{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 1000.0,
  "global_step": 7215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0693000693000693,
      "grad_norm": 84.25032806396484,
      "learning_rate": 9.900000000000002e-06,
      "loss": 5.6087,
      "step": 100
    },
    {
      "epoch": 0.1386001386001386,
      "grad_norm": 94.63692474365234,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 3.348,
      "step": 200
    },
    {
      "epoch": 0.2079002079002079,
      "grad_norm": 3.8304085731506348,
      "learning_rate": 2.9900000000000002e-05,
      "loss": 1.6412,
      "step": 300
    },
    {
      "epoch": 0.2772002772002772,
      "grad_norm": 1.6271604299545288,
      "learning_rate": 3.99e-05,
      "loss": 1.0079,
      "step": 400
    },
    {
      "epoch": 0.3465003465003465,
      "grad_norm": 1.7938034534454346,
      "learning_rate": 4.99e-05,
      "loss": 0.8602,
      "step": 500
    },
    {
      "epoch": 0.4158004158004158,
      "grad_norm": 1.656532883644104,
      "learning_rate": 4.926284437825763e-05,
      "loss": 0.7916,
      "step": 600
    },
    {
      "epoch": 0.4851004851004851,
      "grad_norm": 1.0380038022994995,
      "learning_rate": 4.851824274013403e-05,
      "loss": 0.7504,
      "step": 700
    },
    {
      "epoch": 0.5544005544005544,
      "grad_norm": 1.5392476320266724,
      "learning_rate": 4.7773641102010426e-05,
      "loss": 0.716,
      "step": 800
    },
    {
      "epoch": 0.6237006237006237,
      "grad_norm": 1.010367512702942,
      "learning_rate": 4.702903946388682e-05,
      "loss": 0.6681,
      "step": 900
    },
    {
      "epoch": 0.693000693000693,
      "grad_norm": 1.0135914087295532,
      "learning_rate": 4.628443782576322e-05,
      "loss": 0.58,
      "step": 1000
    },
    {
      "epoch": 0.7623007623007623,
      "grad_norm": 1.3977186679840088,
      "learning_rate": 4.5539836187639616e-05,
      "loss": 0.4681,
      "step": 1100
    },
    {
      "epoch": 0.8316008316008316,
      "grad_norm": 1.3097604513168335,
      "learning_rate": 4.479523454951601e-05,
      "loss": 0.3936,
      "step": 1200
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 1.0134280920028687,
      "learning_rate": 4.405063291139241e-05,
      "loss": 0.3355,
      "step": 1300
    },
    {
      "epoch": 0.9702009702009702,
      "grad_norm": 1.1942052841186523,
      "learning_rate": 4.330603127326881e-05,
      "loss": 0.3031,
      "step": 1400
    },
    {
      "epoch": 1.0395010395010396,
      "grad_norm": 1.3656076192855835,
      "learning_rate": 4.25614296351452e-05,
      "loss": 0.2624,
      "step": 1500
    },
    {
      "epoch": 1.1088011088011087,
      "grad_norm": 1.570897102355957,
      "learning_rate": 4.1816827997021594e-05,
      "loss": 0.2349,
      "step": 1600
    },
    {
      "epoch": 1.178101178101178,
      "grad_norm": 1.404532551765442,
      "learning_rate": 4.107222635889799e-05,
      "loss": 0.2216,
      "step": 1700
    },
    {
      "epoch": 1.2474012474012475,
      "grad_norm": 0.8654778599739075,
      "learning_rate": 4.032762472077439e-05,
      "loss": 0.2005,
      "step": 1800
    },
    {
      "epoch": 1.3167013167013166,
      "grad_norm": 1.196643352508545,
      "learning_rate": 3.9583023082650785e-05,
      "loss": 0.1958,
      "step": 1900
    },
    {
      "epoch": 1.386001386001386,
      "grad_norm": 1.4473341703414917,
      "learning_rate": 3.883842144452718e-05,
      "loss": 0.1791,
      "step": 2000
    },
    {
      "epoch": 1.4553014553014554,
      "grad_norm": 0.9925177097320557,
      "learning_rate": 3.809381980640357e-05,
      "loss": 0.1721,
      "step": 2100
    },
    {
      "epoch": 1.5246015246015245,
      "grad_norm": 1.4818828105926514,
      "learning_rate": 3.734921816827997e-05,
      "loss": 0.1615,
      "step": 2200
    },
    {
      "epoch": 1.593901593901594,
      "grad_norm": 1.7907570600509644,
      "learning_rate": 3.6604616530156365e-05,
      "loss": 0.1438,
      "step": 2300
    },
    {
      "epoch": 1.6632016632016633,
      "grad_norm": 0.9886597394943237,
      "learning_rate": 3.586001489203276e-05,
      "loss": 0.1384,
      "step": 2400
    },
    {
      "epoch": 1.7325017325017324,
      "grad_norm": 1.0584090948104858,
