{
  "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": 4.052004444605685,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 0.5253,
      "step": 10
    },
    {
      "epoch": 0.09111617312072894,
      "grad_norm": 1.4381960454873794,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 0.4498,
      "step": 20
    },
    {
      "epoch": 0.1366742596810934,
      "grad_norm": 1.3543508392140766,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.4,
      "step": 30
    },
    {
      "epoch": 0.18223234624145787,
      "grad_norm": 1.2520872546371757,
      "learning_rate": 6.060606060606061e-06,
      "loss": 0.3763,
      "step": 40
    },
    {
      "epoch": 0.22779043280182232,
      "grad_norm": 1.02523284296708,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 0.3626,
      "step": 50
    },
    {
      "epoch": 0.2733485193621868,
      "grad_norm": 1.093558631219529,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.3496,
      "step": 60
    },
    {
      "epoch": 0.31890660592255127,
      "grad_norm": 1.1794828114399931,
      "learning_rate": 9.998869765883566e-06,
      "loss": 0.3328,
      "step": 70
    },
    {
      "epoch": 0.36446469248291574,
      "grad_norm": 0.9895352612973752,
      "learning_rate": 9.986160499534318e-06,
      "loss": 0.3323,
      "step": 80
    },
    {
      "epoch": 0.41002277904328016,
      "grad_norm": 1.2593162041954078,
      "learning_rate": 9.959365197965824e-06,
      "loss": 0.3476,
      "step": 90
    },
    {
      "epoch": 0.45558086560364464,
      "grad_norm": 1.0247420858839205,
      "learning_rate": 9.918559558613344e-06,
      "loss": 0.3281,
      "step": 100
    },
    {
      "epoch": 0.5011389521640092,
      "grad_norm": 1.1609463270495288,
      "learning_rate": 9.863858858486736e-06,
      "loss": 0.3213,
      "step": 110
    },
    {
      "epoch": 0.5466970387243736,
      "grad_norm": 1.112608179278684,
      "learning_rate": 9.795417628509857e-06,
      "loss": 0.3226,
      "step": 120
    },
    {
      "epoch": 0.592255125284738,
      "grad_norm": 1.1442245883128161,
      "learning_rate": 9.713429216966624e-06,
      "loss": 0.3058,
      "step": 130
    },
    {
      "epoch": 0.6378132118451025,
      "grad_norm": 1.0029316918162978,
      "learning_rate": 9.618125243286989e-06,
      "loss": 0.3114,
      "step": 140
    },
    {
      "epoch": 0.683371298405467,
      "grad_norm": 1.0408244849779362,
      "learning_rate": 9.50977494371594e-06,
      "loss": 0.3091,
      "step": 150
    },
    {
      "epoch": 0.7289293849658315,
      "grad_norm": 1.0789631799175963,
      "learning_rate": 9.388684410713977e-06,
      "loss": 0.3078,
      "step": 160
    },
    {
      "epoch": 0.7744874715261959,
      "grad_norm": 0.9628230660114916,
      "learning_rate": 9.255195728237837e-06,
      "loss": 0.3009,
      "step": 170
    },
    {
      "epoch": 0.8200455580865603,
      "grad_norm": 0.9722514254536355,
      "learning_rate": 9.109686005344258e-06,
      "loss": 0.2947,
      "step": 180
    },
    {
      "epoch": 0.8656036446469249,
      "grad_norm": 0.8777666899714902,
      "learning_rate": 8.952566310846931e-06,
      "loss": 0.2942,
      "step": 190
    },
    {
      "epoch": 0.9111617312072893,
      "grad_norm": 0.9667172893305681,
      "learning_rate": 8.784280512036235e-06,
      "loss": 0.289,
      "step": 200
    },
    {
      "epoch": 0.9567198177676538,
      "grad_norm": 0.9878477819397482,
      "learning_rate": 8.60530402074241e-06,
      "loss": 0.2868,
      "step": 210
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9727406585304033,
      "learning_rate": 8.416142450284565e-06,
      "loss": 0.2717,
      "step": 220
