{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.31612223393045313,
  "eval_steps": 10,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01053740779768177,
      "grad_norm": 3.3616116046905518,
      "learning_rate": 4.982437653670531e-05,
      "loss": 1.7881,
      "step": 10
    },
    {
      "epoch": 0.01053740779768177,
      "eval_loss": 0.6833231449127197,
      "eval_runtime": 13.3064,
      "eval_samples_per_second": 36.073,
      "eval_steps_per_second": 2.255,
      "step": 10
    },
    {
      "epoch": 0.02107481559536354,
      "grad_norm": 1.3658663034439087,
      "learning_rate": 4.964875307341061e-05,
      "loss": 0.5571,
      "step": 20
    },
    {
      "epoch": 0.02107481559536354,
      "eval_loss": 0.5293903350830078,
      "eval_runtime": 13.4286,
      "eval_samples_per_second": 35.745,
      "eval_steps_per_second": 2.234,
      "step": 20
    },
    {
      "epoch": 0.03161222339304531,
      "grad_norm": 1.0748717784881592,
      "learning_rate": 4.947312961011591e-05,
      "loss": 0.4482,
      "step": 30
    },
    {
      "epoch": 0.03161222339304531,
      "eval_loss": 0.47912800312042236,
      "eval_runtime": 13.4918,
      "eval_samples_per_second": 35.577,
      "eval_steps_per_second": 2.224,
      "step": 30
    },
    {
      "epoch": 0.04214963119072708,
      "grad_norm": 0.890529215335846,
      "learning_rate": 4.929750614682122e-05,
      "loss": 0.3722,
      "step": 40
    },
    {
      "epoch": 0.04214963119072708,
      "eval_loss": 0.44374603033065796,
      "eval_runtime": 13.5807,
      "eval_samples_per_second": 35.344,
      "eval_steps_per_second": 2.209,
      "step": 40
    },
    {
      "epoch": 0.05268703898840885,
      "grad_norm": 0.8233364224433899,
      "learning_rate": 4.9121882683526524e-05,
      "loss": 0.3534,
      "step": 50
    },
    {
      "epoch": 0.05268703898840885,
      "eval_loss": 0.4318523108959198,
      "eval_runtime": 13.6096,
      "eval_samples_per_second": 35.269,
      "eval_steps_per_second": 2.204,
      "step": 50
    },
    {
      "epoch": 0.06322444678609063,
      "grad_norm": 0.7144497036933899,
      "learning_rate": 4.894625922023183e-05,
      "loss": 0.3512,
      "step": 60
    },
    {
      "epoch": 0.06322444678609063,
      "eval_loss": 0.41558387875556946,
      "eval_runtime": 13.6488,
      "eval_samples_per_second": 35.168,
      "eval_steps_per_second": 2.198,
      "step": 60
    },
    {
      "epoch": 0.0737618545837724,
      "grad_norm": 0.6796255707740784,
      "learning_rate": 4.877063575693713e-05,
      "loss": 0.3588,
      "step": 70
    },
    {
      "epoch": 0.0737618545837724,
      "eval_loss": 0.4085235297679901,
      "eval_runtime": 13.6512,
      "eval_samples_per_second": 35.162,
      "eval_steps_per_second": 2.198,
      "step": 70
    },
    {
      "epoch": 0.08429926238145416,
      "grad_norm": 0.6846384406089783,
      "learning_rate": 4.8595012293642434e-05,
      "loss": 0.3504,
      "step": 80
    },
    {
      "epoch": 0.08429926238145416,
      "eval_loss": 0.3993188142776489,
      "eval_runtime": 13.6377,
      "eval_samples_per_second": 35.197,
      "eval_steps_per_second": 2.2,
      "step": 80
    },
    {
      "epoch": 0.09483667017913593,
      "grad_norm": 0.7391332983970642,
      "learning_rate": 4.841938883034774e-05,
      "loss": 0.3299,
      "step": 90
    },
    {
      "epoch": 0.09483667017913593,
      "eval_loss": 0.3922707140445709,
      "eval_runtime": 13.6059,
      "eval_samples_per_second": 35.279,
      "eval_steps_per_second": 2.205,
      "step": 90
    },
    {
      "epoch": 0.1053740779768177,
      "grad_norm": 0.6717132925987244,
      "learning_rate": 4.824376536705304e-05,
      "loss": 0.3358,
      "step": 100
    },
    {
      "epoch": 0.1053740779768177,
      "eval_loss": 0.390600323677063,
      "eval_runtime": 13.6022,
      "eval_samples_per_second": 35.288,
      "eval_steps_per_second": 2.206,
