| { | |
| "model": "SNIP Scope top-k sparse autoencoder", | |
| "source_model": "SNIP-0.4M base final hidden layer", | |
| "parameters": 74112, | |
| "training_tokens": 180000, | |
| "heldout_tokens": 40000, | |
| "input_dimension": 96, | |
| "dictionary_features": 384, | |
| "top_k": 16, | |
| "heldout": { | |
| "reconstruction_mse": 0.02585437148809433, | |
| "explained_variance": 0.9740850101195055, | |
| "mean_active_features": 16.0, | |
| "median_active_features": 16.0, | |
| "dead_feature_fraction": 0.033854166666666664 | |
| }, | |
| "pca_16_control": { | |
| "reconstruction_mse": 0.298243910074234, | |
| "explained_variance": 0.7010568067061413 | |
| }, | |
| "training_history": [ | |
| { | |
| "training_step": 100, | |
| "training_loss": 0.18427926301956177, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 200, | |
| "training_loss": 0.09680552780628204, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 300, | |
| "training_loss": 0.0745527446269989, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 400, | |
| "training_loss": 0.0621606670320034, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 500, | |
| "training_loss": 0.051943834871053696, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 600, | |
| "training_loss": 0.048014383763074875, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 700, | |
| "training_loss": 0.04393930733203888, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 800, | |
| "training_loss": 0.04151527211070061, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 900, | |
| "training_loss": 0.03839843347668648, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 1000, | |
| "training_loss": 0.03772205859422684, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 1100, | |
| "training_loss": 0.03755463287234306, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 1200, | |
| "training_loss": 0.03328678011894226, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 1300, | |
| "training_loss": 0.03515448421239853, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 1400, | |
| "training_loss": 0.03331328555941582, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 1500, | |
| "training_loss": 0.03026575781404972, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 1600, | |
| "training_loss": 0.03202933445572853, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 1700, | |
| "training_loss": 0.030269039794802666, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 1800, | |
| "training_loss": 0.029401661828160286, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 1900, | |
| "training_loss": 0.028512846678495407, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 2000, | |
| "training_loss": 0.02790793403983116, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 2100, | |
| "training_loss": 0.029049385339021683, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 2200, | |
| "training_loss": 0.026964839547872543, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 2300, | |
| "training_loss": 0.026676125824451447, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 2400, | |
| "training_loss": 0.024650562554597855, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 2500, | |
| "training_loss": 0.025682823732495308, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 2600, | |
| "training_loss": 0.025776153430342674, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 2700, | |
| "training_loss": 0.02404068596661091, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 2800, | |
| "training_loss": 0.025123972445726395, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 2900, | |
| "training_loss": 0.025397324934601784, | |
| "batch_active_features": 16.0 | |
| }, | |
| { | |
| "training_step": 3000, | |
| "training_loss": 0.02425968647003174, | |
| "batch_active_features": 16.0 | |
| } | |
| ] | |
| } |