      "learning_rate": 3.5115413253909166e-05,
      "loss": 0.1393,
      "step": 2500
    },
    {
      "epoch": 1.8018018018018018,
      "grad_norm": 0.7380561828613281,
      "learning_rate": 3.4370811615785556e-05,
      "loss": 0.1257,
      "step": 2600
    },
    {
      "epoch": 1.871101871101871,
      "grad_norm": 0.8808689117431641,
      "learning_rate": 3.362620997766195e-05,
      "loss": 0.1198,
      "step": 2700
    },
    {
      "epoch": 1.9404019404019404,
      "grad_norm": 0.8636562824249268,
      "learning_rate": 3.288160833953835e-05,
      "loss": 0.1159,
      "step": 2800
    },
    {
      "epoch": 2.0097020097020097,
      "grad_norm": 0.7358367443084717,
      "learning_rate": 3.213700670141475e-05,
      "loss": 0.1038,
      "step": 2900
    },
    {
      "epoch": 2.079002079002079,
      "grad_norm": 0.7814437747001648,
      "learning_rate": 3.1392405063291144e-05,
      "loss": 0.105,
      "step": 3000
    },
    {
      "epoch": 2.1483021483021485,
      "grad_norm": 1.4671565294265747,
      "learning_rate": 3.064780342516754e-05,
      "loss": 0.0935,
      "step": 3100
    },
    {
      "epoch": 2.2176022176022174,
      "grad_norm": 0.721126139163971,
      "learning_rate": 2.9903201787043934e-05,
      "loss": 0.096,
      "step": 3200
    },
    {
      "epoch": 2.286902286902287,
      "grad_norm": 0.6991815567016602,
      "learning_rate": 2.9158600148920327e-05,
      "loss": 0.1034,
      "step": 3300
    },
    {
      "epoch": 2.356202356202356,
      "grad_norm": 0.9121260643005371,
      "learning_rate": 2.8413998510796724e-05,
      "loss": 0.0939,
      "step": 3400
    },
    {
      "epoch": 2.4255024255024256,
      "grad_norm": 1.1622234582901,
      "learning_rate": 2.766939687267312e-05,
      "loss": 0.092,
      "step": 3500
    },
    {
      "epoch": 2.494802494802495,
      "grad_norm": 0.7380202412605286,
      "learning_rate": 2.6924795234549515e-05,
      "loss": 0.084,
      "step": 3600
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 1.413069248199463,
      "learning_rate": 2.618019359642591e-05,
      "loss": 0.0841,
      "step": 3700
    },
    {
      "epoch": 2.6334026334026333,
      "grad_norm": 0.6783232092857361,
      "learning_rate": 2.543559195830231e-05,
      "loss": 0.0831,
      "step": 3800
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 0.8206629157066345,
      "learning_rate": 2.4690990320178705e-05,
      "loss": 0.0853,
      "step": 3900
    },
    {
      "epoch": 2.772002772002772,
      "grad_norm": 0.8955414295196533,
      "learning_rate": 2.3946388682055102e-05,
      "loss": 0.0807,
      "step": 4000
    },
    {
      "epoch": 2.8413028413028414,
      "grad_norm": 0.5236178636550903,
      "learning_rate": 2.3201787043931496e-05,
      "loss": 0.0801,
      "step": 4100
    },
    {
      "epoch": 2.9106029106029108,
      "grad_norm": 0.6238868832588196,
      "learning_rate": 2.2457185405807893e-05,
      "loss": 0.0788,
      "step": 4200
    },
    {
      "epoch": 2.97990297990298,
      "grad_norm": 0.8797939419746399,
      "learning_rate": 2.171258376768429e-05,
      "loss": 0.0767,
      "step": 4300
    },
    {
      "epoch": 3.049203049203049,
      "grad_norm": 0.8538146018981934,
      "learning_rate": 2.0967982129560686e-05,
      "loss": 0.0758,
      "step": 4400
    },
    {
      "epoch": 3.1185031185031185,
      "grad_norm": 0.5005732774734497,
      "learning_rate": 2.0223380491437083e-05,
      "loss": 0.0685,
      "step": 4500
    },
    {
      "epoch": 3.187803187803188,
      "grad_norm": 0.6817125082015991,
      "learning_rate": 1.947877885331348e-05,
      "loss": 0.0702,
      "step": 4600
    },
    {
      "epoch": 3.257103257103257,
      "grad_norm": 0.5497564673423767,
      "learning_rate": 1.8734177215189874e-05,
      "loss": 0.0664,
      "step": 4700
    },
    {
      "epoch": 3.3264033264033266,
      "grad_norm": 0.5136599540710449,
      "learning_rate": 1.798957557706627e-05,
      "loss": 0.0624,
      "step": 4800
    },
    {
      "epoch": 3.3957033957033955,
      "grad_norm": 0.8245359659194946,
      "learning_rate": 1.7244973938942664e-05,
      "loss": 0.0637,
      "step": 4900
    },
    {
      "epoch": 3.465003465003465,
      "grad_norm": 0.6158192157745361,
