{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.103448275862069,
  "eval_steps": 17,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005517241379310344,
      "eval_loss": 3.884207010269165,
      "eval_runtime": 4.4659,
      "eval_samples_per_second": 68.296,
      "eval_steps_per_second": 8.733,
      "step": 1
    },
    {
      "epoch": 0.016551724137931035,
      "grad_norm": 0.6788153648376465,
      "learning_rate": 3e-05,
      "loss": 3.8284,
      "step": 3
    },
    {
      "epoch": 0.03310344827586207,
      "grad_norm": 0.6769624352455139,
      "learning_rate": 6e-05,
      "loss": 3.7716,
      "step": 6
    },
    {
      "epoch": 0.0496551724137931,
      "grad_norm": 0.8537060618400574,
      "learning_rate": 9e-05,
      "loss": 3.8822,
      "step": 9
    },
    {
      "epoch": 0.06620689655172414,
      "grad_norm": 0.9294676780700684,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.7923,
      "step": 12
    },
    {
      "epoch": 0.08275862068965517,
      "grad_norm": 0.9163342118263245,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.315,
      "step": 15
    },
    {
      "epoch": 0.09379310344827586,
      "eval_loss": 3.4180614948272705,
      "eval_runtime": 4.4396,
      "eval_samples_per_second": 68.701,
      "eval_steps_per_second": 8.785,
      "step": 17
    },
    {
      "epoch": 0.0993103448275862,
      "grad_norm": 1.1075429916381836,
      "learning_rate": 9.956320346634876e-05,
      "loss": 3.3909,
      "step": 18
    },
    {
      "epoch": 0.11586206896551725,
      "grad_norm": 1.0358085632324219,
      "learning_rate": 9.917525374361912e-05,
      "loss": 3.0781,
      "step": 21
    },
    {
      "epoch": 0.13241379310344828,
      "grad_norm": 0.6941744685173035,
      "learning_rate": 9.86663298624003e-05,
      "loss": 3.1513,
      "step": 24
    },
    {
      "epoch": 0.1489655172413793,
      "grad_norm": 0.7888012528419495,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.815,
      "step": 27
    },
    {
      "epoch": 0.16551724137931034,
      "grad_norm": 0.6974669694900513,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.7661,
      "step": 30
    },
    {
      "epoch": 0.1820689655172414,
      "grad_norm": 0.7885407209396362,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.8794,
      "step": 33
    },
    {
      "epoch": 0.18758620689655173,
      "eval_loss": 2.820341110229492,
      "eval_runtime": 4.4584,
      "eval_samples_per_second": 68.411,
      "eval_steps_per_second": 8.748,
      "step": 34
    },
    {
      "epoch": 0.1986206896551724,
      "grad_norm": 0.8363791108131409,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.712,
      "step": 36
    },
    {
      "epoch": 0.21517241379310345,
      "grad_norm": 0.7954784035682678,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.5269,
      "step": 39
    },
    {
      "epoch": 0.2317241379310345,
      "grad_norm": 0.5852518081665039,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.4872,
      "step": 42
    },
    {
      "epoch": 0.2482758620689655,
      "grad_norm": 0.5917105674743652,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.6372,
      "step": 45
    },
    {
      "epoch": 0.26482758620689656,
      "grad_norm": 0.5113472938537598,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.3365,
      "step": 48
    },
    {
      "epoch": 0.2813793103448276,
      "grad_norm": 0.6705360412597656,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.512,
      "step": 51
    },
    {
      "epoch": 0.2813793103448276,
      "eval_loss": 2.4239444732666016,
      "eval_runtime": 4.4605,
      "eval_samples_per_second": 68.378,
      "eval_steps_per_second": 8.743,
      "step": 51
    },
    {
      "epoch": 0.2979310344827586,
      "grad_norm": 0.46963927149772644,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.3514,
      "step": 54
    },
    {
      "epoch": 0.31448275862068964,
      "grad_norm": 0.43661412596702576,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.3,
      "step": 57
    },
    {
      "epoch": 0.3310344827586207,
      "grad_norm": 0.48196548223495483,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.2038,
      "step": 60
    },
    {
      "epoch": 0.34758620689655173,
      "grad_norm": 0.47665441036224365,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.2897,
      "step": 63
    },
    {
      "epoch": 0.3641379310344828,
      "grad_norm": 0.4325224459171295,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.1655,
