{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1955,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1278772378516624,
      "grad_norm": 0.15987633168697357,
      "learning_rate": 1.9498721227621484e-05,
      "loss": 0.0362,
      "step": 50
    },
    {
      "epoch": 0.2557544757033248,
      "grad_norm": 0.04608326032757759,
      "learning_rate": 1.8987212276214835e-05,
      "loss": 0.0168,
      "step": 100
    },
    {
      "epoch": 0.3836317135549872,
      "grad_norm": 0.03889036923646927,
      "learning_rate": 1.8475703324808185e-05,
      "loss": 0.0254,
      "step": 150
    },
    {
      "epoch": 0.5115089514066496,
      "grad_norm": 0.05562173202633858,
      "learning_rate": 1.7964194373401536e-05,
      "loss": 0.0502,
      "step": 200
    },
    {
      "epoch": 0.639386189258312,
      "grad_norm": 0.11458363384008408,
      "learning_rate": 1.7452685421994886e-05,
      "loss": 0.0353,
      "step": 250
    },
    {
      "epoch": 0.7672634271099744,
      "grad_norm": 0.0313524566590786,
      "learning_rate": 1.6941176470588237e-05,
      "loss": 0.0423,
      "step": 300
    },
    {
      "epoch": 0.8951406649616368,
      "grad_norm": 0.06919269263744354,
      "learning_rate": 1.6429667519181587e-05,
      "loss": 0.0414,
      "step": 350
    },
    {
      "epoch": 1.0230179028132993,
      "grad_norm": 0.04081420600414276,
      "learning_rate": 1.5918158567774937e-05,
      "loss": 0.0444,
      "step": 400
    },
    {
      "epoch": 1.1508951406649617,
      "grad_norm": 0.2047465294599533,
      "learning_rate": 1.5406649616368288e-05,
      "loss": 0.0103,
      "step": 450
    },
    {
      "epoch": 1.278772378516624,
      "grad_norm": 0.025791389867663383,
      "learning_rate": 1.4895140664961638e-05,
      "loss": 0.0209,
      "step": 500
    },
    {
      "epoch": 1.4066496163682864,
      "grad_norm": 0.9749135375022888,
      "learning_rate": 1.4383631713554989e-05,
      "loss": 0.0443,
      "step": 550
    },
    {
      "epoch": 1.5345268542199488,
      "grad_norm": 0.049570031464099884,
      "learning_rate": 1.3872122762148339e-05,
      "loss": 0.0334,
      "step": 600
    },
    {
      "epoch": 1.6624040920716112,
      "grad_norm": 0.03414261341094971,
      "learning_rate": 1.336061381074169e-05,
      "loss": 0.0263,
      "step": 650
    },
    {
      "epoch": 1.7902813299232738,
      "grad_norm": 0.05060505494475365,
      "learning_rate": 1.284910485933504e-05,
      "loss": 0.0324,
      "step": 700
    },
    {
      "epoch": 1.918158567774936,
      "grad_norm": 0.02642514370381832,
      "learning_rate": 1.233759590792839e-05,
      "loss": 0.0135,
      "step": 750
    },
    {
      "epoch": 2.0460358056265986,
      "grad_norm": 0.025779355317354202,
      "learning_rate": 1.182608695652174e-05,
      "loss": 0.0077,
      "step": 800
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 0.02975759282708168,
      "learning_rate": 1.1314578005115091e-05,
      "loss": 0.019,
      "step": 850
    },
    {
      "epoch": 2.3017902813299234,
      "grad_norm": 0.022426923736929893,
      "learning_rate": 1.0803069053708442e-05,
      "loss": 0.0122,
      "step": 900
    },
    {
      "epoch": 2.4296675191815855,
      "grad_norm": 0.02004999853670597,
      "learning_rate": 1.0291560102301792e-05,
      "loss": 0.0067,
      "step": 950
    },
    {
      "epoch": 2.557544757033248,
      "grad_norm": 0.01824093610048294,
      "learning_rate": 9.78005115089514e-06,
