{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03592276605298608,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.98069151324652e-05,
      "eval_loss": 3.1951746940612793,
      "eval_runtime": 353.9742,
      "eval_samples_per_second": 13.247,
      "eval_steps_per_second": 6.625,
      "step": 1
    },
    {
      "epoch": 0.000449034575662326,
      "grad_norm": 0.28459519147872925,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.6336,
      "step": 5
    },
    {
      "epoch": 0.000898069151324652,
      "grad_norm": 0.35409072041511536,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.6537,
      "step": 10
    },
    {
      "epoch": 0.001347103726986978,
      "grad_norm": 0.49534764885902405,
      "learning_rate": 5e-05,
      "loss": 2.809,
      "step": 15
    },
    {
      "epoch": 0.001796138302649304,
      "grad_norm": 0.5985381007194519,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.9052,
      "step": 20
    },
    {
      "epoch": 0.00224517287831163,
      "grad_norm": 0.9438591003417969,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.8994,
      "step": 25
    },
    {
      "epoch": 0.002694207453973956,
      "grad_norm": 1.277062177658081,
      "learning_rate": 0.0001,
      "loss": 2.8801,
      "step": 30
    },
    {
      "epoch": 0.003143242029636282,
      "grad_norm": 1.6340757608413696,
      "learning_rate": 9.995494831023409e-05,
      "loss": 2.7491,
      "step": 35
    },
    {
      "epoch": 0.003592276605298608,
      "grad_norm": 1.941489338874817,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.8053,
      "step": 40
    },
    {
      "epoch": 0.004041311180960934,
      "grad_norm": 2.2817068099975586,
      "learning_rate": 9.959502176294383e-05,
      "loss": 2.5856,
      "step": 45
    },
    {
      "epoch": 0.00449034575662326,
      "grad_norm": 2.839555501937866,
      "learning_rate": 9.928079551738543e-05,
      "loss": 2.9146,
      "step": 50
    },
    {
      "epoch": 0.004939380332285586,
      "grad_norm": 0.7805606722831726,
      "learning_rate": 9.887776194738432e-05,
      "loss": 2.4364,
      "step": 55
    },
    {
      "epoch": 0.005388414907947912,
      "grad_norm": 0.6951726078987122,
      "learning_rate": 9.838664734667495e-05,
      "loss": 2.3357,
      "step": 60
    },
    {
      "epoch": 0.0058374494836102376,
      "grad_norm": 0.7993314862251282,
      "learning_rate": 9.780833673696254e-05,
      "loss": 2.2939,
      "step": 65
    },
    {
      "epoch": 0.006286484059272564,
      "grad_norm": 1.141896367073059,
      "learning_rate": 9.714387227305422e-05,
      "loss": 2.3438,
      "step": 70
    },
    {
      "epoch": 0.00673551863493489,
      "grad_norm": 1.4399296045303345,
      "learning_rate": 9.639445136482548e-05,
      "loss": 2.4126,
      "step": 75
    },
    {
      "epoch": 0.007184553210597216,
      "grad_norm": 1.676002025604248,
      "learning_rate": 9.55614245194068e-05,
      "loss": 2.4796,
      "step": 80
    },
    {
      "epoch": 0.007633587786259542,
      "grad_norm": 2.033027410507202,
      "learning_rate": 9.464629290747842e-05,
      "loss": 2.5079,
      "step": 85
    },
    {
      "epoch": 0.008082622361921869,
      "grad_norm": 2.0834078788757324,
      "learning_rate": 9.365070565805941e-05,
      "loss": 2.4775,
      "step": 90
    },
    {
      "epoch": 0.008531656937584195,
      "grad_norm": 2.7009525299072266,
      "learning_rate": 9.257645688666556e-05,
      "loss": 2.5451,
      "step": 95
    },
    {
      "epoch": 0.00898069151324652,
      "grad_norm": 3.329258918762207,
      "learning_rate": 9.142548246219212e-05,
      "loss": 2.6497,
      "step": 100
    },
    {
