
+
"val_loss": 1.1156395263671874,
|
| 101 |
+
"val_top1": 0.63,
|
| 102 |
+
"val_macro_f1": 0.6317331233146192,
|
| 103 |
+
"lr": 0.012575650974311119,
|
| 104 |
+
"train_time_s": 113.62670028299726
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.8999506831169128,
|
| 109 |
+
"val_loss": 1.0977762451171875,
|
| 110 |
+
"val_top1": 0.65,
|
| 111 |
+
"val_macro_f1": 0.6514253995334529,
|
| 112 |
+
"lr": 0.005905099284133953,
|
| 113 |
+
"train_time_s": 129.24092872699657
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.5546733140945435,
|
| 118 |
+
"val_loss": 1.059621337890625,
|
| 119 |
+
"val_top1": 0.654,
|
| 120 |
+
"val_macro_f1": 0.6561774190023232,
|
| 121 |
+
"lr": 0.001537674431011102,
|
| 122 |
+
"train_time_s": 144.99802787099725
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.5416405200958252,
|
| 127 |
+
"val_loss": 1.062933837890625,
|
| 128 |
+
"val_top1": 0.65,
|
| 129 |
+
"val_macro_f1": 0.6515320532329333,
|
| 130 |
+
"lr": 1.5230855524017706e-07,
|
| 131 |
+
"train_time_s": 160.61895952599662
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 160.6189987589969,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 919.21826171875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 11173962,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/finetune/f1/s2/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.681625,
|
| 3 |
+
"macro_f1": 0.6818435286504656,
|
| 4 |
+
"balanced_accuracy": 0.6816249999999999,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.77375,
|
| 7 |
+
0.655,
|
| 8 |
+
0.84125,
|
| 9 |
+
0.54375,
|
| 10 |
+
0.5825,
|
| 11 |
+
0.51625,
|
| 12 |
+
0.69875,
|
| 13 |
+
0.63375,
|
| 14 |
+
0.8375,
|
| 15 |
+
0.73375
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.7951188182402055,
|
| 19 |
+
0.6562304320601127,
|
| 20 |
+
0.8303516347933374,
|
| 21 |
+
0.5256797583081572,
|
| 22 |
+
0.6188579017264276,
|
| 23 |
+
0.5247776365946634,
|
| 24 |
+
0.7089410272669626,
|
| 25 |
+
0.6007109004739336,
|
| 26 |
+
0.8170731707317073,
|
| 27 |
+
0.7406940063091482
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
619,
|
| 32 |
+
28,
|
| 33 |
+
34,
|
| 34 |
+
12,
|
| 35 |
+
4,
|
| 36 |
+
1,
|
| 37 |
+
6,
|
| 38 |
+
1,
|
| 39 |
+
62,
|
| 40 |
+
33
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
39,
|
| 44 |
+
524,
|
| 45 |
+
7,
|
| 46 |
+
73,
|
| 47 |
+
29,
|
| 48 |
+
35,
|
| 49 |
+
11,
|
| 50 |
+
73,
|
| 51 |
+
5,
|
| 52 |
+
4
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
25,
|
| 56 |
+
4,
|
| 57 |
+
673,
|
| 58 |
+
7,
|
| 59 |
+
3,
|
| 60 |
+
6,
|
| 61 |
+
3,
|
| 62 |
+
3,
|
| 63 |
+
11,
|
| 64 |
+
65
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
2,
|
| 68 |
+
65,
|
| 69 |
+
5,
|
| 70 |
+
435,
|
| 71 |
+
75,
|
| 72 |
+
95,
|
| 73 |
+
14,
|
| 74 |
+
98,
|
| 75 |
+
8,
|
| 76 |
+
3
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
6,
|
| 80 |
+
41,
|
| 81 |
+
4,
|
| 82 |
+
93,
|
| 83 |
+
466,
|
| 84 |
+
43,
|
| 85 |
+
87,
|
| 86 |
+
52,
|
| 87 |
+
2,
|
| 88 |
+
6
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
1,
|
| 92 |
+
48,
|
| 93 |
+
3,
|
| 94 |
+
101,
|
| 95 |
+
45,
|
| 96 |
+
413,
|
| 97 |
+
78,
|
| 98 |
+
106,
|
| 99 |
+
3,
|
| 100 |
+
2
