{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.441717791411043,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024539877300613498,
      "grad_norm": 0.22866493463516235,
      "learning_rate": 0.0,
      "loss": 4.4901,
      "step": 1
    },
    {
      "epoch": 0.049079754601226995,
      "grad_norm": 0.24644358456134796,
      "learning_rate": 4e-05,
      "loss": 4.4783,
      "step": 2
    },
    {
      "epoch": 0.0736196319018405,
      "grad_norm": 0.19937242567539215,
      "learning_rate": 8e-05,
      "loss": 4.5829,
      "step": 3
    },
    {
      "epoch": 0.09815950920245399,
      "grad_norm": 0.21500074863433838,
      "learning_rate": 0.00012,
      "loss": 4.2699,
      "step": 4
    },
    {
      "epoch": 0.12269938650306748,
      "grad_norm": 0.2759718894958496,
      "learning_rate": 0.00016,
      "loss": 4.2791,
      "step": 5
    },
    {
      "epoch": 0.147239263803681,
      "grad_norm": 0.27005845308303833,
      "learning_rate": 0.0002,
      "loss": 4.284,
      "step": 6
    },
    {
      "epoch": 0.17177914110429449,
      "grad_norm": 0.2469426840543747,
      "learning_rate": 0.00019789473684210526,
      "loss": 4.3003,
      "step": 7
    },
    {
      "epoch": 0.19631901840490798,
      "grad_norm": 0.2804981470108032,
      "learning_rate": 0.00019578947368421054,
      "loss": 4.2118,
      "step": 8
    },
    {
      "epoch": 0.22085889570552147,
      "grad_norm": 0.2733970284461975,
      "learning_rate": 0.0001936842105263158,
      "loss": 4.2774,
      "step": 9
    },
    {
      "epoch": 0.24539877300613497,
      "grad_norm": 0.28491637110710144,
      "learning_rate": 0.00019157894736842104,
      "loss": 4.3476,
      "step": 10
    },
    {
      "epoch": 0.26993865030674846,
      "grad_norm": 0.26830464601516724,
      "learning_rate": 0.00018947368421052632,
      "loss": 4.2176,
      "step": 11
    },
    {
      "epoch": 0.294478527607362,
      "grad_norm": 0.22355224192142487,
      "learning_rate": 0.0001873684210526316,
      "loss": 4.0501,
      "step": 12
    },
    {
      "epoch": 0.31901840490797545,
      "grad_norm": 0.2442767173051834,
      "learning_rate": 0.00018526315789473685,
      "loss": 4.2945,
      "step": 13
    },
    {
      "epoch": 0.34355828220858897,
      "grad_norm": 0.22646744549274445,
      "learning_rate": 0.0001831578947368421,
      "loss": 4.125,
      "step": 14
    },
    {
      "epoch": 0.36809815950920244,
      "grad_norm": 0.21152439713478088,
      "learning_rate": 0.00018105263157894739,
      "loss": 4.0365,
      "step": 15
    },
    {
      "epoch": 0.39263803680981596,
      "grad_norm": 0.2479354739189148,
      "learning_rate": 0.00017894736842105264,
      "loss": 3.9196,
      "step": 16
    },
    {
      "epoch": 0.4171779141104294,
      "grad_norm": 0.21754708886146545,
      "learning_rate": 0.0001768421052631579,
      "loss": 4.0267,
      "step": 17
    },
    {
      "epoch": 0.44171779141104295,
      "grad_norm": 0.22132781147956848,
      "learning_rate": 0.00017473684210526317,
      "loss": 4.2807,
      "step": 18
    },
    {
      "epoch": 0.4662576687116564,
      "grad_norm": 0.21799255907535553,
      "learning_rate": 0.00017263157894736842,
      "loss": 3.7761,
      "step": 19
    },
    {
      "epoch": 0.49079754601226994,
      "grad_norm": 0.2724038064479828,
      "learning_rate": 0.0001705263157894737,
      "loss": 4.0189,
