{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.87719298245614,
  "eval_steps": 500,
  "global_step": 420,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 0.36140677332878113,
      "learning_rate": 4.77807122597034e-05,
      "loss": 1.7972,
      "step": 10
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 0.33242133259773254,
      "learning_rate": 3.232056928191376e-05,
      "loss": 1.6893,
      "step": 20
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.2246789187192917,
      "learning_rate": 1.1892317911069212e-05,
      "loss": 1.6413,
      "step": 30
    },
    {
      "epoch": 0.935672514619883,
      "grad_norm": 0.2739926278591156,
      "learning_rate": 8.066763266625282e-07,
      "loss": 1.6134,
      "step": 40
    },
    {
      "epoch": 1.1871345029239766,
      "grad_norm": 0.37965312600135803,
      "learning_rate": 3.848943205739711e-05,
      "loss": 1.4769,
      "step": 50
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 0.3006901741027832,
      "learning_rate": 3.219473788427984e-05,
      "loss": 1.4539,
      "step": 60
    },
    {
      "epoch": 1.654970760233918,
      "grad_norm": 0.27228423953056335,
      "learning_rate": 2.604226177226137e-05,
      "loss": 1.5344,
      "step": 70
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.26753801107406616,
      "learning_rate": 1.9146971351147655e-05,
      "loss": 1.4816,
      "step": 80
    },
    {
      "epoch": 2.1228070175438596,
      "grad_norm": 0.266255259513855,
      "learning_rate": 1.270117540713368e-05,
      "loss": 1.4132,
      "step": 90
    },
    {
      "epoch": 2.3567251461988303,
      "grad_norm": 0.3016515076160431,
      "learning_rate": 7.1998911101617575e-06,
      "loss": 1.3255,
      "step": 100
    },
    {
      "epoch": 2.590643274853801,
      "grad_norm": 0.27352389693260193,
      "learning_rate": 3.0656000602372558e-06,
      "loss": 1.3132,
      "step": 110
    },
    {
      "epoch": 2.824561403508772,
      "grad_norm": 0.27444812655448914,
      "learning_rate": 6.158030087068001e-07,
      "loss": 1.3476,
      "step": 120
    },
    {
      "epoch": 3.0935672514619883,
      "grad_norm": 0.3967718183994293,
      "learning_rate": 4.388136440446337e-05,
      "loss": 1.1837,
      "step": 130
    },
    {
      "epoch": 3.327485380116959,
      "grad_norm": 0.4026094377040863,
      "learning_rate": 4.245592045215182e-05,
      "loss": 1.3114,
      "step": 140
    },
    {
      "epoch": 3.56140350877193,
      "grad_norm": 0.3775029182434082,
      "learning_rate": 4.0909970437009096e-05,
      "loss": 1.2437,
      "step": 150
    },
    {
      "epoch": 3.7953216374269005,
      "grad_norm": 0.40222153067588806,
      "learning_rate": 3.925418674667405e-05,
      "loss": 1.2936,
      "step": 160
    },
    {
      "epoch": 4.029239766081871,
      "grad_norm": 0.4361186921596527,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.3328,
      "step": 170
    },
    {
      "epoch": 4.2631578947368425,
      "grad_norm": 0.4647097885608673,
      "learning_rate": 3.565952013635635e-05,
      "loss": 1.1235,
      "step": 180
    },
    {
      "epoch": 4.497076023391813,
      "grad_norm": 0.417835533618927,
      "learning_rate": 3.374545281527538e-05,
      "loss": 1.0464,
      "step": 190
    },
    {
      "epoch": 4.730994152046784,
      "grad_norm": 0.42690905928611755,
      "learning_rate": 3.177101170357513e-05,
      "loss": 1.1242,
      "step": 200
    },
    {
      "epoch": 4.964912280701754,
      "grad_norm": 0.4406892955303192,
      "learning_rate": 2.9749827255479755e-05,
      "loss": 1.0463,
      "step": 210
    },
    {
      "epoch": 5.1988304093567255,
      "grad_norm": 0.4422934353351593,
      "learning_rate": 2.769585261546897e-05,
      "loss": 0.9407,
      "step": 220
    },
    {
