Hugging Face's logo

AbstractPhil
/
geo-beatrix

Image Classification
PyTorch
TensorBoard
Safetensors
cifar100
geometric-learning
fractal-encoding
in-training
no-attention
no-cross-entropy
Eval Results (legacy)
Model card Files
xet
Metrics Community
AbstractPhil commited on
Commit
16e935b
·
verified ·
1 Parent(s): d169db3

Epoch 100: 64.35%

Browse files
Files changed (1) hide show
  1. README.md +15 -13
README.md CHANGED
@@ -36,7 +36,7 @@ model-index:
36
 
37
  🚧 **Training in Progress** 🚧
38
 
39
- Current Status: Epoch 50/200
40
 
41
  ---
42
 
@@ -46,17 +46,17 @@ Current Status: Epoch 50/200
46
  |--------|-------|
47
  | **Best Test Accuracy** | **69.08%** |
48
  | **Best Epoch** | 190 |
49
- | **Current Train Accuracy** | 62.17% |
50
- | **Current Test Accuracy** | 57.53% |
51
- | **Current α (Cantor param)** | 0.4202 |
52
  | **Total Parameters** | 198,392,937 |
53
- | **Training Time** | 0:26:36 |
54
 
55
  ### All Training Runs
56
 
57
  | Timestamp | Status | Best Epoch | Test Acc | Train Acc | α |
58
  |-----------|--------|------------|----------|-----------|---|
59
- | `20251010_100047` | 🔄 | 190 | **69.08%** | 62.17% | 0.4202 |
60
 
61
  ### Comparison to State-of-the-Art
62
 
@@ -187,22 +187,24 @@ epoch_checkpoint = hf_hub_download(
187
 
188
  ### Best Checkpoint
189
  - Epoch: 190
190
- - Train Acc: 62.17%
191
  - Test Acc: 69.08%
192
- - Alpha: 0.4202
193
  - Loss: 0.0000
194
 
195
  ### Latest 5 Epochs
196
 
197
- - **Epoch 46**: Train 60.37%, Test 0.00%, α=0.4152, Loss=1.2332
198
- - **Epoch 47**: Train 60.45%, Test 0.00%, α=0.4208, Loss=1.1747
199
- - **Epoch 48**: Train 61.04%, Test 0.00%, α=0.4188, Loss=1.1561
200
- - **Epoch 49**: Train 62.06%, Test 0.00%, α=0.4216, Loss=1.1769
201
- - **Epoch 50**: Train 62.17%, Test 57.53%, α=0.4202, Loss=1.1507
202
 
203
  ### Training Milestones
204
  - 🎯 **50% Accuracy** reached at epoch 35
 
205
  - 📊 **α ≥ 0.40** reached at epoch 9
 
206
 
207
  ---
208
 
 
36
 
37
  🚧 **Training in Progress** 🚧
38
 
39
+ Current Status: Epoch 100/200
40
 
41
  ---
42
 
 
46
  |--------|-------|
47
  | **Best Test Accuracy** | **69.08%** |
48
  | **Best Epoch** | 190 |
49
+ | **Current Train Accuracy** | 74.44% |
50
+ | **Current Test Accuracy** | 64.35% |
51
+ | **Current α (Cantor param)** | 0.4395 |
52
  | **Total Parameters** | 198,392,937 |
53
+ | **Training Time** | 0:54:05 |
54
 
55
  ### All Training Runs
56
 
57
  | Timestamp | Status | Best Epoch | Test Acc | Train Acc | α |
58
  |-----------|--------|------------|----------|-----------|---|
59
+ | `20251010_100047` | 🔄 | 190 | **69.08%** | 74.44% | 0.4395 |
60
 
61
  ### Comparison to State-of-the-Art
62
 
 
187
 
188
  ### Best Checkpoint
189
  - Epoch: 190
190
+ - Train Acc: 74.44%
191
  - Test Acc: 69.08%
192
+ - Alpha: 0.4395
193
  - Loss: 0.0000
194
 
195
  ### Latest 5 Epochs
196
 
197
+ - **Epoch 96**: Train 74.36%, Test 0.00%, α=0.4389, Loss=0.7256
198
+ - **Epoch 97**: Train 76.86%, Test 0.00%, α=0.4412, Loss=0.7426
199
+ - **Epoch 98**: Train 75.64%, Test 0.00%, α=0.4385, Loss=0.7240
200
+ - **Epoch 99**: Train 75.67%, Test 0.00%, α=0.4385, Loss=0.7287
201
+ - **Epoch 100**: Train 74.44%, Test 64.35%, α=0.4395, Loss=0.7165
202
 
203
  ### Training Milestones
204
  - 🎯 **50% Accuracy** reached at epoch 35
205
+ - 🎯 **60% Accuracy** reached at epoch 60
206
  - 📊 **α ≥ 0.40** reached at epoch 9
207
+ - 📊 **α ≥ 0.44** (near triadic equilibrium) at epoch 91
208
 
209
  ---
210