{
  "best_metric": 0.0446239709854126,
  "best_model_checkpoint": "./xlam_lora_new_ete_over_size_3epoch_multi_full_eng/checkpoint-684",
  "epoch": 1.3293653203765563,
  "eval_steps": 171,
  "global_step": 684,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.019435165502581234,
      "grad_norm": 0.2028260976076126,
      "learning_rate": 3.205128205128205e-06,
      "loss": 0.0883,
      "step": 10
    },
    {
      "epoch": 0.03887033100516247,
      "grad_norm": 0.16199472546577454,
      "learning_rate": 6.41025641025641e-06,
      "loss": 0.0862,
      "step": 20
    },
    {
      "epoch": 0.0583054965077437,
      "grad_norm": 0.10014229267835617,
      "learning_rate": 9.615384615384616e-06,
      "loss": 0.0785,
      "step": 30
    },
    {
      "epoch": 0.07774066201032494,
      "grad_norm": 0.07943801581859589,
      "learning_rate": 1.282051282051282e-05,
      "loss": 0.0772,
      "step": 40
    },
    {
      "epoch": 0.09717582751290617,
      "grad_norm": 0.11369317024946213,
      "learning_rate": 1.602564102564103e-05,
      "loss": 0.0649,
      "step": 50
    },
    {
      "epoch": 0.1166109930154874,
      "grad_norm": 0.10264527052640915,
      "learning_rate": 1.923076923076923e-05,
      "loss": 0.0686,
      "step": 60
    },
    {
      "epoch": 0.13604615851806864,
      "grad_norm": 0.08583803474903107,
      "learning_rate": 2.2435897435897437e-05,
      "loss": 0.0657,
      "step": 70
    },
    {
      "epoch": 0.15548132402064987,
      "grad_norm": 0.09326862543821335,
      "learning_rate": 2.4999884878368972e-05,
      "loss": 0.0605,
      "step": 80
    },
    {
      "epoch": 0.1749164895232311,
      "grad_norm": 0.09622487425804138,
      "learning_rate": 2.4995855843928913e-05,
      "loss": 0.0617,
      "step": 90
    },
    {
      "epoch": 0.19435165502581234,
      "grad_norm": 0.10855123400688171,
      "learning_rate": 2.4986072848240374e-05,
      "loss": 0.0548,
      "step": 100
    },
    {
      "epoch": 0.21378682052839357,
      "grad_norm": 0.12510105967521667,
      "learning_rate": 2.4970540396075083e-05,
      "loss": 0.0545,
      "step": 110
    },
    {
      "epoch": 0.2332219860309748,
      "grad_norm": 0.11628145724534988,
      "learning_rate": 2.494926563965445e-05,
      "loss": 0.0601,
      "step": 120
    },
    {
      "epoch": 0.252657151533556,
      "grad_norm": 0.12050613015890121,
      "learning_rate": 2.4922258375356232e-05,
      "loss": 0.0585,
      "step": 130
    },
    {
      "epoch": 0.2720923170361373,
      "grad_norm": 0.08949285745620728,
      "learning_rate": 2.488953103920354e-05,
      "loss": 0.0477,
      "step": 140
    },
    {
      "epoch": 0.2915274825387185,
      "grad_norm": 0.14706853032112122,
      "learning_rate": 2.4851098701138466e-05,
      "loss": 0.0555,
      "step": 150
    },
    {
      "epoch": 0.31096264804129975,
      "grad_norm": 0.13029147684574127,
      "learning_rate": 2.4806979058082832e-05,
      "loss": 0.0493,
      "step": 160
    },
    {
      "epoch": 0.330397813543881,
      "grad_norm": 0.1321103274822235,
      "learning_rate": 2.475719242578929e-05,
      "loss": 0.0547,
      "step": 170
    },
    {
      "epoch": 0.3323413300941391,
      "eval_loss": 0.054034121334552765,