    },
    {
      "epoch": 1.0455580865603644,
      "grad_norm": 0.7915636741448634,
      "learning_rate": 8.217330187099689e-06,
      "loss": 0.1748,
      "step": 230
    },
    {
      "epoch": 1.0911161731207288,
      "grad_norm": 0.7837965142867958,
      "learning_rate": 8.009428881086836e-06,
      "loss": 0.1684,
      "step": 240
    },
    {
      "epoch": 1.1366742596810935,
      "grad_norm": 0.8666778827303715,
      "learning_rate": 7.793025858931317e-06,
      "loss": 0.1692,
      "step": 250
    },
    {
      "epoch": 1.182232346241458,
      "grad_norm": 0.849266584139581,
      "learning_rate": 7.568732464891293e-06,
      "loss": 0.1742,
      "step": 260
    },
    {
      "epoch": 1.2277904328018223,
      "grad_norm": 0.7696615783202124,
      "learning_rate": 7.33718233373407e-06,
      "loss": 0.1711,
      "step": 270
    },
    {
      "epoch": 1.2733485193621867,
      "grad_norm": 0.8661434772503379,
      "learning_rate": 7.099029600701144e-06,
      "loss": 0.1697,
      "step": 280
    },
    {
      "epoch": 1.3189066059225514,
      "grad_norm": 0.8221397461631786,
      "learning_rate": 6.854947053558849e-06,
      "loss": 0.1667,
      "step": 290
    },
    {
      "epoch": 1.3644646924829158,
      "grad_norm": 0.7959283850125798,
      "learning_rate": 6.6056242319551315e-06,
      "loss": 0.1646,
      "step": 300
    },
    {
      "epoch": 1.4100227790432802,
      "grad_norm": 0.7934911795062435,
      "learning_rate": 6.3517654794518156e-06,
      "loss": 0.1625,
      "step": 310
    },
    {
      "epoch": 1.4555808656036446,
      "grad_norm": 0.7890669930103191,
      "learning_rate": 6.094087953735423e-06,
      "loss": 0.1664,
      "step": 320
    },
    {
      "epoch": 1.501138952164009,
      "grad_norm": 0.849926754992192,
      "learning_rate": 5.8333196006277536e-06,
      "loss": 0.1608,
      "step": 330
    },
    {
      "epoch": 1.5466970387243735,
      "grad_norm": 0.7920622918925933,
      "learning_rate": 5.570197097619688e-06,
      "loss": 0.1589,
      "step": 340
    },
    {
      "epoch": 1.592255125284738,
      "grad_norm": 0.8974340210426586,
      "learning_rate": 5.305463772737812e-06,
      "loss": 0.16,
      "step": 350
    },
    {
      "epoch": 1.6378132118451025,
      "grad_norm": 0.8910155901512489,
      "learning_rate": 5.039867504623084e-06,
      "loss": 0.1661,
      "step": 360
    },
    {
      "epoch": 1.683371298405467,
      "grad_norm": 0.8438540298957333,
      "learning_rate": 4.774158609753908e-06,
      "loss": 0.1498,
      "step": 370
    },
    {
      "epoch": 1.7289293849658316,
      "grad_norm": 0.8003749509299389,
      "learning_rate": 4.5090877227822424e-06,
      "loss": 0.1558,
      "step": 380
    },
    {
      "epoch": 1.774487471526196,
      "grad_norm": 0.7879659477066289,
      "learning_rate": 4.245403675970877e-06,
      "loss": 0.1583,
      "step": 390
    },
    {
      "epoch": 1.8200455580865604,
      "grad_norm": 0.7653210529786019,
      "learning_rate": 3.9838513837224814e-06,
      "loss": 0.1495,
      "step": 400
    },
    {
      "epoch": 1.8656036446469249,
      "grad_norm": 0.8205629178189233,
      "learning_rate": 3.7251697381767373e-06,
      "loss": 0.152,
      "step": 410
    },
    {
      "epoch": 1.9111617312072893,
      "grad_norm": 0.8015055799282049,
      "learning_rate": 3.4700895218205026e-06,
      "loss": 0.1454,
      "step": 420
    },
    {
      "epoch": 1.9567198177676537,
      "grad_norm": 0.7703178443216857,
      "learning_rate": 3.2193313430079737e-06,
      "loss": 0.1456,
      "step": 430
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7965347444065239,
      "learning_rate": 2.9736036002230332e-06,
