{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 34077,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044017959327405584,
      "grad_norm": 0.6358331441879272,
      "learning_rate": 1.9706546937817296e-05,
      "loss": 2.539,
      "step": 500
    },
    {
      "epoch": 0.08803591865481117,
      "grad_norm": 0.4060266613960266,
      "learning_rate": 1.9413093875634593e-05,
      "loss": 1.2396,
      "step": 1000
    },
    {
      "epoch": 0.13205387798221674,
      "grad_norm": 4.214008808135986,
      "learning_rate": 1.911964081345189e-05,
      "loss": 0.9035,
      "step": 1500
    },
    {
      "epoch": 0.17607183730962234,
      "grad_norm": 1.6060826778411865,
      "learning_rate": 1.882618775126919e-05,
      "loss": 0.7033,
      "step": 2000
    },
    {
      "epoch": 0.2200897966370279,
      "grad_norm": 4.546453475952148,
      "learning_rate": 1.8532734689086482e-05,
      "loss": 0.6154,
      "step": 2500
    },
    {
      "epoch": 0.2641077559644335,
      "grad_norm": 1.295145034790039,
      "learning_rate": 1.8239281626903777e-05,
      "loss": 0.5954,
      "step": 3000
    },
    {
      "epoch": 0.3081257152918391,
      "grad_norm": 5.553115367889404,
      "learning_rate": 1.7945828564721074e-05,
      "loss": 0.5736,
      "step": 3500
    },
    {
      "epoch": 0.3521436746192447,
      "grad_norm": 6.943908214569092,
      "learning_rate": 1.765237550253837e-05,
      "loss": 0.541,
      "step": 4000
    },
    {
      "epoch": 0.3961616339466502,
      "grad_norm": 1.2528984546661377,
      "learning_rate": 1.7358922440355666e-05,
      "loss": 0.5497,
      "step": 4500
    },
    {
      "epoch": 0.4401795932740558,
      "grad_norm": 5.552521705627441,
      "learning_rate": 1.7065469378172963e-05,
      "loss": 0.5508,
      "step": 5000
    },
    {
      "epoch": 0.4841975526014614,
      "grad_norm": 2.075917959213257,
      "learning_rate": 1.6772016315990257e-05,
      "loss": 0.5487,
      "step": 5500
    },
    {
      "epoch": 0.528215511928867,
      "grad_norm": 2.551165819168091,
      "learning_rate": 1.6478563253807555e-05,
      "loss": 0.5185,
      "step": 6000
    },
    {
      "epoch": 0.5722334712562726,
      "grad_norm": 1.3819420337677002,
      "learning_rate": 1.6185110191624852e-05,
      "loss": 0.5338,
      "step": 6500
    },
    {
      "epoch": 0.6162514305836782,
      "grad_norm": 1.1496446132659912,
      "learning_rate": 1.5891657129442147e-05,
      "loss": 0.5291,
      "step": 7000
    },
    {
      "epoch": 0.6602693899110837,
      "grad_norm": 2.217291831970215,
      "learning_rate": 1.5598204067259444e-05,
      "loss": 0.5396,
      "step": 7500
    },
    {
      "epoch": 0.7042873492384893,
      "grad_norm": 0.9094293117523193,
      "learning_rate": 1.5304751005076738e-05,
      "loss": 0.5232,
      "step": 8000
    },
    {
      "epoch": 0.7483053085658948,
      "grad_norm": 1.1623644828796387,
      "learning_rate": 1.5011297942894036e-05,
      "loss": 0.5318,
      "step": 8500
    },
    {
      "epoch": 0.7923232678933004,
      "grad_norm": 4.72590970993042,
      "learning_rate": 1.4717844880711332e-05,
      "loss": 0.5251,
      "step": 9000
    },
    {
      "epoch": 0.836341227220706,
      "grad_norm": 3.225889205932617,
      "learning_rate": 1.4424391818528627e-05,
      "loss": 0.5254,
      "step": 9500
    },
    {
      "epoch": 0.8803591865481116,
      "grad_norm": 1.6131037473678589,
      "learning_rate": 1.4130938756345925e-05,
      "loss": 0.5248,
      "step": 10000
    },
    {
      "epoch": 0.9243771458755172,
      "grad_norm": 1.3447926044464111,
      "learning_rate": 1.3837485694163219e-05,
      "loss": 0.5351,
      "step": 10500
    },
    {
      "epoch": 0.9683951052029228,
      "grad_norm": 2.7240824699401855,
      "learning_rate": 1.3544032631980515e-05,
      "loss": 0.5108,
      "step": 11000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.48541975021362305,
      "eval_mse": 0.48541975021362305,
      "eval_runtime": 4.5323,
      "eval_samples_per_second": 2227.781,
      "eval_steps_per_second": 139.443,
      "step": 11359
    },
    {
      "epoch": 1.0124130645303284,