      "eval_runtime": 172.2024,
      "eval_samples_per_second": 5.029,
      "eval_steps_per_second": 5.029,
      "step": 171
    },
    {
      "epoch": 0.3498329790464622,
      "grad_norm": 0.14103983342647552,
      "learning_rate": 2.470176172948652e-05,
      "loss": 0.0522,
      "step": 180
    },
    {
      "epoch": 0.36926814454904344,
      "grad_norm": 0.14120739698410034,
      "learning_rate": 2.4640712493322894e-05,
      "loss": 0.0501,
      "step": 190
    },
    {
      "epoch": 0.3887033100516247,
      "grad_norm": 0.1301490068435669,
      "learning_rate": 2.4574072828613354e-05,
      "loss": 0.0492,
      "step": 200
    },
    {
      "epoch": 0.4081384755542059,
      "grad_norm": 0.1606156975030899,
      "learning_rate": 2.450187342089502e-05,
      "loss": 0.0488,
      "step": 210
    },
    {
      "epoch": 0.42757364105678713,
      "grad_norm": 0.1623048037290573,
      "learning_rate": 2.442414751579744e-05,
      "loss": 0.0459,
      "step": 220
    },
    {
      "epoch": 0.44700880655936837,
      "grad_norm": 0.1424696147441864,
      "learning_rate": 2.434093090373396e-05,
      "loss": 0.0441,
      "step": 230
    },
    {
      "epoch": 0.4664439720619496,
      "grad_norm": 0.13980570435523987,
      "learning_rate": 2.4252261903421375e-05,
      "loss": 0.0483,
      "step": 240
    },
    {
      "epoch": 0.4858791375645308,
      "grad_norm": 0.17693087458610535,
      "learning_rate": 2.415818134423528e-05,
      "loss": 0.0451,
      "step": 250
    },
    {
      "epoch": 0.505314303067112,
      "grad_norm": 0.18210634589195251,
      "learning_rate": 2.405873254740942e-05,
      "loss": 0.0466,
      "step": 260
    },
    {
      "epoch": 0.5247494685696933,
      "grad_norm": 0.1527709811925888,
      "learning_rate": 2.395396130608756e-05,
      "loss": 0.0488,
      "step": 270
    },
    {
      "epoch": 0.5441846340722746,
      "grad_norm": 0.15795762836933136,
      "learning_rate": 2.3843915864237143e-05,
      "loss": 0.0448,
      "step": 280
    },
    {
      "epoch": 0.5636197995748558,
      "grad_norm": 0.15495383739471436,
      "learning_rate": 2.3728646894434413e-05,
      "loss": 0.047,
      "step": 290
    },
    {
      "epoch": 0.583054965077437,
      "grad_norm": 0.17630279064178467,
      "learning_rate": 2.3608207474531236e-05,
      "loss": 0.0429,
      "step": 300
    },
    {
      "epoch": 0.6024901305800182,
      "grad_norm": 0.17523537576198578,
      "learning_rate": 2.3482653063214356e-05,
      "loss": 0.0473,
      "step": 310
    },
    {
      "epoch": 0.6219252960825995,
      "grad_norm": 0.1995943933725357,
      "learning_rate": 2.3352041474468373e-05,
      "loss": 0.0392,
      "step": 320
    },
    {
      "epoch": 0.6413604615851807,
      "grad_norm": 0.1683543622493744,
      "learning_rate": 2.3216432850954155e-05,
      "loss": 0.0438,
      "step": 330
    },
    {
      "epoch": 0.660795627087762,
      "grad_norm": 0.1374560445547104,
      "learning_rate": 2.307588963631497e-05,
      "loss": 0.0388,
      "step": 340
    },
    {
      "epoch": 0.6646826601882782,
      "eval_loss": 0.048522137105464935,
      "eval_runtime": 174.8794,
      "eval_samples_per_second": 4.952,
      "eval_steps_per_second": 4.952,
      "step": 342