      "step": 20
    },
    {
      "epoch": 0.5153374233128835,
      "grad_norm": 0.2360616773366928,
      "learning_rate": 0.00016842105263157895,
      "loss": 4.0678,
      "step": 21
    },
    {
      "epoch": 0.5398773006134969,
      "grad_norm": 0.27311208844184875,
      "learning_rate": 0.00016631578947368423,
      "loss": 3.9303,
      "step": 22
    },
    {
      "epoch": 0.5644171779141104,
      "grad_norm": 0.25180256366729736,
      "learning_rate": 0.00016421052631578948,
      "loss": 3.8349,
      "step": 23
    },
    {
      "epoch": 0.588957055214724,
      "grad_norm": 0.2426682859659195,
      "learning_rate": 0.00016210526315789473,
      "loss": 3.9186,
      "step": 24
    },
    {
      "epoch": 0.6134969325153374,
      "grad_norm": 0.3130534887313843,
      "learning_rate": 0.00016,
      "loss": 4.1413,
      "step": 25
    },
    {
      "epoch": 0.6380368098159509,
      "grad_norm": 0.27160903811454773,
      "learning_rate": 0.00015789473684210527,
      "loss": 3.796,
      "step": 26
    },
    {
      "epoch": 0.6625766871165644,
      "grad_norm": 0.26386091113090515,
      "learning_rate": 0.00015578947368421052,
      "loss": 3.8394,
      "step": 27
    },
    {
      "epoch": 0.6871165644171779,
      "grad_norm": 0.2667459547519684,
      "learning_rate": 0.0001536842105263158,
      "loss": 3.9829,
      "step": 28
    },
    {
      "epoch": 0.7116564417177914,
      "grad_norm": 0.2795597314834595,
      "learning_rate": 0.00015157894736842108,
      "loss": 4.087,
      "step": 29
    },
    {
      "epoch": 0.7361963190184049,
      "grad_norm": 0.29572176933288574,
      "learning_rate": 0.00014947368421052633,
      "loss": 4.0322,
      "step": 30
    },
    {
      "epoch": 0.7607361963190185,
      "grad_norm": 0.2846808135509491,
      "learning_rate": 0.00014736842105263158,
      "loss": 3.7933,
      "step": 31
    },
    {
      "epoch": 0.7852760736196319,
      "grad_norm": 0.29450249671936035,
      "learning_rate": 0.00014526315789473686,
      "loss": 4.0124,
      "step": 32
    },
    {
      "epoch": 0.8098159509202454,
      "grad_norm": 0.2883971631526947,
      "learning_rate": 0.0001431578947368421,
      "loss": 3.8332,
      "step": 33
    },
    {
      "epoch": 0.8343558282208589,
      "grad_norm": 0.2615528106689453,
      "learning_rate": 0.00014105263157894736,
      "loss": 3.7383,
      "step": 34
    },
    {
      "epoch": 0.8588957055214724,
      "grad_norm": 0.27048519253730774,
      "learning_rate": 0.00013894736842105264,
      "loss": 3.7105,
      "step": 35
    },
    {
      "epoch": 0.8834355828220859,
      "grad_norm": 0.26699960231781006,
      "learning_rate": 0.0001368421052631579,
      "loss": 3.7337,
      "step": 36
    },
    {
      "epoch": 0.9079754601226994,
      "grad_norm": 0.25291603803634644,
      "learning_rate": 0.00013473684210526317,
      "loss": 3.7371,
      "step": 37
    },
    {
      "epoch": 0.9325153374233128,
      "grad_norm": 0.28793999552726746,
      "learning_rate": 0.00013263157894736842,
      "loss": 3.859,
      "step": 38
    },
    {
      "epoch": 0.9570552147239264,
      "grad_norm": 0.2950488328933716,
      "learning_rate": 0.0001305263157894737,
      "loss": 3.8397,
      "step": 39
    },
    {
      "epoch": 0.9815950920245399,
      "grad_norm": 0.5082619190216064,
      "learning_rate": 0.00012842105263157895,
      "loss": 4.4615,