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
4,
|
| 104 |
+
10,
|
| 105 |
+
7,
|
| 106 |
+
27,
|
| 107 |
+
41,
|
| 108 |
+
91,
|
| 109 |
+
559,
|
| 110 |
+
44,
|
| 111 |
+
0,
|
| 112 |
+
17
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
1,
|
| 116 |
+
65,
|
| 117 |
+
2,
|
| 118 |
+
82,
|
| 119 |
+
36,
|
| 120 |
+
85,
|
| 121 |
+
13,
|
| 122 |
+
507,
|
| 123 |
+
1,
|
| 124 |
+
8
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
38,
|
| 128 |
+
4,
|
| 129 |
+
15,
|
| 130 |
+
8,
|
| 131 |
+
3,
|
| 132 |
+
2,
|
| 133 |
+
0,
|
| 134 |
+
0,
|
| 135 |
+
670,
|
| 136 |
+
60
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
22,
|
| 140 |
+
8,
|
| 141 |
+
71,
|
| 142 |
+
17,
|
| 143 |
+
4,
|
| 144 |
+
3,
|
| 145 |
+
6,
|
| 146 |
+
4,
|
| 147 |
+
78,
|
| 148 |
+
587
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/finetune/f1/s2/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d806bd66ce8780ef9f61164d9856c732aecd0e8cee2011e42ad4b56cd2b58a23
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/frozen/f0.1/s0/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/frozen/f0.1/s0",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "frozen",
|
| 8 |
+
"fraction": 0.1,
|
| 9 |
+
"seed": 0,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.1,
|
| 13 |
+
"weight_decay": 0.0,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 450,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
45,
|
| 26 |
+
45,
|
| 27 |
+
45,
|
| 28 |
+
45,
|
| 29 |
+
45,
|
| 30 |
+
45,
|
| 31 |
+
45,
|
| 32 |
+
45,
|
| 33 |
+
45,
|
| 34 |
+
45
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.44,
|
| 38 |
+
"val_macro_f1": 0.44009913036814596,
|
| 39 |
+
"val_loss": 1.845666015625,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 1.3843863010406494,
|
| 46 |
+
"val_loss": 1.85146240234375,
|
| 47 |
+
"val_top1": 0.416,
|
| 48 |
+
"val_macro_f1": 0.41094460579587794,
|
| 49 |
+
"lr": 0.1,
|
| 50 |
+
"train_time_s": 6.155195332000403
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 1.1762166023254395,
|
| 55 |
+
"val_loss": 1.85185205078125,
|
| 56 |
+
"val_top1": 0.432,
|
| 57 |
+
"val_macro_f1": 0.4283816465787057,
|
| 58 |
+
"lr": 0.09704403844771128,
|
| 59 |
+
"train_time_s": 12.091626259000805
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 1.4299083948135376,
|
| 64 |
+
"val_loss": 2.0896416015625,
|
| 65 |
+
"val_top1": 0.42,
|
| 66 |
+
"val_macro_f1": 0.4143021564356443,
|
| 67 |
+
"lr": 0.08841417617967617,
|
| 68 |
+
"train_time_s": 17.748211211001035
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 1.2334506511688232,
|
| 73 |
+
"val_loss": 1.940521484375,
|
| 74 |
+
"val_top1": 0.41,
|
| 75 |
+
"val_macro_f1": 0.40913836255529956,
|
| 76 |
+
"lr": 0.07515099733151176,
|
| 77 |
+
"train_time_s": 23.817515388001084
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 1.1678426265716553,
|
| 82 |
+
"val_loss": 1.970739990234375,
|
| 83 |
+
"val_top1": 0.42,
|
| 84 |
+
"val_macro_f1": 0.41561868648255046,
|
| 85 |
+
"lr": 0.05885423701597917,
|
| 86 |
+
"train_time_s": 29.884542739001517
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 1.0756964683532715,
|
| 91 |
+
"val_loss": 1.8877965087890625,
|
| 92 |
+
"val_top1": 0.428,
|
| 93 |