    },
    {
      "epoch": 0.6802307925903431,
      "grad_norm": 0.166055366396904,
      "learning_rate": 2.293047654642309e-05,
      "loss": 0.0469,
      "step": 350
    },
    {
      "epoch": 0.6996659580929244,
      "grad_norm": 0.14119000732898712,
      "learning_rate": 2.2780260539580116e-05,
      "loss": 0.0424,
      "step": 360
    },
    {
      "epoch": 0.7191011235955056,
      "grad_norm": 0.23057888448238373,
      "learning_rate": 2.2625310785684688e-05,
      "loss": 0.0451,
      "step": 370
    },
    {
      "epoch": 0.7385362890980869,
      "grad_norm": 0.1304253786802292,
      "learning_rate": 2.2465698634381892e-05,
      "loss": 0.0434,
      "step": 380
    },
    {
      "epoch": 0.7579714546006681,
      "grad_norm": 0.17952455580234528,
      "learning_rate": 2.2301497582208884e-05,
      "loss": 0.0409,
      "step": 390
    },
    {
      "epoch": 0.7774066201032493,
      "grad_norm": 0.15560920536518097,
      "learning_rate": 2.2132783238751987e-05,
      "loss": 0.0465,
      "step": 400
    },
    {
      "epoch": 0.7968417856058305,
      "grad_norm": 0.12066332250833511,
      "learning_rate": 2.1959633291830785e-05,
      "loss": 0.0433,
      "step": 410
    },
    {
      "epoch": 0.8162769511084118,
      "grad_norm": 0.15932129323482513,
      "learning_rate": 2.1782127471725232e-05,
      "loss": 0.0458,
      "step": 420
    },
    {
      "epoch": 0.835712116610993,
      "grad_norm": 0.19025273621082306,
      "learning_rate": 2.160034751446231e-05,
      "loss": 0.0522,
      "step": 430
    },
    {
      "epoch": 0.8551472821135743,
      "grad_norm": 0.15156866610050201,
      "learning_rate": 2.1414377124179038e-05,
      "loss": 0.0433,
      "step": 440
    },
    {
      "epoch": 0.8745824476161554,
      "grad_norm": 0.1594618409872055,
      "learning_rate": 2.1224301934579293e-05,
      "loss": 0.0434,
      "step": 450
    },
    {
      "epoch": 0.8940176131187367,
      "grad_norm": 0.16077858209609985,
      "learning_rate": 2.1030209469502098e-05,
      "loss": 0.0426,
      "step": 460
    },
    {
      "epoch": 0.9134527786213179,
      "grad_norm": 0.15807421505451202,
      "learning_rate": 2.0832189102619543e-05,
      "loss": 0.0461,
      "step": 470
    },
    {
      "epoch": 0.9328879441238992,
      "grad_norm": 0.20585452020168304,
      "learning_rate": 2.0630332016282927e-05,
      "loss": 0.0429,
      "step": 480
    },
    {
      "epoch": 0.9523231096264804,
      "grad_norm": 0.1859339326620102,
      "learning_rate": 2.0424731159536083e-05,
      "loss": 0.0432,
      "step": 490
    },
    {
      "epoch": 0.9717582751290617,
      "grad_norm": 0.20674780011177063,
      "learning_rate": 2.021548120531516e-05,
      "loss": 0.0392,
      "step": 500
    },
    {
      "epoch": 0.9911934406316428,
      "grad_norm": 0.22314420342445374,
      "learning_rate": 2.0002678506854606e-05,
      "loss": 0.041,
      "step": 510
    },
    {
      "epoch": 0.9970239902824173,
      "eval_loss": 0.04610577970743179,
      "eval_runtime": 175.1913,
      "eval_samples_per_second": 4.943,
      "eval_steps_per_second": 4.943,
      "step": 513
    },
    {
      "epoch": 1.010628606134224,
      "grad_norm": 0.1707136183977127,
      "learning_rate": 1.9786421053319455e-05,