      "step": 40
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.35117432475090027,
      "learning_rate": 0.0001263157894736842,
      "loss": 4.106,
      "step": 41
    },
    {
      "epoch": 1.0245398773006136,
      "grad_norm": 0.291339635848999,
      "learning_rate": 0.00012421052631578949,
      "loss": 3.6844,
      "step": 42
    },
    {
      "epoch": 1.049079754601227,
      "grad_norm": 0.26923683285713196,
      "learning_rate": 0.00012210526315789474,
      "loss": 3.7629,
      "step": 43
    },
    {
      "epoch": 1.0736196319018405,
      "grad_norm": 0.32863032817840576,
      "learning_rate": 0.00012,
      "loss": 3.6329,
      "step": 44
    },
    {
      "epoch": 1.098159509202454,
      "grad_norm": 0.2884359359741211,
      "learning_rate": 0.00011789473684210525,
      "loss": 3.7889,
      "step": 45
    },
    {
      "epoch": 1.1226993865030674,
      "grad_norm": 0.317252516746521,
      "learning_rate": 0.00011578947368421053,
      "loss": 3.6176,
      "step": 46
    },
    {
      "epoch": 1.147239263803681,
      "grad_norm": 0.2913956344127655,
      "learning_rate": 0.0001136842105263158,
      "loss": 3.6274,
      "step": 47
    },
    {
      "epoch": 1.1717791411042944,
      "grad_norm": 0.2767329514026642,
      "learning_rate": 0.00011157894736842105,
      "loss": 3.7869,
      "step": 48
    },
    {
      "epoch": 1.196319018404908,
      "grad_norm": 0.33513787388801575,
      "learning_rate": 0.00010947368421052633,
      "loss": 3.4515,
      "step": 49
    },
    {
      "epoch": 1.2208588957055215,
      "grad_norm": 0.3269072473049164,
      "learning_rate": 0.00010736842105263158,
      "loss": 3.7793,
      "step": 50
    },
    {
      "epoch": 1.2453987730061349,
      "grad_norm": 0.2994535267353058,
      "learning_rate": 0.00010526315789473685,
      "loss": 3.6807,
      "step": 51
    },
    {
      "epoch": 1.2699386503067485,
      "grad_norm": 0.2776726484298706,
      "learning_rate": 0.00010315789473684211,
      "loss": 3.6728,
      "step": 52
    },
    {
      "epoch": 1.294478527607362,
      "grad_norm": 0.2912645637989044,
      "learning_rate": 0.00010105263157894738,
      "loss": 3.6962,
      "step": 53
    },
    {
      "epoch": 1.3190184049079754,
      "grad_norm": 0.31402450799942017,
      "learning_rate": 9.894736842105263e-05,
      "loss": 3.6572,
      "step": 54
    },
    {
      "epoch": 1.343558282208589,
      "grad_norm": 0.3782373070716858,
      "learning_rate": 9.68421052631579e-05,
      "loss": 3.7145,
      "step": 55
    },
    {
      "epoch": 1.3680981595092025,
      "grad_norm": 0.369768351316452,
      "learning_rate": 9.473684210526316e-05,
      "loss": 3.7962,
      "step": 56
    },
    {
      "epoch": 1.392638036809816,
      "grad_norm": 0.328006774187088,
      "learning_rate": 9.263157894736843e-05,
      "loss": 3.767,
      "step": 57
    },
    {
      "epoch": 1.4171779141104295,
      "grad_norm": 0.36224353313446045,
      "learning_rate": 9.052631578947369e-05,
      "loss": 3.7565,
      "step": 58
    },
    {
      "epoch": 1.441717791411043,
      "grad_norm": 0.5099565982818604,
      "learning_rate": 8.842105263157894e-05,
      "loss": 4.1504,
      "step": 59
    },
    {
      "epoch": 1.4662576687116564,
      "grad_norm": 0.34383177757263184,
      "learning_rate": 8.631578947368421e-05,
      "loss": 3.7287,
      "step": 60
    },
    {