+
"val_macro_f1": 0.4264721259716658,
|
| 94 |
+
"lr": 0.04148952504169839,
|
| 95 |
+
"train_time_s": 35.79857658900164
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.8500015735626221,
|
| 100 |
+
"val_loss": 1.874067626953125,
|
| 101 |
+
"val_top1": 0.426,
|
| 102 |
+
"val_macro_f1": 0.42714003184264404,
|
| 103 |
+
"lr": 0.025151301948622237,
|
| 104 |
+
"train_time_s": 41.87412414300161
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.9025719165802002,
|
| 109 |
+
"val_loss": 1.8612298583984375,
|
| 110 |
+
"val_top1": 0.424,
|
| 111 |
+
"val_macro_f1": 0.42130096464073963,
|
| 112 |
+
"lr": 0.011810198568267906,
|
| 113 |
+
"train_time_s": 47.843332691001706
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.8374037146568298,
|
| 118 |
+
"val_loss": 1.831461669921875,
|
| 119 |
+
"val_top1": 0.434,
|
| 120 |
+
"val_macro_f1": 0.4353035632787007,
|
| 121 |
+
"lr": 0.003075348862022204,
|
| 122 |
+
"train_time_s": 53.8075837710021
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.8359435796737671,
|
| 127 |
+
"val_loss": 1.845666015625,
|
| 128 |
+
"val_top1": 0.44,
|
| 129 |
+
"val_macro_f1": 0.44009913036814596,
|
| 130 |
+
"lr": 3.046171104803541e-07,
|
| 131 |
+
"train_time_s": 59.79376875100206
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 59.79379628400238,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 832.591796875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 5130,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/frozen/f0.1/s0/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.44375,
|
| 3 |
+
"macro_f1": 0.4421897116384993,
|
| 4 |
+
"balanced_accuracy": 0.44375,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.54375,
|
| 7 |
+
0.385,
|
| 8 |
+
0.60125,
|
| 9 |
+
0.37,
|
| 10 |
+
0.37875,
|
| 11 |
+
0.21,
|
| 12 |
+
0.47375,
|
| 13 |
+
0.43,
|
| 14 |
+
0.59375,
|
| 15 |
+
0.45125
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.5788423153692615,
|
| 19 |
+
0.3786109403810694,
|
| 20 |
+
0.5909090909090908,
|
| 21 |
+
0.3400344629523262,
|
| 22 |
+
0.3997361477572559,
|
| 23 |
+
0.24068767908309452,
|
| 24 |
+
0.45552884615384615,
|
| 25 |
+
0.41001191895113226,
|
| 26 |
+
0.5740181268882175,
|
| 27 |
+
0.45351758793969854
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
435,
|
| 32 |
+
62,
|
| 33 |
+
44,
|
| 34 |
+
9,
|
| 35 |
+
6,
|
| 36 |
+
3,
|
| 37 |
+
14,
|
| 38 |
+
10,
|
| 39 |
+
138,
|
| 40 |
+
79
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
59,
|
| 44 |
+
308,
|
| 45 |
+
24,
|
| 46 |
+
118,
|
| 47 |
+
59,
|
| 48 |
+
51,
|
| 49 |
+
50,
|
| 50 |
+
101,
|
| 51 |
+
19,
|
| 52 |
+
11
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
31,
|
| 56 |
+
10,
|
| 57 |
+
481,
|
| 58 |
+
10,
|
| 59 |
+
0,
|
| 60 |
+
18,
|
| 61 |
+
19,
|
| 62 |
+
10,
|
| 63 |
+
47,
|
| 64 |
+
174
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
12,
|
| 68 |
+
79,
|
| 69 |
+
24,
|
| 70 |
+
296,
|
| 71 |
+
92,
|
| 72 |
+
86,
|
| 73 |
+
69,
|
| 74 |
+
117,
|
| 75 |
+
18,
|
| 76 |
+
7
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
7,
|
| 80 |
+
82,
|
| 81 |
+
9,
|
| 82 |
+
176,
|
| 83 |
+
303,
|
| 84 |
+
54,
|
| 85 |
+
79,
|
| 86 |
+
69,
|
| 87 |
+
5,
|
| 88 |
+
16
