{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.99988330026841,
  "eval_steps": 250,
  "global_step": 5355,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2333994631812347,
      "grad_norm": 1.2788289785385132,
      "learning_rate": 9.992757124875143e-05,
      "loss": 0.3573,
      "step": 250
    },
    {
      "epoch": 0.2333994631812347,
      "eval_loss": 0.18718622624874115,
      "eval_runtime": 18.4863,
      "eval_samples_per_second": 4.706,
      "eval_steps_per_second": 4.706,
      "step": 250
    },
    {
      "epoch": 0.4667989263624694,
      "grad_norm": 1.7301123142242432,
      "learning_rate": 9.895259863857224e-05,
      "loss": 0.1155,
      "step": 500
    },
    {
      "epoch": 0.4667989263624694,
      "eval_loss": 0.11222057044506073,
      "eval_runtime": 18.4689,
      "eval_samples_per_second": 4.711,
      "eval_steps_per_second": 4.711,
      "step": 500
    },
    {
      "epoch": 0.7001983895437041,
      "grad_norm": 0.40849488973617554,
      "learning_rate": 9.686044398977847e-05,
      "loss": 0.079,
      "step": 750
    },
    {
      "epoch": 0.7001983895437041,
      "eval_loss": 0.0827888771891594,
      "eval_runtime": 18.4255,
      "eval_samples_per_second": 4.722,
      "eval_steps_per_second": 4.722,
      "step": 750
    },
    {
      "epoch": 0.9335978527249388,
      "grad_norm": 0.27379560470581055,
      "learning_rate": 9.369885385026829e-05,
      "loss": 0.0672,
      "step": 1000
    },
    {
      "epoch": 0.9335978527249388,
      "eval_loss": 0.07405883818864822,
      "eval_runtime": 18.0866,
      "eval_samples_per_second": 4.81,
      "eval_steps_per_second": 4.81,
      "step": 1000
    },
    {
      "epoch": 1.1669973159061735,
      "grad_norm": 0.15424582362174988,
      "learning_rate": 8.953998111520053e-05,
      "loss": 0.0555,
      "step": 1250
    },
    {
      "epoch": 1.1669973159061735,
      "eval_loss": 0.07201890647411346,
      "eval_runtime": 18.1777,
      "eval_samples_per_second": 4.786,
      "eval_steps_per_second": 4.786,
      "step": 1250
    },
    {
      "epoch": 1.4003967790874081,
      "grad_norm": 0.1671038419008255,
      "learning_rate": 8.447873837450339e-05,
      "loss": 0.055,
      "step": 1500
    },
    {
      "epoch": 1.4003967790874081,
      "eval_loss": 0.07005530595779419,
      "eval_runtime": 18.0977,
      "eval_samples_per_second": 4.807,
      "eval_steps_per_second": 4.807,
      "step": 1500
    },
    {
      "epoch": 1.6337962422686427,
      "grad_norm": 0.12481052428483963,
      "learning_rate": 7.863063184521596e-05,
      "loss": 0.053,
      "step": 1750
    },
    {
      "epoch": 1.6337962422686427,
      "eval_loss": 0.06806331127882004,
      "eval_runtime": 18.1718,
      "eval_samples_per_second": 4.788,
      "eval_steps_per_second": 4.788,
      "step": 1750
    },
    {
      "epoch": 1.8671957054498773,
      "grad_norm": 0.14744804799556732,
      "learning_rate": 7.212912532203201e-05,
      "loss": 0.0526,
      "step": 2000
    },
    {
      "epoch": 1.8671957054498773,
      "eval_loss": 0.06636130809783936,
      "eval_runtime": 18.0865,
      "eval_samples_per_second": 4.81,
      "eval_steps_per_second": 4.81,
      "step": 2000
    },
    {
      "epoch": 2.100595168631112,
      "grad_norm": 0.07688289880752563,
      "learning_rate": 6.51225943052036e-05,
      "loss": 0.047,
      "step": 2250
    },
    {
      "epoch": 2.100595168631112,
      "eval_loss": 0.06469345092773438,
      "eval_runtime": 18.051,
      "eval_samples_per_second": 4.82,
      "eval_steps_per_second": 4.82,
      "step": 2250
    },
    {
      "epoch": 2.333994631812347,
      "grad_norm": 0.09491775184869766,
      "learning_rate": 5.777093981781615e-05,
      "loss": 0.0406,
      "step": 2500
    },
    {
      "epoch": 2.333994631812347,
      "eval_loss": 0.06455763429403305,
      "eval_runtime": 18.0482,
      "eval_samples_per_second": 4.82,
      "eval_steps_per_second": 4.82,
      "step": 2500
    },
    {
      "epoch": 2.5673940949935816,
      "grad_norm": 0.09282498061656952,
      "learning_rate": 5.024193919091694e-05,
      "loss": 0.0411,
      "step": 2750
    },
    {
      "epoch": 2.5673940949935816,
