{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 21460,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11649580615097857,
      "grad_norm": 2.5263092517852783,
      "learning_rate": 4.883504193849022e-05,
      "loss": 0.612,
      "step": 500
    },
    {
      "epoch": 0.23299161230195714,
      "grad_norm": 2.820680856704712,
      "learning_rate": 4.767008387698043e-05,
      "loss": 0.4835,
      "step": 1000
    },
    {
      "epoch": 0.3494874184529357,
      "grad_norm": 2.4191653728485107,
      "learning_rate": 4.650512581547065e-05,
      "loss": 0.4403,
      "step": 1500
    },
    {
      "epoch": 0.4659832246039143,
      "grad_norm": 2.0218257904052734,
      "learning_rate": 4.534016775396086e-05,
      "loss": 0.4163,
      "step": 2000
    },
    {
      "epoch": 0.5824790307548928,
      "grad_norm": 2.193092107772827,
      "learning_rate": 4.4175209692451076e-05,
      "loss": 0.4056,
      "step": 2500
    },
    {
      "epoch": 0.6989748369058714,
      "grad_norm": 2.5563910007476807,
      "learning_rate": 4.3010251630941286e-05,
      "loss": 0.3903,
      "step": 3000
    },
    {
      "epoch": 0.8154706430568499,
      "grad_norm": 2.4142184257507324,
      "learning_rate": 4.1845293569431504e-05,
      "loss": 0.3818,
      "step": 3500
    },
    {
      "epoch": 0.9319664492078286,
      "grad_norm": 2.6781787872314453,
      "learning_rate": 4.068033550792172e-05,
      "loss": 0.3752,
      "step": 4000
    },
    {
      "epoch": 1.048462255358807,
      "grad_norm": 3.981492757797241,
      "learning_rate": 3.951537744641193e-05,
      "loss": 0.3407,
      "step": 4500
    },
    {
      "epoch": 1.1649580615097856,
      "grad_norm": 2.2366013526916504,
      "learning_rate": 3.835041938490215e-05,
      "loss": 0.3079,
      "step": 5000
    },
    {
      "epoch": 1.281453867660764,
      "grad_norm": 2.7982800006866455,
      "learning_rate": 3.718546132339236e-05,
      "loss": 0.3003,
      "step": 5500
    },
    {
      "epoch": 1.3979496738117427,
      "grad_norm": 2.147766590118408,
      "learning_rate": 3.602050326188258e-05,
      "loss": 0.3042,
      "step": 6000
    },
    {
      "epoch": 1.5144454799627214,
      "grad_norm": 3.3207345008850098,
      "learning_rate": 3.485554520037279e-05,
      "loss": 0.2994,
      "step": 6500
    },
    {
      "epoch": 1.6309412861136998,
      "grad_norm": 2.8516502380371094,
      "learning_rate": 3.3690587138863e-05,
      "loss": 0.3019,
      "step": 7000
    },
    {
      "epoch": 1.7474370922646785,
      "grad_norm": 2.4767708778381348,
      "learning_rate": 3.2525629077353216e-05,
      "loss": 0.3029,
      "step": 7500
    },
    {
      "epoch": 1.8639328984156571,
      "grad_norm": 2.9029157161712646,
      "learning_rate": 3.1360671015843426e-05,
      "loss": 0.2971,
      "step": 8000
    },
    {
      "epoch": 1.9804287045666356,
      "grad_norm": 3.0262856483459473,
      "learning_rate": 3.0195712954333644e-05,
      "loss": 0.2926,
      "step": 8500
    },
    {
      "epoch": 2.096924510717614,
      "grad_norm": 2.862046957015991,
      "learning_rate": 2.9030754892823857e-05,
      "loss": 0.2322,
      "step": 9000
    },
    {
      "epoch": 2.213420316868593,
      "grad_norm": 2.759274482727051,
      "learning_rate": 2.786579683131407e-05,
      "loss": 0.2295,
      "step": 9500
    },
    {
      "epoch": 2.3299161230195713,
      "grad_norm": 3.3560988903045654,
      "learning_rate": 2.670083876980429e-05,
      "loss": 0.2288,
      "step": 10000
    },
    {
      "epoch": 2.4464119291705497,
      "grad_norm": 2.7938876152038574,
      "learning_rate": 2.5535880708294503e-05,
      "loss": 0.228,
      "step": 10500
    },
    {
      "epoch": 2.562907735321528,
