{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9842696629213483,
  "eval_steps": 500,
  "global_step": 498,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0599250936329588,
      "grad_norm": 0.43755268500481287,
      "learning_rate": 5e-06,
      "loss": 0.7166,
      "step": 10
    },
    {
      "epoch": 0.1198501872659176,
      "grad_norm": 0.27887068997618736,
      "learning_rate": 5e-06,
      "loss": 0.6497,
      "step": 20
    },
    {
      "epoch": 0.1797752808988764,
      "grad_norm": 0.23086038315964058,
      "learning_rate": 5e-06,
      "loss": 0.6345,
      "step": 30
    },
    {
      "epoch": 0.2397003745318352,
      "grad_norm": 0.2341891068390615,
      "learning_rate": 5e-06,
      "loss": 0.6191,
      "step": 40
    },
    {
      "epoch": 0.299625468164794,
      "grad_norm": 0.20601260069861693,
      "learning_rate": 5e-06,
      "loss": 0.6116,
      "step": 50
    },
    {
      "epoch": 0.3595505617977528,
      "grad_norm": 0.20563409032056135,
      "learning_rate": 5e-06,
      "loss": 0.5996,
      "step": 60
    },
    {
      "epoch": 0.41947565543071164,
      "grad_norm": 0.22531739495172456,
      "learning_rate": 5e-06,
      "loss": 0.6009,
      "step": 70
    },
    {
      "epoch": 0.4794007490636704,
      "grad_norm": 0.20987173643198698,
      "learning_rate": 5e-06,
      "loss": 0.5868,
      "step": 80
    },
    {
      "epoch": 0.5393258426966292,
      "grad_norm": 0.218100189832543,
      "learning_rate": 5e-06,
      "loss": 0.5867,
      "step": 90
    },
    {
      "epoch": 0.599250936329588,
      "grad_norm": 0.20699834408218468,
      "learning_rate": 5e-06,
      "loss": 0.5742,
      "step": 100
    },
    {
      "epoch": 0.6591760299625468,
      "grad_norm": 0.21651508965442265,
      "learning_rate": 5e-06,
      "loss": 0.5793,
      "step": 110
    },
    {
      "epoch": 0.7191011235955056,
      "grad_norm": 0.21505752361824734,
      "learning_rate": 5e-06,
      "loss": 0.5758,
      "step": 120
    },
    {
      "epoch": 0.7790262172284644,
      "grad_norm": 0.20535093449616573,
      "learning_rate": 5e-06,
      "loss": 0.5722,
      "step": 130
    },
    {
      "epoch": 0.8389513108614233,
      "grad_norm": 0.21007383376279185,
      "learning_rate": 5e-06,
      "loss": 0.566,
      "step": 140
    },
    {
      "epoch": 0.898876404494382,
      "grad_norm": 0.20414838879898575,
      "learning_rate": 5e-06,
      "loss": 0.5683,
      "step": 150
    },
    {
      "epoch": 0.9588014981273408,
      "grad_norm": 0.2070485319078679,
      "learning_rate": 5e-06,
      "loss": 0.5616,
      "step": 160
    },
    {
      "epoch": 0.9947565543071161,
      "eval_loss": 0.564882755279541,
      "eval_runtime": 171.7377,
      "eval_samples_per_second": 26.179,
      "eval_steps_per_second": 0.413,
      "step": 166
    },
    {
      "epoch": 1.0187265917602997,
      "grad_norm": 0.2501598895319095,
      "learning_rate": 5e-06,
      "loss": 0.5638,
      "step": 170
    },
    {
      "epoch": 1.0786516853932584,
      "grad_norm": 0.21286574219603713,
      "learning_rate": 5e-06,
      "loss": 0.5375,
      "step": 180
    },
    {
      "epoch": 1.1385767790262173,
      "grad_norm": 0.21450560334810348,
      "learning_rate": 5e-06,
      "loss": 0.5492,
      "step": 190
    },
    {
      "epoch": 1.198501872659176,
      "grad_norm": 0.24697885639857056,
      "learning_rate": 5e-06,
      "loss": 0.5372,
      "step": 200
    },
    {
      "epoch": 1.2584269662921348,
      "grad_norm": 0.22507578960487684,
      "learning_rate": 5e-06,
      "loss": 0.5421,
      "step": 210
    },
    {
      "epoch": 1.3183520599250937,
      "grad_norm": 0.215757150388599,
      "learning_rate": 5e-06,
      "loss": 0.5343,
      "step": 220
    },
    {
      "epoch": 1.3782771535580525,
      "grad_norm": 0.20852383609091527,
      "learning_rate": 5e-06,
      "loss": 0.5342,
      "step": 230
    },
    {
      "epoch": 1.4382022471910112,
      "grad_norm": 0.2303655417835911,
      "learning_rate": 5e-06,
      "loss": 0.5323,
      "step": 240
    },
    {
      "epoch": 1.4981273408239701,
      "grad_norm": 0.2234138263551834,
      "learning_rate": 5e-06,
      "loss": 0.531,
      "step": 250
    },
    {
      "epoch": 1.5580524344569289,
      "grad_norm": 0.2169924894523469,
      "learning_rate": 5e-06,
      "loss": 0.5223,
      "step": 260
    },
    {
