{
  "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": 0.651349663734436,
      "learning_rate": 0.0006666666666666666,
      "loss": 4.8949,
      "step": 16
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.1445673555135727,
      "learning_rate": 0.0009999301905929286,
      "loss": 4.8663,
      "step": 32
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.1684003323316574,
      "learning_rate": 0.0009982557393033759,
      "loss": 4.9032,
      "step": 48
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.1190505176782608,
      "learning_rate": 0.0009943559569286732,
      "loss": 4.8437,
      "step": 64
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.127385675907135,
      "learning_rate": 0.0009882482608435923,
      "loss": 4.8599,
      "step": 80
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 0.1187027171254158,
      "learning_rate": 0.0009799599295015153,
      "loss": 4.9368,
      "step": 96
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 0.14755752682685852,
      "learning_rate": 0.000969527980602239,
      "loss": 4.8873,
      "step": 112
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 0.12241631001234055,
      "learning_rate": 0.0009569990057619413,
      "loss": 4.8978,
      "step": 128
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 0.24350175261497498,
      "learning_rate": 0.0009424289624237143,
      "loss": 4.9195,
      "step": 144
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 0.26752641797065735,
      "learning_rate": 0.0009258829239380381,
      "loss": 4.8751,
      "step": 160
    },
    {
      "epoch": 0.4536082474226804,
      "grad_norm": 0.1479790061712265,
      "learning_rate": 0.0009074347889294017,
      "loss": 4.8514,
      "step": 176
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 0.2047603875398636,
      "learning_rate": 0.0008871669512471068,
      "loss": 4.857,
      "step": 192
    },
    {
      "epoch": 0.5360824742268041,
      "grad_norm": 0.16178925335407257,
      "learning_rate": 0.0008651699319743347,
      "loss": 4.8986,
      "step": 208
    },
    {
      "epoch": 0.5773195876288659,
      "grad_norm": 0.14003640413284302,
      "learning_rate": 0.0008415419751390154,
      "loss": 4.8395,
      "step": 224
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 0.14736343920230865,
      "learning_rate": 0.0008163886089321493,
      "loss": 4.8982,
      "step": 240
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": 0.1361091136932373,
      "learning_rate": 0.0007898221743932888,
      "loss": 4.9129,
      "step": 256
    },
    {
      "epoch": 0.7010309278350515,
      "grad_norm": 0.1403878629207611,
      "learning_rate": 0.0007619613236681844,
      "loss": 4.8745,
      "step": 272
    },
    {
      "epoch": 0.7422680412371134,
      "grad_norm": 0.1756931096315384,
      "learning_rate": 0.000732930490079499,
      "loss": 4.9091,
      "step": 288
    },
    {
      "epoch": 0.7835051546391752,
      "grad_norm": 0.1545019894838333,
      "learning_rate": 0.0007028593323773818,
      "loss": 4.8666,
      "step": 304
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": 0.13788259029388428,
      "learning_rate": 0.0006718821556520151,
      "loss": 4.8873,
      "step": 320
    },
    {
      "epoch": 0.865979381443299,
      "grad_norm": 0.1487036943435669,
      "learning_rate": 0.000640137311494478,
      "loss": 4.8503,
      "step": 336
    },
    {
      "epoch": 0.9072164948453608,
      "grad_norm": 0.11844358593225479,
      "learning_rate": 0.0006077665800849568,
      "loss": 4.8911,
      "step": 352
    },
    {
      "epoch": 0.9484536082474226,
      "grad_norm": 0.14698012173175812,
      "learning_rate": 0.0005749145369680407,
      "loss": 4.8839,
      "step": 368
    },
    {
      "epoch": 0.9896907216494846,
      "grad_norm": 0.15790720283985138,
      "learning_rate": 0.0005417279073432449,
      "loss": 4.8374,
      "step": 384
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.08333557407549637,
      "eval_cap_loss": 1.7252829168567951,
      "eval_con_loss": 1.9740812087181918,
      "eval_loss": 3.699364125728607,
      "step": 388
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.08333557407549637,
      "eval_cap_loss": 1.7252829168567951,
      "eval_con_loss": 1.9740812087181918,
      "eval_loss": 3.699364125728607,
      "eval_runtime": 146.0914,
      "eval_samples_per_second": 21.226,
      "eval_steps_per_second": 2.656,
      "step": 388
    },
    {
      "epoch": 1.0309278350515463,
      "grad_norm": 0.2379327416419983,
      "learning_rate": 0.0005083549107546504,