      "loss": 0.1401,
      "step": 440
    },
    {
      "epoch": 2.0455580865603644,
      "grad_norm": 0.7224665974614691,
      "learning_rate": 2.7336004808348094e-06,
      "loss": 0.0746,
      "step": 450
    },
    {
      "epoch": 2.091116173120729,
      "grad_norm": 0.6344834885792635,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.0704,
      "step": 460
    },
    {
      "epoch": 2.1366742596810933,
      "grad_norm": 0.6333151400219024,
      "learning_rate": 2.273462085252146e-06,
      "loss": 0.0719,
      "step": 470
    },
    {
      "epoch": 2.1822323462414577,
      "grad_norm": 0.6345496356388078,
      "learning_rate": 2.0546267121888863e-06,
      "loss": 0.0683,
      "step": 480
    },
    {
      "epoch": 2.2277904328018225,
      "grad_norm": 0.663831749653779,
      "learning_rate": 1.8441120965239912e-06,
      "loss": 0.0707,
      "step": 490
    },
    {
      "epoch": 2.273348519362187,
      "grad_norm": 0.6978500583302198,
      "learning_rate": 1.642512947611622e-06,
      "loss": 0.0719,
      "step": 500
    },
    {
      "epoch": 2.3189066059225514,
      "grad_norm": 0.5899803755413382,
      "learning_rate": 1.4503987883766857e-06,
      "loss": 0.0655,
      "step": 510
    },
    {
      "epoch": 2.364464692482916,
      "grad_norm": 0.597275435306883,
      "learning_rate": 1.2683123463975144e-06,
      "loss": 0.0658,
      "step": 520
    },
    {
      "epoch": 2.41002277904328,
      "grad_norm": 0.6130036081797414,
      "learning_rate": 1.0967680206861198e-06,
      "loss": 0.0691,
      "step": 530
    },
    {
      "epoch": 2.4555808656036446,
      "grad_norm": 0.6291943478576331,
      "learning_rate": 9.362504284973683e-07,
      "loss": 0.0701,
      "step": 540
    },
    {
      "epoch": 2.501138952164009,
      "grad_norm": 0.6719915377398242,
      "learning_rate": 7.872130362724422e-07,
      "loss": 0.0689,
      "step": 550
    },
    {
      "epoch": 2.5466970387243735,
      "grad_norm": 0.6866035161561178,
      "learning_rate": 6.500768785841482e-07,
      "loss": 0.065,
      "step": 560
    },
    {
      "epoch": 2.592255125284738,
      "grad_norm": 0.6382818453339463,
      "learning_rate": 5.252293687031196e-07,
      "loss": 0.0661,
      "step": 570
    },
    {
      "epoch": 2.6378132118451028,
      "grad_norm": 0.6023391864806479,
      "learning_rate": 4.130232041450866e-07,
      "loss": 0.0613,
      "step": 580
    },
    {
      "epoch": 2.6833712984054667,
      "grad_norm": 0.6283362244939039,
      "learning_rate": 3.1377537029107174e-07,
      "loss": 0.065,
      "step": 590
    },
    {
      "epoch": 2.7289293849658316,
      "grad_norm": 0.6324038348983413,
      "learning_rate": 2.2776624489530664e-07,
      "loss": 0.0662,
      "step": 600
    },
    {
      "epoch": 2.774487471526196,
      "grad_norm": 0.6463288010084847,
      "learning_rate": 1.55238806010668e-07,
      "loss": 0.0637,
      "step": 610
    },
    {
      "epoch": 2.8200455580865604,
      "grad_norm": 0.5961299692551064,
      "learning_rate": 9.639794556925041e-08,
      "loss": 0.0645,
      "step": 620
    },
    {
      "epoch": 2.865603644646925,
      "grad_norm": 0.6588358857173194,
      "learning_rate": 5.1409890557246876e-08,
      "loss": 0.0644,
      "step": 630
    },
    {
      "epoch": 2.9111617312072893,
      "grad_norm": 0.5976452121379741,
      "learning_rate": 2.0401733419315727e-08,
      "loss": 0.0626,
      "step": 640
    },
    {
      "epoch": 2.9567198177676537,
      "grad_norm": 0.6600908299010216,
      "learning_rate": 3.4610730190648423e-09,
      "loss": 0.0641,
      "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
}