{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 3751,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.026659557451346308,
      "grad_norm": 7.0857120383857755,
      "learning_rate": 2.6329787234042554e-06,
      "loss": 1.0624,
      "step": 100
    },
    {
      "epoch": 0.053319114902692616,
      "grad_norm": 6.581000668568491,
      "learning_rate": 5.292553191489362e-06,
      "loss": 0.7422,
      "step": 200
    },
    {
      "epoch": 0.07997867235403892,
      "grad_norm": 7.4656274686679085,
      "learning_rate": 7.95212765957447e-06,
      "loss": 0.7649,
      "step": 300
    },
    {
      "epoch": 0.10663822980538523,
      "grad_norm": 4.554989486482939,
      "learning_rate": 9.998854140728647e-06,
      "loss": 0.7662,
      "step": 400
    },
    {
      "epoch": 0.13329778725673153,
      "grad_norm": 4.023821679311659,
      "learning_rate": 9.967263823916638e-06,
      "loss": 0.784,
      "step": 500
    },
    {
      "epoch": 0.15995734470807785,
      "grad_norm": 4.221747608519819,
      "learning_rate": 9.892664857121854e-06,
      "loss": 0.79,
      "step": 600
    },
    {
      "epoch": 0.18661690215942414,
      "grad_norm": 3.838998761862227,
      "learning_rate": 9.775703149433419e-06,
      "loss": 0.7811,
      "step": 700
    },
    {
      "epoch": 0.21327645961077046,
      "grad_norm": 4.346355062560185,
      "learning_rate": 9.617391404288412e-06,
      "loss": 0.8124,
      "step": 800
    },
    {
      "epoch": 0.23993601706211676,
      "grad_norm": 4.985043330591158,
      "learning_rate": 9.41910035106149e-06,
      "loss": 0.7959,
      "step": 900
    },
    {
      "epoch": 0.26659557451346305,
      "grad_norm": 4.43851554256146,
      "learning_rate": 9.18254687671603e-06,
      "loss": 0.8065,
      "step": 1000
    },
    {
      "epoch": 0.2932551319648094,
      "grad_norm": 4.6639168705369425,
      "learning_rate": 8.909779160277951e-06,
      "loss": 0.7854,
      "step": 1100
    },
    {
      "epoch": 0.3199146894161557,
      "grad_norm": 3.7379632914857375,
      "learning_rate": 8.603158938844122e-06,
      "loss": 0.7729,
      "step": 1200
    },
    {
      "epoch": 0.346574246867502,
      "grad_norm": 4.820935299394203,
      "learning_rate": 8.265341058673722e-06,
      "loss": 0.7831,
      "step": 1300
    },
    {
      "epoch": 0.3732338043188483,
      "grad_norm": 3.6917931938034148,
      "learning_rate": 7.899250488417746e-06,
      "loss": 0.7967,
      "step": 1400
    },
    {
      "epoch": 0.39989336177019463,
      "grad_norm": 4.773594475659506,
      "learning_rate": 7.5080569935157375e-06,
      "loss": 0.7979,
      "step": 1500
    },
    {
      "epoch": 0.4265529192215409,
      "grad_norm": 4.447857956208416,
      "learning_rate": 7.095147691039425e-06,
      "loss": 0.7843,
      "step": 1600
    },
    {
      "epoch": 0.4532124766728872,
      "grad_norm": 4.389149312164256,
      "learning_rate": 6.664097722614934e-06,
      "loss": 0.7721,
      "step": 1700
    },
    {
      "epoch": 0.4798720341242335,
      "grad_norm": 3.915206329218288,
      "learning_rate": 6.218639299349676e-06,
      "loss": 0.7526,
      "step": 1800
    },
    {
      "epoch": 0.5065315915755798,
      "grad_norm": 5.180289969908035,
      "learning_rate": 5.7626293867858985e-06,
      "loss": 0.7854,
      "step": 1900
    },
    {
      "epoch": 0.5331911490269261,
      "grad_norm": 4.139436495632767,
