{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8849382716049383,
  "eval_steps": 256,
  "global_step": 1792,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06320987654320988,
      "grad_norm": 0.04219071567058563,
      "learning_rate": 0.000248046875,
      "loss": 0.006440815050154924,
      "step": 128
    },
    {
      "epoch": 0.12641975308641976,
      "grad_norm": 0.04216855764389038,
      "learning_rate": 0.000498046875,
      "loss": 0.006011463236063719,
      "step": 256
    },
    {
      "epoch": 0.12641975308641976,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.005870252109428004,
      "eval_loss": 0.005870252109428004,
      "eval_mse_loss": 443.6981372368045,
      "step": 256
    },
    {
      "epoch": 0.12641975308641976,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.005870252109428004,
      "eval_loss": 0.005870252109428004,
      "eval_mse_loss": 443.6981372368045,
      "eval_runtime": 8.5982,
      "eval_samples_per_second": 304.482,
      "eval_steps_per_second": 4.768,
      "step": 256
    },
    {
      "epoch": 0.18962962962962962,
      "grad_norm": 0.04382074996829033,
      "learning_rate": 0.000748046875,
      "loss": 0.005682823713868856,
      "step": 384
    },
    {
      "epoch": 0.2528395061728395,
      "grad_norm": 0.04206819832324982,
      "learning_rate": 0.000998046875,
      "loss": 0.005469319876283407,
      "step": 512
    },
    {
      "epoch": 0.2528395061728395,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.005397265197754633,
      "eval_loss": 0.005397265197754633,
      "eval_mse_loss": 463.40619789681784,
      "step": 512
    },
    {
      "epoch": 0.2528395061728395,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.005397265197754633,
      "eval_loss": 0.005397265197754633,
      "eval_mse_loss": 463.40619789681784,
      "eval_runtime": 7.4659,
      "eval_samples_per_second": 350.662,
      "eval_steps_per_second": 5.492,
      "step": 512
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.040812306106090546,
      "learning_rate": 0.0009827157247249464,
      "loss": 0.005451996345072985,
      "step": 640
    },
    {
      "epoch": 0.37925925925925924,
      "grad_norm": 0.05150594562292099,
      "learning_rate": 0.0009315344337660421,
      "loss": 0.005260218400508165,
      "step": 768
    },
    {
      "epoch": 0.37925925925925924,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.005222608051376372,
      "eval_loss": 0.005222608051376372,
      "eval_mse_loss": 478.69413199075836,
      "step": 768
    },
    {
      "epoch": 0.37925925925925924,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.005222608051376372,
      "eval_loss": 0.005222608051376372,
      "eval_mse_loss": 478.69413199075836,
      "eval_runtime": 8.0676,
      "eval_samples_per_second": 324.508,
      "eval_steps_per_second": 5.082,
      "step": 768
    },
    {
      "epoch": 0.44246913580246916,
      "grad_norm": 0.0297068003565073,
      "learning_rate": 0.0008500491898731988,
      "loss": 0.005236003547906876,
      "step": 896
    },
    {
      "epoch": 0.505679012345679,
      "grad_norm": 0.03605964779853821,
      "learning_rate": 0.0007439821899385376,
      "loss": 0.005152056459337473,
      "step": 1024
    },
    {
      "epoch": 0.505679012345679,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.005151342339359406,
      "eval_loss": 0.005151342339359406,
      "eval_mse_loss": 487.98453800852707,
      "step": 1024
    },
    {
      "epoch": 0.505679012345679,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.005151342339359406,
      "eval_loss": 0.005151342339359406,
      "eval_mse_loss": 487.98453800852707,
      "eval_runtime": 8.1175,
      "eval_samples_per_second": 322.512,
      "eval_steps_per_second": 5.051,
      "step": 1024
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.03870987519621849,
      "learning_rate": 0.0006207818531897271,
      "loss": 0.005106513388454914,
      "step": 1152
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.024118751287460327,
      "learning_rate": 0.0004890997654891032,
      "loss": 0.005096105858683586,
      "step": 1280
    },
    {
      "epoch": 0.6320987654320988,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.005091924810918366,
      "eval_loss": 0.005091924810918366,
      "eval_mse_loss": 497.0737781059451,
      "step": 1280
    },
    {
      "epoch": 0.6320987654320988,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.005091924810918366,
      "eval_loss": 0.005091924810918366,
      "eval_mse_loss": 497.0737781059451,
      "eval_runtime": 8.4448,
      "eval_samples_per_second": 310.013,
      "eval_steps_per_second": 4.855,
      "step": 1280
    },
    {
      "epoch": 0.6953086419753086,
      "grad_norm": 0.02920917421579361,
      "learning_rate": 0.00035818313279679524,
      "loss": 0.005061750765889883,
      "step": 1408
    },
    {
      "epoch": 0.7585185185185185,
      "grad_norm": 0.018508030101656914,
      "learning_rate": 0.00023722540797531234,
      "loss": 0.005014664493501186,
      "step": 1536
    },
    {
      "epoch": 0.7585185185185185,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.00502042164571765,
      "eval_loss": 0.00502042164571765,
      "eval_mse_loss": 502.0919985887481,
      "step": 1536
    },
    {
      "epoch": 0.7585185185185185,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.00502042164571765,
      "eval_loss": 0.00502042164571765,
      "eval_mse_loss": 502.0919985887481,
      "eval_runtime": 7.5012,
      "eval_samples_per_second": 349.012,
      "eval_steps_per_second": 5.466,
      "step": 1536
    },
    {
      "epoch": 0.8217283950617283,
      "grad_norm": 0.020617935806512833,
      "learning_rate": 0.00013472069233656453,
      "loss": 0.004991861991584301,
      "step": 1664
    },
    {
      "epoch": 0.8849382716049383,
      "grad_norm": 0.016280537471175194,
      "learning_rate": 5.786724825584927e-05,
      "loss": 0.004958455916494131,
      "step": 1792
    },
    {
      "epoch": 0.8849382716049383,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.0049657613470605235,
      "eval_loss": 0.0049657613470605235,
      "eval_mse_loss": 505.7769038502763,
      "step": 1792
    },
    {
      "epoch": 0.8849382716049383,
      "eval_bleu": 0.0,
      "eval_cos_loss": 0.0049657613470605235,
      "eval_loss": 0.0049657613470605235,
      "eval_mse_loss": 505.7769038502763,
      "eval_runtime": 8.1016,
      "eval_samples_per_second": 323.148,
      "eval_steps_per_second": 5.061,
      "step": 1792
    }
  ],
  "logging_steps": 128,
  "max_steps": 2025,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 256,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}