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
16,
|
| 92 |
+
131,
|
| 93 |
+
14,
|
| 94 |
+
107,
|
| 95 |
+
87,
|
| 96 |
+
168,
|
| 97 |
+
139,
|
| 98 |
+
123,
|
| 99 |
+
5,
|
| 100 |
+
10
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
8,
|
| 104 |
+
45,
|
| 105 |
+
15,
|
| 106 |
+
54,
|
| 107 |
+
87,
|
| 108 |
+
110,
|
| 109 |
+
379,
|
| 110 |
+
72,
|
| 111 |
+
5,
|
| 112 |
+
25
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
3,
|
| 116 |
+
75,
|
| 117 |
+
7,
|
| 118 |
+
144,
|
| 119 |
+
68,
|
| 120 |
+
54,
|
| 121 |
+
96,
|
| 122 |
+
344,
|
| 123 |
+
3,
|
| 124 |
+
6
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
102,
|
| 128 |
+
18,
|
| 129 |
+
45,
|
| 130 |
+
15,
|
| 131 |
+
8,
|
| 132 |
+
20,
|
| 133 |
+
3,
|
| 134 |
+
11,
|
| 135 |
+
475,
|
| 136 |
+
103
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
30,
|
| 140 |
+
17,
|
| 141 |
+
165,
|
| 142 |
+
12,
|
| 143 |
+
6,
|
| 144 |
+
32,
|
| 145 |
+
16,
|
| 146 |
+
21,
|
| 147 |
+
140,
|
| 148 |
+
361
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|
downstream/C128_l0.01_clean/frozen/f0.1/s0/test_predictions.npy
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbe5f5f73f0dfebe7a1744f37d8a5968432a46fd6130b6f620eaf4119a9f5909
|
| 3 |
+
size 8128
|
downstream/C128_l0.01_clean/frozen/f0.1/s1/metrics.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"out_dir": "/kaggle/working/OSAE/runs_fast/downstream/C128_l0.01_clean/frozen/f0.1/s1",
|
| 4 |
+
"data_dir": "/tmp/stl10",
|
| 5 |
+
"init": "pretrained",
|
| 6 |
+
"pretrained": "/kaggle/working/OSAE/runs_fast/pretrain/C128_l0.01_clean_ps0/encoder.pt",
|
| 7 |
+
"protocol": "frozen",
|
| 8 |
+
"fraction": 0.1,
|
| 9 |
+
"seed": 1,
|
| 10 |
+
"steps": 1000,
|
| 11 |
+
"batch_size": 128,
|
| 12 |
+
"lr": 0.1,
|
| 13 |
+
"weight_decay": 0.0,
|
| 14 |
+
"momentum": 0.9,
|
| 15 |
+
"warmup_steps": 100,
|
| 16 |
+
"label_smoothing": 0.0,
|
| 17 |
+
"eval_every": 100,
|
| 18 |
+
"patience": 0,
|
| 19 |
+
"amp": "auto",
|
| 20 |
+
"deterministic": false
|
| 21 |
+
},
|
| 22 |
+
"n_train": 450,
|
| 23 |
+
"n_val": 500,
|
| 24 |
+
"train_class_counts": [
|
| 25 |
+
45,
|
| 26 |
+
45,
|
| 27 |
+
45,
|
| 28 |
+
45,
|
| 29 |
+
45,
|
| 30 |
+
45,
|
| 31 |
+
45,
|
| 32 |
+
45,
|
| 33 |
+
45,
|
| 34 |
+
45
|
| 35 |
+
],
|
| 36 |
+
"best": {
|
| 37 |
+
"val_top1": 0.446,
|
| 38 |
+
"val_macro_f1": 0.4453593226150893,
|
| 39 |
+
"val_loss": 1.8388778076171874,
|
| 40 |
+
"step": 800
|
| 41 |
+
},
|
| 42 |
+
"history": [
|
| 43 |
+
{
|
| 44 |
+
"step": 100,
|
| 45 |
+
"train_loss": 2.4660844802856445,
|
| 46 |
+
"val_loss": 1.86965625,
|
| 47 |
+
"val_top1": 0.414,
|
| 48 |
+
"val_macro_f1": 0.4079415310510881,
|
| 49 |
+
"lr": 0.1,
|
| 50 |
+
"train_time_s": 7.266183196999918
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"step": 200,
|
| 54 |
+
"train_loss": 1.7698860168457031,
|
| 55 |
+
"val_loss": 1.946380615234375,
|
| 56 |
+
"val_top1": 0.408,
|
| 57 |
+
"val_macro_f1": 0.40676453298966575,
|
| 58 |
+
"lr": 0.09704403844771128,
|
| 59 |
+
"train_time_s": 13.105111814999873
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"step": 300,
|
| 63 |
+
"train_loss": 1.4437757730484009,
|
| 64 |
+
"val_loss": 1.9902896728515624,
|
| 65 |