      "epoch": 0.00898069151324652,
      "eval_loss": 2.4617698192596436,
      "eval_runtime": 356.5654,
      "eval_samples_per_second": 13.15,
      "eval_steps_per_second": 6.577,
      "step": 100
    },
    {
      "epoch": 0.009429726088908847,
      "grad_norm": 0.7947559952735901,
      "learning_rate": 9.019985651834703e-05,
      "loss": 2.3265,
      "step": 105
    },
    {
      "epoch": 0.009878760664571173,
      "grad_norm": 0.9079984426498413,
      "learning_rate": 8.890178771592199e-05,
      "loss": 2.3397,
      "step": 110
    },
    {
      "epoch": 0.010327795240233499,
      "grad_norm": 1.0366816520690918,
      "learning_rate": 8.753361526263621e-05,
      "loss": 2.2172,
      "step": 115
    },
    {
      "epoch": 0.010776829815895825,
      "grad_norm": 1.396443486213684,
      "learning_rate": 8.609780469772623e-05,
      "loss": 2.3083,
      "step": 120
    },
    {
      "epoch": 0.01122586439155815,
      "grad_norm": 1.6878368854522705,
      "learning_rate": 8.459694344887732e-05,
      "loss": 2.3579,
      "step": 125
    },
    {
      "epoch": 0.011674898967220475,
      "grad_norm": 2.2573277950286865,
      "learning_rate": 8.303373616950408e-05,
      "loss": 2.4,
      "step": 130
    },
    {
      "epoch": 0.012123933542882801,
      "grad_norm": 2.4351515769958496,
      "learning_rate": 8.141099986478212e-05,
      "loss": 2.557,
      "step": 135
    },
    {
      "epoch": 0.012572968118545127,
      "grad_norm": 2.702453851699829,
      "learning_rate": 7.973165881521434e-05,
      "loss": 2.485,
      "step": 140
    },
    {
      "epoch": 0.013022002694207453,
      "grad_norm": 2.9839582443237305,
      "learning_rate": 7.799873930687978e-05,
      "loss": 2.3986,
      "step": 145
    },
    {
      "epoch": 0.01347103726986978,
      "grad_norm": 3.9269957542419434,
      "learning_rate": 7.621536417786159e-05,
      "loss": 2.6132,
      "step": 150
    },
    {
      "epoch": 0.013920071845532105,
      "grad_norm": 0.9305656552314758,
      "learning_rate": 7.438474719068173e-05,
      "loss": 2.2556,
      "step": 155
    },
    {
      "epoch": 0.014369106421194431,
      "grad_norm": 1.079910159111023,
      "learning_rate": 7.251018724088367e-05,
      "loss": 2.1759,
      "step": 160
    },
    {
      "epoch": 0.014818140996856757,
      "grad_norm": 1.2208424806594849,
      "learning_rate": 7.059506241219965e-05,
      "loss": 2.2838,
      "step": 165
    },
    {
      "epoch": 0.015267175572519083,
      "grad_norm": 1.546343207359314,
      "learning_rate": 6.864282388901544e-05,
      "loss": 2.2865,
      "step": 170
    },
    {
      "epoch": 0.01571621014818141,
      "grad_norm": 1.7968132495880127,
      "learning_rate": 6.665698973710288e-05,
      "loss": 2.3424,
      "step": 175
    },
    {
      "epoch": 0.016165244723843737,
      "grad_norm": 2.363734006881714,
      "learning_rate": 6.464113856382752e-05,
      "loss": 2.3408,
      "step": 180
    },
    {
      "epoch": 0.01661427929950606,
      "grad_norm": 2.706956624984741,
      "learning_rate": 6.259890306925627e-05,
      "loss": 2.2287,
      "step": 185
    },
    {
      "epoch": 0.01706331387516839,
      "grad_norm": 2.653686285018921,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 2.3489,
      "step": 190
    },
    {
      "epoch": 0.017512348450830714,
      "grad_norm": 3.6265406608581543,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 2.3393,
      "step": 195
    },
    {
      "epoch": 0.01796138302649304,
      "grad_norm": 4.439182281494141,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 2.4922,
      "step": 200
    },
    {
      "epoch": 0.01796138302649304,
      "eval_loss": 2.3509719371795654,
