{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010757025682398816,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.6892564205997043e-05,
      "eval_loss": 1.630568504333496,
      "eval_runtime": 590.6874,
      "eval_samples_per_second": 26.506,
      "eval_steps_per_second": 13.254,
      "step": 1
    },
    {
      "epoch": 0.0001344628210299852,
      "grad_norm": 0.345037043094635,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.9699,
      "step": 5
    },
    {
      "epoch": 0.0002689256420599704,
      "grad_norm": 0.3418862521648407,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.8948,
      "step": 10
    },
    {
      "epoch": 0.0004033884630899556,
      "grad_norm": 0.5471668839454651,
      "learning_rate": 5e-05,
      "loss": 1.1082,
      "step": 15
    },
    {
      "epoch": 0.0005378512841199408,
      "grad_norm": 0.6115098595619202,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.1124,
      "step": 20
    },
    {
      "epoch": 0.000672314105149926,
      "grad_norm": 0.8527878522872925,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.1729,
      "step": 25
    },
    {
      "epoch": 0.0008067769261799112,
      "grad_norm": 1.074232578277588,
      "learning_rate": 0.0001,
      "loss": 1.356,
      "step": 30
    },
    {
      "epoch": 0.0009412397472098965,
      "grad_norm": 1.3583526611328125,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.4972,
      "step": 35
    },
    {
      "epoch": 0.0010757025682398816,
      "grad_norm": 2.0084147453308105,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.5281,
      "step": 40
    },
    {
      "epoch": 0.0012101653892698668,
      "grad_norm": 3.7616775035858154,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.6957,
      "step": 45
    },
    {
      "epoch": 0.001344628210299852,
      "grad_norm": 6.697372913360596,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.9272,
      "step": 50
    },
    {
      "epoch": 0.0014790910313298372,
      "grad_norm": 0.46635526418685913,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.9388,
      "step": 55
    },
    {
      "epoch": 0.0016135538523598225,
      "grad_norm": 0.5440621972084045,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.8323,
      "step": 60
    },
    {
      "epoch": 0.0017480166733898077,
      "grad_norm": 0.6659886240959167,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.9362,
      "step": 65
    },
    {
      "epoch": 0.001882479494419793,
      "grad_norm": 0.7471917867660522,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.8368,
      "step": 70
    },
    {
      "epoch": 0.002016942315449778,
      "grad_norm": 0.9752324819564819,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.9363,
      "step": 75
    },
    {
      "epoch": 0.002151405136479763,
      "grad_norm": 1.0163908004760742,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.9598,
      "step": 80
    },
    {
      "epoch": 0.0022858679575097486,
      "grad_norm": 1.6247353553771973,
      "learning_rate": 9.464629290747842e-05,
      "loss": 1.0901,
      "step": 85
    },
    {
      "epoch": 0.0024203307785397336,
      "grad_norm": 1.683845043182373,
      "learning_rate": 9.365070565805941e-05,
      "loss": 1.3387,
      "step": 90
    },
    {
      "epoch": 0.002554793599569719,
      "grad_norm": 2.1092941761016846,
      "learning_rate": 9.257645688666556e-05,
      "loss": 1.1503,
      "step": 95
    },
    {
      "epoch": 0.002689256420599704,
      "grad_norm": 5.764535427093506,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.4292,
      "step": 100
    },
    {
      "epoch": 0.002689256420599704,
      "eval_loss": 1.023895263671875,
      "eval_runtime": 591.7149,
      "eval_samples_per_second": 26.46,
      "eval_steps_per_second": 13.231,
      "step": 100
    },
    {
      "epoch": 0.0028237192416296895,
      "grad_norm": 0.5576226115226746,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.7047,
      "step": 105
    },
    {
      "epoch": 0.0029581820626596745,
      "grad_norm": 0.6110519766807556,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.7021,
      "step": 110
    },
    {
      "epoch": 0.00309264488368966,
      "grad_norm": 0.576543390750885,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.7997,
      "step": 115
    },
    {
      "epoch": 0.003227107704719645,
      "grad_norm": 0.9036309123039246,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.7819,
      "step": 120
    },
    {
      "epoch": 0.0033615705257496304,
      "grad_norm": 0.9142856001853943,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.9531,
      "step": 125
    },
    {
      "epoch": 0.0034960333467796154,
      "grad_norm": 1.1154049634933472,
      "learning_rate": 8.303373616950408e-05,
      "loss": 1.0073,
      "step": 130
    },
    {
