trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04387311894002545,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002193655947001272,
      "grad_norm": 3.5356061458587646,
      "learning_rate": 2.997806344052999e-05,
      "loss": 0.2274,
      "step": 50
    },
    {
      "epoch": 0.004387311894002544,
      "grad_norm": 0.4738060534000397,
      "learning_rate": 2.9956126881059976e-05,
      "loss": 0.0055,
      "step": 100
    },
    {
      "epoch": 0.006580967841003817,
      "grad_norm": 0.18818098306655884,
      "learning_rate": 2.993419032158996e-05,
      "loss": 0.0014,
      "step": 150
    },
    {
      "epoch": 0.008774623788005089,
      "grad_norm": 0.009225570596754551,
      "learning_rate": 2.991225376211995e-05,
      "loss": 0.0005,
      "step": 200
    },
    {
      "epoch": 0.010968279735006362,
      "grad_norm": 0.032771218568086624,
      "learning_rate": 2.9890317202649936e-05,
      "loss": 0.0009,
      "step": 250
    },
    {
      "epoch": 0.013161935682007634,
      "grad_norm": 0.03574460744857788,
      "learning_rate": 2.9868380643179925e-05,
      "loss": 0.0005,
      "step": 300
    },
    {
      "epoch": 0.015355591629008906,
      "grad_norm": 0.0016715412493795156,
      "learning_rate": 2.984644408370991e-05,
      "loss": 0.0001,
      "step": 350
    },
    {
      "epoch": 0.017549247576010178,
      "grad_norm": 0.0006590808043256402,
      "learning_rate": 2.9824507524239897e-05,
      "loss": 0.0001,
      "step": 400
    },
    {
      "epoch": 0.01974290352301145,
      "grad_norm": 0.00635514734312892,
      "learning_rate": 2.9802570964769886e-05,
      "loss": 0.0002,
      "step": 450
    },
    {
      "epoch": 0.021936559470012724,
      "grad_norm": 0.0005727710667997599,
      "learning_rate": 2.9780634405299875e-05,
      "loss": 0.0001,
      "step": 500
    },
    {
      "epoch": 0.024130215417013996,
      "grad_norm": 0.0005088996258564293,
      "learning_rate": 2.975869784582986e-05,
      "loss": 0.0002,
      "step": 550
    },
    {
      "epoch": 0.026323871364015268,
      "grad_norm": 0.010593525134027004,
      "learning_rate": 2.9736761286359847e-05,
      "loss": 0.0002,
      "step": 600
    },
    {
      "epoch": 0.02851752731101654,
      "grad_norm": 0.006351508665829897,
      "learning_rate": 2.9714824726889836e-05,
      "loss": 0.0001,
      "step": 650
    },
    {
      "epoch": 0.03071118325801781,
      "grad_norm": 0.0015719968359917402,
      "learning_rate": 2.969288816741982e-05,
      "loss": 0.0,
      "step": 700
    },
    {
      "epoch": 0.03290483920501908,
      "grad_norm": 0.0007212675409391522,
      "learning_rate": 2.967095160794981e-05,
      "loss": 0.0,
      "step": 750
    },
    {
      "epoch": 0.035098495152020355,
      "grad_norm": 0.00027612957637757063,
      "learning_rate": 2.96490150484798e-05,
      "loss": 0.0,
      "step": 800
    },
    {
      "epoch": 0.03729215109902163,
      "grad_norm": 0.0005350236897356808,
      "learning_rate": 2.9627078489009782e-05,
      "loss": 0.0,
      "step": 850
    },
    {
      "epoch": 0.0394858070460229,
      "grad_norm": 0.0006030969670973718,
      "learning_rate": 2.960514192953977e-05,
      "loss": 0.0,
      "step": 900
    },
    {
      "epoch": 0.04167946299302418,
      "grad_norm": 0.00019211292965337634,
      "learning_rate": 2.958320537006976e-05,
      "loss": 0.0001,
      "step": 950
    },
    {
      "epoch": 0.04387311894002545,
      "grad_norm": 0.00020958702953066677,
      "learning_rate": 2.9561268810599746e-05,
      "loss": 0.0,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 68379,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}