      "loss": 4.8517,
      "step": 400
    },
    {
      "epoch": 1.0721649484536082,
      "grad_norm": 0.19742196798324585,
      "learning_rate": 0.00047494459910644044,
      "loss": 4.8684,
      "step": 416
    },
    {
      "epoch": 1.1134020618556701,
      "grad_norm": 0.16078642010688782,
      "learning_rate": 0.0004416461909609119,
      "loss": 4.8392,
      "step": 432
    },
    {
      "epoch": 1.1546391752577319,
      "grad_norm": 0.08572334796190262,
      "learning_rate": 0.00040860840509215494,
      "loss": 4.8405,
      "step": 448
    },
    {
      "epoch": 1.1958762886597938,
      "grad_norm": 0.1408192217350006,
      "learning_rate": 0.00037597879627190335,
      "loss": 4.9271,
      "step": 464
    },
    {
      "epoch": 1.2371134020618557,
      "grad_norm": 0.1493539661169052,
      "learning_rate": 0.00034390309625410685,
      "loss": 4.8443,
      "step": 480
    },
    {
      "epoch": 1.2783505154639174,
      "grad_norm": 0.1724126935005188,
      "learning_rate": 0.0003125245629015395,
      "loss": 4.8752,
      "step": 496
    },
    {
      "epoch": 1.3195876288659794,
      "grad_norm": 0.14615976810455322,
      "learning_rate": 0.00028198334036140874,
      "loss": 4.8231,
      "step": 512
    },
    {
      "epoch": 1.3608247422680413,
      "grad_norm": 0.13363386690616608,
      "learning_rate": 0.00025241583314757326,
      "loss": 4.8644,
      "step": 528
    },
    {
      "epoch": 1.402061855670103,
      "grad_norm": 0.17828340828418732,
      "learning_rate": 0.00022395409692487172,
      "loss": 4.8331,
      "step": 544
    },
    {
      "epoch": 1.443298969072165,
      "grad_norm": 0.1240629181265831,
      "learning_rate": 0.0001967252487164663,
      "loss": 4.8677,
      "step": 560
    },
    {
      "epoch": 1.4845360824742269,
      "grad_norm": 0.16822531819343567,
      "learning_rate": 0.00017085089916835921,
      "loss": 4.856,
      "step": 576
    },
    {
      "epoch": 1.5257731958762886,
      "grad_norm": 0.1542797088623047,
      "learning_rate": 0.00014644660940672628,
      "loss": 4.8461,
      "step": 592
    },
    {
      "epoch": 1.5670103092783505,
      "grad_norm": 0.12938471138477325,
      "learning_rate": 0.0001236213749138743,
      "loss": 4.8883,
      "step": 608
    },
    {
      "epoch": 1.6082474226804124,
      "grad_norm": 0.21958403289318085,
      "learning_rate": 0.0001024771387279585,
      "loss": 4.8829,
      "step": 624
    },
    {
      "epoch": 1.6494845360824741,
      "grad_norm": 0.13377727568149567,
      "learning_rate": 8.310833614062651e-05,
      "loss": 4.8772,
      "step": 640
    },
    {
      "epoch": 1.690721649484536,
      "grad_norm": 0.124494768679142,
      "learning_rate": 6.560147292608176e-05,
      "loss": 4.8758,
      "step": 656
    },
    {
      "epoch": 1.731958762886598,
      "grad_norm": 0.1438254714012146,
      "learning_rate": 5.003473898529609e-05,
      "loss": 4.8465,
      "step": 672
    },
    {
      "epoch": 1.7731958762886597,
      "grad_norm": 0.12780630588531494,
      "learning_rate": 3.6477659130931316e-05,
      "loss": 4.8857,
      "step": 688
    },
    {
      "epoch": 1.8144329896907216,
      "grad_norm": 0.12371128052473068,
      "learning_rate": 2.4990782572647973e-05,
      "loss": 4.9022,
      "step": 704
    },
    {
      "epoch": 1.8556701030927836,
      "grad_norm": 0.14497648179531097,
      "learning_rate": 1.5625412489637337e-05,
      "loss": 4.8414,
      "step": 720
    },
    {
      "epoch": 1.8969072164948453,
      "grad_norm": 0.13651418685913086,
      "learning_rate": 8.423376898168244e-06,
      "loss": 4.8314,
      "step": 736
    },
    {
      "epoch": 1.9381443298969072,
      "grad_norm": 0.1279928982257843,
      "learning_rate": 3.416841837512952e-06,
      "loss": 4.9007,
      "step": 752
    },
    {
      "epoch": 1.9793814432989691,
      "grad_norm": 0.13989858329296112,
      "learning_rate": 6.281677086071303e-07,
      "loss": 4.8226,
      "step": 768
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.08337060838622823,
      "eval_cap_loss": 1.716913080246178,
      "eval_con_loss": 1.969243642288385,
      "eval_loss": 3.6861567269895494,
      "step": 776
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.08337060838622823,
      "eval_cap_loss": 1.716913080246178,
      "eval_con_loss": 1.969243642288385,
      "eval_loss": 3.6861567269895494,
      "eval_runtime": 142.9819,
      "eval_samples_per_second": 21.688,
      "eval_steps_per_second": 2.714,
      "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
}