How to find a validation error depending on the number of eras on a small scale using h2o.grid in R

Question

How to find a validation error depending on the number of eras on a small scale using h2o.grid in R

I have a very noisy dataset with 2000 observations and 42 functions (financial data), and I'm doing binary classification. Here I set up the network using h2o.gridand providing a validation set. I have set epochs=1000, and I intend to stop training when the error in the misclassification does not improve at> = 1% for 5 scoring events ( stopping_rounds=5, stopping_tolerance=0.01). I am interested to know what is the value for epochs, which minimizes the verification error.

hyper_params = list(rho = c(0.9,0.95,0.99),
                 epsilon = 10^(c(-10, -8, -6, -4)),
                 hidden=list(c(64, 64)),
                 activation=c("Tanh", "Rectifier", "RectifierWithDropout"))
grid = h2o.grid("deeplearning", x = predictors, y = response,
                training_frame = tempTrain, validation_frame = tempValid,
                grid_id="h2oGrid10", hyper_params = hyper_params,
                adaptive_rate = TRUE, stopping_metric="misclassification",
                variable_importances = TRUE, epochs = 1000,
                stopping_rounds=5, stopping_tolerance=0.01, max_w2 = 20)

In accordance with this issue, the solution should be as follows:

gridErr = h2o.getGrid("h2oGrid10", sort_by="err", decreasing=FALSE)
best_model = h2o.getModel(gridErr@model_ids[[1]])
solution = rev(best_model@model$scoring_history$epochs)[1]

Where solution=1000. In any case, checking scoring_history, we observe the following result, which is rather ambiguous.

cbind(best_model@model$scoring_history$epochs,
+       best_model@model$scoring_history$validation_classification_error)
      [,1]      [,2]
 [1,]    0       NaN
 [2,]   10 0.4971347
 [3,]  160 0.4813754
 [4,]  320 0.4770774
 [5,]  490 0.4799427
 [6,]  660 0.4727794
 [7,]  840 0.4713467
 [8,] 1000 0.4727794
 [9,] 1000 0.4713467