{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.031813361611876985,
  "eval_steps": 4,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010604453870625664,
      "grad_norm": 50.370243072509766,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.3739,
      "step": 1
    },
    {
      "epoch": 0.0010604453870625664,
      "eval_loss": 2.191164255142212,
      "eval_runtime": 12.6474,
      "eval_samples_per_second": 31.39,
      "eval_steps_per_second": 7.907,
      "step": 1
    },
    {
      "epoch": 0.0021208907741251328,
      "grad_norm": 6.063844203948975,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8177,
      "step": 2
    },
    {
      "epoch": 0.003181336161187699,
      "grad_norm": 10.836545944213867,
      "learning_rate": 6e-06,
      "loss": 1.5552,
      "step": 3
    },
    {
      "epoch": 0.0042417815482502655,
      "grad_norm": 62.376041412353516,
      "learning_rate": 8.000000000000001e-06,
      "loss": 4.2674,
      "step": 4
    },
    {
      "epoch": 0.0042417815482502655,
      "eval_loss": 2.1745495796203613,
      "eval_runtime": 12.0434,
      "eval_samples_per_second": 32.964,
      "eval_steps_per_second": 8.303,
      "step": 4
    },
    {
      "epoch": 0.005302226935312832,
      "grad_norm": 67.61026000976562,
      "learning_rate": 1e-05,
      "loss": 3.6308,
      "step": 5
    },
    {
      "epoch": 0.006362672322375398,
      "grad_norm": 13.211626052856445,
      "learning_rate": 9.960573506572391e-06,
      "loss": 1.4316,
      "step": 6
    },
    {
      "epoch": 0.007423117709437964,
      "grad_norm": 15.127080917358398,
      "learning_rate": 9.842915805643156e-06,
      "loss": 2.0175,
      "step": 7
    },
    {
      "epoch": 0.008483563096500531,
      "grad_norm": 37.87991714477539,
      "learning_rate": 9.648882429441258e-06,
      "loss": 4.118,
      "step": 8
    },
    {
      "epoch": 0.008483563096500531,
      "eval_loss": 1.9948686361312866,
      "eval_runtime": 12.035,
      "eval_samples_per_second": 32.987,
      "eval_steps_per_second": 8.309,
      "step": 8
    },
    {
      "epoch": 0.009544008483563097,
      "grad_norm": 6.558854103088379,
      "learning_rate": 9.381533400219319e-06,
      "loss": 1.7887,
      "step": 9
    },
    {
      "epoch": 0.010604453870625663,
      "grad_norm": 5.9140472412109375,
      "learning_rate": 9.045084971874738e-06,
      "loss": 1.4467,
      "step": 10
    },
    {
      "epoch": 0.01166489925768823,
      "grad_norm": 3.2007501125335693,
      "learning_rate": 8.644843137107058e-06,
      "loss": 0.9777,
      "step": 11
    },
    {
      "epoch": 0.012725344644750796,
      "grad_norm": 1.8626435995101929,
      "learning_rate": 8.18711994874345e-06,
      "loss": 0.6741,
      "step": 12
    },
    {
      "epoch": 0.012725344644750796,
      "eval_loss": 1.8991509675979614,
      "eval_runtime": 12.0396,
      "eval_samples_per_second": 32.974,
      "eval_steps_per_second": 8.306,
      "step": 12
    },
    {
      "epoch": 0.013785790031813362,
      "grad_norm": 4.286941051483154,
      "learning_rate": 7.679133974894984e-06,
      "loss": 1.3396,
      "step": 13
    },
    {
      "epoch": 0.014846235418875928,
      "grad_norm": 3.3442118167877197,
      "learning_rate": 7.128896457825364e-06,
      "loss": 1.3243,
      "step": 14
    },
    {
      "epoch": 0.015906680805938492,
      "grad_norm": 4.28988790512085,
      "learning_rate": 6.545084971874738e-06,
      "loss": 1.2747,
      "step": 15
    },
