{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.6716417910447765,
  "eval_steps": 500,
  "global_step": 65,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 11.831602096557617,
      "learning_rate": 0.00019692307692307696,
      "loss": 9.5753,
      "step": 1
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 10.040313720703125,
      "learning_rate": 0.00019384615384615385,
      "loss": 9.3879,
      "step": 2
    },
    {
      "epoch": 0.22388059701492538,
      "grad_norm": 11.504229545593262,
      "learning_rate": 0.0001907692307692308,
      "loss": 9.2222,
      "step": 3
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 13.777145385742188,
      "learning_rate": 0.0001876923076923077,
      "loss": 9.0187,
      "step": 4
    },
    {
      "epoch": 0.373134328358209,
      "grad_norm": 16.53196907043457,
      "learning_rate": 0.00018461538461538463,
      "loss": 8.8251,
      "step": 5
    },
    {
      "epoch": 0.44776119402985076,
      "grad_norm": 23.02943229675293,
      "learning_rate": 0.00018153846153846155,
      "loss": 8.4652,
      "step": 6
    },
    {
      "epoch": 0.5223880597014925,
      "grad_norm": 20.641206741333008,
      "learning_rate": 0.00017846153846153847,
      "loss": 8.1413,
      "step": 7
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 16.40256690979004,
      "learning_rate": 0.0001753846153846154,
      "loss": 7.9036,
      "step": 8
    },
    {
      "epoch": 0.6716417910447762,
      "grad_norm": 19.79137420654297,
      "learning_rate": 0.00017230769230769234,
      "loss": 7.8958,
      "step": 9
    },
    {
      "epoch": 0.746268656716418,
      "grad_norm": 10.174325942993164,
      "learning_rate": 0.00016923076923076923,
      "loss": 7.6606,
      "step": 10
    },
    {
      "epoch": 0.8208955223880597,
      "grad_norm": 11.052704811096191,
      "learning_rate": 0.00016615384615384617,
      "loss": 7.6561,
      "step": 11
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 12.233122825622559,
      "learning_rate": 0.0001630769230769231,
      "loss": 7.5328,
      "step": 12
    },
    {
      "epoch": 0.9701492537313433,
      "grad_norm": 10.275497436523438,
      "learning_rate": 0.00016,
      "loss": 7.4978,
      "step": 13
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.3966779708862305,
      "learning_rate": 0.00015692307692307693,
      "loss": 3.0154,
      "step": 14
    },
    {
      "epoch": 1.0746268656716418,
      "grad_norm": 13.597101211547852,
      "learning_rate": 0.00015384615384615385,
      "loss": 7.3022,
      "step": 15
    },
    {
      "epoch": 1.1492537313432836,
      "grad_norm": 12.541572570800781,
      "learning_rate": 0.00015076923076923077,
      "loss": 7.4243,
      "step": 16
    },
    {
      "epoch": 1.2238805970149254,
      "grad_norm": 7.609414577484131,
      "learning_rate": 0.00014769230769230772,
      "loss": 7.3352,
      "step": 17
    },
    {
      "epoch": 1.2985074626865671,
      "grad_norm": 8.79019546508789,
      "learning_rate": 0.0001446153846153846,
      "loss": 7.3403,
      "step": 18
    },
    {
      "epoch": 1.373134328358209,
      "grad_norm": 7.513161659240723,
      "learning_rate": 0.00014153846153846156,
      "loss": 7.3048,
      "step": 19
    },
    {
      "epoch": 1.4477611940298507,
      "grad_norm": Infinity,
      "learning_rate": 0.00014153846153846156,
      "loss": 7.3934,
      "step": 20
    },
    {
      "epoch": 1.5223880597014925,
      "grad_norm": 11.386406898498535,
      "learning_rate": 0.00013846153846153847,
      "loss": 7.2708,
      "step": 21
    },
    {
      "epoch": 1.5970149253731343,
      "grad_norm": NaN,
      "learning_rate": 0.00013846153846153847,
      "loss": 7.2549,
      "step": 22
    },
    {
      "epoch": 1.671641791044776,
