{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 13,
  "global_step": 69,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 0.7634550333023071,
      "learning_rate": 0.0,
      "loss": 1.4302,
      "step": 1
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 0.6962459683418274,
      "learning_rate": 3.75e-05,
      "loss": 1.4551,
      "step": 2
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 0.5518960952758789,
      "learning_rate": 7.5e-05,
      "loss": 1.1797,
      "step": 3
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.5505545735359192,
      "learning_rate": 0.0001125,
      "loss": 1.2842,
      "step": 4
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.22443649172782898,
      "learning_rate": 0.00015,
      "loss": 1.0566,
      "step": 5
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 0.1337110549211502,
      "learning_rate": 0.00014992117531118204,
      "loss": 1.0601,
      "step": 6
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 0.13790792226791382,
      "learning_rate": 0.00014968488534344127,
      "loss": 1.1489,
      "step": 7
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.11578402668237686,
      "learning_rate": 0.00014929168196294593,
      "loss": 0.9451,
      "step": 8
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 0.11953484266996384,
      "learning_rate": 0.0001487424835144104,
      "loss": 0.9878,
      "step": 9
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.10787869244813919,
      "learning_rate": 0.00014803857267625851,
      "loss": 1.061,
      "step": 10
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 0.0799792930483818,
      "learning_rate": 0.0001471815934648687,
      "loss": 1.1069,
      "step": 11
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.0694027692079544,
      "learning_rate": 0.00014617354739489765,
      "loss": 1.0718,
      "step": 12
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 0.06417166441679001,
      "learning_rate": 0.0001450167888046499,
      "loss": 1.0039,
      "step": 13
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 0.06427249312400818,
      "learning_rate": 0.0001437140193574118,
      "loss": 0.9702,
      "step": 14
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.0544593371450901,
      "learning_rate": 0.00014226828173159164,
      "loss": 0.8267,
      "step": 15
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.07362852245569229,
      "learning_rate": 0.0001406829525144033,
      "loss": 0.9722,
      "step": 16
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 0.07204615324735641,
      "learning_rate": 0.00013896173431569029,
      "loss": 0.9663,
      "step": 17
    },
    {
      "epoch": 0.7391304347826086,
      "eval_loss": 0.90576171875,
      "eval_runtime": 4.3927,
      "eval_samples_per_second": 2.277,
      "eval_steps_per_second": 0.455,
      "step": 17
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 0.06425914168357849,
      "learning_rate": 0.00013710864712030893,
      "loss": 0.9819,
      "step": 18
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 0.036391615867614746,
      "learning_rate": 0.0001351280188992675,
      "loss": 0.8041,
      "step": 19
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.04094429686665535,
      "learning_rate": 0.0001330244755015493,
      "loss": 1.0254,
      "step": 20
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 0.04050302132964134,
      "learning_rate": 0.00013080292985022816,
      "loss": 1.0042,
      "step": 21
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 0.038431670516729355,
      "learning_rate": 0.0001284685704681088,
      "loss": 0.9805,
      "step": 22
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.04781308397650719,
      "learning_rate": 0.0001260268493596915,
      "loss": 1.0522,
      "step": 23
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.03875584527850151,
      "learning_rate": 0.000123483469277763,
      "loss": 0.9946,
      "step": 24
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 0.038722969591617584,
      "learning_rate": 0.000120844370404353,
      "loss": 1.0386,
      "step": 25