      "step": 100
    },
    {
      "epoch": 0.11591148577449947,
      "grad_norm": 0.6522348523139954,
      "learning_rate": 4.8068141903758344e-05,
      "loss": 0.311,
      "step": 110
    },
    {
      "epoch": 0.11591148577449947,
      "eval_loss": 0.3844388425350189,
      "eval_runtime": 13.5921,
      "eval_samples_per_second": 35.315,
      "eval_steps_per_second": 2.207,
      "step": 110
    },
    {
      "epoch": 0.12644889357218125,
      "grad_norm": 0.5558998584747314,
      "learning_rate": 4.789251844046364e-05,
      "loss": 0.3161,
      "step": 120
    },
    {
      "epoch": 0.12644889357218125,
      "eval_loss": 0.3852270245552063,
      "eval_runtime": 13.5961,
      "eval_samples_per_second": 35.304,
      "eval_steps_per_second": 2.207,
      "step": 120
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 0.639998197555542,
      "learning_rate": 4.7716894977168955e-05,
      "loss": 0.3037,
      "step": 130
    },
    {
      "epoch": 0.136986301369863,
      "eval_loss": 0.3841981887817383,
      "eval_runtime": 13.6057,
      "eval_samples_per_second": 35.279,
      "eval_steps_per_second": 2.205,
      "step": 130
    },
    {
      "epoch": 0.1475237091675448,
      "grad_norm": 0.583459198474884,
      "learning_rate": 4.754127151387426e-05,
      "loss": 0.3232,
      "step": 140
    },
    {
      "epoch": 0.1475237091675448,
      "eval_loss": 0.3742731213569641,
      "eval_runtime": 13.5955,
      "eval_samples_per_second": 35.306,
      "eval_steps_per_second": 2.207,
      "step": 140
    },
    {
      "epoch": 0.15806111696522657,
      "grad_norm": 0.5834677219390869,
      "learning_rate": 4.736564805057956e-05,
      "loss": 0.317,
      "step": 150
    },
    {
      "epoch": 0.15806111696522657,
      "eval_loss": 0.3765258193016052,
      "eval_runtime": 13.5995,
      "eval_samples_per_second": 35.295,
      "eval_steps_per_second": 2.206,
      "step": 150
    },
    {
      "epoch": 0.16859852476290832,
      "grad_norm": 0.5975239872932434,
      "learning_rate": 4.7190024587284866e-05,
      "loss": 0.2987,
      "step": 160
    },
    {
      "epoch": 0.16859852476290832,
      "eval_loss": 0.37060925364494324,
      "eval_runtime": 13.5971,
      "eval_samples_per_second": 35.302,
      "eval_steps_per_second": 2.206,
      "step": 160
    },
    {
      "epoch": 0.1791359325605901,
      "grad_norm": 0.6860706806182861,
      "learning_rate": 4.7014401123990165e-05,
      "loss": 0.3166,
      "step": 170
    },
    {
      "epoch": 0.1791359325605901,
      "eval_loss": 0.37034350633621216,
      "eval_runtime": 13.5923,
      "eval_samples_per_second": 35.314,
      "eval_steps_per_second": 2.207,
      "step": 170
    },
    {
      "epoch": 0.18967334035827185,
      "grad_norm": 0.7161134481430054,
      "learning_rate": 4.683877766069547e-05,
      "loss": 0.3036,
      "step": 180
    },
    {
      "epoch": 0.18967334035827185,
      "eval_loss": 0.3633898198604584,
      "eval_runtime": 13.6104,
      "eval_samples_per_second": 35.267,
      "eval_steps_per_second": 2.204,
      "step": 180
    },
    {
      "epoch": 0.20021074815595363,
      "grad_norm": 0.8212491273880005,
      "learning_rate": 4.6663154197400776e-05,
      "loss": 0.3023,
      "step": 190
    },
    {
      "epoch": 0.20021074815595363,
      "eval_loss": 0.36356136202812195,
      "eval_runtime": 13.5967,
      "eval_samples_per_second": 35.303,
      "eval_steps_per_second": 2.206,
      "step": 190
    },
    {
      "epoch": 0.2107481559536354,
      "grad_norm": 0.5965659022331238,
      "learning_rate": 4.6487530734106075e-05,
      "loss": 0.2999,
      "step": 200
    },
    {
      "epoch": 0.2107481559536354,
      "eval_loss": 0.3622604310512543,
      "eval_runtime": 13.5997,
      "eval_samples_per_second": 35.295,
      "eval_steps_per_second": 2.206,
      "step": 200
    },
    {
      "epoch": 0.22128556375131717,