      "eval_loss": 0.062036558985710144,
      "eval_runtime": 18.1073,
      "eval_samples_per_second": 4.805,
      "eval_steps_per_second": 4.805,
      "step": 2750
    },
    {
      "epoch": 2.8010269576379976,
      "grad_norm": 0.08291701227426529,
      "learning_rate": 4.270741709782294e-05,
      "loss": 0.0352,
      "step": 3000
    },
    {
      "epoch": 2.8010269576379976,
      "eval_loss": 0.06604798883199692,
      "eval_runtime": 17.9809,
      "eval_samples_per_second": 4.838,
      "eval_steps_per_second": 4.838,
      "step": 3000
    },
    {
      "epoch": 3.034426420819232,
      "grad_norm": 0.19006969034671783,
      "learning_rate": 3.533932422115467e-05,
      "loss": 0.0337,
      "step": 3250
    },
    {
      "epoch": 3.034426420819232,
      "eval_loss": 0.06463699042797089,
      "eval_runtime": 18.651,
      "eval_samples_per_second": 4.665,
      "eval_steps_per_second": 4.665,
      "step": 3250
    },
    {
      "epoch": 3.267825884000467,
      "grad_norm": 0.25927212834358215,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0326,
      "step": 3500
    },
    {
      "epoch": 3.267825884000467,
      "eval_loss": 0.06334705650806427,
      "eval_runtime": 18.2494,
      "eval_samples_per_second": 4.767,
      "eval_steps_per_second": 4.767,
      "step": 3500
    },
    {
      "epoch": 3.5012253471817014,
      "grad_norm": 0.16726678609848022,
      "learning_rate": 2.1767400323218395e-05,
      "loss": 0.0323,
      "step": 3750
    },
    {
      "epoch": 3.5012253471817014,
      "eval_loss": 0.06246271729469299,
      "eval_runtime": 18.773,
      "eval_samples_per_second": 4.634,
      "eval_steps_per_second": 4.634,
      "step": 3750
    },
    {
      "epoch": 3.734624810362936,
      "grad_norm": 0.17899206280708313,
      "learning_rate": 1.587330382125886e-05,
      "loss": 0.0321,
      "step": 4000
    },
    {
      "epoch": 3.734624810362936,
      "eval_loss": 0.06137511879205704,
      "eval_runtime": 18.2283,
      "eval_samples_per_second": 4.773,
      "eval_steps_per_second": 4.773,
      "step": 4000
    },
    {
      "epoch": 3.968024273544171,
      "grad_norm": 0.18272684514522552,
      "learning_rate": 1.0758036902783486e-05,
      "loss": 0.0317,
      "step": 4250
    },
    {
      "epoch": 3.968024273544171,
      "eval_loss": 0.061556510627269745,
      "eval_runtime": 18.3575,
      "eval_samples_per_second": 4.739,
      "eval_steps_per_second": 4.739,
      "step": 4250
    },
    {
      "epoch": 4.201423736725405,
      "grad_norm": 0.08759083598852158,
      "learning_rate": 6.538338708981339e-06,
      "loss": 0.0271,
      "step": 4500
    },
    {
      "epoch": 4.201423736725405,
      "eval_loss": 0.06755289435386658,
      "eval_runtime": 18.3197,
      "eval_samples_per_second": 4.749,
      "eval_steps_per_second": 4.749,
      "step": 4500
    },
    {
      "epoch": 4.43482319990664,
      "grad_norm": 0.1162794902920723,
      "learning_rate": 3.310509970796161e-06,
      "loss": 0.0258,
      "step": 4750
    },
    {
      "epoch": 4.43482319990664,
      "eval_loss": 0.06878142058849335,
      "eval_runtime": 18.2508,
      "eval_samples_per_second": 4.767,
      "eval_steps_per_second": 4.767,
      "step": 4750
    },
    {
      "epoch": 4.6682226630878745,
      "grad_norm": 0.11602241545915604,
      "learning_rate": 1.148215261515445e-06,
      "loss": 0.0257,
      "step": 5000
    },
    {
      "epoch": 4.6682226630878745,
      "eval_loss": 0.0677771121263504,
      "eval_runtime": 18.0738,
      "eval_samples_per_second": 4.814,
      "eval_steps_per_second": 4.814,
      "step": 5000
    },
    {
      "epoch": 4.901855525732291,
      "grad_norm": 0.09153954684734344,
      "learning_rate": 1.0080184519835056e-07,
      "loss": 0.0227,
      "step": 5250
    },
    {
      "epoch": 4.901855525732291,
      "eval_loss": 0.06972444802522659,
      "eval_runtime": 18.058,
      "eval_samples_per_second": 4.818,
      "eval_steps_per_second": 4.818,
      "step": 5250
    }
  ],
  "logging_steps": 250,
  "max_steps": 5355,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9338931727998157e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}