{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005656748500961648,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.54233133461553e-05,
      "grad_norm": 3.156315565109253,
      "learning_rate": 1e-05,
      "loss": 6.3547,
      "step": 1
    },
    {
      "epoch": 7.54233133461553e-05,
      "eval_loss": 6.566169261932373,
      "eval_runtime": 1323.5586,
      "eval_samples_per_second": 8.436,
      "eval_steps_per_second": 1.055,
      "step": 1
    },
    {
      "epoch": 0.0001508466266923106,
      "grad_norm": 3.608928918838501,
      "learning_rate": 2e-05,
      "loss": 6.6439,
      "step": 2
    },
    {
      "epoch": 0.00022626994003846588,
      "grad_norm": 3.671382427215576,
      "learning_rate": 3e-05,
      "loss": 6.4279,
      "step": 3
    },
    {
      "epoch": 0.0003016932533846212,
      "grad_norm": 3.6660938262939453,
      "learning_rate": 4e-05,
      "loss": 6.3964,
      "step": 4
    },
    {
      "epoch": 0.0003771165667307765,
      "grad_norm": 4.2082672119140625,
      "learning_rate": 5e-05,
      "loss": 6.6657,
      "step": 5
    },
    {
      "epoch": 0.00045253988007693175,
      "grad_norm": 3.8837738037109375,
      "learning_rate": 6e-05,
      "loss": 6.4626,
      "step": 6
    },
    {
      "epoch": 0.0005279631934230871,
      "grad_norm": 4.669962406158447,
      "learning_rate": 7e-05,
      "loss": 6.3364,
      "step": 7
    },
    {
      "epoch": 0.0006033865067692424,
      "grad_norm": 3.6005444526672363,
      "learning_rate": 8e-05,
      "loss": 5.4372,
      "step": 8
    },
    {
      "epoch": 0.0006788098201153976,
      "grad_norm": 3.552445650100708,
      "learning_rate": 9e-05,
      "loss": 5.2645,
      "step": 9
    },
    {
      "epoch": 0.0006788098201153976,
      "eval_loss": 4.850156307220459,
      "eval_runtime": 1323.3509,
      "eval_samples_per_second": 8.437,
      "eval_steps_per_second": 1.055,
      "step": 9
    },
    {
      "epoch": 0.000754233133461553,
      "grad_norm": 3.7075414657592773,
      "learning_rate": 0.0001,
      "loss": 4.7484,
      "step": 10
    },
    {
      "epoch": 0.0008296564468077082,
      "grad_norm": 3.7549526691436768,
      "learning_rate": 9.99695413509548e-05,
      "loss": 4.4416,
      "step": 11
    },
    {
      "epoch": 0.0009050797601538635,
      "grad_norm": 3.413628339767456,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.7846,
      "step": 12
    },
    {
      "epoch": 0.0009805030735000188,
      "grad_norm": 2.9563262462615967,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.5005,
      "step": 13
    },
    {
      "epoch": 0.0010559263868461742,
      "grad_norm": 2.9408886432647705,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.4305,
      "step": 14
    },
    {
      "epoch": 0.0011313497001923295,
      "grad_norm": 2.1472573280334473,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.1604,
      "step": 15
    },
    {
      "epoch": 0.0012067730135384847,
      "grad_norm": 2.671536922454834,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.0808,
      "step": 16
    },
    {
      "epoch": 0.00128219632688464,
      "grad_norm": 2.8072383403778076,
      "learning_rate": 9.851478631379982e-05,
      "loss": 3.2296,
      "step": 17
    },
    {
      "epoch": 0.0013576196402307953,
      "grad_norm": 2.2312707901000977,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.0198,
      "step": 18
    },
    {
      "epoch": 0.0013576196402307953,
      "eval_loss": 2.764563798904419,
      "eval_runtime": 1323.5053,
      "eval_samples_per_second": 8.436,
      "eval_steps_per_second": 1.055,
      "step": 18
    },
    {
      "epoch": 0.0014330429535769507,
      "grad_norm": 3.1025147438049316,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.6769,
      "step": 19
    },
    {
      "epoch": 0.001508466266923106,
      "grad_norm": 1.560180425643921,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.5627,
      "step": 20
    },
    {
      "epoch": 0.0015838895802692612,
      "grad_norm": 2.205591917037964,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.6943,
      "step": 21
    },
    {
      "epoch": 0.0016593128936154165,
      "grad_norm": 1.5366450548171997,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.5889,
      "step": 22
    },
    {
      "epoch": 0.0017347362069615718,
      "grad_norm": 1.582607626914978,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.5521,
      "step": 23
    },
    {
      "epoch": 0.001810159520307727,
      "grad_norm": 1.9383635520935059,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.4834,
      "step": 24
    },
    {
      "epoch": 0.0018855828336538825,
      "grad_norm": 1.7182579040527344,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.574,
      "step": 25
    },