      "step": 66
    },
    {
      "epoch": 0.37517241379310345,
      "eval_loss": 2.257903575897217,
      "eval_runtime": 4.4787,
      "eval_samples_per_second": 68.1,
      "eval_steps_per_second": 8.708,
      "step": 68
    },
    {
      "epoch": 0.38068965517241377,
      "grad_norm": 0.45721158385276794,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.1911,
      "step": 69
    },
    {
      "epoch": 0.3972413793103448,
      "grad_norm": 0.5159802436828613,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.249,
      "step": 72
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 0.4334803819656372,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.0298,
      "step": 75
    },
    {
      "epoch": 0.4303448275862069,
      "grad_norm": 0.4824793338775635,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.1161,
      "step": 78
    },
    {
      "epoch": 0.44689655172413795,
      "grad_norm": 0.507147490978241,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.1276,
      "step": 81
    },
    {
      "epoch": 0.463448275862069,
      "grad_norm": 0.5079874396324158,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.3072,
      "step": 84
    },
    {
      "epoch": 0.4689655172413793,
      "eval_loss": 2.1795969009399414,
      "eval_runtime": 4.4446,
      "eval_samples_per_second": 68.623,
      "eval_steps_per_second": 8.775,
      "step": 85
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5210072994232178,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.006,
      "step": 87
    },
    {
      "epoch": 0.496551724137931,
      "grad_norm": 0.4956110119819641,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.0443,
      "step": 90
    },
    {
      "epoch": 0.5131034482758621,
      "grad_norm": 0.5796875357627869,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.173,
      "step": 93
    },
    {
      "epoch": 0.5296551724137931,
      "grad_norm": 0.5329291224479675,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.1224,
      "step": 96
    },
    {
      "epoch": 0.5462068965517242,
      "grad_norm": 0.555596113204956,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.0329,
      "step": 99
    },
    {
      "epoch": 0.5627586206896552,
      "grad_norm": 0.462854266166687,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.9292,
      "step": 102
    },
    {
      "epoch": 0.5627586206896552,
      "eval_loss": 2.1433825492858887,
      "eval_runtime": 4.4422,
      "eval_samples_per_second": 68.66,
      "eval_steps_per_second": 8.779,
      "step": 102
    },
    {
      "epoch": 0.5793103448275863,
      "grad_norm": 0.53304523229599,
      "learning_rate": 5e-05,
      "loss": 2.1968,
      "step": 105
    },
    {
      "epoch": 0.5958620689655172,
      "grad_norm": 0.4985330402851105,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.0337,
      "step": 108
    },
    {
      "epoch": 0.6124137931034482,
      "grad_norm": 0.5477891564369202,
      "learning_rate": 4.504772348747687e-05,
      "loss": 2.1453,
      "step": 111
    },
    {
      "epoch": 0.6289655172413793,
      "grad_norm": 0.5858056545257568,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 2.1941,
      "step": 114
    },
    {
      "epoch": 0.6455172413793103,
      "grad_norm": 0.4582912027835846,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.9992,
      "step": 117
    },
    {
      "epoch": 0.6565517241379311,
      "eval_loss": 2.1214051246643066,
      "eval_runtime": 4.4514,
      "eval_samples_per_second": 68.518,
      "eval_steps_per_second": 8.761,
      "step": 119
    },
    {
      "epoch": 0.6620689655172414,
      "grad_norm": 0.5721688270568848,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.0894,
      "step": 120
    },
    {
      "epoch": 0.6786206896551724,
      "grad_norm": 0.5939153432846069,
      "learning_rate": 3.533749813077677e-05,
      "loss": 2.0367,
      "step": 123
    },
    {
      "epoch": 0.6951724137931035,
      "grad_norm": 0.5539590716362,
      "learning_rate": 3.298534127791785e-05,
      "loss": 2.1166,
      "step": 126
    },
    {
      "epoch": 0.7117241379310345,
      "grad_norm": 0.5420939326286316,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.9757,
      "step": 129
    },
    {
      "epoch": 0.7282758620689656,
      "grad_norm": 0.5419110059738159,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.9603,
      "step": 132
    },
    {
      "epoch": 0.7448275862068966,
