AbstractPhil commited on
Commit
407f35b
Β·
verified Β·
1 Parent(s): 1de88e8

Update README - Run 20251012_221046

Browse files
Files changed (1) hide show
  1. README.md +12 -11
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  type: imagenet-1k
22
  metrics:
23
  - type: accuracy
24
- value: 64.86
25
  ---
26
 
27
  # David: Multi-Scale Feature Classifier
@@ -55,14 +55,15 @@ exist simultaneously in the same shared space with the correct checks and spacin
55
  ## Performance
56
 
57
  ### Best Results
58
- - **Validation Accuracy**: 64.86%
59
- - **Best Epoch**: 2
60
- - **Final Train Accuracy**: 62.79%
61
 
62
  ### Per-Scale Performance
63
- - **Scale 256**: 64.86%
64
- - **Scale 512**: 70.63%
65
- - **Scale 768**: 70.71%
 
66
 
67
 
68
  ## Usage
@@ -83,8 +84,8 @@ AbstractPhil/david-shared-space/
83
  β”‚ └── 20251012_221046/
84
  β”‚ β”œβ”€β”€ MODEL_SUMMARY.txt # 🎯 Human-readable performance summary
85
  β”‚ β”œβ”€β”€ training_history.json # πŸ“ˆ Epoch-by-epoch training curve
86
- β”‚ β”œβ”€β”€ best_model_acc64.86.safetensors # ⭐ Accuracy in filename!
87
- β”‚ β”œβ”€β”€ best_model_acc64.86_metadata.json
88
  β”‚ β”œβ”€β”€ final_model.safetensors
89
  β”‚ β”œβ”€β”€ checkpoint_epoch_X_accYY.YY.safetensors
90
  β”‚ β”œβ”€β”€ david_config.json
@@ -106,7 +107,7 @@ from huggingface_hub import hf_hub_download
106
  # Specify model variant and run
107
  model_name = "david_high_accuracy"
108
  run_id = "20251012_221046"
109
- accuracy = "64.86" # From MODELS_INDEX.json
110
 
111
  # Download config
112
  config_path = hf_hub_download(
@@ -215,4 +216,4 @@ Special thanks to Claude (Anthropic) for debugging assistance.
215
 
216
  ---
217
 
218
- *Generated on 2025-10-12 22:24:48*
 
21
  type: imagenet-1k
22
  metrics:
23
  - type: accuracy
24
+ value: 65.19
25
  ---
26
 
27
  # David: Multi-Scale Feature Classifier
 
55
  ## Performance
56
 
57
  ### Best Results
58
+ - **Validation Accuracy**: 65.19%
59
+ - **Best Epoch**: 3
60
+ - **Final Train Accuracy**: 63.58%
61
 
62
  ### Per-Scale Performance
63
+ - **Scale 256**: 65.19%
64
+ - **Scale 512**: 71.13%
65
+ - **Scale 768**: 72.20%
66
+ - **Scale 1024**: 71.39%
67
 
68
 
69
  ## Usage
 
84
  β”‚ └── 20251012_221046/
85
  β”‚ β”œβ”€β”€ MODEL_SUMMARY.txt # 🎯 Human-readable performance summary
86
  β”‚ β”œβ”€β”€ training_history.json # πŸ“ˆ Epoch-by-epoch training curve
87
+ β”‚ β”œβ”€β”€ best_model_acc65.19.safetensors # ⭐ Accuracy in filename!
88
+ β”‚ β”œβ”€β”€ best_model_acc65.19_metadata.json
89
  β”‚ β”œβ”€β”€ final_model.safetensors
90
  β”‚ β”œβ”€β”€ checkpoint_epoch_X_accYY.YY.safetensors
91
  β”‚ β”œβ”€β”€ david_config.json
 
107
  # Specify model variant and run
108
  model_name = "david_high_accuracy"
109
  run_id = "20251012_221046"
110
+ accuracy = "65.19" # From MODELS_INDEX.json
111
 
112
  # Download config
113
  config_path = hf_hub_download(
 
216
 
217
  ---
218
 
219
+ *Generated on 2025-10-12 22:29:28*