{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 10100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9900990099009901,
      "grad_norm": 10830.5537109375,
      "learning_rate": 0.0005993999999999999,
      "loss": 1.2778,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17797619047619048,
      "eval_loss": 4.991881370544434,
      "eval_runtime": 6.3501,
      "eval_samples_per_second": 37.795,
      "eval_steps_per_second": 1.26,
      "step": 1010
    },
    {
      "epoch": 1.9801980198019802,
      "grad_norm": 12182.1923828125,
      "learning_rate": 0.0005341318681318681,
      "loss": 1.1301,
      "step": 2000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.20255218525766472,
      "eval_loss": 4.643928050994873,
      "eval_runtime": 5.6378,
      "eval_samples_per_second": 42.57,
      "eval_steps_per_second": 1.419,
      "step": 2020
    },
    {
      "epoch": 2.9702970297029703,
      "grad_norm": 11544.783203125,
      "learning_rate": 0.00046819780219780217,
      "loss": 1.0468,
      "step": 3000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.23992987606001304,
      "eval_loss": 4.329844951629639,
      "eval_runtime": 5.6063,
      "eval_samples_per_second": 42.809,
      "eval_steps_per_second": 1.427,
      "step": 3030
    },
    {
      "epoch": 3.9603960396039604,
      "grad_norm": 10567.1142578125,
      "learning_rate": 0.0004022637362637362,
      "loss": 0.9842,
      "step": 4000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.2685665362035225,
      "eval_loss": 4.115429878234863,
      "eval_runtime": 5.663,
      "eval_samples_per_second": 42.381,
      "eval_steps_per_second": 1.413,
      "step": 4040
    },
    {
      "epoch": 4.9504950495049505,
      "grad_norm": 10359.140625,
      "learning_rate": 0.0003363296703296703,
      "loss": 0.9369,
      "step": 5000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.2893183300717547,
      "eval_loss": 3.944108486175537,
      "eval_runtime": 5.7246,
      "eval_samples_per_second": 41.924,
      "eval_steps_per_second": 1.397,
      "step": 5050
    },
    {
      "epoch": 5.9405940594059405,
      "grad_norm": 10749.0302734375,
      "learning_rate": 0.00027039560439560435,
      "loss": 0.9021,
      "step": 6000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.30401174168297457,
      "eval_loss": 3.8409361839294434,
      "eval_runtime": 5.6946,
      "eval_samples_per_second": 42.145,
      "eval_steps_per_second": 1.405,
      "step": 6060
    },
    {
      "epoch": 6.930693069306931,
      "grad_norm": 10786.7880859375,
      "learning_rate": 0.00020446153846153845,
      "loss": 0.8748,
      "step": 7000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3148401826484018,
      "eval_loss": 3.7550878524780273,
      "eval_runtime": 5.6957,
      "eval_samples_per_second": 42.137,
      "eval_steps_per_second": 1.405,
      "step": 7070
    },
    {
      "epoch": 7.920792079207921,
      "grad_norm": 11502.447265625,
      "learning_rate": 0.00013852747252747252,
      "loss": 0.851,
      "step": 8000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.323899217221135,
      "eval_loss": 3.684725284576416,
      "eval_runtime": 5.6021,
      "eval_samples_per_second": 42.841,
      "eval_steps_per_second": 1.428,
      "step": 8080
    },
    {
      "epoch": 8.910891089108912,
      "grad_norm": 11624.4814453125,
      "learning_rate": 7.25934065934066e-05,
      "loss": 0.8329,
      "step": 9000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.33088714938030006,
      "eval_loss": 3.6328799724578857,
      "eval_runtime": 5.5532,
      "eval_samples_per_second": 43.219,
      "eval_steps_per_second": 1.441,
      "step": 9090
    },
    {
      "epoch": 9.900990099009901,
      "grad_norm": 12129.1943359375,
      "learning_rate": 6.659340659340659e-06,
      "loss": 0.8156,
      "step": 10000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.3351108936725375,
      "eval_loss": 3.6097142696380615,
      "eval_runtime": 5.5755,
      "eval_samples_per_second": 43.045,
      "eval_steps_per_second": 1.435,
      "step": 10100
    },
    {
      "epoch": 10.0,
      "step": 10100,
      "total_flos": 8.444174598144e+16,
      "train_loss": 0.9637339843145691,
      "train_runtime": 10989.9202,
      "train_samples_per_second": 29.406,
      "train_steps_per_second": 0.919
    }
  ],
  "logging_steps": 1000,
  "max_steps": 10100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 8.444174598144e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}