      "epoch": 0.003630496167809601,
      "grad_norm": 1.7030612230300903,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.0398,
      "step": 135
    },
    {
      "epoch": 0.003764958988839586,
      "grad_norm": 1.6508612632751465,
      "learning_rate": 7.973165881521434e-05,
      "loss": 1.1582,
      "step": 140
    },
    {
      "epoch": 0.003899421809869571,
      "grad_norm": 2.199151039123535,
      "learning_rate": 7.799873930687978e-05,
      "loss": 1.1028,
      "step": 145
    },
    {
      "epoch": 0.004033884630899556,
      "grad_norm": 14.890746116638184,
      "learning_rate": 7.621536417786159e-05,
      "loss": 1.5997,
      "step": 150
    },
    {
      "epoch": 0.004168347451929542,
      "grad_norm": 0.3813338577747345,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.9074,
      "step": 155
    },
    {
      "epoch": 0.004302810272959526,
      "grad_norm": 0.48821568489074707,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.5692,
      "step": 160
    },
    {
      "epoch": 0.004437273093989512,
      "grad_norm": 0.6882808804512024,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.6684,
      "step": 165
    },
    {
      "epoch": 0.004571735915019497,
      "grad_norm": 0.8933084011077881,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.8534,
      "step": 170
    },
    {
      "epoch": 0.004706198736049483,
      "grad_norm": 0.9639412760734558,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.8509,
      "step": 175
    },
    {
      "epoch": 0.004840661557079467,
      "grad_norm": 1.5868816375732422,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.9711,
      "step": 180
    },
    {
      "epoch": 0.004975124378109453,
      "grad_norm": 1.5396876335144043,
      "learning_rate": 6.259890306925627e-05,
      "loss": 1.1357,
      "step": 185
    },
    {
      "epoch": 0.005109587199139438,
      "grad_norm": 1.8136801719665527,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.9835,
      "step": 190
    },
    {
      "epoch": 0.0052440500201694235,
      "grad_norm": 2.167841911315918,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 1.1127,
      "step": 195
    },
    {
      "epoch": 0.005378512841199408,
      "grad_norm": 19.674968719482422,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 1.6539,
      "step": 200
    },
    {
      "epoch": 0.005378512841199408,
      "eval_loss": 0.9393494129180908,
      "eval_runtime": 591.1646,
      "eval_samples_per_second": 26.485,
      "eval_steps_per_second": 13.243,
      "step": 200
    },
    {
      "epoch": 0.0055129756622293935,
      "grad_norm": 0.5495665669441223,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.7572,
      "step": 205
    },
    {
      "epoch": 0.005647438483259379,
      "grad_norm": 0.47913676500320435,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.671,
      "step": 210
    },
    {
      "epoch": 0.005781901304289364,
      "grad_norm": 0.7315741181373596,
      "learning_rate": 5e-05,
      "loss": 0.6678,
      "step": 215
    },
    {
      "epoch": 0.005916364125319349,
      "grad_norm": 0.839297890663147,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.6533,
      "step": 220
    },
    {
      "epoch": 0.0060508269463493344,
      "grad_norm": 1.2474215030670166,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.8951,
      "step": 225
    },
    {
      "epoch": 0.00618528976737932,
      "grad_norm": 1.4702121019363403,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.9299,
      "step": 230
    },
    {
      "epoch": 0.0063197525884093044,
      "grad_norm": 1.7270251512527466,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.974,
      "step": 235
    },
    {
      "epoch": 0.00645421540943929,
      "grad_norm": 2.3765015602111816,
      "learning_rate": 3.94660365002137e-05,
      "loss": 1.2234,
      "step": 240
    },
    {
      "epoch": 0.006588678230469275,
      "grad_norm": 2.6356091499328613,
      "learning_rate": 3.740109693074375e-05,
      "loss": 1.1109,
      "step": 245
    },
    {
      "epoch": 0.006723141051499261,
      "grad_norm": 4.3721442222595215,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 1.069,
      "step": 250
    },
    {
      "epoch": 0.006857603872529245,
      "grad_norm": 0.4549669027328491,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.8248,
      "step": 255
    },
    {
      "epoch": 0.006992066693559231,
      "grad_norm": 0.8009957075119019,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.6723,
      "step": 260
    },
    {
      "epoch": 0.007126529514589216,
      "grad_norm": 0.686644434928894,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.6772,
      "step": 265
    },
    {
      "epoch": 0.007260992335619202,
      "grad_norm": 0.8266721963882446,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.7437,
      "step": 270
    },