      "epoch": 5.432748538011696,
      "grad_norm": 0.46315091848373413,
      "learning_rate": 2.5623267293451826e-05,
      "loss": 0.8377,
      "step": 230
    },
    {
      "epoch": 5.666666666666667,
      "grad_norm": 0.5057820081710815,
      "learning_rate": 2.3546379277238107e-05,
      "loss": 0.9125,
      "step": 240
    },
    {
      "epoch": 5.900584795321637,
      "grad_norm": 0.5013360381126404,
      "learning_rate": 2.1479526258069087e-05,
      "loss": 0.9502,
      "step": 250
    },
    {
      "epoch": 6.1345029239766085,
      "grad_norm": 0.7791084051132202,
      "learning_rate": 1.9436976651092144e-05,
      "loss": 0.8194,
      "step": 260
    },
    {
      "epoch": 6.368421052631579,
      "grad_norm": 0.4837506115436554,
      "learning_rate": 1.7432831094079355e-05,
      "loss": 0.7167,
      "step": 270
    },
    {
      "epoch": 6.60233918128655,
      "grad_norm": 0.5172699689865112,
      "learning_rate": 1.5480925104388762e-05,
      "loss": 0.7622,
      "step": 280
    },
    {
      "epoch": 6.83625730994152,
      "grad_norm": 0.5458669662475586,
      "learning_rate": 1.3594733566170926e-05,
      "loss": 0.767,
      "step": 290
    },
    {
      "epoch": 7.0701754385964914,
      "grad_norm": 0.46376243233680725,
      "learning_rate": 1.1787277707188616e-05,
      "loss": 0.7493,
      "step": 300
    },
    {
      "epoch": 7.304093567251462,
      "grad_norm": 0.5310298800468445,
      "learning_rate": 1.0071035207430352e-05,
      "loss": 0.6112,
      "step": 310
    },
    {
      "epoch": 7.538011695906433,
      "grad_norm": 0.49246639013290405,
      "learning_rate": 8.45785406007852e-06,
      "loss": 0.6109,
      "step": 320
    },
    {
      "epoch": 7.771929824561403,
      "grad_norm": 0.5299611687660217,
      "learning_rate": 6.958870779488447e-06,
      "loss": 0.6453,
      "step": 330
    },
    {
      "epoch": 8.005847953216374,
      "grad_norm": 0.4647846519947052,
      "learning_rate": 5.584433520825541e-06,
      "loss": 0.6664,
      "step": 340
    },
    {
      "epoch": 8.239766081871345,
      "grad_norm": 0.4858466386795044,
      "learning_rate": 4.344030642100133e-06,
      "loss": 0.5755,
      "step": 350
    },
    {
      "epoch": 8.473684210526315,
      "grad_norm": 0.4467305839061737,
      "learning_rate": 3.2462252017684797e-06,
      "loss": 0.5977,
      "step": 360
    },
    {
      "epoch": 8.707602339181287,
      "grad_norm": 0.47269728779792786,
      "learning_rate": 2.298595844092377e-06,
      "loss": 0.5428,
      "step": 370
    },
    {
      "epoch": 8.941520467836257,
      "grad_norm": 0.4306669235229492,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 0.5528,
      "step": 380
    },
    {
      "epoch": 9.175438596491228,
      "grad_norm": 0.42190077900886536,
      "learning_rate": 8.78951127094127e-07,
      "loss": 0.5825,
      "step": 390
    },
    {
      "epoch": 9.409356725146198,
      "grad_norm": 0.4262978434562683,
      "learning_rate": 4.16736213181515e-07,
      "loss": 0.5498,
      "step": 400
    },
    {
      "epoch": 9.64327485380117,
      "grad_norm": 0.4205697774887085,
      "learning_rate": 1.2423061586496477e-07,
      "loss": 0.5318,
      "step": 410
    },
    {
      "epoch": 9.87719298245614,
      "grad_norm": 0.4037964940071106,
      "learning_rate": 3.453632722358324e-09,
      "loss": 0.5299,
      "step": 420
    },
    {
      "epoch": 9.87719298245614,
      "step": 420,
      "total_flos": 6.211299136336036e+17,
      "train_loss": 0.5820885260899862,
      "train_runtime": 3633.6741,
      "train_samples_per_second": 3.762,
      "train_steps_per_second": 0.116
    }
  ],
  "logging_steps": 10,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.211299136336036e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}