{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1332,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0903954802259887,
      "grad_norm": 1.8916133642196655,
      "learning_rate": 9.5e-05,
      "loss": 5.9949,
      "step": 20
    },
    {
      "epoch": 0.1807909604519774,
      "grad_norm": 2.2982795238494873,
      "learning_rate": 9.913636363636364e-05,
      "loss": 5.7733,
      "step": 40
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 1.444909930229187,
      "learning_rate": 9.822727272727274e-05,
      "loss": 5.7282,
      "step": 60
    },
    {
      "epoch": 0.3615819209039548,
      "grad_norm": 2.519259214401245,
      "learning_rate": 9.731818181818181e-05,
      "loss": 5.6798,
      "step": 80
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 1.8974443674087524,
      "learning_rate": 9.640909090909092e-05,
      "loss": 5.6396,
      "step": 100
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 1.7946267127990723,
      "learning_rate": 9.55e-05,
      "loss": 5.6075,
      "step": 120
    },
    {
      "epoch": 0.632768361581921,
      "grad_norm": 1.672841191291809,
      "learning_rate": 9.459090909090909e-05,
      "loss": 5.6705,
      "step": 140
    },
    {
      "epoch": 0.7231638418079096,
      "grad_norm": 1.7475985288619995,
      "learning_rate": 9.368181818181818e-05,
      "loss": 5.5931,
      "step": 160
    },
    {
      "epoch": 0.8135593220338984,
      "grad_norm": 1.6054518222808838,
      "learning_rate": 9.277272727272728e-05,
      "loss": 5.543,
      "step": 180
    },
    {
      "epoch": 0.903954802259887,
      "grad_norm": 1.4981119632720947,
      "learning_rate": 9.186363636363636e-05,
      "loss": 5.5685,
      "step": 200
    },
    {
      "epoch": 0.9943502824858758,
      "grad_norm": 2.0669379234313965,
      "learning_rate": 9.095454545454546e-05,
      "loss": 5.6052,
      "step": 220
    },
    {
      "epoch": 1.0,
      "eval_loss": 5.506160736083984,
      "eval_runtime": 24.9734,
      "eval_samples_per_second": 3.964,
      "eval_steps_per_second": 3.964,
      "step": 222
    },
    {
      "epoch": 1.0813559322033899,
      "grad_norm": 1.6721880435943604,
      "learning_rate": 9.004545454545455e-05,
      "loss": 4.9631,
      "step": 240
    },
    {
      "epoch": 1.1717514124293786,
      "grad_norm": 1.9324918985366821,
      "learning_rate": 8.913636363636364e-05,
      "loss": 4.8356,
      "step": 260
    },
    {
      "epoch": 1.2621468926553672,
      "grad_norm": 1.4607415199279785,
      "learning_rate": 8.822727272727274e-05,
      "loss": 4.8845,
      "step": 280
    },
    {
      "epoch": 1.352542372881356,
      "grad_norm": 1.8261921405792236,
      "learning_rate": 8.731818181818183e-05,
      "loss": 4.8498,
      "step": 300
    },
    {
      "epoch": 1.4429378531073447,
      "grad_norm": 1.818604588508606,
      "learning_rate": 8.640909090909092e-05,
      "loss": 4.7645,
      "step": 320
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 1.6225180625915527,
      "learning_rate": 8.55e-05,
      "loss": 4.8982,
      "step": 340
    },
    {
      "epoch": 1.623728813559322,
      "grad_norm": 1.8790407180786133,
      "learning_rate": 8.45909090909091e-05,
      "loss": 4.8945,
      "step": 360
    },
    {
      "epoch": 1.7141242937853107,
      "grad_norm": 1.3966808319091797,
      "learning_rate": 8.368181818181818e-05,
      "loss": 4.8538,
      "step": 380
    },
    {
      "epoch": 1.8045197740112995,
      "grad_norm": 1.648871898651123,
      "learning_rate": 8.277272727272728e-05,
      "loss": 4.8468,
      "step": 400
    },
    {
      "epoch": 1.8949152542372882,
      "grad_norm": 1.3894695043563843,
      "learning_rate": 8.186363636363636e-05,
      "loss": 4.906,
      "step": 420
    },
    {
      "epoch": 1.985310734463277,
      "grad_norm": 1.8563967943191528,
      "learning_rate": 8.095454545454546e-05,
      "loss": 4.9646,
      "step": 440
    },
    {
      "epoch": 2.0,
      "eval_loss": 5.620055675506592,
      "eval_runtime": 24.422,
      "eval_samples_per_second": 4.054,
      "eval_steps_per_second": 4.054,
      "step": 444
    },
    {
      "epoch": 2.072316384180791,
