{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 381,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007874015748031496,
      "grad_norm": 97.86459103253922,
      "learning_rate": 5.128205128205128e-07,
      "loss": 10.8466,
      "step": 1
    },
    {
      "epoch": 0.03937007874015748,
      "grad_norm": 51.400005997600886,
      "learning_rate": 2.564102564102564e-06,
      "loss": 10.5913,
      "step": 5
    },
    {
      "epoch": 0.07874015748031496,
      "grad_norm": 18.973044788046785,
      "learning_rate": 5.128205128205128e-06,
      "loss": 9.5728,
      "step": 10
    },
    {
      "epoch": 0.11811023622047244,
      "grad_norm": 18.974754241662772,
      "learning_rate": 7.692307692307694e-06,
      "loss": 8.6008,
      "step": 15
    },
    {
      "epoch": 0.15748031496062992,
      "grad_norm": 16.264940537929053,
      "learning_rate": 1.0256410256410256e-05,
      "loss": 7.6501,
      "step": 20
    },
    {
      "epoch": 0.1968503937007874,
      "grad_norm": 13.83260251756727,
      "learning_rate": 1.2820512820512823e-05,
      "loss": 6.519,
      "step": 25
    },
    {
      "epoch": 0.23622047244094488,
      "grad_norm": 11.83126275501012,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 5.9682,
      "step": 30
    },
    {
      "epoch": 0.2755905511811024,
      "grad_norm": 11.5143365026344,
      "learning_rate": 1.794871794871795e-05,
      "loss": 5.3936,
      "step": 35
    },
    {
      "epoch": 0.31496062992125984,
      "grad_norm": 12.072390547814743,
      "learning_rate": 1.9999578095183126e-05,
      "loss": 4.7938,
      "step": 40
    },
    {
      "epoch": 0.3543307086614173,
      "grad_norm": 11.243881904676005,
      "learning_rate": 1.9984815164333163e-05,
      "loss": 4.3308,
      "step": 45
    },
    {
      "epoch": 0.3937007874015748,
      "grad_norm": 11.150844255163953,
      "learning_rate": 1.9948992579873538e-05,
      "loss": 3.8431,
      "step": 50
    },
    {
      "epoch": 0.4330708661417323,
      "grad_norm": 9.63318982358096,
      "learning_rate": 1.989218589765658e-05,
      "loss": 3.5038,
      "step": 55
    },
    {
      "epoch": 0.47244094488188976,
      "grad_norm": 8.283345964506,
      "learning_rate": 1.981451493252418e-05,
      "loss": 3.2468,
      "step": 60
    },
    {
      "epoch": 0.5118110236220472,
      "grad_norm": 7.133949874571078,
      "learning_rate": 1.971614350559814e-05,
      "loss": 2.9607,
      "step": 65
    },
    {
      "epoch": 0.5511811023622047,
      "grad_norm": 12.013998534508621,
      "learning_rate": 1.9597279098753893e-05,
      "loss": 2.9499,
      "step": 70
    },
    {
      "epoch": 0.5905511811023622,
      "grad_norm": 14.00843961898459,
      "learning_rate": 1.9458172417006347e-05,
      "loss": 2.8118,
      "step": 75
    },
    {
      "epoch": 0.6299212598425197,
      "grad_norm": 4.942733823635868,
      "learning_rate": 1.929911685973088e-05,
      "loss": 2.7099,
      "step": 80
    },
    {
      "epoch": 0.6692913385826772,
      "grad_norm": 4.505148495160888,
      "learning_rate": 1.9120447901834708e-05,
      "loss": 2.6232,
      "step": 85
    },
    {
      "epoch": 0.7086614173228346,
      "grad_norm": 4.482679636836862,
      "learning_rate": 1.8922542386183942e-05,
      "loss": 2.5165,
      "step": 90
    },
    {
      "epoch": 0.7480314960629921,
      "grad_norm": 4.421296731369613,
      "learning_rate": 1.8705817728778626e-05,
      "loss": 2.5159,
      "step": 95
    },
    {
      "epoch": 0.7874015748031497,
      "grad_norm": 4.031128786638602,