      "epoch": 1.6179775280898876,
      "grad_norm": 0.23687218077177816,
      "learning_rate": 5e-06,
      "loss": 0.5353,
      "step": 270
    },
    {
      "epoch": 1.6779026217228465,
      "grad_norm": 0.21583840528024137,
      "learning_rate": 5e-06,
      "loss": 0.5294,
      "step": 280
    },
    {
      "epoch": 1.7378277153558053,
      "grad_norm": 0.23534186766123893,
      "learning_rate": 5e-06,
      "loss": 0.5295,
      "step": 290
    },
    {
      "epoch": 1.797752808988764,
      "grad_norm": 0.22832718342353497,
      "learning_rate": 5e-06,
      "loss": 0.5234,
      "step": 300
    },
    {
      "epoch": 1.857677902621723,
      "grad_norm": 0.2182245052548769,
      "learning_rate": 5e-06,
      "loss": 0.5254,
      "step": 310
    },
    {
      "epoch": 1.9176029962546817,
      "grad_norm": 0.2339332310716746,
      "learning_rate": 5e-06,
      "loss": 0.527,
      "step": 320
    },
    {
      "epoch": 1.9775280898876404,
      "grad_norm": 0.22377767747656874,
      "learning_rate": 5e-06,
      "loss": 0.5224,
      "step": 330
    },
    {
      "epoch": 1.9955056179775281,
      "eval_loss": 0.5431503653526306,
      "eval_runtime": 172.1699,
      "eval_samples_per_second": 26.114,
      "eval_steps_per_second": 0.412,
      "step": 333
    },
    {
      "epoch": 2.0374531835205993,
      "grad_norm": 0.22333193029912074,
      "learning_rate": 5e-06,
      "loss": 0.5163,
      "step": 340
    },
    {
      "epoch": 2.097378277153558,
      "grad_norm": 0.21868652020103954,
      "learning_rate": 5e-06,
      "loss": 0.4937,
      "step": 350
    },
    {
      "epoch": 2.157303370786517,
      "grad_norm": 0.28765166235887135,
      "learning_rate": 5e-06,
      "loss": 0.4951,
      "step": 360
    },
    {
      "epoch": 2.2172284644194757,
      "grad_norm": 0.22543561231331818,
      "learning_rate": 5e-06,
      "loss": 0.4991,
      "step": 370
    },
    {
      "epoch": 2.2771535580524347,
      "grad_norm": 0.2326538158591729,
      "learning_rate": 5e-06,
      "loss": 0.4958,
      "step": 380
    },
    {
      "epoch": 2.337078651685393,
      "grad_norm": 0.22438885993310223,
      "learning_rate": 5e-06,
      "loss": 0.4951,
      "step": 390
    },
    {
      "epoch": 2.397003745318352,
      "grad_norm": 0.21898245588065546,
      "learning_rate": 5e-06,
      "loss": 0.5016,
      "step": 400
    },
    {
      "epoch": 2.4569288389513106,
      "grad_norm": 0.23740177057741296,
      "learning_rate": 5e-06,
      "loss": 0.4962,
      "step": 410
    },
    {
      "epoch": 2.5168539325842696,
      "grad_norm": 0.2247697624740929,
      "learning_rate": 5e-06,
      "loss": 0.5034,
      "step": 420
    },
    {
      "epoch": 2.5767790262172285,
      "grad_norm": 0.21874023100759993,
      "learning_rate": 5e-06,
      "loss": 0.4974,
      "step": 430
    },
    {
      "epoch": 2.6367041198501875,
      "grad_norm": 0.21718625410004955,
      "learning_rate": 5e-06,
      "loss": 0.4986,
      "step": 440
    },
    {
      "epoch": 2.696629213483146,
      "grad_norm": 0.224073653725935,
      "learning_rate": 5e-06,
      "loss": 0.4939,
      "step": 450
    },
    {
      "epoch": 2.756554307116105,
      "grad_norm": 0.2254630995617039,
      "learning_rate": 5e-06,
      "loss": 0.4925,
      "step": 460
    },
    {
      "epoch": 2.8164794007490634,
      "grad_norm": 0.22113881489914033,
      "learning_rate": 5e-06,
      "loss": 0.4924,
      "step": 470
    },
    {
      "epoch": 2.8764044943820224,
      "grad_norm": 0.2288326125817775,
      "learning_rate": 5e-06,
      "loss": 0.4964,
      "step": 480
    },
    {
      "epoch": 2.9363295880149813,
      "grad_norm": 0.23496214308685273,
      "learning_rate": 5e-06,
      "loss": 0.4975,
      "step": 490
    },
    {
      "epoch": 2.9842696629213483,
      "eval_loss": 0.532910943031311,
      "eval_runtime": 172.5554,
      "eval_samples_per_second": 26.055,
      "eval_steps_per_second": 0.411,
      "step": 498
    },
    {
      "epoch": 2.9842696629213483,
      "step": 498,
      "total_flos": 833959168573440.0,
      "train_loss": 0.5430538529851829,
      "train_runtime": 28026.0355,
      "train_samples_per_second": 9.142,
      "train_steps_per_second": 0.018
    }
  ],
  "logging_steps": 10,
  "max_steps": 498,
  "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": 833959168573440.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}