{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.988610478359909,
  "eval_steps": 500,
  "global_step": 657,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04555808656036447,
      "grad_norm": 16.628382336058554,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 1.5883,
      "step": 10
    },
    {
      "epoch": 0.09111617312072894,
      "grad_norm": 3.221028223725061,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 0.9317,
      "step": 20
    },
    {
      "epoch": 0.1366742596810934,
      "grad_norm": 1.5103642702449496,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.5336,
      "step": 30
    },
    {
      "epoch": 0.18223234624145787,
      "grad_norm": 1.0681798496560502,
      "learning_rate": 6.060606060606061e-06,
      "loss": 0.4417,
      "step": 40
    },
    {
      "epoch": 0.22779043280182232,
      "grad_norm": 0.9679921213671909,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 0.3979,
      "step": 50
    },
    {
      "epoch": 0.2733485193621868,
      "grad_norm": 0.926628742270625,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.3744,
      "step": 60
    },
    {
      "epoch": 0.31890660592255127,
      "grad_norm": 0.9491261260284587,
      "learning_rate": 9.998869765883566e-06,
      "loss": 0.3486,
      "step": 70
    },
    {
      "epoch": 0.36446469248291574,
      "grad_norm": 0.84920311370356,
      "learning_rate": 9.986160499534318e-06,
      "loss": 0.3453,
      "step": 80
    },
    {
      "epoch": 0.41002277904328016,
      "grad_norm": 0.9789183018412179,
      "learning_rate": 9.959365197965824e-06,
      "loss": 0.3572,
      "step": 90
    },
    {
      "epoch": 0.45558086560364464,
      "grad_norm": 0.9102455500916922,
      "learning_rate": 9.918559558613344e-06,
      "loss": 0.3356,
      "step": 100
    },
    {
      "epoch": 0.5011389521640092,
      "grad_norm": 0.9258850899143908,
      "learning_rate": 9.863858858486736e-06,
      "loss": 0.3278,
      "step": 110
    },
    {
      "epoch": 0.5466970387243736,
      "grad_norm": 0.8922762696366542,
      "learning_rate": 9.795417628509857e-06,
      "loss": 0.3268,
      "step": 120
    },
    {
      "epoch": 0.592255125284738,
      "grad_norm": 0.9396732926347776,
      "learning_rate": 9.713429216966624e-06,
      "loss": 0.3108,
      "step": 130
    },
    {
      "epoch": 0.6378132118451025,
      "grad_norm": 0.845601467481683,
      "learning_rate": 9.618125243286989e-06,
      "loss": 0.3164,
      "step": 140
    },
    {
      "epoch": 0.683371298405467,
      "grad_norm": 0.8159514975969553,
      "learning_rate": 9.50977494371594e-06,
      "loss": 0.3127,
      "step": 150
    },
    {
      "epoch": 0.7289293849658315,
      "grad_norm": 0.8778654186332652,
      "learning_rate": 9.388684410713977e-06,
      "loss": 0.3118,
      "step": 160
    },
    {
      "epoch": 0.7744874715261959,
      "grad_norm": 0.8158041504461108,
      "learning_rate": 9.255195728237837e-06,
      "loss": 0.3033,
      "step": 170
    },
    {
      "epoch": 0.8200455580865603,
      "grad_norm": 0.8241477933179293,
      "learning_rate": 9.109686005344258e-06,
      "loss": 0.298,
      "step": 180
    },
    {
      "epoch": 0.8656036446469249,
      "grad_norm": 0.7836442953404367,
      "learning_rate": 8.952566310846931e-06,
      "loss": 0.2967,
      "step": 190
    },
    {
      "epoch": 0.9111617312072893,
      "grad_norm": 0.8589198296868927,
      "learning_rate": 8.784280512036235e-06,
      "loss": 0.2908,
      "step": 200
    },
    {
      "epoch": 0.9567198177676538,
      "grad_norm": 0.8976108880329798,
      "learning_rate": 8.60530402074241e-06,
      "loss": 0.288,
      "step": 210
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8244261812910136,
      "learning_rate": 8.416142450284565e-06,