      "learning_rate": 1.847073103835222e-05,
      "loss": 2.432,
      "step": 100
    },
    {
      "epoch": 0.8267716535433071,
      "grad_norm": 3.8222494747123665,
      "learning_rate": 1.821777815225245e-05,
      "loss": 2.322,
      "step": 105
    },
    {
      "epoch": 0.8661417322834646,
      "grad_norm": 3.0512683342688938,
      "learning_rate": 1.7947492590636998e-05,
      "loss": 2.3086,
      "step": 110
    },
    {
      "epoch": 0.905511811023622,
      "grad_norm": 3.487728646307278,
      "learning_rate": 1.766044443118978e-05,
      "loss": 2.2626,
      "step": 115
    },
    {
      "epoch": 0.9448818897637795,
      "grad_norm": 3.429390931093978,
      "learning_rate": 1.735723910673132e-05,
      "loss": 2.2276,
      "step": 120
    },
    {
      "epoch": 0.984251968503937,
      "grad_norm": 3.0101351501349285,
      "learning_rate": 1.7038516128259118e-05,
      "loss": 2.1477,
      "step": 125
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.1499931812286377,
      "eval_runtime": 9.2946,
      "eval_samples_per_second": 26.682,
      "eval_steps_per_second": 3.335,
      "step": 127
    },
    {
      "epoch": 1.0236220472440944,
      "grad_norm": 2.951694006526968,
      "learning_rate": 1.670494773611149e-05,
      "loss": 1.975,
      "step": 130
    },
    {
      "epoch": 1.0629921259842519,
      "grad_norm": 4.048795878335224,
      "learning_rate": 1.6357237482099682e-05,
      "loss": 2.0001,
      "step": 135
    },
    {
      "epoch": 1.1023622047244095,
      "grad_norm": 3.297695818798186,
      "learning_rate": 1.5996118745598817e-05,
      "loss": 1.9234,
      "step": 140
    },
    {
      "epoch": 1.141732283464567,
      "grad_norm": 3.038860034781639,
      "learning_rate": 1.5622353186727542e-05,
      "loss": 1.9526,
      "step": 145
    },
    {
      "epoch": 1.1811023622047245,
      "grad_norm": 3.066625145980664,
      "learning_rate": 1.523672913987878e-05,
      "loss": 1.9514,
      "step": 150
    },
    {
      "epoch": 1.220472440944882,
      "grad_norm": 2.8503120369521238,
      "learning_rate": 1.4840059950989992e-05,
      "loss": 1.8463,
      "step": 155
    },
    {
      "epoch": 1.2598425196850394,
      "grad_norm": 2.879622274636194,
      "learning_rate": 1.4433182262059861e-05,
      "loss": 1.9393,
      "step": 160
    },
    {
      "epoch": 1.2992125984251968,
      "grad_norm": 2.865024409867327,
      "learning_rate": 1.4016954246529697e-05,
      "loss": 1.8229,
      "step": 165
    },
    {
      "epoch": 1.3385826771653544,
      "grad_norm": 3.0018089829005796,
      "learning_rate": 1.3592253799251377e-05,
      "loss": 1.9101,
      "step": 170
    },
    {
      "epoch": 1.3779527559055118,
      "grad_norm": 2.6200297090547564,
      "learning_rate": 1.3159976684859528e-05,
      "loss": 1.8719,
      "step": 175
    },
    {
      "epoch": 1.4173228346456692,
      "grad_norm": 3.2482197763587703,
      "learning_rate": 1.2721034648453353e-05,
      "loss": 1.8663,
      "step": 180
    },
    {
      "epoch": 1.4566929133858268,
      "grad_norm": 2.509202477142822,
      "learning_rate": 1.2276353492572937e-05,
      "loss": 1.8042,
      "step": 185
    },
    {
      "epoch": 1.4960629921259843,
      "grad_norm": 2.3022341616451265,
      "learning_rate": 1.1826871124526072e-05,
      "loss": 1.8121,
      "step": 190
    },
    {
      "epoch": 1.5354330708661417,
      "grad_norm": 3.1813641245330238,
      "learning_rate": 1.1373535578184083e-05,
      "loss": 1.8176,
      "step": 195