      "loss": 0.0266,
      "step": 1000
    },
    {
      "epoch": 2.6854219948849103,
      "grad_norm": 0.018175149336457253,
      "learning_rate": 9.278772378516625e-06,
      "loss": 0.0055,
      "step": 1050
    },
    {
      "epoch": 2.813299232736573,
      "grad_norm": 0.024839840829372406,
      "learning_rate": 8.767263427109976e-06,
      "loss": 0.0279,
      "step": 1100
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.03608064725995064,
      "learning_rate": 8.255754475703326e-06,
      "loss": 0.0061,
      "step": 1150
    },
    {
      "epoch": 3.0690537084398977,
      "grad_norm": 0.02351670153439045,
      "learning_rate": 7.744245524296677e-06,
      "loss": 0.0072,
      "step": 1200
    },
    {
      "epoch": 3.1969309462915603,
      "grad_norm": 0.023821713402867317,
      "learning_rate": 7.232736572890025e-06,
      "loss": 0.0074,
      "step": 1250
    },
    {
      "epoch": 3.3248081841432224,
      "grad_norm": 0.05748629570007324,
      "learning_rate": 6.721227621483376e-06,
      "loss": 0.018,
      "step": 1300
    },
    {
      "epoch": 3.452685421994885,
      "grad_norm": 0.028405383229255676,
      "learning_rate": 6.209718670076726e-06,
      "loss": 0.0046,
      "step": 1350
    },
    {
      "epoch": 3.580562659846547,
      "grad_norm": 0.02582070790231228,
      "learning_rate": 5.6982097186700766e-06,
      "loss": 0.0022,
      "step": 1400
    },
    {
      "epoch": 3.70843989769821,
      "grad_norm": 0.10114799439907074,
      "learning_rate": 5.186700767263427e-06,
      "loss": 0.0158,
      "step": 1450
    },
    {
      "epoch": 3.836317135549872,
      "grad_norm": 0.019817985594272614,
      "learning_rate": 4.675191815856777e-06,
      "loss": 0.0111,
      "step": 1500
    },
    {
      "epoch": 3.9641943734015346,
      "grad_norm": 0.015444358810782433,
      "learning_rate": 4.163682864450128e-06,
      "loss": 0.0046,
      "step": 1550
    },
    {
      "epoch": 4.092071611253197,
      "grad_norm": 0.022258592769503593,
      "learning_rate": 3.6521739130434787e-06,
      "loss": 0.0043,
      "step": 1600
    },
    {
      "epoch": 4.21994884910486,
      "grad_norm": 0.01617886684834957,
      "learning_rate": 3.140664961636829e-06,
      "loss": 0.0031,
      "step": 1650
    },
    {
      "epoch": 4.3478260869565215,
      "grad_norm": 0.02081909030675888,
      "learning_rate": 2.6291560102301796e-06,
      "loss": 0.0051,
      "step": 1700
    },
    {
      "epoch": 4.475703324808184,
      "grad_norm": 0.014306459575891495,
      "learning_rate": 2.1176470588235296e-06,
      "loss": 0.0069,
      "step": 1750
    },
    {
      "epoch": 4.603580562659847,
      "grad_norm": 0.02191161923110485,
      "learning_rate": 1.60613810741688e-06,
      "loss": 0.0076,
      "step": 1800
    },
    {
      "epoch": 4.731457800511509,
      "grad_norm": 0.013770988211035728,
      "learning_rate": 1.0946291560102302e-06,
      "loss": 0.0144,
      "step": 1850
    },
    {
      "epoch": 4.859335038363171,
      "grad_norm": 0.14902222156524658,
      "learning_rate": 5.831202046035806e-07,
      "loss": 0.0091,
      "step": 1900
    },
    {
      "epoch": 4.987212276214834,
      "grad_norm": 0.012432758696377277,
      "learning_rate": 7.161125319693095e-08,
      "loss": 0.0052,
      "step": 1950
    }
  ],
  "logging_steps": 50,
  "max_steps": 1955,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 2.422012135404073e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}