      "loss": 0.274,
      "step": 220
    },
    {
      "epoch": 1.0455580865603644,
      "grad_norm": 0.7709445009431932,
      "learning_rate": 8.217330187099689e-06,
      "loss": 0.178,
      "step": 230
    },
    {
      "epoch": 1.0911161731207288,
      "grad_norm": 0.7371669649380324,
      "learning_rate": 8.009428881086836e-06,
      "loss": 0.1706,
      "step": 240
    },
    {
      "epoch": 1.1366742596810935,
      "grad_norm": 0.8325359027964357,
      "learning_rate": 7.793025858931317e-06,
      "loss": 0.1717,
      "step": 250
    },
    {
      "epoch": 1.182232346241458,
      "grad_norm": 0.7810927662905283,
      "learning_rate": 7.568732464891293e-06,
      "loss": 0.1768,
      "step": 260
    },
    {
      "epoch": 1.2277904328018223,
      "grad_norm": 0.7328567227225008,
      "learning_rate": 7.33718233373407e-06,
      "loss": 0.174,
      "step": 270
    },
    {
      "epoch": 1.2733485193621867,
      "grad_norm": 0.829615067889057,
      "learning_rate": 7.099029600701144e-06,
      "loss": 0.1721,
      "step": 280
    },
    {
      "epoch": 1.3189066059225514,
      "grad_norm": 0.7764413190939856,
      "learning_rate": 6.854947053558849e-06,
      "loss": 0.169,
      "step": 290
    },
    {
      "epoch": 1.3644646924829158,
      "grad_norm": 0.7592152186492857,
      "learning_rate": 6.6056242319551315e-06,
      "loss": 0.1667,
      "step": 300
    },
    {
      "epoch": 1.4100227790432802,
      "grad_norm": 0.7583979219386041,
      "learning_rate": 6.3517654794518156e-06,
      "loss": 0.1644,
      "step": 310
    },
    {
      "epoch": 1.4555808656036446,
      "grad_norm": 0.7329938588396943,
      "learning_rate": 6.094087953735423e-06,
      "loss": 0.168,
      "step": 320
    },
    {
      "epoch": 1.501138952164009,
      "grad_norm": 0.8196364714199265,
      "learning_rate": 5.8333196006277536e-06,
      "loss": 0.1617,
      "step": 330
    },
    {
      "epoch": 1.5466970387243735,
      "grad_norm": 0.7565763296431312,
      "learning_rate": 5.570197097619688e-06,
      "loss": 0.1611,
      "step": 340
    },
    {
      "epoch": 1.592255125284738,
      "grad_norm": 0.8868392512031471,
      "learning_rate": 5.305463772737812e-06,
      "loss": 0.1609,
      "step": 350
    },
    {
      "epoch": 1.6378132118451025,
      "grad_norm": 0.8812463705246544,
      "learning_rate": 5.039867504623084e-06,
      "loss": 0.1677,
      "step": 360
    },
    {
      "epoch": 1.683371298405467,
      "grad_norm": 0.7633777742059934,
      "learning_rate": 4.774158609753908e-06,
      "loss": 0.1512,
      "step": 370
    },
    {
      "epoch": 1.7289293849658316,
      "grad_norm": 0.7820693250794272,
      "learning_rate": 4.5090877227822424e-06,
      "loss": 0.1572,
      "step": 380
    },
    {
      "epoch": 1.774487471526196,
      "grad_norm": 0.7688524374447184,
      "learning_rate": 4.245403675970877e-06,
      "loss": 0.1617,
      "step": 390
    },
    {
      "epoch": 1.8200455580865604,
      "grad_norm": 0.7254423021253176,
      "learning_rate": 3.9838513837224814e-06,
      "loss": 0.1519,
      "step": 400
    },
    {
      "epoch": 1.8656036446469249,
      "grad_norm": 0.8076268890579671,
      "learning_rate": 3.7251697381767373e-06,
      "loss": 0.154,
      "step": 410
    },
    {
      "epoch": 1.9111617312072893,
      "grad_norm": 0.7615743261772087,
      "learning_rate": 3.4700895218205026e-06,
      "loss": 0.1468,
      "step": 420
    },
    {
      "epoch": 1.9567198177676537,
      "grad_norm": 0.7511849885826963,
      "learning_rate": 3.2193313430079737e-06,
      "loss": 0.147,
      "step": 430
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7584213495047252,
      "learning_rate": 2.9736036002230332e-06,
      "loss": 0.1429,
