
=====================
Starting a PyAMFF job
=====================

    0.02s: Reading inputs
             Fingerprints used:
             Type:  BP
             Li:   2 G1s   2 G2s
    0.03s: Processing training data
             Number of training images: 69
    0.20s: Calculating fingerprints
    9.25s: Defining machine-learning model
             Model type: neural_network
             Model structure: 2
             Creating model from saved potential
             Energy coefficient: 1.000000
             Force coefficent:   0.050000
             Energy tolerance:   0.000100
             Force tolerance:    0.010000
             Loss tolerance:     0.023853
             Parallelization setup:
               Number of processes:           2
               Total number of batches:       2
               Number of batches per process: 1
    9.26s: Partitioning data
    9.59s: Training started
             Epoch    LossValue   EnergyRMSE    ForceRMSE
           0     0.561799     0.560296     0.183639
           1     0.094069     0.059778     0.324825
           2     0.086703     0.052490     0.308619
           3     0.084014     0.051708     0.296127
           4     0.071153     0.049070     0.230429
           5     0.053105     0.039920     0.156619
           6     0.033468     0.016405     0.130457
           7     0.032691     0.014726     0.130524
           8     0.032548     0.014053     0.131295
           9     0.032483     0.013761     0.131590
          10     0.032166     0.013278     0.131024
          11     0.030759     0.011946     0.126762
          12     0.028929     0.011157     0.119364
          13     0.027067     0.011446     0.109690
          14     0.026037     0.011400     0.104687
          15     0.025791     0.011785     0.102592
          16     0.025748     0.011845     0.102244
          17     0.025249     0.011770     0.099898
          18     0.025102     0.009074     0.104670
          19     0.024695     0.010381     0.100208
          20     0.024401     0.010304     0.098919
          21     0.024356     0.009854     0.099608
          22     0.024349     0.009887     0.099514
          23     0.024344     0.009888     0.099484
          24     0.024321     0.009869     0.099408
          25     0.024249     0.009816     0.099160
          26     0.024074     0.009761     0.098417
          27     0.025009     0.011701     0.098849
          28     0.023800     0.009670     0.097256
          29     0.023609     0.009654     0.096351
          30     0.063723     0.059380     0.103412
          31     0.023500     0.009137     0.096826
          32     0.023787     0.010798     0.094785
          33     0.023341     0.009229     0.095878
          34     0.023301     0.009133     0.095866
          35     0.023090     0.008875     0.095328
          36     0.022900     0.009163     0.093858
          37     0.022779     0.009074     0.093437
          38     0.022619     0.009407     0.091994
          39     0.022544     0.009158     0.092126
          40     0.022443     0.008998     0.091946
          41     0.022493     0.009570     0.091035
          42     0.022216     0.008290     0.092175
          43     0.022154     0.008283     0.091893
          44     0.022765     0.010540     0.090239
          45     0.022064     0.008198     0.091609
          46     0.022009     0.008159     0.091414
          47     0.026216     0.016967     0.089373
          48     0.021967     0.008072     0.091366
          49     0.021932     0.008062     0.091217
             Max Epoch Reached
   20.25s: Training done, time used: 10.66s