      "loss": 0.0468,
      "step": 520
    },
    {
      "epoch": 1.0300637716368053,
      "grad_norm": 0.18121393024921417,
      "learning_rate": 1.9566808424684284e-05,
      "loss": 0.0361,
      "step": 530
    },
    {
      "epoch": 1.0494989371393866,
      "grad_norm": 0.17815589904785156,
      "learning_rate": 1.9343941745879695e-05,
      "loss": 0.0418,
      "step": 540
    },
    {
      "epoch": 1.0689341026419679,
      "grad_norm": 0.17634443938732147,
      "learning_rate": 1.9117923640227314e-05,
      "loss": 0.0437,
      "step": 550
    },
    {
      "epoch": 1.088369268144549,
      "grad_norm": 0.18102432787418365,
      "learning_rate": 1.8888858182184925e-05,
      "loss": 0.0426,
      "step": 560
    },
    {
      "epoch": 1.1078044336471302,
      "grad_norm": 0.20596696436405182,
      "learning_rate": 1.865685084942331e-05,
      "loss": 0.0414,
      "step": 570
    },
    {
      "epoch": 1.1272395991497115,
      "grad_norm": 0.2145373523235321,
      "learning_rate": 1.8422008474257013e-05,
      "loss": 0.0354,
      "step": 580
    },
    {
      "epoch": 1.1466747646522928,
      "grad_norm": 0.2385258674621582,
      "learning_rate": 1.8184439194451326e-05,
      "loss": 0.0357,
      "step": 590
    },
    {
      "epoch": 1.166109930154874,
      "grad_norm": 0.23679479956626892,
      "learning_rate": 1.7944252403428097e-05,
      "loss": 0.041,
      "step": 600
    },
    {
      "epoch": 1.1855450956574551,
      "grad_norm": 0.1947854906320572,
      "learning_rate": 1.770155869989343e-05,
      "loss": 0.0407,
      "step": 610
    },
    {
      "epoch": 1.2049802611600364,
      "grad_norm": 0.25392264127731323,
      "learning_rate": 1.7456469836910334e-05,
      "loss": 0.0405,
      "step": 620
    },
    {
      "epoch": 1.2244154266626177,
      "grad_norm": 0.2636931240558624,
      "learning_rate": 1.7209098670439817e-05,
      "loss": 0.0442,
      "step": 630
    },
    {
      "epoch": 1.243850592165199,
      "grad_norm": 0.19380666315555573,
      "learning_rate": 1.695955910737419e-05,
      "loss": 0.0344,
      "step": 640
    },
    {
      "epoch": 1.26328575766778,
      "grad_norm": 0.2423335164785385,
      "learning_rate": 1.670796605308638e-05,
      "loss": 0.0415,
      "step": 650
    },
    {
      "epoch": 1.2827209231703613,
      "grad_norm": 0.20322546362876892,
      "learning_rate": 1.6454435358519524e-05,
      "loss": 0.0381,
      "step": 660
    },
    {
      "epoch": 1.3021560886729426,
      "grad_norm": 0.20570382475852966,
      "learning_rate": 1.6199083766841115e-05,
      "loss": 0.035,
      "step": 670
    },
    {
      "epoch": 1.321591254175524,
      "grad_norm": 0.23237545788288116,
      "learning_rate": 1.594202885968636e-05,
      "loss": 0.0447,
      "step": 680
    },
    {
      "epoch": 1.3293653203765563,
      "eval_loss": 0.0446239709854126,
      "eval_runtime": 174.4977,
      "eval_samples_per_second": 4.963,
      "eval_steps_per_second": 4.963,
      "step": 684
    }
  ],
  "logging_steps": 10,
  "max_steps": 1542,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 171,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.2403746980397056e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}