{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9850746268656714,
  "eval_steps": 500,
  "global_step": 525,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 5.9803857599927595,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 3.0422,
      "step": 10
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 2.217843129478048,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 2.4412,
      "step": 20
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 1.8496604433568333,
      "learning_rate": 9.99910461334869e-06,
      "loss": 2.1975,
      "step": 30
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 2.211490671202065,
      "learning_rate": 9.983195548029173e-06,
      "loss": 2.0619,
      "step": 40
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 1.4387489754724267,
      "learning_rate": 9.947461858764978e-06,
      "loss": 1.9967,
      "step": 50
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 1.8279329868726204,
      "learning_rate": 9.892045704727864e-06,
      "loss": 1.9387,
      "step": 60
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 1.6474902291327627,
      "learning_rate": 9.817167547748729e-06,
      "loss": 1.9172,
      "step": 70
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 1.657541170060607,
      "learning_rate": 9.723125275255325e-06,
      "loss": 1.8705,
      "step": 80
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 1.696974285018719,
      "learning_rate": 9.610293015188067e-06,
      "loss": 1.8323,
      "step": 90
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 1.5303782561090193,
      "learning_rate": 9.47911964760858e-06,
      "loss": 1.8171,
      "step": 100
    },
    {
      "epoch": 0.6254442075337597,
      "grad_norm": 1.5651172480757691,
      "learning_rate": 9.330127018922195e-06,
      "loss": 1.8148,
      "step": 110
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 1.5409210855141433,
      "learning_rate": 9.163907865818806e-06,
      "loss": 1.783,
      "step": 120
    },
    {
      "epoch": 0.7391613361762616,
      "grad_norm": 1.5363163924078007,
      "learning_rate": 8.98112345719122e-06,
      "loss": 1.7854,
      "step": 130
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 1.5576565905261832,
      "learning_rate": 8.782500963412156e-06,
      "loss": 1.7504,
      "step": 140
    },
    {
      "epoch": 0.8528784648187633,
      "grad_norm": 1.521719538010432,
      "learning_rate": 8.568830563435695e-06,
      "loss": 1.7504,
      "step": 150
    },
    {
      "epoch": 0.9097370291400142,
      "grad_norm": 1.5810495823530497,
      "learning_rate": 8.34096230123198e-06,
      "loss": 1.7645,
      "step": 160
    },
    {
      "epoch": 0.9665955934612651,
      "grad_norm": 1.41921208948242,
      "learning_rate": 8.099802704061194e-06,
      "loss": 1.7222,
      "step": 170
    },
    {
      "epoch": 1.023454157782516,
      "grad_norm": 2.303489781396609,
      "learning_rate": 7.846311176040331e-06,
      "loss": 1.6839,
      "step": 180
    },
    {
      "epoch": 1.080312722103767,
      "grad_norm": 1.7804848302086473,
      "learning_rate": 7.581496181350203e-06,
      "loss": 1.5172,
      "step": 190
    },
    {
      "epoch": 1.1371712864250179,
      "grad_norm": 1.5922077446873317,
      "learning_rate": 7.30641123226703e-06,
      "loss": 1.5129,
      "step": 200
    },
    {
      "epoch": 1.1940298507462686,
      "grad_norm": 1.600712736103309,
      "learning_rate": 7.022150697979385e-06,
      "loss": 1.5027,
      "step": 210
    },
    {
      "epoch": 1.2508884150675195,
      "grad_norm": 1.5405911558473169,
      "learning_rate": 6.7298454508642945e-06,
      "loss": 1.4733,
      "step": 220
    },
    {
      "epoch": 1.3077469793887704,
      "grad_norm": 1.6005186629850159,
      "learning_rate": 6.4306583675428435e-06,
      "loss": 1.5009,
      "step": 230
    },
    {
      "epoch": 1.3646055437100213,
      "grad_norm": 1.6179249599606138,
      "learning_rate": 6.125779702613471e-06,
      "loss": 1.4981,
      "step": 240
    },
    {
      "epoch": 1.4214641080312722,
      "grad_norm": 1.5595473213575002,
      "learning_rate": 5.816422353467562e-06,
      "loss": 1.4929,
      "step": 250
    },
    {
      "epoch": 1.4783226723525231,
      "grad_norm": 1.610680010605817,
      "learning_rate": 5.503817035025341e-06,
      "loss": 1.4962,
      "step": 260
    },
    {
      "epoch": 1.535181236673774,
      "grad_norm": 1.5401109765819234,
      "learning_rate": 5.189207383588353e-06,
      "loss": 1.4828,
      "step": 270
    },
    {
      "epoch": 1.5920398009950247,
      "grad_norm": 1.5437992683845965,
      "learning_rate": 4.873845009286879e-06,
      "loss": 1.4943,
      "step": 280
    },