    {
      "epoch": 0.016967126193001062,
      "grad_norm": 6.8414387702941895,
      "learning_rate": 5.936906572928625e-06,
      "loss": 2.1388,
      "step": 16
    },
    {
      "epoch": 0.016967126193001062,
      "eval_loss": 1.8425121307373047,
      "eval_runtime": 12.0455,
      "eval_samples_per_second": 32.958,
      "eval_steps_per_second": 8.302,
      "step": 16
    },
    {
      "epoch": 0.018027571580063628,
      "grad_norm": 3.806147336959839,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 1.2853,
      "step": 17
    },
    {
      "epoch": 0.019088016967126194,
      "grad_norm": 4.244113922119141,
      "learning_rate": 4.686047402353433e-06,
      "loss": 1.5234,
      "step": 18
    },
    {
      "epoch": 0.02014846235418876,
      "grad_norm": 7.888317584991455,
      "learning_rate": 4.063093427071376e-06,
      "loss": 2.2812,
      "step": 19
    },
    {
      "epoch": 0.021208907741251327,
      "grad_norm": 2.340810537338257,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 1.0116,
      "step": 20
    },
    {
      "epoch": 0.021208907741251327,
      "eval_loss": 1.7961992025375366,
      "eval_runtime": 12.0387,
      "eval_samples_per_second": 32.977,
      "eval_steps_per_second": 8.307,
      "step": 20
    },
    {
      "epoch": 0.022269353128313893,
      "grad_norm": 3.8034589290618896,
      "learning_rate": 2.871103542174637e-06,
      "loss": 1.3958,
      "step": 21
    },
    {
      "epoch": 0.02332979851537646,
      "grad_norm": 6.965836524963379,
      "learning_rate": 2.320866025105016e-06,
      "loss": 1.8758,
      "step": 22
    },
    {
      "epoch": 0.024390243902439025,
      "grad_norm": 4.387767791748047,
      "learning_rate": 1.8128800512565514e-06,
      "loss": 1.3097,
      "step": 23
    },
    {
      "epoch": 0.02545068928950159,
      "grad_norm": 8.105076789855957,
      "learning_rate": 1.3551568628929434e-06,
      "loss": 2.1157,
      "step": 24
    },
    {
      "epoch": 0.02545068928950159,
      "eval_loss": 1.7690712213516235,
      "eval_runtime": 12.0722,
      "eval_samples_per_second": 32.885,
      "eval_steps_per_second": 8.283,
      "step": 24
    },
    {
      "epoch": 0.026511134676564158,
      "grad_norm": 8.858282089233398,
      "learning_rate": 9.549150281252633e-07,
      "loss": 2.477,
      "step": 25
    },
    {
      "epoch": 0.027571580063626724,
      "grad_norm": 3.955355167388916,
      "learning_rate": 6.184665997806832e-07,
      "loss": 1.2449,
      "step": 26
    },
    {
      "epoch": 0.02863202545068929,
      "grad_norm": 14.918992042541504,
      "learning_rate": 3.511175705587433e-07,
      "loss": 2.8614,
      "step": 27
    },
    {
      "epoch": 0.029692470837751856,
      "grad_norm": 5.202910423278809,
      "learning_rate": 1.5708419435684463e-07,
      "loss": 1.7343,
      "step": 28
    },
    {
      "epoch": 0.029692470837751856,
      "eval_loss": 1.7612024545669556,
      "eval_runtime": 12.0446,
      "eval_samples_per_second": 32.961,
      "eval_steps_per_second": 8.303,
      "step": 28
    },
    {
      "epoch": 0.030752916224814422,
      "grad_norm": 11.204444885253906,
      "learning_rate": 3.9426493427611177e-08,
      "loss": 2.9151,
      "step": 29
    },
    {
      "epoch": 0.031813361611876985,
      "grad_norm": 4.0536274909973145,
      "learning_rate": 0.0,
      "loss": 1.3745,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1544053158051840.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}