{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 776,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.09626785665750504,
      "learning_rate": 0.0006666666666666666,
      "loss": 4.9272,
      "step": 16
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.09776347130537033,
      "learning_rate": 0.0009997207818651273,
      "loss": 4.8403,
      "step": 32
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.18136683106422424,
      "learning_rate": 0.0009974889075442521,
      "loss": 4.9176,
      "step": 48
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.10246019065380096,
      "learning_rate": 0.0009930351269950143,
      "loss": 4.8586,
      "step": 64
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.26106250286102295,
      "learning_rate": 0.0009863793318825185,
      "loss": 4.8768,
      "step": 80
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 0.13016994297504425,
      "learning_rate": 0.0009775512486034563,
      "loss": 4.9537,
      "step": 96
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 0.14532029628753662,
      "learning_rate": 0.0009665903055208013,
      "loss": 4.9051,
      "step": 112
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 0.12766750156879425,
      "learning_rate": 0.0009535454568671704,
      "loss": 4.9145,
      "step": 128
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 0.16211313009262085,
      "learning_rate": 0.0009384749641033358,
      "loss": 4.9382,
      "step": 144
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 0.18606019020080566,
      "learning_rate": 0.0009214461357083985,
      "loss": 4.8932,
      "step": 160
    },
    {
      "epoch": 0.4536082474226804,
      "grad_norm": 0.10332559049129486,
      "learning_rate": 0.0009025350265637815,
      "loss": 4.8723,
      "step": 176
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 0.21772044897079468,
      "learning_rate": 0.0008818260982736661,
      "loss": 4.875,
      "step": 192
    },
    {
      "epoch": 0.5360824742268041,
      "grad_norm": 0.1752215325832367,
      "learning_rate": 0.0008594118419389648,
      "loss": 4.9184,
      "step": 208
    },
    {
      "epoch": 0.5773195876288659,
      "grad_norm": 0.15603622794151306,
      "learning_rate": 0.0008353923650696118,
      "loss": 4.8573,
      "step": 224
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 0.19524474442005157,
      "learning_rate": 0.0008098749444801224,
      "loss": 4.9145,
      "step": 240
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": 0.14055490493774414,
      "learning_rate": 0.0007829735471652976,
      "loss": 4.9301,
      "step": 256
    },
    {
      "epoch": 0.7010309278350515,
      "grad_norm": 0.1492496281862259,
      "learning_rate": 0.0007548083212959587,
      "loss": 4.8914,
      "step": 272
    },
    {
      "epoch": 0.7422680412371134,
      "grad_norm": 0.20217546820640564,
      "learning_rate": 0.0007255050596080509,
      "loss": 4.9268,
      "step": 288
    },
    {
      "epoch": 0.7835051546391752,
      "grad_norm": 0.12439503520727158,
      "learning_rate": 0.0006951946375817474,
      "loss": 4.8838,
      "step": 304
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": 0.15163038671016693,
      "learning_rate": 0.0006640124289197845,
      "loss": 4.9025,
      "step": 320
    },
    {
      "epoch": 0.865979381443299,
      "grad_norm": 0.15424683690071106,
      "learning_rate": 0.0006320977009356432,
      "loss": 4.867,
      "step": 336
    },
    {
      "epoch": 0.9072164948453608,
      "grad_norm": 0.12109530717134476,
      "learning_rate": 0.000599592992551918,
      "loss": 4.9068,
      "step": 352
    },
    {
      "epoch": 0.9484536082474226,
      "grad_norm": 0.15034383535385132,
      "learning_rate": 0.0005666434776868895,
      "loss": 4.8993,
      "step": 368
    },
    {
      "epoch": 0.9896907216494846,
      "grad_norm": 0.1772756278514862,
      "learning_rate": 0.0005333963168725609,
      "loss": 4.8522,
      "step": 384
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.08197595877772341,
      "eval_cap_loss": 1.7311131333567433,
      "eval_con_loss": 2.0061442756775727,
      "eval_loss": 3.737257410570518,
      "step": 388
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.08197595877772341,
      "eval_cap_loss": 1.7311131333567433,
      "eval_con_loss": 2.0061442756775727,
      "eval_loss": 3.737257410570518,
      "eval_runtime": 142.0128,
      "eval_samples_per_second": 21.836,
      "eval_steps_per_second": 2.732,
      "step": 388
    },
    {
      "epoch": 1.0309278350515463,
      "grad_norm": 0.1598144769668579,
      "learning_rate": 0.0005,