    {
      "epoch": 0.0019610061470000375,
      "grad_norm": 1.902744174003601,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.4183,
      "step": 26
    },
    {
      "epoch": 0.002036429460346193,
      "grad_norm": 1.877042293548584,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.4997,
      "step": 27
    },
    {
      "epoch": 0.002036429460346193,
      "eval_loss": 2.507841110229492,
      "eval_runtime": 1323.4725,
      "eval_samples_per_second": 8.436,
      "eval_steps_per_second": 1.055,
      "step": 27
    },
    {
      "epoch": 0.0021118527736923485,
      "grad_norm": 1.5418832302093506,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.4695,
      "step": 28
    },
    {
      "epoch": 0.0021872760870385037,
      "grad_norm": 1.6520047187805176,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.471,
      "step": 29
    },
    {
      "epoch": 0.002262699400384659,
      "grad_norm": 1.7770787477493286,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.5716,
      "step": 30
    },
    {
      "epoch": 0.0023381227137308142,
      "grad_norm": 2.1953811645507812,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.6485,
      "step": 31
    },
    {
      "epoch": 0.0024135460270769695,
      "grad_norm": 2.0734782218933105,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.4759,
      "step": 32
    },
    {
      "epoch": 0.0024889693404231247,
      "grad_norm": 1.8175076246261597,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.4829,
      "step": 33
    },
    {
      "epoch": 0.00256439265376928,
      "grad_norm": 2.310616970062256,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.6573,
      "step": 34
    },
    {
      "epoch": 0.0026398159671154353,
      "grad_norm": 0.9801550507545471,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.4736,
      "step": 35
    },
    {
      "epoch": 0.0027152392804615905,
      "grad_norm": 6.086284637451172,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.4809,
      "step": 36
    },
    {
      "epoch": 0.0027152392804615905,
      "eval_loss": 2.5135347843170166,
      "eval_runtime": 1324.1065,
      "eval_samples_per_second": 8.432,
      "eval_steps_per_second": 1.054,
      "step": 36
    },
    {
      "epoch": 0.0027906625938077458,
      "grad_norm": 0.9378789663314819,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.4888,
      "step": 37
    },
    {
      "epoch": 0.0028660859071539015,
      "grad_norm": 1.425811529159546,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.5393,
      "step": 38
    },
    {
      "epoch": 0.0029415092205000567,
      "grad_norm": 0.885962724685669,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.4674,
      "step": 39
    },
    {
      "epoch": 0.003016932533846212,
      "grad_norm": 1.203602910041809,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.4967,
      "step": 40
    },
    {
      "epoch": 0.0030923558471923672,
      "grad_norm": 0.8594803810119629,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.4137,
      "step": 41
    },
    {
      "epoch": 0.0031677791605385225,
      "grad_norm": 1.4859495162963867,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.5474,
      "step": 42
    },
    {
      "epoch": 0.0032432024738846777,
      "grad_norm": 0.9513015747070312,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.3964,
      "step": 43
    },
    {
      "epoch": 0.003318625787230833,
      "grad_norm": 0.8883151412010193,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.5413,
      "step": 44
    },
    {
      "epoch": 0.0033940491005769883,
      "grad_norm": 1.0262858867645264,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.4256,
      "step": 45
    },
    {
      "epoch": 0.0033940491005769883,
      "eval_loss": 2.4895801544189453,
      "eval_runtime": 1323.5763,
      "eval_samples_per_second": 8.435,
      "eval_steps_per_second": 1.055,
      "step": 45
    },
    {
      "epoch": 0.0034694724139231435,
      "grad_norm": 1.1027235984802246,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.526,
      "step": 46
    },
    {
      "epoch": 0.0035448957272692988,
      "grad_norm": 3.1927082538604736,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.6,
      "step": 47
    },
    {
      "epoch": 0.003620319040615454,
      "grad_norm": 1.3928576707839966,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.6268,
      "step": 48
    },
    {
      "epoch": 0.0036957423539616097,
      "grad_norm": 0.8399583101272583,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.4112,
      "step": 49
    },
    {
      "epoch": 0.003771165667307765,
      "grad_norm": 1.293001413345337,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.4761,
      "step": 50
    },
    {
      "epoch": 0.0038465889806539202,
