configs.ja.json

{
 "<h1>Configurable Optimizer</h1>\n": "<h1>\u8a2d\u5b9a\u53ef\u80fd\u306a\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc</h1>\n",
 "<p> <a id=\"OptimizerConfigs\"></a></p>\n<h2>Optimizer Configurations</h2>\n": "<p><a id=\"OptimizerConfigs\"></a></p>\n<h2>\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc\u69cb\u6210</h2>\n",
 "<p>Beta values <span translate=no>_^_0_^_</span> for Adam </p>\n": "<p><span translate=no>_^_0_^_</span>\u30a2\u30c0\u30e0\u306e\u30d9\u30fc\u30bf\u5024</p>\n",
 "<p>Epsilon <span translate=no>_^_0_^_</span> for adam </p>\n": "<p>\u30a4\u30d7\u30b7\u30ed\u30f3\u30fb\u30d5\u30a9\u30fc\u30fb\u30a2\u30c0\u30e0 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Learning rate <span translate=no>_^_0_^_</span> </p>\n": "<p>\u5b66\u7fd2\u7387 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Model embedding size for Noam optimizer </p>\n": "<p>Noam \u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc\u306e\u30e2\u30c7\u30eb\u57cb\u3081\u8fbc\u307f\u30b5\u30a4\u30ba</p>\n",
 "<p>Momentum for SGD </p>\n": "<p>\u30b7\u30f3\u30ac\u30dd\u30fc\u30eb\u30c9\u30eb\u306e\u30e2\u30e1\u30f3\u30bf\u30e0</p>\n",
 "<p>Number of warmup optimizer steps </p>\n": "<p>\u30a6\u30a9\u30fc\u30e0\u30a2\u30c3\u30d7\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc\u306e\u30b9\u30c6\u30c3\u30d7\u6570</p>\n",
 "<p>Optimizer </p>\n": "<p>\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc</p>\n",
 "<p>Parameters to be optimized </p>\n": "<p>\u6700\u9069\u5316\u3059\u308b\u30d1\u30e9\u30e1\u30fc\u30bf\u30fc</p>\n",
 "<p>Total number of optimizer steps (for cosine decay) </p>\n": "<p>\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30b9\u30c6\u30c3\u30d7\u306e\u7dcf\u6570 (\u30b3\u30b5\u30a4\u30f3\u6e1b\u8870\u7528)</p>\n",
 "<p>Weight decay </p>\n": "<p>\u4f53\u91cd\u6e1b\u5c11</p>\n",
 "<p>Whether the adam update is optimized (different epsilon) </p>\n": "<p>adam\u30a2\u30c3\u30d7\u30c7\u30fc\u30c8\u304c\u6700\u9069\u5316\u3055\u308c\u3066\u3044\u308b\u304b\u3069\u3046\u304b (\u30a4\u30d7\u30b7\u30ed\u30f3\u304c\u7570\u306a\u308b)</p>\n",
 "<p>Whether to degenerate to SGD in AdaBelief </p>\n": "<p>AdabElief \u3067 SGD \u306b\u7e2e\u9000\u3055\u305b\u308b\u304b\u3069\u3046\u304b</p>\n",
 "<p>Whether to use AMSGrad </p>\n": "<p>\u30a2\u30e0\u30b9\u30b0\u30e9\u30fc\u30c9\u3092\u4f7f\u7528\u3059\u308b\u304b\u3069\u3046\u304b</p>\n",
 "<p>Whether to use Rectified Adam in AdaBelief </p>\n": "<p>AdabElief \u3067\u30ec\u30af\u30c6\u30a3\u30d5\u30a1\u30a4\u30c9\u30a2\u30c0\u30e0\u3092\u4f7f\u7528\u3059\u308b\u304b\u3069\u3046\u304b</p>\n",
 "<p>Whether weight decay is absolute or should be multiplied by learning rate </p>\n": "<p>\u6e1b\u91cf\u304c\u7d76\u5bfe\u4f53\u91cd\u306a\u306e\u304b\u3001\u305d\u308c\u3068\u3082\u5b66\u7fd2\u7387\u3067\u639b\u3051\u308b\u3079\u304d\u306a\u306e\u304b</p>\n",
 "<p>Whether weight decay is decoupled; i.e. weight decay is not added to gradients </p>\n": "<p>\u91cd\u307f\u6e1b\u8870\u304c\u5207\u308a\u96e2\u3055\u308c\u3066\u3044\u308b\u304b\u3069\u3046\u304b\u3001\u3064\u307e\u308a\u91cd\u307f\u6e1b\u8870\u304c\u52fe\u914d\u306b\u52a0\u3048\u3089\u308c\u306a\u3044\u304b\u3069\u3046\u304b</p>\n",
 "Configurable optimizer module": "\u8a2d\u5b9a\u53ef\u80fd\u306a\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30e2\u30b8\u30e5\u30fc\u30eb",
 "This implements a configurable module for optimizers.": "\u3053\u308c\u306b\u3088\u308a\u3001\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc\u7528\u306e\u8a2d\u5b9a\u53ef\u80fd\u306a\u30e2\u30b8\u30e5\u30fc\u30eb\u304c\u5b9f\u88c5\u3055\u308c\u307e\u3059\u3002"
}