+
"val_top1": 0.416,
|
| 66 |
+
"val_macro_f1": 0.4106488661073076,
|
| 67 |
+
"lr": 0.08841417617967617,
|
| 68 |
+
"train_time_s": 18.812408579000476
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"step": 400,
|
| 72 |
+
"train_loss": 1.1257678270339966,
|
| 73 |
+
"val_loss": 1.956866455078125,
|
| 74 |
+
"val_top1": 0.438,
|
| 75 |
+
"val_macro_f1": 0.437109893095986,
|
| 76 |
+
"lr": 0.07515099733151176,
|
| 77 |
+
"train_time_s": 24.661498603000837
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"step": 500,
|
| 81 |
+
"train_loss": 0.95513516664505,
|
| 82 |
+
"val_loss": 2.0018597412109376,
|
| 83 |
+
"val_top1": 0.424,
|
| 84 |
+
"val_macro_f1": 0.4172086181453885,
|
| 85 |
+
"lr": 0.05885423701597917,
|
| 86 |
+
"train_time_s": 30.518781046000186
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"step": 600,
|
| 90 |
+
"train_loss": 0.9779168367385864,
|
| 91 |
+
"val_loss": 1.9543453369140624,
|
| 92 |
+
"val_top1": 0.428,
|
| 93 |
+
"val_macro_f1": 0.42845451438749854,
|
| 94 |
+
"lr": 0.04148952504169839,
|
| 95 |
+
"train_time_s": 36.381413778000024
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"step": 700,
|
| 99 |
+
"train_loss": 0.982588529586792,
|
| 100 |
+
"val_loss": 1.9029217529296876,
|
| 101 |
+
"val_top1": 0.432,
|
| 102 |
+
"val_macro_f1": 0.4296990464012257,
|
| 103 |
+
"lr": 0.025151301948622237,
|
| 104 |
+
"train_time_s": 42.23041101600029
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"step": 800,
|
| 108 |
+
"train_loss": 0.9052144289016724,
|
| 109 |
+
"val_loss": 1.8388778076171874,
|
| 110 |
+
"val_top1": 0.446,
|
| 111 |
+
"val_macro_f1": 0.4453593226150893,
|
| 112 |
+
"lr": 0.011810198568267906,
|
| 113 |
+
"train_time_s": 47.970417442000326
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"step": 900,
|
| 117 |
+
"train_loss": 0.8832823038101196,
|
| 118 |
+
"val_loss": 1.860576171875,
|
| 119 |
+
"val_top1": 0.444,
|
| 120 |
+
"val_macro_f1": 0.44384931618871476,
|
| 121 |
+
"lr": 0.003075348862022204,
|
| 122 |
+
"train_time_s": 53.84162593600013
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"step": 1000,
|
| 126 |
+
"train_loss": 0.8680331707000732,
|
| 127 |
+
"val_loss": 1.84340185546875,
|
| 128 |
+
"val_top1": 0.44,
|
| 129 |
+
"val_macro_f1": 0.43927184072709924,
|
| 130 |
+
"lr": 3.046171104803541e-07,
|
| 131 |
+
"train_time_s": 59.67688776700015
|
| 132 |
+
}
|
| 133 |
+
],
|
| 134 |
+
"train_time_s": 59.676914024000325,
|
| 135 |
+
"amp_resolved": "fp16",
|
| 136 |
+
"steps_run": 1000,
|
| 137 |
+
"peak_gpu_mem_mb": 832.591796875,
|
| 138 |
+
"params_total": 11173962,
|
| 139 |
+
"params_trainable": 5130,
|
| 140 |
+
"env": {
|
| 141 |
+
"python": "3.13.16",
|
| 142 |
+
"platform": "Linux-6.18.55+-x86_64-with-glibc2.39",
|
| 143 |
+
"torch": "2.11.0+cu130",
|
| 144 |
+
"cuda_available": true,
|
| 145 |
+
"cudnn": 92700,
|
| 146 |
+
"gpu": "Tesla T4",
|
| 147 |
+
"cuda": "13.0"
|
| 148 |
+
}
|
| 149 |
+
}
|
downstream/C128_l0.01_clean/frozen/f0.1/s1/test_metrics.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"top1": 0.43975,
|
| 3 |
+
"macro_f1": 0.4375152966060824,
|
| 4 |
+
"balanced_accuracy": 0.43975,
|
| 5 |
+
"per_class_accuracy": [
|
| 6 |
+
0.57,