      "grad_norm": 0.5101600289344788,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.9635,
      "step": 135
    },
    {
      "epoch": 0.7503448275862069,
      "eval_loss": 2.1131086349487305,
      "eval_runtime": 4.4579,
      "eval_samples_per_second": 68.417,
      "eval_steps_per_second": 8.748,
      "step": 136
    },
    {
      "epoch": 0.7613793103448275,
      "grad_norm": 0.5550276637077332,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.0373,
      "step": 138
    },
    {
      "epoch": 0.7779310344827586,
      "grad_norm": 0.5338502526283264,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.1343,
      "step": 141
    },
    {
      "epoch": 0.7944827586206896,
      "grad_norm": 0.47092920541763306,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.9688,
      "step": 144
    },
    {
      "epoch": 0.8110344827586207,
      "grad_norm": 0.5254806876182556,
      "learning_rate": 1.800157297483417e-05,
      "loss": 2.0718,
      "step": 147
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 0.5177105069160461,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.188,
      "step": 150
    },
    {
      "epoch": 0.8441379310344828,
      "grad_norm": 0.49027958512306213,
      "learning_rate": 1.435357758543015e-05,
      "loss": 2.1538,
      "step": 153
    },
    {
      "epoch": 0.8441379310344828,
      "eval_loss": 2.107172966003418,
      "eval_runtime": 4.4092,
      "eval_samples_per_second": 69.174,
      "eval_steps_per_second": 8.845,
      "step": 153
    },
    {
      "epoch": 0.8606896551724138,
      "grad_norm": 0.4854514002799988,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.8567,
      "step": 156
    },
    {
      "epoch": 0.8772413793103448,
      "grad_norm": 0.4650457203388214,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 2.0116,
      "step": 159
    },
    {
      "epoch": 0.8937931034482759,
      "grad_norm": 0.4151840806007385,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.0101,
      "step": 162
    },
    {
      "epoch": 0.9103448275862069,
      "grad_norm": 0.49467867612838745,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.0835,
      "step": 165
    },
    {
      "epoch": 0.926896551724138,
      "grad_norm": 0.622384786605835,
      "learning_rate": 6.837175952121306e-06,
      "loss": 2.2758,
      "step": 168
    },
    {
      "epoch": 0.9379310344827586,
      "eval_loss": 2.102418899536133,
      "eval_runtime": 4.4651,
      "eval_samples_per_second": 68.308,
      "eval_steps_per_second": 8.734,
      "step": 170
    },
    {
      "epoch": 0.9434482758620689,
      "grad_norm": 0.5099430680274963,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.9916,
      "step": 171
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.49288663268089294,
      "learning_rate": 4.549673247541875e-06,
      "loss": 2.1636,
      "step": 174
    },
    {
      "epoch": 0.976551724137931,
      "grad_norm": 0.5609566569328308,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 2.0894,
      "step": 177
    },
    {
      "epoch": 0.993103448275862,
      "grad_norm": 0.45057249069213867,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.0022,
      "step": 180
    },
    {
      "epoch": 1.0096551724137932,
      "grad_norm": 0.4906492233276367,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.3473,
      "step": 183
    },
    {
      "epoch": 1.0262068965517241,
      "grad_norm": 0.6296617984771729,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.0053,
      "step": 186
    },
    {
      "epoch": 1.0317241379310345,
      "eval_loss": 2.1006078720092773,
      "eval_runtime": 4.4441,
      "eval_samples_per_second": 68.63,
      "eval_steps_per_second": 8.776,
      "step": 187
    },
    {
      "epoch": 1.042758620689655,
      "grad_norm": 0.4491814374923706,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.0738,
      "step": 189
    },
    {
      "epoch": 1.0593103448275862,
      "grad_norm": 0.566460907459259,
      "learning_rate": 4.367965336512403e-07,
      "loss": 2.149,
      "step": 192
    },
    {
      "epoch": 1.0758620689655172,
      "grad_norm": 0.4609183073043823,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 2.0185,
      "step": 195
    },
    {
      "epoch": 1.0924137931034483,
      "grad_norm": 0.5644339323043823,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.8901,
      "step": 198
    }
  ],
  "logging_steps": 3,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.27034770292736e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}