      "learning_rate": 1.650037230081906e-05,
      "loss": 0.065,
      "step": 5000
    },
    {
      "epoch": 3.5343035343035343,
      "grad_norm": 0.9357655048370361,
      "learning_rate": 1.575577066269546e-05,
      "loss": 0.0683,
      "step": 5100
    },
    {
      "epoch": 3.6036036036036037,
      "grad_norm": 0.6707029938697815,
      "learning_rate": 1.5011169024571856e-05,
      "loss": 0.0635,
      "step": 5200
    },
    {
      "epoch": 3.672903672903673,
      "grad_norm": 0.6795034408569336,
      "learning_rate": 1.4266567386448252e-05,
      "loss": 0.0648,
      "step": 5300
    },
    {
      "epoch": 3.742203742203742,
      "grad_norm": 0.9226582050323486,
      "learning_rate": 1.3521965748324647e-05,
      "loss": 0.0613,
      "step": 5400
    },
    {
      "epoch": 3.8115038115038113,
      "grad_norm": 0.7824294567108154,
      "learning_rate": 1.2777364110201044e-05,
      "loss": 0.0652,
      "step": 5500
    },
    {
      "epoch": 3.8808038808038807,
      "grad_norm": 0.5446070432662964,
      "learning_rate": 1.203276247207744e-05,
      "loss": 0.0661,
      "step": 5600
    },
    {
      "epoch": 3.95010395010395,
      "grad_norm": 0.4837566614151001,
      "learning_rate": 1.1288160833953836e-05,
      "loss": 0.0603,
      "step": 5700
    },
    {
      "epoch": 4.0194040194040195,
      "grad_norm": 0.7145822048187256,
      "learning_rate": 1.054355919583023e-05,
      "loss": 0.0604,
      "step": 5800
    },
    {
      "epoch": 4.088704088704088,
      "grad_norm": 1.1573742628097534,
      "learning_rate": 9.798957557706628e-06,
      "loss": 0.0593,
      "step": 5900
    },
    {
      "epoch": 4.158004158004158,
      "grad_norm": 0.6243206262588501,
      "learning_rate": 9.054355919583025e-06,
      "loss": 0.0632,
      "step": 6000
    },
    {
      "epoch": 4.227304227304227,
      "grad_norm": 0.6134985089302063,
      "learning_rate": 8.30975428145942e-06,
      "loss": 0.0601,
      "step": 6100
    },
    {
      "epoch": 4.296604296604297,
      "grad_norm": 1.786774754524231,
      "learning_rate": 7.565152643335816e-06,
      "loss": 0.0541,
      "step": 6200
    },
    {
      "epoch": 4.365904365904366,
      "grad_norm": 0.9844805598258972,
      "learning_rate": 6.820551005212211e-06,
      "loss": 0.0569,
      "step": 6300
    },
    {
      "epoch": 4.435204435204435,
      "grad_norm": 0.7235813736915588,
      "learning_rate": 6.075949367088608e-06,
      "loss": 0.0586,
      "step": 6400
    },
    {
      "epoch": 4.504504504504505,
      "grad_norm": 0.6935411095619202,
      "learning_rate": 5.331347728965004e-06,
      "loss": 0.0602,
      "step": 6500
    },
    {
      "epoch": 4.573804573804574,
      "grad_norm": 0.6599699854850769,
      "learning_rate": 4.5867460908414e-06,
      "loss": 0.0589,
      "step": 6600
    },
    {
      "epoch": 4.643104643104643,
      "grad_norm": 0.7888091206550598,
      "learning_rate": 3.842144452717796e-06,
      "loss": 0.0543,
      "step": 6700
    },
    {
      "epoch": 4.712404712404712,
      "grad_norm": 0.4492560923099518,
      "learning_rate": 3.0975428145941924e-06,
      "loss": 0.0555,
      "step": 6800
    },
    {
      "epoch": 4.781704781704782,
      "grad_norm": 0.570002555847168,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 0.0548,
      "step": 6900
    },
    {
      "epoch": 4.851004851004851,
      "grad_norm": 0.48206043243408203,
      "learning_rate": 1.6083395383469843e-06,
      "loss": 0.059,
      "step": 7000
    },
    {
      "epoch": 4.92030492030492,
      "grad_norm": 0.6836007237434387,
      "learning_rate": 8.637379002233806e-07,
      "loss": 0.054,
      "step": 7100
    },
    {
      "epoch": 4.98960498960499,
      "grad_norm": 0.8150354027748108,
      "learning_rate": 1.1913626209977663e-07,
      "loss": 0.0569,
      "step": 7200
    },
    {
      "epoch": 5.0,
      "step": 7215,
      "total_flos": 9204713354568960.0,
      "train_loss": 0.3190814718469843,
      "train_runtime": 955.3205,
      "train_samples_per_second": 120.792,
      "train_steps_per_second": 7.552
    }
  ],
  "logging_steps": 100,
  "max_steps": 7215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9204713354568960.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}