      "epoch": 1.49079754601227,
      "grad_norm": 0.3374960124492645,
      "learning_rate": 8.421052631578948e-05,
      "loss": 3.6406,
      "step": 61
    },
    {
      "epoch": 1.5153374233128836,
      "grad_norm": 0.37655407190322876,
      "learning_rate": 8.210526315789474e-05,
      "loss": 3.4329,
      "step": 62
    },
    {
      "epoch": 1.539877300613497,
      "grad_norm": 0.3573070466518402,
      "learning_rate": 8e-05,
      "loss": 3.6985,
      "step": 63
    },
    {
      "epoch": 1.5644171779141103,
      "grad_norm": 0.3968324065208435,
      "learning_rate": 7.789473684210526e-05,
      "loss": 3.915,
      "step": 64
    },
    {
      "epoch": 1.588957055214724,
      "grad_norm": 0.37501779198646545,
      "learning_rate": 7.578947368421054e-05,
      "loss": 3.7973,
      "step": 65
    },
    {
      "epoch": 1.6134969325153374,
      "grad_norm": 0.36463961005210876,
      "learning_rate": 7.368421052631579e-05,
      "loss": 3.8112,
      "step": 66
    },
    {
      "epoch": 1.6380368098159508,
      "grad_norm": 0.383979856967926,
      "learning_rate": 7.157894736842105e-05,
      "loss": 3.7039,
      "step": 67
    },
    {
      "epoch": 1.6625766871165644,
      "grad_norm": 0.3805975914001465,
      "learning_rate": 6.947368421052632e-05,
      "loss": 3.6588,
      "step": 68
    },
    {
      "epoch": 1.687116564417178,
      "grad_norm": 0.4338545799255371,
      "learning_rate": 6.736842105263159e-05,
      "loss": 3.7894,
      "step": 69
    },
    {
      "epoch": 1.7116564417177913,
      "grad_norm": 0.3537883162498474,
      "learning_rate": 6.526315789473685e-05,
      "loss": 3.8445,
      "step": 70
    },
    {
      "epoch": 1.7361963190184049,
      "grad_norm": 0.4303135871887207,
      "learning_rate": 6.31578947368421e-05,
      "loss": 3.8192,
      "step": 71
    },
    {
      "epoch": 1.7607361963190185,
      "grad_norm": 0.38495582342147827,
      "learning_rate": 6.105263157894737e-05,
      "loss": 3.8933,
      "step": 72
    },
    {
      "epoch": 1.7852760736196318,
      "grad_norm": 0.36495280265808105,
      "learning_rate": 5.894736842105263e-05,
      "loss": 3.6696,
      "step": 73
    },
    {
      "epoch": 1.8098159509202454,
      "grad_norm": 0.3398817479610443,
      "learning_rate": 5.68421052631579e-05,
      "loss": 3.6511,
      "step": 74
    },
    {
      "epoch": 1.834355828220859,
      "grad_norm": 0.33734577894210815,
      "learning_rate": 5.4736842105263165e-05,
      "loss": 3.5523,
      "step": 75
    },
    {
      "epoch": 1.8588957055214723,
      "grad_norm": 0.40718579292297363,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 3.7777,
      "step": 76
    },
    {
      "epoch": 1.883435582822086,
      "grad_norm": 0.4228849411010742,
      "learning_rate": 5.052631578947369e-05,
      "loss": 3.7897,
      "step": 77
    },
    {
      "epoch": 1.9079754601226995,
      "grad_norm": 0.35545432567596436,
      "learning_rate": 4.842105263157895e-05,
      "loss": 3.6704,
      "step": 78
    },
    {
      "epoch": 1.9325153374233128,
      "grad_norm": 0.4092422425746918,
      "learning_rate": 4.6315789473684214e-05,
      "loss": 3.7458,
      "step": 79
    },
    {
      "epoch": 1.9570552147239264,
      "grad_norm": 0.347904235124588,
      "learning_rate": 4.421052631578947e-05,
      "loss": 3.7274,
      "step": 80
    },
    {
      "epoch": 1.98159509202454,