      "step": 440
    },
    {
      "epoch": 2.0455580865603644,
      "grad_norm": 0.6815225387343684,
      "learning_rate": 2.7336004808348094e-06,
      "loss": 0.0751,
      "step": 450
    },
    {
      "epoch": 2.091116173120729,
      "grad_norm": 0.6174750652979677,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.0711,
      "step": 460
    },
    {
      "epoch": 2.1366742596810933,
      "grad_norm": 0.6236626143150734,
      "learning_rate": 2.273462085252146e-06,
      "loss": 0.0722,
      "step": 470
    },
    {
      "epoch": 2.1822323462414577,
      "grad_norm": 0.5971939289865311,
      "learning_rate": 2.0546267121888863e-06,
      "loss": 0.0693,
      "step": 480
    },
    {
      "epoch": 2.2277904328018225,
      "grad_norm": 0.631697145877715,
      "learning_rate": 1.8441120965239912e-06,
      "loss": 0.0713,
      "step": 490
    },
    {
      "epoch": 2.273348519362187,
      "grad_norm": 0.6817300872785331,
      "learning_rate": 1.642512947611622e-06,
      "loss": 0.0729,
      "step": 500
    },
    {
      "epoch": 2.3189066059225514,
      "grad_norm": 0.5682490177071967,
      "learning_rate": 1.4503987883766857e-06,
      "loss": 0.0656,
      "step": 510
    },
    {
      "epoch": 2.364464692482916,
      "grad_norm": 0.5912819077013511,
      "learning_rate": 1.2683123463975144e-06,
      "loss": 0.0658,
      "step": 520
    },
    {
      "epoch": 2.41002277904328,
      "grad_norm": 0.606352905873965,
      "learning_rate": 1.0967680206861198e-06,
      "loss": 0.0694,
      "step": 530
    },
    {
      "epoch": 2.4555808656036446,
      "grad_norm": 0.6353412192229968,
      "learning_rate": 9.362504284973683e-07,
      "loss": 0.0701,
      "step": 540
    },
    {
      "epoch": 2.501138952164009,
      "grad_norm": 0.6607014617898831,
      "learning_rate": 7.872130362724422e-07,
      "loss": 0.0691,
      "step": 550
    },
    {
      "epoch": 2.5466970387243735,
      "grad_norm": 0.6527059303311876,
      "learning_rate": 6.500768785841482e-07,
      "loss": 0.0647,
      "step": 560
    },
    {
      "epoch": 2.592255125284738,
      "grad_norm": 0.6203144834959747,
      "learning_rate": 5.252293687031196e-07,
      "loss": 0.0669,
      "step": 570
    },
    {
      "epoch": 2.6378132118451028,
      "grad_norm": 0.6069382959627451,
      "learning_rate": 4.130232041450866e-07,
      "loss": 0.0624,
      "step": 580
    },
    {
      "epoch": 2.6833712984054667,
      "grad_norm": 0.6304879856190249,
      "learning_rate": 3.1377537029107174e-07,
      "loss": 0.0655,
      "step": 590
    },
    {
      "epoch": 2.7289293849658316,
      "grad_norm": 0.6325528536254185,
      "learning_rate": 2.2776624489530664e-07,
      "loss": 0.0667,
      "step": 600
    },
    {
      "epoch": 2.774487471526196,
      "grad_norm": 0.6179538898003908,
      "learning_rate": 1.55238806010668e-07,
      "loss": 0.0644,
      "step": 610
    },
    {
      "epoch": 2.8200455580865604,
      "grad_norm": 0.5965673740089573,
      "learning_rate": 9.639794556925041e-08,
      "loss": 0.0659,
      "step": 620
    },
    {
      "epoch": 2.865603644646925,
      "grad_norm": 0.6382075048871372,
      "learning_rate": 5.1409890557246876e-08,
      "loss": 0.0645,
      "step": 630
    },
    {
      "epoch": 2.9111617312072893,
      "grad_norm": 0.612194769673645,
      "learning_rate": 2.0401733419315727e-08,
      "loss": 0.063,
      "step": 640
    },
    {
      "epoch": 2.9567198177676537,
      "grad_norm": 0.6571824905728761,
      "learning_rate": 3.4610730190648423e-09,
      "loss": 0.0647,
      "step": 650
    }
  ],
  "logging_steps": 10,
  "max_steps": 657,
  "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": 418097876697088.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}