      "eval_runtime": 356.6582,
      "eval_samples_per_second": 13.147,
      "eval_steps_per_second": 6.575,
      "step": 200
    },
    {
      "epoch": 0.018410417602155366,
      "grad_norm": 1.0145143270492554,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 2.114,
      "step": 205
    },
    {
      "epoch": 0.018859452177817693,
      "grad_norm": 1.121131420135498,
      "learning_rate": 5.212206015980742e-05,
      "loss": 2.1236,
      "step": 210
    },
    {
      "epoch": 0.019308486753480018,
      "grad_norm": 1.5506993532180786,
      "learning_rate": 5e-05,
      "loss": 2.2213,
      "step": 215
    },
    {
      "epoch": 0.019757521329142345,
      "grad_norm": 1.7119569778442383,
      "learning_rate": 4.78779398401926e-05,
      "loss": 2.3372,
      "step": 220
    },
    {
      "epoch": 0.02020655590480467,
      "grad_norm": 2.3294599056243896,
      "learning_rate": 4.575970377622456e-05,
      "loss": 2.348,
      "step": 225
    },
    {
      "epoch": 0.020655590480466997,
      "grad_norm": 2.8338170051574707,
      "learning_rate": 4.364910901265606e-05,
      "loss": 2.361,
      "step": 230
    },
    {
      "epoch": 0.021104625056129322,
      "grad_norm": 2.876967668533325,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 2.275,
      "step": 235
    },
    {
      "epoch": 0.02155365963179165,
      "grad_norm": 2.95035719871521,
      "learning_rate": 3.94660365002137e-05,
      "loss": 2.3335,
      "step": 240
    },
    {
      "epoch": 0.022002694207453974,
      "grad_norm": 4.696662425994873,
      "learning_rate": 3.740109693074375e-05,
      "loss": 2.4499,
      "step": 245
    },
    {
      "epoch": 0.0224517287831163,
      "grad_norm": 4.856019496917725,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 2.6149,
      "step": 250
    },
    {
      "epoch": 0.022900763358778626,
      "grad_norm": 1.1213271617889404,
      "learning_rate": 3.334301026289712e-05,
      "loss": 2.1865,
      "step": 255
    },
    {
      "epoch": 0.02334979793444095,
      "grad_norm": 1.2899647951126099,
      "learning_rate": 3.135717611098458e-05,
      "loss": 2.2324,
      "step": 260
    },
    {
      "epoch": 0.023798832510103278,
      "grad_norm": 1.463903546333313,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 2.1198,
      "step": 265
    },
    {
      "epoch": 0.024247867085765602,
      "grad_norm": 1.8549535274505615,
      "learning_rate": 2.748981275911633e-05,
      "loss": 2.3003,
      "step": 270
    },
    {
      "epoch": 0.02469690166142793,
      "grad_norm": 2.2730584144592285,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 2.3141,
      "step": 275
    },
    {
      "epoch": 0.025145936237090254,
      "grad_norm": 2.8046603202819824,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 2.2976,
      "step": 280
    },
    {
      "epoch": 0.025594970812752582,
      "grad_norm": 3.0348989963531494,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 2.3604,
      "step": 285
    },
    {
      "epoch": 0.026044005388414906,
      "grad_norm": 3.0083751678466797,
      "learning_rate": 2.026834118478567e-05,
      "loss": 2.2966,
      "step": 290
    },
    {
      "epoch": 0.026493039964077234,
      "grad_norm": 3.9714059829711914,
      "learning_rate": 1.858900013521788e-05,
      "loss": 2.4667,
      "step": 295
    },
    {
      "epoch": 0.02694207453973956,
      "grad_norm": 4.601074695587158,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 2.5235,
      "step": 300
    },
    {
      "epoch": 0.02694207453973956,
      "eval_loss": 2.3027594089508057,
      "eval_runtime": 356.3728,
      "eval_samples_per_second": 13.158,
      "eval_steps_per_second": 6.58,