      "grad_norm": 0.4824892282485962,
      "learning_rate": 4.210526315789474e-05,
      "loss": 4.1638,
      "step": 81
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4248393177986145,
      "learning_rate": 4e-05,
      "loss": 3.745,
      "step": 82
    },
    {
      "epoch": 2.0245398773006134,
      "grad_norm": 0.3163289427757263,
      "learning_rate": 3.789473684210527e-05,
      "loss": 3.5776,
      "step": 83
    },
    {
      "epoch": 2.049079754601227,
      "grad_norm": 0.3455757200717926,
      "learning_rate": 3.578947368421053e-05,
      "loss": 3.6495,
      "step": 84
    },
    {
      "epoch": 2.0736196319018405,
      "grad_norm": 0.3899824917316437,
      "learning_rate": 3.368421052631579e-05,
      "loss": 3.6556,
      "step": 85
    },
    {
      "epoch": 2.098159509202454,
      "grad_norm": 0.3984885513782501,
      "learning_rate": 3.157894736842105e-05,
      "loss": 3.7719,
      "step": 86
    },
    {
      "epoch": 2.1226993865030677,
      "grad_norm": 0.40226855874061584,
      "learning_rate": 2.9473684210526314e-05,
      "loss": 3.3394,
      "step": 87
    },
    {
      "epoch": 2.147239263803681,
      "grad_norm": 0.3950856924057007,
      "learning_rate": 2.7368421052631583e-05,
      "loss": 3.5942,
      "step": 88
    },
    {
      "epoch": 2.1717791411042944,
      "grad_norm": 0.39255067706108093,
      "learning_rate": 2.5263157894736845e-05,
      "loss": 3.4995,
      "step": 89
    },
    {
      "epoch": 2.196319018404908,
      "grad_norm": 0.37770238518714905,
      "learning_rate": 2.3157894736842107e-05,
      "loss": 3.6029,
      "step": 90
    },
    {
      "epoch": 2.2208588957055215,
      "grad_norm": 0.38814443349838257,
      "learning_rate": 2.105263157894737e-05,
      "loss": 3.3722,
      "step": 91
    },
    {
      "epoch": 2.245398773006135,
      "grad_norm": 0.4377780556678772,
      "learning_rate": 1.8947368421052634e-05,
      "loss": 3.7746,
      "step": 92
    },
    {
      "epoch": 2.2699386503067487,
      "grad_norm": 0.38481786847114563,
      "learning_rate": 1.6842105263157896e-05,
      "loss": 3.5693,
      "step": 93
    },
    {
      "epoch": 2.294478527607362,
      "grad_norm": 0.41932356357574463,
      "learning_rate": 1.4736842105263157e-05,
      "loss": 3.6215,
      "step": 94
    },
    {
      "epoch": 2.3190184049079754,
      "grad_norm": 0.43382129073143005,
      "learning_rate": 1.2631578947368422e-05,
      "loss": 3.7024,
      "step": 95
    },
    {
      "epoch": 2.3435582822085887,
      "grad_norm": 0.44826310873031616,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 3.7194,
      "step": 96
    },
    {
      "epoch": 2.3680981595092025,
      "grad_norm": 0.4052298963069916,
      "learning_rate": 8.421052631578948e-06,
      "loss": 3.5246,
      "step": 97
    },
    {
      "epoch": 2.392638036809816,
      "grad_norm": 0.3732044994831085,
      "learning_rate": 6.315789473684211e-06,
      "loss": 3.553,
      "step": 98
    },
    {
      "epoch": 2.4171779141104293,
      "grad_norm": 0.3546232581138611,
      "learning_rate": 4.210526315789474e-06,
      "loss": 3.7083,
      "step": 99
    },
    {
      "epoch": 2.441717791411043,
      "grad_norm": 0.41070520877838135,
      "learning_rate": 2.105263157894737e-06,
      "loss": 3.6641,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.4261073355997184e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}