{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 870,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14367816091954022,
      "grad_norm": 1.424246072769165,
      "learning_rate": 5.517241379310345e-05,
      "loss": 2.0273,
      "step": 25
    },
    {
      "epoch": 0.28735632183908044,
      "grad_norm": 0.9430229663848877,
      "learning_rate": 0.00011264367816091954,
      "loss": 1.8285,
      "step": 50
    },
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 0.7553120851516724,
      "learning_rate": 0.00017011494252873563,
      "loss": 1.6756,
      "step": 75
    },
    {
      "epoch": 0.5747126436781609,
      "grad_norm": 0.7407281398773193,
      "learning_rate": 0.00019693486590038314,
      "loss": 1.5606,
      "step": 100
    },
    {
      "epoch": 0.7183908045977011,
      "grad_norm": 0.7509495615959167,
      "learning_rate": 0.0001905491698595147,
      "loss": 1.5438,
      "step": 125
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.7058537602424622,
      "learning_rate": 0.00018416347381864626,
      "loss": 1.4816,
      "step": 150
    },
    {
      "epoch": 1.0057471264367817,
      "grad_norm": 0.6202262043952942,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.5232,
      "step": 175
    },
    {
      "epoch": 1.1494252873563218,
      "grad_norm": 0.7314026355743408,
      "learning_rate": 0.00017139208173690932,
      "loss": 1.4954,
      "step": 200
    },
    {
      "epoch": 1.293103448275862,
      "grad_norm": 0.7846217155456543,
      "learning_rate": 0.00016500638569604087,
      "loss": 1.4199,
      "step": 225
    },
    {
      "epoch": 1.4367816091954024,
      "grad_norm": 0.751372754573822,
      "learning_rate": 0.00015862068965517243,
      "loss": 1.48,
      "step": 250
    },
    {
      "epoch": 1.5804597701149425,
      "grad_norm": 0.7667829990386963,
      "learning_rate": 0.00015223499361430396,
      "loss": 1.4346,
      "step": 275
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 0.7370414733886719,
      "learning_rate": 0.00014584929757343552,
      "loss": 1.4334,
      "step": 300
    },
    {
      "epoch": 1.867816091954023,
      "grad_norm": 0.9422834515571594,
      "learning_rate": 0.00013946360153256705,
      "loss": 1.3969,
      "step": 325
    },
    {
      "epoch": 2.0114942528735633,
      "grad_norm": 0.7596230506896973,
      "learning_rate": 0.0001330779054916986,
      "loss": 1.4241,
      "step": 350
    },
    {
      "epoch": 2.1551724137931036,
      "grad_norm": 0.9657158851623535,
      "learning_rate": 0.00012669220945083016,
      "loss": 1.3115,
      "step": 375
    },
    {
      "epoch": 2.2988505747126435,
      "grad_norm": 0.9675273895263672,
      "learning_rate": 0.00012030651340996169,
      "loss": 1.3382,
      "step": 400
    },
    {
      "epoch": 2.442528735632184,
      "grad_norm": 0.9593296647071838,
      "learning_rate": 0.00011392081736909323,
      "loss": 1.3843,
      "step": 425
    },
    {
      "epoch": 2.586206896551724,
      "grad_norm": 0.8661421537399292,
      "learning_rate": 0.00010753512132822479,
      "loss": 1.3161,
      "step": 450
    },
    {
      "epoch": 2.7298850574712645,
      "grad_norm": 0.9521291851997375,
      "learning_rate": 0.00010114942528735633,
      "loss": 1.3355,
      "step": 475
    },
    {
      "epoch": 2.873563218390805,
      "grad_norm": 1.0091650485992432,
      "learning_rate": 9.476372924648788e-05,
      "loss": 1.3052,
      "step": 500
    },
    {
      "epoch": 3.0172413793103448,
      "grad_norm": 0.9030539989471436,
      "learning_rate": 8.837803320561942e-05,
      "loss": 1.2682,
      "step": 525
    },
    {
      "epoch": 3.160919540229885,
      "grad_norm": 1.0906364917755127,
      "learning_rate": 8.199233716475096e-05,
      "loss": 1.2097,
      "step": 550
    },
    {
      "epoch": 3.3045977011494254,
      "grad_norm": 1.1765050888061523,
      "learning_rate": 7.56066411238825e-05,
      "loss": 1.2564,
      "step": 575
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 1.1693239212036133,
      "learning_rate": 6.922094508301405e-05,
      "loss": 1.2207,
      "step": 600
    },
    {
      "epoch": 3.5919540229885056,
      "grad_norm": 1.0836124420166016,
      "learning_rate": 6.283524904214559e-05,
      "loss": 1.2338,
      "step": 625
    },
    {
      "epoch": 3.735632183908046,
      "grad_norm": 1.0297603607177734,
      "learning_rate": 5.644955300127714e-05,
      "loss": 1.2179,
      "step": 650
    },
    {
      "epoch": 3.8793103448275863,
      "grad_norm": 1.3402975797653198,
      "learning_rate": 5.0063856960408687e-05,
      "loss": 1.2363,
      "step": 675
    },
    {
      "epoch": 4.022988505747127,
      "grad_norm": 1.1158450841903687,
      "learning_rate": 4.367816091954024e-05,
      "loss": 1.1844,
      "step": 700
    },
    {
      "epoch": 4.166666666666667,
      "grad_norm": 1.3297624588012695,
      "learning_rate": 3.729246487867178e-05,
      "loss": 1.1176,
      "step": 725
    },
    {
      "epoch": 4.310344827586207,
      "grad_norm": 1.3470237255096436,
      "learning_rate": 3.090676883780332e-05,
      "loss": 1.1639,
      "step": 750
    },
    {
      "epoch": 4.454022988505747,
      "grad_norm": 1.293717861175537,
      "learning_rate": 2.4521072796934867e-05,
      "loss": 1.1668,
      "step": 775
    },
    {
      "epoch": 4.597701149425287,
      "grad_norm": 1.400448203086853,
      "learning_rate": 1.8135376756066413e-05,
      "loss": 1.1751,
      "step": 800
    },
    {
      "epoch": 4.741379310344827,
      "grad_norm": 1.1660029888153076,
      "learning_rate": 1.1749680715197957e-05,
      "loss": 1.1406,
      "step": 825
    },
    {
      "epoch": 4.885057471264368,
      "grad_norm": 1.311295747756958,
      "learning_rate": 5.3639846743295025e-06,
      "loss": 1.1406,
      "step": 850
    }
  ],
  "logging_steps": 25,
  "max_steps": 870,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.6060942324334592e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}