      "grad_norm": 1.446750521659851,
      "learning_rate": 8.004545454545455e-05,
      "loss": 4.3823,
      "step": 460
    },
    {
      "epoch": 2.1627118644067798,
      "grad_norm": 1.1743519306182861,
      "learning_rate": 7.913636363636364e-05,
      "loss": 4.2338,
      "step": 480
    },
    {
      "epoch": 2.2531073446327685,
      "grad_norm": 1.5246398448944092,
      "learning_rate": 7.822727272727273e-05,
      "loss": 4.2925,
      "step": 500
    },
    {
      "epoch": 2.3435028248587573,
      "grad_norm": 1.6647032499313354,
      "learning_rate": 7.731818181818183e-05,
      "loss": 4.2874,
      "step": 520
    },
    {
      "epoch": 2.4338983050847456,
      "grad_norm": 1.7699276208877563,
      "learning_rate": 7.64090909090909e-05,
      "loss": 4.2792,
      "step": 540
    },
    {
      "epoch": 2.5242937853107343,
      "grad_norm": 1.5570639371871948,
      "learning_rate": 7.55e-05,
      "loss": 4.3313,
      "step": 560
    },
    {
      "epoch": 2.614689265536723,
      "grad_norm": 1.5719196796417236,
      "learning_rate": 7.45909090909091e-05,
      "loss": 4.2433,
      "step": 580
    },
    {
      "epoch": 2.705084745762712,
      "grad_norm": 1.3264689445495605,
      "learning_rate": 7.368181818181818e-05,
      "loss": 4.2903,
      "step": 600
    },
    {
      "epoch": 2.7954802259887006,
      "grad_norm": 1.7016714811325073,
      "learning_rate": 7.277272727272728e-05,
      "loss": 4.3354,
      "step": 620
    },
    {
      "epoch": 2.8858757062146894,
      "grad_norm": 2.0133845806121826,
      "learning_rate": 7.186363636363636e-05,
      "loss": 4.338,
      "step": 640
    },
    {
      "epoch": 2.976271186440678,
      "grad_norm": 1.3552452325820923,
      "learning_rate": 7.095454545454546e-05,
      "loss": 4.3492,
      "step": 660
    },
    {
      "epoch": 3.0,
      "eval_loss": 5.867856502532959,
      "eval_runtime": 23.5513,
      "eval_samples_per_second": 4.204,
      "eval_steps_per_second": 4.204,
      "step": 666
    },
    {
      "epoch": 3.063276836158192,
      "grad_norm": 1.0316146612167358,
      "learning_rate": 7.004545454545455e-05,
      "loss": 4.0605,
      "step": 680
    },
    {
      "epoch": 3.153672316384181,
      "grad_norm": 1.5106645822525024,
      "learning_rate": 6.913636363636364e-05,
      "loss": 3.8914,
      "step": 700
    },
    {
      "epoch": 3.2440677966101696,
      "grad_norm": 1.211243748664856,
      "learning_rate": 6.822727272727273e-05,
      "loss": 3.9177,
      "step": 720
    },
    {
      "epoch": 3.334463276836158,
      "grad_norm": 1.2083691358566284,
      "learning_rate": 6.731818181818183e-05,
      "loss": 3.9629,
      "step": 740
    },
    {
      "epoch": 3.4248587570621467,
      "grad_norm": 1.6045001745224,
      "learning_rate": 6.64090909090909e-05,
      "loss": 3.9449,
      "step": 760
    },
    {
      "epoch": 3.5152542372881355,
      "grad_norm": 1.8037244081497192,
      "learning_rate": 6.55e-05,
      "loss": 3.9325,
      "step": 780
    },
    {
      "epoch": 3.605649717514124,
      "grad_norm": 1.5021991729736328,
      "learning_rate": 6.45909090909091e-05,
      "loss": 3.9516,
      "step": 800
    },
    {
      "epoch": 3.696045197740113,
      "grad_norm": 1.5164258480072021,
      "learning_rate": 6.368181818181818e-05,
      "loss": 3.9408,
      "step": 820
    },
    {
      "epoch": 3.7864406779661017,
      "grad_norm": 1.5084543228149414,
      "learning_rate": 6.277272727272727e-05,
      "loss": 3.9545,
      "step": 840
    },
    {
      "epoch": 3.8768361581920905,
      "grad_norm": 1.895159363746643,
      "learning_rate": 6.186363636363637e-05,
      "loss": 3.9951,
      "step": 860
    },
    {
      "epoch": 3.9672316384180792,
      "grad_norm": 1.7579407691955566,
      "learning_rate": 6.0954545454545456e-05,
      "loss": 3.9633,
      "step": 880
    },
    {
      "epoch": 4.0,
      "eval_loss": 6.0311665534973145,
      "eval_runtime": 23.8205,
      "eval_samples_per_second": 4.156,
      "eval_steps_per_second": 4.156,
      "step": 888
    },
    {
      "epoch": 4.054237288135593,
      "grad_norm": 1.2332321405410767,
      "learning_rate": 6.004545454545455e-05,