|
| 7 |
+
0.3575,
|
| 8 |
+
0.60375,
|
| 9 |
+
0.355,
|
| 10 |
+
0.37125,
|
| 11 |
+
0.1875,
|
| 12 |
+
0.46875,
|
| 13 |
+
0.4425,
|
| 14 |
+
0.58625,
|
| 15 |
+
0.455
|
| 16 |
+
],
|
| 17 |
+
"per_class_f1": [
|
| 18 |
+
0.6003949967083607,
|
| 19 |
+
0.3620253164556962,
|
| 20 |
+
0.5926380368098159,
|
| 21 |
+
0.3317757009345795,
|
| 22 |
+
0.38101347017318793,
|
| 23 |
+
0.21961932650073207,
|
| 24 |
+
0.44937088076692633,
|
| 25 |
+
0.40877598152424943,
|
| 26 |
+
0.5751072961373391,
|
| 27 |
+
0.4544319600499376
|
| 28 |
+
],
|
| 29 |
+
"confusion_matrix": [
|
| 30 |
+
[
|
| 31 |
+
456,
|
| 32 |
+
47,
|
| 33 |
+
41,
|
| 34 |
+
11,
|
| 35 |
+
10,
|
| 36 |
+
8,
|
| 37 |
+
13,
|
| 38 |
+
5,
|
| 39 |
+
127,
|
| 40 |
+
82
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
66,
|
| 44 |
+
286,
|
| 45 |
+
20,
|
| 46 |
+
115,
|
| 47 |
+
61,
|
| 48 |
+
52,
|
| 49 |
+
52,
|
| 50 |
+
120,
|
| 51 |
+
16,
|
| 52 |
+
12
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
31,
|
| 56 |
+
8,
|
| 57 |
+
483,
|
| 58 |
+
12,
|
| 59 |
+
2,
|
| 60 |
+
14,
|
| 61 |
+
24,
|
| 62 |
+
8,
|
| 63 |
+
48,
|
| 64 |
+
170
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
12,
|
| 68 |
+
80,
|
| 69 |
+
23,
|
| 70 |
+
284,
|
| 71 |
+
100,
|
| 72 |
+
78,
|
| 73 |
+
74,
|
| 74 |
+
117,
|
| 75 |
+
20,
|
| 76 |
+
12
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
10,
|
| 80 |
+
85,
|
| 81 |
+
10,
|
| 82 |
+
164,
|
| 83 |
+
297,
|
| 84 |
+
51,
|
| 85 |
+
78,
|
| 86 |
+
84,
|
| 87 |
+
5,
|
| 88 |
+
16
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
10,
|
| 92 |
+
124,
|
| 93 |
+
12,
|
| 94 |
+
114,
|
| 95 |
+
107,
|
| 96 |
+
150,
|
| 97 |
+
140,
|
| 98 |
+
129,
|
| 99 |
+
5,
|
| 100 |
+
9
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
5,
|
| 104 |
+
41,
|
| 105 |
+
13,
|
| 106 |
+
51,
|
| 107 |
+
99,
|
| 108 |
+
104,
|
| 109 |
+
375,
|
| 110 |
+
81,
|
| 111 |
+
5,
|
| 112 |
+
26
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
0,
|
| 116 |
+
78,
|
| 117 |
+
8,
|
| 118 |
+
129,
|
| 119 |
+
70,
|
| 120 |
+
54,
|
| 121 |
+
95,
|
| 122 |
+
354,
|
| 123 |
+
3,
|
| 124 |
+
9
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
101,
|
| 128 |
+
18,
|
| 129 |
+
45,
|
| 130 |
+
17,
|
| 131 |
+
7,
|
| 132 |
+
29,
|
| 133 |
+
2,
|
| 134 |
+
10,
|
| 135 |
+
469,
|
| 136 |
+
102
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
28,
|
| 140 |
+
13,
|
| 141 |
+
175,
|
| 142 |
+
15,
|
| 143 |
+
6,
|
| 144 |
+
26,
|
| 145 |
+
16,
|
| 146 |
+
24,
|
| 147 |
+
133,
|
| 148 |
+
364
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"n": 8000,
|
| 152 |
+
"inference": {
|
| 153 |
+
"params_total": 11173962,
|
| 154 |
+
"amp": "auto",
|
| 155 |
+
"benchmark": {
|
| 156 |
+
"bs1": {
|
| 157 |
+
"latency_ms_median": 3.0639289998362074,
|
| 158 |
+
"latency_ms_p90": 3.2141113002580823,
|
| 159 |
+
"throughput_img_s": 326.3783201417064,
|
| 160 |
+
"peak_gpu_mem_mb": 76.3740234375
|
| 161 |
+
},
|
| 162 |
+
"bs256": {
|
| 163 |
+
"latency_ms_median": 44.95981049967668,
|
| 164 |
+
"latency_ms_p90": 45.17436420137528,
|
| 165 |
+
"throughput_img_s": 5693.974177267517,
|
| 166 |
+
"peak_gpu_mem_mb": 441.84228515625
|
| 167 |
+
}
|
| 168 |
+
}
|
| 169 |
+
}
|
| 170 |
+
}
|