    {
      "epoch": 0.007395455156649186,
      "grad_norm": 1.1992957592010498,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.7368,
      "step": 275
    },
    {
      "epoch": 0.007529917977679172,
      "grad_norm": 1.295320749282837,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.9103,
      "step": 280
    },
    {
      "epoch": 0.007664380798709157,
      "grad_norm": 1.72942054271698,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.9956,
      "step": 285
    },
    {
      "epoch": 0.007798843619739142,
      "grad_norm": 2.2148993015289307,
      "learning_rate": 2.026834118478567e-05,
      "loss": 1.1809,
      "step": 290
    },
    {
      "epoch": 0.007933306440769127,
      "grad_norm": 2.855957269668579,
      "learning_rate": 1.858900013521788e-05,
      "loss": 1.046,
      "step": 295
    },
    {
      "epoch": 0.008067769261799113,
      "grad_norm": 19.326793670654297,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 1.4139,
      "step": 300
    },
    {
      "epoch": 0.008067769261799113,
      "eval_loss": 0.9035645127296448,
      "eval_runtime": 593.6939,
      "eval_samples_per_second": 26.372,
      "eval_steps_per_second": 13.187,
      "step": 300
    },
    {
      "epoch": 0.008202232082829098,
      "grad_norm": 0.5819787979125977,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.7786,
      "step": 305
    },
    {
      "epoch": 0.008336694903859083,
      "grad_norm": 0.6248407959938049,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.7007,
      "step": 310
    },
    {
      "epoch": 0.008471157724889069,
      "grad_norm": 0.7559268474578857,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.6342,
      "step": 315
    },
    {
      "epoch": 0.008605620545919053,
      "grad_norm": 1.1455119848251343,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.8618,
      "step": 320
    },
    {
      "epoch": 0.008740083366949038,
      "grad_norm": 1.2570725679397583,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.8012,
      "step": 325
    },
    {
      "epoch": 0.008874546187979023,
      "grad_norm": 1.401977777481079,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.8714,
      "step": 330
    },
    {
      "epoch": 0.009009009009009009,
      "grad_norm": 1.8925217390060425,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.9404,
      "step": 335
    },
    {
      "epoch": 0.009143471830038994,
      "grad_norm": 1.870854377746582,
      "learning_rate": 6.349294341940593e-06,
      "loss": 1.1038,
      "step": 340
    },
    {
      "epoch": 0.00927793465106898,
      "grad_norm": 3.0395100116729736,
      "learning_rate": 5.353707092521582e-06,
      "loss": 1.2661,
      "step": 345
    },
    {
      "epoch": 0.009412397472098965,
      "grad_norm": 7.892786502838135,
      "learning_rate": 4.43857548059321e-06,
      "loss": 1.2146,
      "step": 350
    },
    {
      "epoch": 0.00954686029312895,
      "grad_norm": 0.4488086998462677,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.7294,
      "step": 355
    },
    {
      "epoch": 0.009681323114158934,
      "grad_norm": 0.5826189517974854,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.6767,
      "step": 360
    },
    {
      "epoch": 0.00981578593518892,
      "grad_norm": 0.7776308655738831,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.815,
      "step": 365
    },
    {
      "epoch": 0.009950248756218905,
      "grad_norm": 1.0107591152191162,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.7308,
      "step": 370
    },
    {
      "epoch": 0.01008471157724889,
      "grad_norm": 1.2522705793380737,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.8853,
      "step": 375
    },
    {
      "epoch": 0.010219174398278876,
      "grad_norm": 1.5564030408859253,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.9467,
      "step": 380
    },
    {
      "epoch": 0.010353637219308862,
      "grad_norm": 1.795711636543274,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.9253,
      "step": 385
    },
    {
      "epoch": 0.010488100040338847,
      "grad_norm": 2.1192917823791504,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 1.0559,
      "step": 390
    },
    {
      "epoch": 0.01062256286136883,
      "grad_norm": 3.0219783782958984,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 1.256,
      "step": 395
    },
    {
      "epoch": 0.010757025682398816,
      "grad_norm": 6.556485176086426,
      "learning_rate": 0.0,
      "loss": 1.2223,
      "step": 400
    },
    {
      "epoch": 0.010757025682398816,
      "eval_loss": 0.8996598720550537,
      "eval_runtime": 591.1926,
      "eval_samples_per_second": 26.484,
      "eval_steps_per_second": 13.243,
      "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": 2.767885636416307e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}