      "learning_rate": 5.300016309678104e-06,
      "loss": 0.7381,
      "step": 2000
    },
    {
      "epoch": 0.5598507064782725,
      "grad_norm": 4.936713870803515,
      "learning_rate": 4.834805565744173e-06,
      "loss": 0.7471,
      "step": 2100
    },
    {
      "epoch": 0.5865102639296188,
      "grad_norm": 4.5976706617804,
      "learning_rate": 4.371025144389e-06,
      "loss": 0.7611,
      "step": 2200
    },
    {
      "epoch": 0.6131698213809651,
      "grad_norm": 5.820707950034038,
      "learning_rate": 3.912690650685726e-06,
      "loss": 0.7374,
      "step": 2300
    },
    {
      "epoch": 0.6398293788323114,
      "grad_norm": 3.951105419131897,
      "learning_rate": 3.4637705365856666e-06,
      "loss": 0.7444,
      "step": 2400
    },
    {
      "epoch": 0.6664889362836577,
      "grad_norm": 4.529901890166711,
      "learning_rate": 3.0281517403997245e-06,
      "loss": 0.7452,
      "step": 2500
    },
    {
      "epoch": 0.693148493735004,
      "grad_norm": 2.851635488548725,
      "learning_rate": 2.6096060320590393e-06,
      "loss": 0.7345,
      "step": 2600
    },
    {
      "epoch": 0.7198080511863503,
      "grad_norm": 3.6802521221701947,
      "learning_rate": 2.2117573555516774e-06,
      "loss": 0.7348,
      "step": 2700
    },
    {
      "epoch": 0.7464676086376966,
      "grad_norm": 3.6788331738320075,
      "learning_rate": 1.8380504512982329e-06,
      "loss": 0.7352,
      "step": 2800
    },
    {
      "epoch": 0.773127166089043,
      "grad_norm": 3.664797807064228,
      "learning_rate": 1.491721030146963e-06,
      "loss": 0.7299,
      "step": 2900
    },
    {
      "epoch": 0.7997867235403893,
      "grad_norm": 3.9751097792558783,
      "learning_rate": 1.1757677572344577e-06,
      "loss": 0.7353,
      "step": 3000
    },
    {
      "epoch": 0.8264462809917356,
      "grad_norm": 3.7953764140303985,
      "learning_rate": 8.929262882873524e-07,
      "loss": 0.7297,
      "step": 3100
    },
    {
      "epoch": 0.8531058384430819,
      "grad_norm": 3.4294084377480814,
      "learning_rate": 6.456455831696234e-07,
      "loss": 0.7151,
      "step": 3200
    },
    {
      "epoch": 0.8797653958944281,
      "grad_norm": 4.751586217200114,
      "learning_rate": 4.3606670176271014e-07,
      "loss": 0.695,
      "step": 3300
    },
    {
      "epoch": 0.9064249533457744,
      "grad_norm": 4.643644454272238,
      "learning_rate": 2.660042657725931e-07,
      "loss": 0.7423,
      "step": 3400
    },
    {
      "epoch": 0.9330845107971207,
      "grad_norm": 4.371360024084083,
      "learning_rate": 1.3693074697528231e-07,
      "loss": 0.7068,
      "step": 3500
    },
    {
      "epoch": 0.959744068248467,
      "grad_norm": 5.224648142017166,
      "learning_rate": 4.996371793965837e-08,
      "loss": 0.7121,
      "step": 3600
    },
    {
      "epoch": 0.9864036256998134,
      "grad_norm": 4.815750775150759,
      "learning_rate": 5.8561756162400785e-09,
      "loss": 0.7437,
      "step": 3700
    },
    {
      "epoch": 1.0,
      "step": 3751,
      "total_flos": 84620534874112.0,
      "train_loss": 0.7639887226768826,
      "train_runtime": 3882.0564,
      "train_samples_per_second": 7.728,
      "train_steps_per_second": 0.966
    }
  ],
  "logging_steps": 100,
  "max_steps": 3751,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 84620534874112.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}