      "grad_norm": 3.100569486618042,
      "learning_rate": 2.4370922646784717e-05,
      "loss": 0.2288,
      "step": 11000
    },
    {
      "epoch": 2.679403541472507,
      "grad_norm": 2.6765120029449463,
      "learning_rate": 2.320596458527493e-05,
      "loss": 0.2307,
      "step": 11500
    },
    {
      "epoch": 2.7958993476234855,
      "grad_norm": 2.7146239280700684,
      "learning_rate": 2.2041006523765145e-05,
      "loss": 0.2275,
      "step": 12000
    },
    {
      "epoch": 2.9123951537744643,
      "grad_norm": 3.6457717418670654,
      "learning_rate": 2.087604846225536e-05,
      "loss": 0.2328,
      "step": 12500
    },
    {
      "epoch": 3.0288909599254428,
      "grad_norm": 3.6852147579193115,
      "learning_rate": 1.9711090400745573e-05,
      "loss": 0.2172,
      "step": 13000
    },
    {
      "epoch": 3.145386766076421,
      "grad_norm": 3.0440313816070557,
      "learning_rate": 1.854613233923579e-05,
      "loss": 0.1749,
      "step": 13500
    },
    {
      "epoch": 3.2618825722273996,
      "grad_norm": 2.364924192428589,
      "learning_rate": 1.7381174277726004e-05,
      "loss": 0.1767,
      "step": 14000
    },
    {
      "epoch": 3.3783783783783785,
      "grad_norm": 2.6927711963653564,
      "learning_rate": 1.6216216216216218e-05,
      "loss": 0.172,
      "step": 14500
    },
    {
      "epoch": 3.494874184529357,
      "grad_norm": 3.143772602081299,
      "learning_rate": 1.5051258154706432e-05,
      "loss": 0.1787,
      "step": 15000
    },
    {
      "epoch": 3.6113699906803354,
      "grad_norm": 2.1713764667510986,
      "learning_rate": 1.3886300093196648e-05,
      "loss": 0.1724,
      "step": 15500
    },
    {
      "epoch": 3.7278657968313142,
      "grad_norm": 4.549355506896973,
      "learning_rate": 1.2721342031686858e-05,
      "loss": 0.1744,
      "step": 16000
    },
    {
      "epoch": 3.8443616029822927,
      "grad_norm": 1.8248041868209839,
      "learning_rate": 1.1556383970177074e-05,
      "loss": 0.1781,
      "step": 16500
    },
    {
      "epoch": 3.960857409133271,
      "grad_norm": 3.255676507949829,
      "learning_rate": 1.039142590866729e-05,
      "loss": 0.1752,
      "step": 17000
    },
    {
      "epoch": 4.0773532152842495,
      "grad_norm": 4.369929790496826,
      "learning_rate": 9.226467847157502e-06,
      "loss": 0.1491,
      "step": 17500
    },
    {
      "epoch": 4.193849021435228,
      "grad_norm": 3.5270001888275146,
      "learning_rate": 8.061509785647716e-06,
      "loss": 0.1355,
      "step": 18000
    },
    {
      "epoch": 4.310344827586207,
      "grad_norm": 3.747748613357544,
      "learning_rate": 6.896551724137932e-06,
      "loss": 0.1402,
      "step": 18500
    },
    {
      "epoch": 4.426840633737186,
      "grad_norm": 2.4927761554718018,
      "learning_rate": 5.731593662628146e-06,
      "loss": 0.1341,
      "step": 19000
    },
    {
      "epoch": 4.543336439888164,
      "grad_norm": 3.129467010498047,
      "learning_rate": 4.56663560111836e-06,
      "loss": 0.1349,
      "step": 19500
    },
    {
      "epoch": 4.659832246039143,
      "grad_norm": 5.417072772979736,
      "learning_rate": 3.401677539608574e-06,
      "loss": 0.1322,
      "step": 20000
    },
    {
      "epoch": 4.776328052190121,
      "grad_norm": 3.4678492546081543,
      "learning_rate": 2.2367194780987884e-06,
      "loss": 0.1402,
      "step": 20500
    },
    {
      "epoch": 4.8928238583410995,
      "grad_norm": 3.649914026260376,
      "learning_rate": 1.0717614165890028e-06,
      "loss": 0.1375,
      "step": 21000
    }
  ],
  "logging_steps": 500,
  "max_steps": 21460,
  "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": 9.096814400558976e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}