      "step": 300
    },
    {
      "epoch": 0.027391109115401886,
      "grad_norm": 1.0686273574829102,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 2.3023,
      "step": 305
    },
    {
      "epoch": 0.02784014369106421,
      "grad_norm": 1.3059085607528687,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 2.1677,
      "step": 310
    },
    {
      "epoch": 0.02828917826672654,
      "grad_norm": 1.4381647109985352,
      "learning_rate": 1.246638473736378e-05,
      "loss": 2.282,
      "step": 315
    },
    {
      "epoch": 0.028738212842388863,
      "grad_norm": 1.7172763347625732,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 2.0908,
      "step": 320
    },
    {
      "epoch": 0.02918724741805119,
      "grad_norm": 2.1044275760650635,
      "learning_rate": 9.800143481652979e-06,
      "loss": 2.322,
      "step": 325
    },
    {
      "epoch": 0.029636281993713515,
      "grad_norm": 2.5188639163970947,
      "learning_rate": 8.574517537807897e-06,
      "loss": 2.2956,
      "step": 330
    },
    {
      "epoch": 0.030085316569375842,
      "grad_norm": 3.0851542949676514,
      "learning_rate": 7.423543113334436e-06,
      "loss": 2.2503,
      "step": 335
    },
    {
      "epoch": 0.030534351145038167,
      "grad_norm": 3.5301318168640137,
      "learning_rate": 6.349294341940593e-06,
      "loss": 2.3532,
      "step": 340
    },
    {
      "epoch": 0.030983385720700495,
      "grad_norm": 3.9213593006134033,
      "learning_rate": 5.353707092521582e-06,
      "loss": 2.6252,
      "step": 345
    },
    {
      "epoch": 0.03143242029636282,
      "grad_norm": 4.902388572692871,
      "learning_rate": 4.43857548059321e-06,
      "loss": 2.5284,
      "step": 350
    },
    {
      "epoch": 0.03188145487202514,
      "grad_norm": 1.0451959371566772,
      "learning_rate": 3.605548635174533e-06,
      "loss": 2.2551,
      "step": 355
    },
    {
      "epoch": 0.032330489447687474,
      "grad_norm": 1.2155513763427734,
      "learning_rate": 2.85612772694579e-06,
      "loss": 2.139,
      "step": 360
    },
    {
      "epoch": 0.0327795240233498,
      "grad_norm": 1.5189533233642578,
      "learning_rate": 2.191663263037458e-06,
      "loss": 2.2051,
      "step": 365
    },
    {
      "epoch": 0.03322855859901212,
      "grad_norm": 1.8762248754501343,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 2.2809,
      "step": 370
    },
    {
      "epoch": 0.03367759317467445,
      "grad_norm": 2.338930130004883,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 2.2125,
      "step": 375
    },
    {
      "epoch": 0.03412662775033678,
      "grad_norm": 2.407233476638794,
      "learning_rate": 7.192044826145771e-07,
      "loss": 2.3318,
      "step": 380
    },
    {
      "epoch": 0.0345756623259991,
      "grad_norm": 2.822512149810791,
      "learning_rate": 4.049782370561583e-07,
      "loss": 2.2985,
      "step": 385
    },
    {
      "epoch": 0.03502469690166143,
      "grad_norm": 3.503061294555664,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 2.4015,
      "step": 390
    },
    {
      "epoch": 0.03547373147732375,
      "grad_norm": 3.7975668907165527,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 2.4348,
      "step": 395
    },
    {
      "epoch": 0.03592276605298608,
      "grad_norm": 4.950035095214844,
      "learning_rate": 0.0,
      "loss": 2.444,
      "step": 400
    },
    {
      "epoch": 0.03592276605298608,
      "eval_loss": 2.294800281524658,
      "eval_runtime": 356.4397,
      "eval_samples_per_second": 13.155,
      "eval_steps_per_second": 6.579,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.4341894659322675e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}