    },
    {
      "epoch": 1.1304347826086956,
      "grad_norm": 0.036717191338539124,
      "learning_rate": 0.00011811571647716395,
      "loss": 0.8828,
      "step": 26
    },
    {
      "epoch": 1.1739130434782608,
      "grad_norm": 0.04138258099555969,
      "learning_rate": 0.00011530388039387589,
      "loss": 0.9724,
      "step": 27
    },
    {
      "epoch": 1.2173913043478262,
      "grad_norm": 0.035979870706796646,
      "learning_rate": 0.00011241542932794879,
      "loss": 0.8765,
      "step": 28
    },
    {
      "epoch": 1.2608695652173914,
      "grad_norm": 0.03545432165265083,
      "learning_rate": 0.00010945710939068444,
      "loss": 0.9277,
      "step": 29
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 0.04141005128622055,
      "learning_rate": 0.00010643582987537115,
      "loss": 0.9895,
      "step": 30
    },
    {
      "epoch": 1.3043478260869565,
      "eval_loss": 0.873291015625,
      "eval_runtime": 4.3467,
      "eval_samples_per_second": 2.301,
      "eval_steps_per_second": 0.46,
      "step": 30
    },
    {
      "epoch": 1.3478260869565217,
      "grad_norm": 0.03391469269990921,
      "learning_rate": 0.00010335864712030894,
      "loss": 0.824,
      "step": 31
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.032858580350875854,
      "learning_rate": 0.00010023274802840461,
      "loss": 0.8816,
      "step": 32
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 0.03364916890859604,
      "learning_rate": 9.706543328182691e-05,
      "loss": 0.9536,
      "step": 33
    },
    {
      "epoch": 1.4782608695652173,
      "grad_norm": 0.034717388451099396,
      "learning_rate": 9.386410029092507e-05,
      "loss": 1.0142,
      "step": 34
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 0.040148813277482986,
      "learning_rate": 9.063622591723429e-05,
      "loss": 0.9756,
      "step": 35
    },
    {
      "epoch": 1.5652173913043477,
      "grad_norm": 0.03408735245466232,
      "learning_rate": 8.738934901091897e-05,
      "loss": 0.9312,
      "step": 36
    },
    {
      "epoch": 1.608695652173913,
      "grad_norm": 0.0321255587041378,
      "learning_rate": 8.413105280343893e-05,
      "loss": 0.9043,
      "step": 37
    },
    {
      "epoch": 1.6521739130434783,
      "grad_norm": 0.03103114850819111,
      "learning_rate": 8.086894719656108e-05,
      "loss": 0.7712,
      "step": 38
    },
    {
      "epoch": 1.6956521739130435,
      "grad_norm": 0.03416038304567337,
      "learning_rate": 7.761065098908105e-05,
      "loss": 0.9062,
      "step": 39
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.03245851770043373,
      "learning_rate": 7.436377408276571e-05,
      "loss": 0.9055,
      "step": 40
    },
    {
      "epoch": 1.7826086956521738,
      "grad_norm": 0.03590395301580429,
      "learning_rate": 7.113589970907489e-05,
      "loss": 0.9229,
      "step": 41
    },
    {
      "epoch": 1.8260869565217392,
      "grad_norm": 0.032267358154058456,
      "learning_rate": 6.793456671817309e-05,
      "loss": 0.7598,
      "step": 42
    },
    {
      "epoch": 1.8695652173913042,
      "grad_norm": 0.03612128645181656,
      "learning_rate": 6.476725197159537e-05,
      "loss": 0.9722,
      "step": 43
    },
    {
      "epoch": 1.8695652173913042,
      "eval_loss": 0.8590087890625,
      "eval_runtime": 4.3562,
      "eval_samples_per_second": 2.296,
      "eval_steps_per_second": 0.459,
      "step": 43
    },
    {
      "epoch": 1.9130434782608696,
      "grad_norm": 0.03612411394715309,
      "learning_rate": 6.164135287969106e-05,
      "loss": 0.9539,
      "step": 44
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 0.03321658819913864,
      "learning_rate": 5.856417012462883e-05,
      "loss": 0.9355,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.03923092409968376,
      "learning_rate": 5.554289060931557e-05,
      "loss": 0.9976,
      "step": 46
    },
    {
      "epoch": 2.0434782608695654,
      "grad_norm": 0.03545928746461868,
      "learning_rate": 5.258457067205121e-05,
      "loss": 0.9478,
      "step": 47
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.033447980880737305,