      "grad_norm": 9.923229217529297,
      "learning_rate": 0.0001353846153846154,
      "loss": 7.3161,
      "step": 23
    },
    {
      "epoch": 1.7462686567164178,
      "grad_norm": 7.624272346496582,
      "learning_rate": 0.0001323076923076923,
      "loss": 7.2844,
      "step": 24
    },
    {
      "epoch": 1.8208955223880596,
      "grad_norm": 6.796629905700684,
      "learning_rate": 0.00012923076923076923,
      "loss": 7.2594,
      "step": 25
    },
    {
      "epoch": 1.8955223880597014,
      "grad_norm": 5.520105838775635,
      "learning_rate": 0.00012615384615384615,
      "loss": 7.2639,
      "step": 26
    },
    {
      "epoch": 1.9701492537313432,
      "grad_norm": 5.706660270690918,
      "learning_rate": 0.0001230769230769231,
      "loss": 7.2271,
      "step": 27
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.667247295379639,
      "learning_rate": 0.00012,
      "loss": 2.942,
      "step": 28
    },
    {
      "epoch": 2.074626865671642,
      "grad_norm": 8.385282516479492,
      "learning_rate": 0.00011692307692307694,
      "loss": 7.1126,
      "step": 29
    },
    {
      "epoch": 2.1492537313432836,
      "grad_norm": 4.17704963684082,
      "learning_rate": 0.00011384615384615384,
      "loss": 7.2177,
      "step": 30
    },
    {
      "epoch": 2.2238805970149254,
      "grad_norm": 7.29147481918335,
      "learning_rate": 0.00011076923076923077,
      "loss": 7.2731,
      "step": 31
    },
    {
      "epoch": 2.298507462686567,
      "grad_norm": 5.086247444152832,
      "learning_rate": 0.0001076923076923077,
      "loss": 7.1494,
      "step": 32
    },
    {
      "epoch": 2.373134328358209,
      "grad_norm": 4.92710542678833,
      "learning_rate": 0.00010461538461538463,
      "loss": 7.1479,
      "step": 33
    },
    {
      "epoch": 2.4477611940298507,
      "grad_norm": 5.310170650482178,
      "learning_rate": 0.00010153846153846153,
      "loss": 7.1172,
      "step": 34
    },
    {
      "epoch": 2.5223880597014925,
      "grad_norm": 5.681138515472412,
      "learning_rate": 9.846153846153848e-05,
      "loss": 7.1665,
      "step": 35
    },
    {
      "epoch": 2.5970149253731343,
      "grad_norm": 6.48416805267334,
      "learning_rate": 9.53846153846154e-05,
      "loss": 7.229,
      "step": 36
    },
    {
      "epoch": 2.671641791044776,
      "grad_norm": 7.22155237197876,
      "learning_rate": 9.230769230769232e-05,
      "loss": 7.2443,
      "step": 37
    },
    {
      "epoch": 2.746268656716418,
      "grad_norm": 5.244325160980225,
      "learning_rate": 8.923076923076924e-05,
      "loss": 7.1864,
      "step": 38
    },
    {
      "epoch": 2.8208955223880596,
      "grad_norm": 6.491042613983154,
      "learning_rate": 8.615384615384617e-05,
      "loss": 7.1403,
      "step": 39
    },
    {
      "epoch": 2.8955223880597014,
      "grad_norm": 4.748079299926758,
      "learning_rate": 8.307692307692309e-05,
      "loss": 7.2464,
      "step": 40
    },
    {
      "epoch": 2.970149253731343,
      "grad_norm": 4.683705806732178,
      "learning_rate": 8e-05,
      "loss": 7.1566,
      "step": 41
    },
    {
      "epoch": 3.0,
      "grad_norm": 8.315367698669434,
      "learning_rate": 7.692307692307693e-05,
      "loss": 2.7335,
      "step": 42
    },
    {
      "epoch": 3.074626865671642,
      "grad_norm": 8.71499252319336,
      "learning_rate": 7.384615384615386e-05,
      "loss": 7.0353,
      "step": 43
    },
    {
      "epoch": 3.1492537313432836,
      "grad_norm": 4.421390056610107,
      "learning_rate": 7.076923076923078e-05,
      "loss": 7.1684,
      "step": 44
    },
    {
      "epoch": 3.2238805970149254,
      "grad_norm": 4.962438106536865,
      "learning_rate": 6.76923076923077e-05,
      "loss": 7.0518,