      "grad_norm": 1.8170539140701294,
      "learning_rate": 1.3250579569797812e-05,
      "loss": 0.5247,
      "step": 11500
    },
    {
      "epoch": 1.056431023857734,
      "grad_norm": 3.0960614681243896,
      "learning_rate": 1.2957126507615108e-05,
      "loss": 0.5071,
      "step": 12000
    },
    {
      "epoch": 1.1004489831851396,
      "grad_norm": 1.9027760028839111,
      "learning_rate": 1.2663673445432406e-05,
      "loss": 0.4881,
      "step": 12500
    },
    {
      "epoch": 1.144466942512545,
      "grad_norm": 2.4669666290283203,
      "learning_rate": 1.23702203832497e-05,
      "loss": 0.497,
      "step": 13000
    },
    {
      "epoch": 1.1884849018399506,
      "grad_norm": 4.2728095054626465,
      "learning_rate": 1.2076767321066996e-05,
      "loss": 0.5037,
      "step": 13500
    },
    {
      "epoch": 1.2325028611673563,
      "grad_norm": 2.4737207889556885,
      "learning_rate": 1.1783314258884293e-05,
      "loss": 0.5081,
      "step": 14000
    },
    {
      "epoch": 1.2765208204947618,
      "grad_norm": 3.5890121459960938,
      "learning_rate": 1.1489861196701589e-05,
      "loss": 0.5156,
      "step": 14500
    },
    {
      "epoch": 1.3205387798221675,
      "grad_norm": 0.9171675443649292,
      "learning_rate": 1.1196408134518883e-05,
      "loss": 0.5041,
      "step": 15000
    },
    {
      "epoch": 1.364556739149573,
      "grad_norm": 0.7652862071990967,
      "learning_rate": 1.090295507233618e-05,
      "loss": 0.4898,
      "step": 15500
    },
    {
      "epoch": 1.4085746984769787,
      "grad_norm": 1.9014813899993896,
      "learning_rate": 1.0609502010153477e-05,
      "loss": 0.5096,
      "step": 16000
    },
    {
      "epoch": 1.4525926578043842,
      "grad_norm": 3.0211782455444336,
      "learning_rate": 1.0316048947970774e-05,
      "loss": 0.5192,
      "step": 16500
    },
    {
      "epoch": 1.4966106171317897,
      "grad_norm": 1.619178295135498,
      "learning_rate": 1.0022595885788068e-05,
      "loss": 0.5106,
      "step": 17000
    },
    {
      "epoch": 1.5406285764591954,
      "grad_norm": 2.8226287364959717,
      "learning_rate": 9.729142823605366e-06,
      "loss": 0.5127,
      "step": 17500
    },
    {
      "epoch": 1.584646535786601,
      "grad_norm": 1.5159013271331787,
      "learning_rate": 9.435689761422662e-06,
      "loss": 0.521,
      "step": 18000
    },
    {
      "epoch": 1.6286644951140063,
      "grad_norm": 1.251665472984314,
      "learning_rate": 9.142236699239957e-06,
      "loss": 0.5104,
      "step": 18500
    },
    {
      "epoch": 1.672682454441412,
      "grad_norm": 1.2266521453857422,
      "learning_rate": 8.848783637057253e-06,
      "loss": 0.4991,
      "step": 19000
    },
    {
      "epoch": 1.7167004137688178,
      "grad_norm": 3.0873475074768066,
      "learning_rate": 8.555330574874549e-06,
      "loss": 0.495,
      "step": 19500
    },
    {
      "epoch": 1.7607183730962233,
      "grad_norm": 1.2593939304351807,
      "learning_rate": 8.261877512691847e-06,
      "loss": 0.5173,
      "step": 20000
    },
    {
      "epoch": 1.8047363324236287,
      "grad_norm": 1.4156285524368286,
      "learning_rate": 7.96842445050914e-06,
      "loss": 0.5047,
      "step": 20500
    },
    {
      "epoch": 1.8487542917510345,
      "grad_norm": 1.6748478412628174,
      "learning_rate": 7.674971388326438e-06,
      "loss": 0.5194,
      "step": 21000
    },
    {
      "epoch": 1.8927722510784402,
      "grad_norm": 2.2740602493286133,
      "learning_rate": 7.381518326143734e-06,
      "loss": 0.5165,
      "step": 21500
    },
    {
      "epoch": 1.9367902104058454,
      "grad_norm": 3.551628589630127,
      "learning_rate": 7.088065263961031e-06,
      "loss": 0.5218,
      "step": 22000
    },
    {
      "epoch": 1.9808081697332511,
      "grad_norm": 3.0715420246124268,
      "learning_rate": 6.794612201778326e-06,
      "loss": 0.5048,
      "step": 22500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.46880388259887695,
      "eval_mse": 0.46880388259887695,
      "eval_runtime": 4.5138,
      "eval_samples_per_second": 2236.922,
      "eval_steps_per_second": 140.015,