      "learning_rate": 4.969611960612409e-05,
      "loss": 0.9971,
      "step": 48
    },
    {
      "epoch": 2.130434782608696,
      "grad_norm": 0.030967000871896744,
      "learning_rate": 4.688428352283603e-05,
      "loss": 0.8506,
      "step": 49
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 0.03545485809445381,
      "learning_rate": 4.4155629595646986e-05,
      "loss": 0.9329,
      "step": 50
    },
    {
      "epoch": 2.217391304347826,
      "grad_norm": 0.03325090929865837,
      "learning_rate": 4.151653072223699e-05,
      "loss": 0.8462,
      "step": 51
    },
    {
      "epoch": 2.260869565217391,
      "grad_norm": 0.029995175078511238,
      "learning_rate": 3.8973150640308497e-05,
      "loss": 0.897,
      "step": 52
    },
    {
      "epoch": 2.3043478260869565,
      "grad_norm": 0.03587409108877182,
      "learning_rate": 3.653142953189118e-05,
      "loss": 0.9556,
      "step": 53
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 0.03194161877036095,
      "learning_rate": 3.419707014977183e-05,
      "loss": 0.8,
      "step": 54
    },
    {
      "epoch": 2.391304347826087,
      "grad_norm": 0.03137723729014397,
      "learning_rate": 3.197552449845067e-05,
      "loss": 0.8569,
      "step": 55
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.032495368272066116,
      "learning_rate": 2.987198110073249e-05,
      "loss": 0.9253,
      "step": 56
    },
    {
      "epoch": 2.4347826086956523,
      "eval_loss": 0.85205078125,
      "eval_runtime": 4.3748,
      "eval_samples_per_second": 2.286,
      "eval_steps_per_second": 0.457,
      "step": 56
    },
    {
      "epoch": 2.4782608695652173,
      "grad_norm": 0.03498929366469383,
      "learning_rate": 2.7891352879691055e-05,
      "loss": 0.9917,
      "step": 57
    },
    {
      "epoch": 2.5217391304347827,
      "grad_norm": 0.03751672804355621,
      "learning_rate": 2.6038265684309694e-05,
      "loss": 0.9478,
      "step": 58
    },
    {
      "epoch": 2.5652173913043477,
      "grad_norm": 0.03346884623169899,
      "learning_rate": 2.4317047485596673e-05,
      "loss": 0.9106,
      "step": 59
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 0.033841464668512344,
      "learning_rate": 2.2731718268408336e-05,
      "loss": 0.8862,
      "step": 60
    },
    {
      "epoch": 2.6521739130434785,
      "grad_norm": 0.030843093991279602,
      "learning_rate": 2.1285980642588184e-05,
      "loss": 0.7553,
      "step": 61
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 0.03349591791629791,
      "learning_rate": 1.9983211195350096e-05,
      "loss": 0.8867,
      "step": 62
    },
    {
      "epoch": 2.7391304347826084,
      "grad_norm": 0.03341041877865791,
      "learning_rate": 1.8826452605102335e-05,
      "loss": 0.8867,
      "step": 63
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.03790866583585739,
      "learning_rate": 1.781840653513128e-05,
      "loss": 0.9058,
      "step": 64
    },
    {
      "epoch": 2.8260869565217392,
      "grad_norm": 0.02903052605688572,
      "learning_rate": 1.696142732374149e-05,
      "loss": 0.7474,
      "step": 65
    },
    {
      "epoch": 2.869565217391304,
      "grad_norm": 0.032797202467918396,
      "learning_rate": 1.625751648558959e-05,
      "loss": 0.9536,
      "step": 66
    },
    {
      "epoch": 2.9130434782608696,
      "grad_norm": 0.032798297703266144,
      "learning_rate": 1.570831803705405e-05,
      "loss": 0.939,
      "step": 67
    },
    {
      "epoch": 2.9565217391304346,
      "grad_norm": 0.03150875121355057,
      "learning_rate": 1.5315114656558717e-05,
      "loss": 0.9233,
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.04027010127902031,
      "learning_rate": 1.5078824688817951e-05,
      "loss": 0.9819,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.849609375,
      "eval_runtime": 4.3942,
      "eval_samples_per_second": 2.276,
      "eval_steps_per_second": 0.455,
      "step": 69
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 69,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.464101375758041e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}