      "loss": 4.8689,
      "step": 400
    },
    {
      "epoch": 1.0721649484536082,
      "grad_norm": 0.15655860304832458,
      "learning_rate": 0.0004666036831274392,
      "loss": 4.8865,
      "step": 416
    },
    {
      "epoch": 1.1134020618556701,
      "grad_norm": 0.15307271480560303,
      "learning_rate": 0.00043335652231311076,
      "loss": 4.8548,
      "step": 432
    },
    {
      "epoch": 1.1546391752577319,
      "grad_norm": 0.07996341586112976,
      "learning_rate": 0.00040040700744808206,
      "loss": 4.8571,
      "step": 448
    },
    {
      "epoch": 1.1958762886597938,
      "grad_norm": 0.14137883484363556,
      "learning_rate": 0.000367902299064357,
      "loss": 4.9429,
      "step": 464
    },
    {
      "epoch": 1.2371134020618557,
      "grad_norm": 0.14231054484844208,
      "learning_rate": 0.00033598757108021545,
      "loss": 4.8607,
      "step": 480
    },
    {
      "epoch": 1.2783505154639174,
      "grad_norm": 0.1808304786682129,
      "learning_rate": 0.00030480536241825264,
      "loss": 4.8901,
      "step": 496
    },
    {
      "epoch": 1.3195876288659794,
      "grad_norm": 0.14347229897975922,
      "learning_rate": 0.000274494940391949,
      "loss": 4.839,
      "step": 512
    },
    {
      "epoch": 1.3608247422680413,
      "grad_norm": 0.12875933945178986,
      "learning_rate": 0.00024519167870404123,
      "loss": 4.8809,
      "step": 528
    },
    {
      "epoch": 1.402061855670103,
      "grad_norm": 0.17960529029369354,
      "learning_rate": 0.00021702645283470234,
      "loss": 4.848,
      "step": 544
    },
    {
      "epoch": 1.443298969072165,
      "grad_norm": 0.12456343322992325,
      "learning_rate": 0.00019012505551987762,
      "loss": 4.8828,
      "step": 560
    },
    {
      "epoch": 1.4845360824742269,
      "grad_norm": 0.1851247102022171,
      "learning_rate": 0.0001646076349303884,
      "loss": 4.8708,
      "step": 576
    },
    {
      "epoch": 1.5257731958762886,
      "grad_norm": 0.1590530276298523,
      "learning_rate": 0.00014058815806103543,
      "loss": 4.8611,
      "step": 592
    },
    {
      "epoch": 1.5670103092783505,
      "grad_norm": 0.13291551172733307,
      "learning_rate": 0.00011817390172633402,
      "loss": 4.9032,
      "step": 608
    },
    {
      "epoch": 1.6082474226804124,
      "grad_norm": 0.20336174964904785,
      "learning_rate": 9.746497343621857e-05,
      "loss": 4.8976,
      "step": 624
    },
    {
      "epoch": 1.6494845360824741,
      "grad_norm": 0.13562831282615662,
      "learning_rate": 7.85538642916015e-05,
      "loss": 4.8911,
      "step": 640
    },
    {
      "epoch": 1.690721649484536,
      "grad_norm": 0.13604836165905,
      "learning_rate": 6.152503589666425e-05,
      "loss": 4.8916,
      "step": 656
    },
    {
      "epoch": 1.731958762886598,
      "grad_norm": 0.15518011152744293,
      "learning_rate": 4.645454313282965e-05,
      "loss": 4.8618,
      "step": 672
    },
    {
      "epoch": 1.7731958762886597,
      "grad_norm": 0.11967703700065613,
      "learning_rate": 3.340969447919873e-05,
      "loss": 4.9006,
      "step": 688
    },
    {
      "epoch": 1.8144329896907216,
      "grad_norm": 0.13278520107269287,
      "learning_rate": 2.2448751396543787e-05,
      "loss": 4.9169,
      "step": 704
    },
    {
      "epoch": 1.8556701030927836,
      "grad_norm": 0.15354037284851074,
      "learning_rate": 1.3620668117481471e-05,
      "loss": 4.8556,
      "step": 720
    },
    {
      "epoch": 1.8969072164948453,
      "grad_norm": 0.14049023389816284,
      "learning_rate": 6.964873004985717e-06,
      "loss": 4.8451,
      "step": 736
    },
    {
      "epoch": 1.9381443298969072,
      "grad_norm": 0.13459183275699615,
      "learning_rate": 2.511092455747932e-06,
      "loss": 4.9148,
      "step": 752
    },
    {
      "epoch": 1.9793814432989691,
      "grad_norm": 0.1388990879058838,
      "learning_rate": 2.792181348726941e-07,
      "loss": 4.8364,
      "step": 768
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.083526303042587,
      "eval_cap_loss": 1.723467393327005,
      "eval_con_loss": 1.9934953146988583,
      "eval_loss": 3.7169627135561916,
      "step": 776
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.083526303042587,
      "eval_cap_loss": 1.723467393327005,
      "eval_con_loss": 1.9934953146988583,
      "eval_loss": 3.7169627135561916,
      "eval_runtime": 142.3121,
      "eval_samples_per_second": 21.79,
      "eval_steps_per_second": 2.726,
      "step": 776
    }
  ],
  "logging_steps": 16,
  "max_steps": 776,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null,
  "tau_value": 2.5431
}