    },
    {
      "epoch": 1.574803149606299,
      "grad_norm": 2.6018779161783914,
      "learning_rate": 1.0917303014419036e-05,
      "loss": 1.8582,
      "step": 200
    },
    {
      "epoch": 1.6141732283464567,
      "grad_norm": 2.477600344836676,
      "learning_rate": 1.045913570439972e-05,
      "loss": 1.8783,
      "step": 205
    },
    {
      "epoch": 1.6535433070866141,
      "grad_norm": 2.4376336894838335,
      "learning_rate": 1e-05,
      "loss": 1.7568,
      "step": 210
    },
    {
      "epoch": 1.6929133858267718,
      "grad_norm": 2.5393277649924046,
      "learning_rate": 9.540864295600282e-06,
      "loss": 1.7657,
      "step": 215
    },
    {
      "epoch": 1.7322834645669292,
      "grad_norm": 2.558708403448478,
      "learning_rate": 9.082696985580964e-06,
      "loss": 1.7453,
      "step": 220
    },
    {
      "epoch": 1.7716535433070866,
      "grad_norm": 2.6628644142413984,
      "learning_rate": 8.626464421815919e-06,
      "loss": 1.8246,
      "step": 225
    },
    {
      "epoch": 1.811023622047244,
      "grad_norm": 2.4749331824893046,
      "learning_rate": 8.173128875473933e-06,
      "loss": 1.7386,
      "step": 230
    },
    {
      "epoch": 1.8503937007874016,
      "grad_norm": 2.4118889944549817,
      "learning_rate": 7.72364650742707e-06,
      "loss": 1.744,
      "step": 235
    },
    {
      "epoch": 1.889763779527559,
      "grad_norm": 2.1983857820686485,
      "learning_rate": 7.278965351546648e-06,
      "loss": 1.7167,
      "step": 240
    },
    {
      "epoch": 1.9291338582677167,
      "grad_norm": 2.3266205479938664,
      "learning_rate": 6.840023315140476e-06,
      "loss": 1.7168,
      "step": 245
    },
    {
      "epoch": 1.968503937007874,
      "grad_norm": 2.6053794749618344,
      "learning_rate": 6.407746200748628e-06,
      "loss": 1.7855,
      "step": 250
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.8472861051559448,
      "eval_runtime": 9.2247,
      "eval_samples_per_second": 26.884,
      "eval_steps_per_second": 3.361,
      "step": 254
    },
    {
      "epoch": 2.0078740157480315,
      "grad_norm": 4.344086351254557,
      "learning_rate": 5.983045753470308e-06,
      "loss": 1.6109,
      "step": 255
    },
    {
      "epoch": 2.047244094488189,
      "grad_norm": 4.783883169799299,
      "learning_rate": 5.566817737940142e-06,
      "loss": 1.3618,
      "step": 260
    },
    {
      "epoch": 2.0866141732283463,
      "grad_norm": 3.518842708372338,
      "learning_rate": 5.159940049010015e-06,
      "loss": 1.3088,
      "step": 265
    },
    {
      "epoch": 2.1259842519685037,
      "grad_norm": 3.1090620552580006,
      "learning_rate": 4.763270860121222e-06,
      "loss": 1.2353,
      "step": 270
    },
    {
      "epoch": 2.1653543307086616,
      "grad_norm": 3.11493213597681,
      "learning_rate": 4.3776468132724605e-06,
      "loss": 1.2021,
      "step": 275
    },
    {
      "epoch": 2.204724409448819,
      "grad_norm": 5.279030916691569,
      "learning_rate": 4.003881254401183e-06,
      "loss": 1.2297,
      "step": 280
    },
    {
      "epoch": 2.2440944881889764,
      "grad_norm": 3.199352297712251,
      "learning_rate": 3.6427625179003223e-06,
      "loss": 1.2056,
      "step": 285
    },
    {
      "epoch": 2.283464566929134,
      "grad_norm": 3.320605244796421,
      "learning_rate": 3.2950522638885106e-06,
      "loss": 1.2402,
      "step": 290
    },
    {
      "epoch": 2.322834645669291,
      "grad_norm": 3.376499709728643,
      "learning_rate": 2.9614838717408866e-06,