      "grad_norm": 0.6638055443763733,
      "learning_rate": 4.631190727081138e-05,
      "loss": 0.2924,
      "step": 210
    },
    {
      "epoch": 0.22128556375131717,
      "eval_loss": 0.36028483510017395,
      "eval_runtime": 13.6089,
      "eval_samples_per_second": 35.271,
      "eval_steps_per_second": 2.204,
      "step": 210
    },
    {
      "epoch": 0.23182297154899895,
      "grad_norm": 0.4681139886379242,
      "learning_rate": 4.6136283807516686e-05,
      "loss": 0.3012,
      "step": 220
    },
    {
      "epoch": 0.23182297154899895,
      "eval_loss": 0.3585042357444763,
      "eval_runtime": 13.6099,
      "eval_samples_per_second": 35.269,
      "eval_steps_per_second": 2.204,
      "step": 220
    },
    {
      "epoch": 0.24236037934668073,
      "grad_norm": 0.6495727300643921,
      "learning_rate": 4.596066034422199e-05,
      "loss": 0.2884,
      "step": 230
    },
    {
      "epoch": 0.24236037934668073,
      "eval_loss": 0.36549657583236694,
      "eval_runtime": 13.6085,
      "eval_samples_per_second": 35.272,
      "eval_steps_per_second": 2.205,
      "step": 230
    },
    {
      "epoch": 0.2528977871443625,
      "grad_norm": 0.4928750991821289,
      "learning_rate": 4.57850368809273e-05,
      "loss": 0.2838,
      "step": 240
    },
    {
      "epoch": 0.2528977871443625,
      "eval_loss": 0.35502439737319946,
      "eval_runtime": 13.6002,
      "eval_samples_per_second": 35.293,
      "eval_steps_per_second": 2.206,
      "step": 240
    },
    {
      "epoch": 0.26343519494204426,
      "grad_norm": 0.6839736700057983,
      "learning_rate": 4.5609413417632596e-05,
      "loss": 0.2861,
      "step": 250
    },
    {
      "epoch": 0.26343519494204426,
      "eval_loss": 0.3560730516910553,
      "eval_runtime": 13.6056,
      "eval_samples_per_second": 35.28,
      "eval_steps_per_second": 2.205,
      "step": 250
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.5583881735801697,
      "learning_rate": 4.54337899543379e-05,
      "loss": 0.3019,
      "step": 260
    },
    {
      "epoch": 0.273972602739726,
      "eval_loss": 0.3566754162311554,
      "eval_runtime": 13.5986,
      "eval_samples_per_second": 35.298,
      "eval_steps_per_second": 2.206,
      "step": 260
    },
    {
      "epoch": 0.2845100105374078,
      "grad_norm": 0.5884770750999451,
      "learning_rate": 4.525816649104321e-05,
      "loss": 0.3112,
      "step": 270
    },
    {
      "epoch": 0.2845100105374078,
      "eval_loss": 0.3552027940750122,
      "eval_runtime": 13.6456,
      "eval_samples_per_second": 35.176,
      "eval_steps_per_second": 2.199,
      "step": 270
    },
    {
      "epoch": 0.2950474183350896,
      "grad_norm": 0.540367603302002,
      "learning_rate": 4.5082543027748506e-05,
      "loss": 0.2805,
      "step": 280
    },
    {
      "epoch": 0.2950474183350896,
      "eval_loss": 0.3551066815853119,
      "eval_runtime": 13.59,
      "eval_samples_per_second": 35.32,
      "eval_steps_per_second": 2.208,
      "step": 280
    },
    {
      "epoch": 0.3055848261327713,
      "grad_norm": 0.4952965974807739,
      "learning_rate": 4.490691956445381e-05,
      "loss": 0.318,
      "step": 290
    },
    {
      "epoch": 0.3055848261327713,
      "eval_loss": 0.35322481393814087,
      "eval_runtime": 13.5781,
      "eval_samples_per_second": 35.351,
      "eval_steps_per_second": 2.209,
      "step": 290
    },
    {
      "epoch": 0.31612223393045313,
      "grad_norm": 0.48861801624298096,
      "learning_rate": 4.473129610115912e-05,
      "loss": 0.2878,
      "step": 300
    },
    {
      "epoch": 0.31612223393045313,
      "eval_loss": 0.3530054986476898,
      "eval_runtime": 13.5721,
      "eval_samples_per_second": 35.367,
      "eval_steps_per_second": 2.21,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 2847,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.584170488771379e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}