      "grad_norm": 1.18425714969635,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.4176,
      "step": 51
    },
    {
      "epoch": 0.003922012294000075,
      "grad_norm": 0.9308878183364868,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.4435,
      "step": 52
    },
    {
      "epoch": 0.00399743560734623,
      "grad_norm": 0.8556021451950073,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.5139,
      "step": 53
    },
    {
      "epoch": 0.004072858920692386,
      "grad_norm": 0.7264602184295654,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.3871,
      "step": 54
    },
    {
      "epoch": 0.004072858920692386,
      "eval_loss": 2.4673752784729004,
      "eval_runtime": 1323.4747,
      "eval_samples_per_second": 8.436,
      "eval_steps_per_second": 1.055,
      "step": 54
    },
    {
      "epoch": 0.004148282234038542,
      "grad_norm": 1.2506457567214966,
      "learning_rate": 5e-05,
      "loss": 2.3847,
      "step": 55
    },
    {
      "epoch": 0.004223705547384697,
      "grad_norm": 0.8360309600830078,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.4915,
      "step": 56
    },
    {
      "epoch": 0.004299128860730852,
      "grad_norm": 0.7913613319396973,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.4851,
      "step": 57
    },
    {
      "epoch": 0.0043745521740770075,
      "grad_norm": 0.8072302937507629,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.45,
      "step": 58
    },
    {
      "epoch": 0.004449975487423163,
      "grad_norm": 0.6270408630371094,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.4552,
      "step": 59
    },
    {
      "epoch": 0.004525398800769318,
      "grad_norm": 1.4017157554626465,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.5578,
      "step": 60
    },
    {
      "epoch": 0.004600822114115473,
      "grad_norm": 0.829573929309845,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.4176,
      "step": 61
    },
    {
      "epoch": 0.0046762454274616285,
      "grad_norm": 0.8128294348716736,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.445,
      "step": 62
    },
    {
      "epoch": 0.004751668740807784,
      "grad_norm": 0.8237362504005432,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.4833,
      "step": 63
    },
    {
      "epoch": 0.004751668740807784,
      "eval_loss": 2.470191240310669,
      "eval_runtime": 1323.4084,
      "eval_samples_per_second": 8.437,
      "eval_steps_per_second": 1.055,
      "step": 63
    },
    {
      "epoch": 0.004827092054153939,
      "grad_norm": 1.046515941619873,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.6124,
      "step": 64
    },
    {
      "epoch": 0.004902515367500094,
      "grad_norm": 0.7122370600700378,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.3582,
      "step": 65
    },
    {
      "epoch": 0.0049779386808462495,
      "grad_norm": 1.1943559646606445,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.3669,
      "step": 66
    },
    {
      "epoch": 0.005053361994192405,
      "grad_norm": 0.792339563369751,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.4925,
      "step": 67
    },
    {
      "epoch": 0.00512878530753856,
      "grad_norm": 0.9303301572799683,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.357,
      "step": 68
    },
    {
      "epoch": 0.005204208620884715,
      "grad_norm": 1.2022520303726196,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.3788,
      "step": 69
    },
    {
      "epoch": 0.0052796319342308705,
      "grad_norm": 0.982182502746582,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.5207,
      "step": 70
    },
    {
      "epoch": 0.005355055247577026,
      "grad_norm": 0.7129021883010864,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.4658,
      "step": 71
    },
    {
      "epoch": 0.005430478560923181,
      "grad_norm": 1.0058438777923584,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.4702,
      "step": 72
    },
    {
      "epoch": 0.005430478560923181,
      "eval_loss": 2.4624416828155518,
      "eval_runtime": 1323.3721,
      "eval_samples_per_second": 8.437,
      "eval_steps_per_second": 1.055,
      "step": 72
    },
    {
      "epoch": 0.005505901874269336,
      "grad_norm": 1.0868438482284546,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.4515,
      "step": 73
    },
    {
      "epoch": 0.0055813251876154915,
      "grad_norm": 0.7750610709190369,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.4766,
      "step": 74
    },
    {
      "epoch": 0.005656748500961648,
      "grad_norm": 0.6583645939826965,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.4686,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.617690146471936e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}