      "loss": 1.2743,
      "step": 295
    },
    {
      "epoch": 2.362204724409449,
      "grad_norm": 3.0517704287796397,
      "learning_rate": 2.642760893268684e-06,
      "loss": 1.206,
      "step": 300
    },
    {
      "epoch": 2.4015748031496065,
      "grad_norm": 3.0861115081810517,
      "learning_rate": 2.339555568810221e-06,
      "loss": 1.1712,
      "step": 305
    },
    {
      "epoch": 2.440944881889764,
      "grad_norm": 3.181141612142621,
      "learning_rate": 2.052507409363004e-06,
      "loss": 1.1674,
      "step": 310
    },
    {
      "epoch": 2.4803149606299213,
      "grad_norm": 3.296777400430187,
      "learning_rate": 1.7822218477475496e-06,
      "loss": 1.1969,
      "step": 315
    },
    {
      "epoch": 2.5196850393700787,
      "grad_norm": 3.0166358743310386,
      "learning_rate": 1.5292689616477808e-06,
      "loss": 1.1863,
      "step": 320
    },
    {
      "epoch": 2.559055118110236,
      "grad_norm": 3.1695663564175343,
      "learning_rate": 1.294182271221377e-06,
      "loss": 1.1468,
      "step": 325
    },
    {
      "epoch": 2.5984251968503935,
      "grad_norm": 3.1650310230949374,
      "learning_rate": 1.0774576138160596e-06,
      "loss": 1.2172,
      "step": 330
    },
    {
      "epoch": 2.637795275590551,
      "grad_norm": 3.130799463981766,
      "learning_rate": 8.79552098165296e-07,
      "loss": 1.2009,
      "step": 335
    },
    {
      "epoch": 2.677165354330709,
      "grad_norm": 3.3222405034526297,
      "learning_rate": 7.00883140269123e-07,
      "loss": 1.2493,
      "step": 340
    },
    {
      "epoch": 2.716535433070866,
      "grad_norm": 3.2043683266572915,
      "learning_rate": 5.418275829936537e-07,
      "loss": 1.1749,
      "step": 345
    },
    {
      "epoch": 2.7559055118110236,
      "grad_norm": 3.18928929645315,
      "learning_rate": 4.0272090124611086e-07,
      "loss": 1.1584,
      "step": 350
    },
    {
      "epoch": 2.795275590551181,
      "grad_norm": 3.169825614669709,
      "learning_rate": 2.838564944018618e-07,
      "loss": 1.1369,
      "step": 355
    },
    {
      "epoch": 2.8346456692913384,
      "grad_norm": 3.196801372855951,
      "learning_rate": 1.854850674758213e-07,
      "loss": 1.1763,
      "step": 360
    },
    {
      "epoch": 2.8740157480314963,
      "grad_norm": 3.1501989250825013,
      "learning_rate": 1.0781410234342093e-07,
      "loss": 1.1612,
      "step": 365
    },
    {
      "epoch": 2.9133858267716537,
      "grad_norm": 3.2335057860947454,
      "learning_rate": 5.10074201264632e-08,
      "loss": 1.2047,
      "step": 370
    },
    {
      "epoch": 2.952755905511811,
      "grad_norm": 3.139504284825472,
      "learning_rate": 1.518483566683826e-08,
      "loss": 1.2345,
      "step": 375
    },
    {
      "epoch": 2.9921259842519685,
      "grad_norm": 3.172440172340041,
      "learning_rate": 4.2190481687631736e-10,
      "loss": 1.1423,
      "step": 380
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.9131228923797607,
      "eval_runtime": 9.2288,
      "eval_samples_per_second": 26.872,
      "eval_steps_per_second": 3.359,
      "step": 381
    },
    {
      "epoch": 3.0,
      "step": 381,
      "total_flos": 14587822080000.0,
      "train_loss": 2.4270567033547428,
      "train_runtime": 1375.9881,
      "train_samples_per_second": 4.426,
      "train_steps_per_second": 0.277
    }
  ],
  "logging_steps": 5,
  "max_steps": 381,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 14587822080000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}