    {
      "epoch": 1.6488983653162759,
      "grad_norm": 1.569798351736018,
      "learning_rate": 4.5589845168051176e-06,
      "loss": 1.47,
      "step": 290
    },
    {
      "epoch": 1.7057569296375266,
      "grad_norm": 1.5635972598860413,
      "learning_rate": 4.245878514193131e-06,
      "loss": 1.4717,
      "step": 300
    },
    {
      "epoch": 1.7626154939587777,
      "grad_norm": 1.583256520765993,
      "learning_rate": 3.935772629621996e-06,
      "loss": 1.4759,
      "step": 310
    },
    {
      "epoch": 1.8194740582800284,
      "grad_norm": 1.5703071827809085,
      "learning_rate": 3.62990055590697e-06,
      "loss": 1.4731,
      "step": 320
    },
    {
      "epoch": 1.8763326226012793,
      "grad_norm": 1.5673344510472709,
      "learning_rate": 3.3294791425130512e-06,
      "loss": 1.4609,
      "step": 330
    },
    {
      "epoch": 1.9331911869225302,
      "grad_norm": 1.5649245970464676,
      "learning_rate": 3.035703554568331e-06,
      "loss": 1.4557,
      "step": 340
    },
    {
      "epoch": 1.9900497512437811,
      "grad_norm": 1.5535579680886489,
      "learning_rate": 2.749742518144061e-06,
      "loss": 1.4604,
      "step": 350
    },
    {
      "epoch": 2.046908315565032,
      "grad_norm": 2.6898081511100944,
      "learning_rate": 2.4727336707170973e-06,
      "loss": 1.2976,
      "step": 360
    },
    {
      "epoch": 2.1037668798862827,
      "grad_norm": 2.294462090007101,
      "learning_rate": 2.2057790353119533e-06,
      "loss": 1.2109,
      "step": 370
    },
    {
      "epoch": 2.160625444207534,
      "grad_norm": 2.0734336172332375,
      "learning_rate": 1.949940636327671e-06,
      "loss": 1.2101,
      "step": 380
    },
    {
      "epoch": 2.2174840085287846,
      "grad_norm": 1.9313522409801105,
      "learning_rate": 1.7062362744910321e-06,
      "loss": 1.2124,
      "step": 390
    },
    {
      "epoch": 2.2743425728500357,
      "grad_norm": 1.9741447028673955,
      "learning_rate": 1.4756354777446004e-06,
      "loss": 1.2204,
      "step": 400
    },
    {
      "epoch": 2.3312011371712864,
      "grad_norm": 1.9826092702551152,
      "learning_rate": 1.2590556441781725e-06,
      "loss": 1.2031,
      "step": 410
    },
    {
      "epoch": 2.388059701492537,
      "grad_norm": 1.9337513040949874,
      "learning_rate": 1.057358392348171e-06,
      "loss": 1.1978,
      "step": 420
    },
    {
      "epoch": 2.4449182658137882,
      "grad_norm": 1.9619207022209448,
      "learning_rate": 8.713461335044981e-07,
      "loss": 1.1929,
      "step": 430
    },
    {
      "epoch": 2.501776830135039,
      "grad_norm": 1.9462643434600588,
      "learning_rate": 7.017588793615499e-07,
      "loss": 1.2075,
      "step": 440
    },
    {
      "epoch": 2.55863539445629,
      "grad_norm": 1.9622874707007205,
      "learning_rate": 5.492712981130171e-07,
      "loss": 1.2068,
      "step": 450
    },
    {
      "epoch": 2.6154939587775408,
      "grad_norm": 1.9185457493104283,
      "learning_rate": 4.144900304025101e-07,
      "loss": 1.1924,
      "step": 460
    },
    {
      "epoch": 2.672352523098792,
      "grad_norm": 1.9287168348109207,
      "learning_rate": 2.979512759278719e-07,
      "loss": 1.1847,
      "step": 470
    },
    {
      "epoch": 2.7292110874200426,
      "grad_norm": 1.898626201871725,
      "learning_rate": 2.0011866028038617e-07,
      "loss": 1.192,
      "step": 480
    },
    {
      "epoch": 2.7860696517412933,
      "grad_norm": 1.9641608263451322,
      "learning_rate": 1.2138139050522024e-07,
      "loss": 1.204,
      "step": 490
    },
    {
      "epoch": 2.8429282160625444,
      "grad_norm": 1.9152149742726723,
      "learning_rate": 6.20527067208232e-08,
      "loss": 1.2093,
      "step": 500
    },
    {
      "epoch": 2.8429282160625444,
      "eval_loss": 1.7461528778076172,
      "eval_runtime": 307.7688,
      "eval_samples_per_second": 32.492,
      "eval_steps_per_second": 0.51,
      "step": 500
    },
    {
      "epoch": 2.8997867803837956,
      "grad_norm": 1.9127782775890796,
      "learning_rate": 2.236863595720562e-08,
      "loss": 1.1844,
      "step": 510
    },
    {
      "epoch": 2.9566453447050463,
      "grad_norm": 1.8938021124768716,
      "learning_rate": 2.4870531706872037e-09,
      "loss": 1.1984,
      "step": 520
    },
    {
      "epoch": 2.9850746268656714,
      "step": 525,
      "total_flos": 165772559646720.0,
      "train_loss": 1.5532971572875978,
      "train_runtime": 24046.0291,
      "train_samples_per_second": 11.228,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 10,
  "max_steps": 525,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 165772559646720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}