      "step": 45
    },
    {
      "epoch": 3.298507462686567,
      "grad_norm": 4.061994552612305,
      "learning_rate": 6.461538461538462e-05,
      "loss": 7.0753,
      "step": 46
    },
    {
      "epoch": 3.373134328358209,
      "grad_norm": 10.23737621307373,
      "learning_rate": 6.153846153846155e-05,
      "loss": 7.2593,
      "step": 47
    },
    {
      "epoch": 3.4477611940298507,
      "grad_norm": 5.402864456176758,
      "learning_rate": 5.846153846153847e-05,
      "loss": 7.1255,
      "step": 48
    },
    {
      "epoch": 3.5223880597014925,
      "grad_norm": 7.442513465881348,
      "learning_rate": 5.538461538461539e-05,
      "loss": 6.9086,
      "step": 49
    },
    {
      "epoch": 3.5970149253731343,
      "grad_norm": 12.119452476501465,
      "learning_rate": 5.230769230769231e-05,
      "loss": 7.2655,
      "step": 50
    },
    {
      "epoch": 3.671641791044776,
      "grad_norm": 4.1253156661987305,
      "learning_rate": 4.923076923076924e-05,
      "loss": 7.129,
      "step": 51
    },
    {
      "epoch": 3.746268656716418,
      "grad_norm": 7.582332611083984,
      "learning_rate": 4.615384615384616e-05,
      "loss": 7.1866,
      "step": 52
    },
    {
      "epoch": 3.8208955223880596,
      "grad_norm": 9.213349342346191,
      "learning_rate": 4.3076923076923084e-05,
      "loss": 7.2262,
      "step": 53
    },
    {
      "epoch": 3.8955223880597014,
      "grad_norm": 4.230329513549805,
      "learning_rate": 4e-05,
      "loss": 7.0612,
      "step": 54
    },
    {
      "epoch": 3.970149253731343,
      "grad_norm": 3.959320545196533,
      "learning_rate": 3.692307692307693e-05,
      "loss": 7.095,
      "step": 55
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.782017469406128,
      "learning_rate": 3.384615384615385e-05,
      "loss": 2.8985,
      "step": 56
    },
    {
      "epoch": 4.074626865671641,
      "grad_norm": 8.111074447631836,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 7.0008,
      "step": 57
    },
    {
      "epoch": 4.149253731343284,
      "grad_norm": 3.9246532917022705,
      "learning_rate": 2.7692307692307694e-05,
      "loss": 7.1253,
      "step": 58
    },
    {
      "epoch": 4.223880597014926,
      "grad_norm": 11.857646942138672,
      "learning_rate": 2.461538461538462e-05,
      "loss": 6.9411,
      "step": 59
    },
    {
      "epoch": 4.298507462686567,
      "grad_norm": 2.8319931030273438,
      "learning_rate": 2.1538461538461542e-05,
      "loss": 7.1616,
      "step": 60
    },
    {
      "epoch": 4.373134328358209,
      "grad_norm": 3.061171293258667,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 7.1291,
      "step": 61
    },
    {
      "epoch": 4.447761194029851,
      "grad_norm": 5.19327449798584,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 7.1867,
      "step": 62
    },
    {
      "epoch": 4.522388059701493,
      "grad_norm": 3.0203020572662354,
      "learning_rate": 1.230769230769231e-05,
      "loss": 7.1364,
      "step": 63
    },
    {
      "epoch": 4.597014925373134,
      "grad_norm": 3.957735300064087,
      "learning_rate": 9.230769230769232e-06,
      "loss": 7.139,
      "step": 64
    },
    {
      "epoch": 4.6716417910447765,
      "grad_norm": 4.099056243896484,
      "learning_rate": 6.153846153846155e-06,
      "loss": 7.1104,
      "step": 65
    },
    {
      "epoch": 4.6716417910447765,
      "step": 65,
      "total_flos": 46267156615872.0,
      "train_loss": 7.157758657748882,
      "train_runtime": 2311.3066,
      "train_samples_per_second": 0.58,
      "train_steps_per_second": 0.028
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 65,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 46267156615872.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}