      "step": 22718
    },
    {
      "epoch": 2.024826129060657,
      "grad_norm": 1.7051458358764648,
      "learning_rate": 6.501159139595622e-06,
      "loss": 0.5349,
      "step": 23000
    },
    {
      "epoch": 2.0688440883880626,
      "grad_norm": 2.6633028984069824,
      "learning_rate": 6.207706077412918e-06,
      "loss": 0.4895,
      "step": 23500
    },
    {
      "epoch": 2.112862047715468,
      "grad_norm": 1.9820642471313477,
      "learning_rate": 5.914253015230215e-06,
      "loss": 0.5008,
      "step": 24000
    },
    {
      "epoch": 2.1568800070428735,
      "grad_norm": 1.2028346061706543,
      "learning_rate": 5.620799953047511e-06,
      "loss": 0.4816,
      "step": 24500
    },
    {
      "epoch": 2.2008979663702792,
      "grad_norm": 1.2734020948410034,
      "learning_rate": 5.3273468908648065e-06,
      "loss": 0.4952,
      "step": 25000
    },
    {
      "epoch": 2.2449159256976845,
      "grad_norm": 1.3878185749053955,
      "learning_rate": 5.033893828682102e-06,
      "loss": 0.5007,
      "step": 25500
    },
    {
      "epoch": 2.28893388502509,
      "grad_norm": 2.8702523708343506,
      "learning_rate": 4.740440766499399e-06,
      "loss": 0.5138,
      "step": 26000
    },
    {
      "epoch": 2.332951844352496,
      "grad_norm": 2.3792970180511475,
      "learning_rate": 4.446987704316695e-06,
      "loss": 0.4914,
      "step": 26500
    },
    {
      "epoch": 2.376969803679901,
      "grad_norm": 1.627300500869751,
      "learning_rate": 4.1535346421339915e-06,
      "loss": 0.5116,
      "step": 27000
    },
    {
      "epoch": 2.420987763007307,
      "grad_norm": 3.074572801589966,
      "learning_rate": 3.860081579951287e-06,
      "loss": 0.5001,
      "step": 27500
    },
    {
      "epoch": 2.4650057223347126,
      "grad_norm": 3.1290581226348877,
      "learning_rate": 3.566628517768583e-06,
      "loss": 0.5009,
      "step": 28000
    },
    {
      "epoch": 2.5090236816621183,
      "grad_norm": 1.4590922594070435,
      "learning_rate": 3.273175455585879e-06,
      "loss": 0.4948,
      "step": 28500
    },
    {
      "epoch": 2.5530416409895236,
      "grad_norm": 1.742438554763794,
      "learning_rate": 2.9797223934031757e-06,
      "loss": 0.4972,
      "step": 29000
    },
    {
      "epoch": 2.5970596003169293,
      "grad_norm": 1.680262565612793,
      "learning_rate": 2.6862693312204715e-06,
      "loss": 0.5051,
      "step": 29500
    },
    {
      "epoch": 2.641077559644335,
      "grad_norm": 2.896779775619507,
      "learning_rate": 2.3928162690377677e-06,
      "loss": 0.4851,
      "step": 30000
    },
    {
      "epoch": 2.6850955189717407,
      "grad_norm": 2.4820384979248047,
      "learning_rate": 2.0993632068550636e-06,
      "loss": 0.5053,
      "step": 30500
    },
    {
      "epoch": 2.729113478299146,
      "grad_norm": 4.39924430847168,
      "learning_rate": 1.8059101446723598e-06,
      "loss": 0.4989,
      "step": 31000
    },
    {
      "epoch": 2.7731314376265517,
      "grad_norm": 1.578857660293579,
      "learning_rate": 1.5124570824896559e-06,
      "loss": 0.5038,
      "step": 31500
    },
    {
      "epoch": 2.8171493969539574,
      "grad_norm": 4.331024646759033,
      "learning_rate": 1.219004020306952e-06,
      "loss": 0.505,
      "step": 32000
    },
    {
      "epoch": 2.8611673562813627,
      "grad_norm": 1.4179637432098389,
      "learning_rate": 9.25550958124248e-07,
      "loss": 0.5041,
      "step": 32500
    },
    {
      "epoch": 2.9051853156087684,
      "grad_norm": 4.137328147888184,
      "learning_rate": 6.320978959415442e-07,
      "loss": 0.4894,
      "step": 33000
    },
    {
      "epoch": 2.949203274936174,
      "grad_norm": 1.429250717163086,
      "learning_rate": 3.386448337588403e-07,
      "loss": 0.4982,
      "step": 33500
    },
    {
      "epoch": 2.9932212342635793,
      "grad_norm": 3.0007667541503906,
      "learning_rate": 4.519177157613641e-08,
      "loss": 0.5104,
      "step": 34000
    }
  ],
  "logging_steps": 500,
  "max_steps": 34077,
  "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": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}