      "loss": 3.7544,
      "step": 900
    },
    {
      "epoch": 4.144632768361582,
      "grad_norm": 1.4505114555358887,
      "learning_rate": 5.913636363636363e-05,
      "loss": 3.6543,
      "step": 920
    },
    {
      "epoch": 4.235028248587571,
      "grad_norm": 1.600288987159729,
      "learning_rate": 5.822727272727273e-05,
      "loss": 3.617,
      "step": 940
    },
    {
      "epoch": 4.3254237288135595,
      "grad_norm": 1.30964994430542,
      "learning_rate": 5.7318181818181824e-05,
      "loss": 3.605,
      "step": 960
    },
    {
      "epoch": 4.415819209039548,
      "grad_norm": 1.263311505317688,
      "learning_rate": 5.640909090909091e-05,
      "loss": 3.6401,
      "step": 980
    },
    {
      "epoch": 4.506214689265537,
      "grad_norm": 1.4733268022537231,
      "learning_rate": 5.550000000000001e-05,
      "loss": 3.6869,
      "step": 1000
    },
    {
      "epoch": 4.596610169491526,
      "grad_norm": 1.2877130508422852,
      "learning_rate": 5.4590909090909096e-05,
      "loss": 3.661,
      "step": 1020
    },
    {
      "epoch": 4.6870056497175145,
      "grad_norm": 2.0695672035217285,
      "learning_rate": 5.368181818181819e-05,
      "loss": 3.6567,
      "step": 1040
    },
    {
      "epoch": 4.777401129943502,
      "grad_norm": 1.6412814855575562,
      "learning_rate": 5.277272727272727e-05,
      "loss": 3.7096,
      "step": 1060
    },
    {
      "epoch": 4.867796610169491,
      "grad_norm": 1.3960940837860107,
      "learning_rate": 5.186363636363637e-05,
      "loss": 3.6971,
      "step": 1080
    },
    {
      "epoch": 4.95819209039548,
      "grad_norm": 1.1688611507415771,
      "learning_rate": 5.095454545454546e-05,
      "loss": 3.638,
      "step": 1100
    },
    {
      "epoch": 5.0,
      "eval_loss": 6.19950532913208,
      "eval_runtime": 24.1889,
      "eval_samples_per_second": 4.093,
      "eval_steps_per_second": 4.093,
      "step": 1110
    },
    {
      "epoch": 5.045197740112994,
      "grad_norm": 1.2310229539871216,
      "learning_rate": 5.004545454545455e-05,
      "loss": 3.4653,
      "step": 1120
    },
    {
      "epoch": 5.135593220338983,
      "grad_norm": 1.0305955410003662,
      "learning_rate": 4.913636363636364e-05,
      "loss": 3.3167,
      "step": 1140
    },
    {
      "epoch": 5.2259887005649714,
      "grad_norm": 1.1152170896530151,
      "learning_rate": 4.822727272727273e-05,
      "loss": 3.3735,
      "step": 1160
    },
    {
      "epoch": 5.31638418079096,
      "grad_norm": 1.3132717609405518,
      "learning_rate": 4.7318181818181824e-05,
      "loss": 3.4021,
      "step": 1180
    },
    {
      "epoch": 5.406779661016949,
      "grad_norm": 1.0768282413482666,
      "learning_rate": 4.640909090909091e-05,
      "loss": 3.3842,
      "step": 1200
    },
    {
      "epoch": 5.497175141242938,
      "grad_norm": 1.283962607383728,
      "learning_rate": 4.55e-05,
      "loss": 3.3741,
      "step": 1220
    },
    {
      "epoch": 5.5875706214689265,
      "grad_norm": 1.479189395904541,
      "learning_rate": 4.45909090909091e-05,
      "loss": 3.4405,
      "step": 1240
    },
    {
      "epoch": 5.677966101694915,
      "grad_norm": 1.7963414192199707,
      "learning_rate": 4.3681818181818185e-05,
      "loss": 3.3677,
      "step": 1260
    },
    {
      "epoch": 5.768361581920904,
      "grad_norm": 1.2746598720550537,
      "learning_rate": 4.2772727272727274e-05,
      "loss": 3.4565,
      "step": 1280
    },
    {
      "epoch": 5.858757062146893,
      "grad_norm": 1.3244794607162476,
      "learning_rate": 4.186363636363637e-05,
      "loss": 3.4152,
      "step": 1300
    },
    {
      "epoch": 5.9491525423728815,
      "grad_norm": 1.5454453229904175,
      "learning_rate": 4.095454545454546e-05,
      "loss": 3.4649,
      "step": 1320
    },
    {
      "epoch": 6.0,
      "eval_loss": 6.328514575958252,
      "eval_runtime": 24.2123,
      "eval_samples_per_second": 4.089,
      "eval_steps_per_second": 4.089,
      "step": 1332
    }
  ],
  "logging_steps": 20,
  "max_steps": 2220,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3980325845764800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}