{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1605,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 0.012311354279518127,
      "learning_rate": 4.844236760124611e-05,
      "loss": 0.252,
      "step": 50
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 0.11957651376724243,
      "learning_rate": 4.6884735202492216e-05,
      "loss": 0.0064,
      "step": 100
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 0.0069496892392635345,
      "learning_rate": 4.532710280373832e-05,
      "loss": 0.0007,
      "step": 150
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.0055118128657341,
      "learning_rate": 4.376947040498442e-05,
      "loss": 0.0035,
      "step": 200
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 0.007157029118388891,
      "learning_rate": 4.221183800623053e-05,
      "loss": 0.0066,
      "step": 250
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 0.005454342812299728,
      "learning_rate": 4.0654205607476636e-05,
      "loss": 0.0003,
      "step": 300
    },
    {
      "epoch": 0.6542056074766355,
      "grad_norm": 0.0042994399555027485,
      "learning_rate": 3.909657320872274e-05,
      "loss": 0.0002,
      "step": 350
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.0036757723428308964,
      "learning_rate": 3.753894080996885e-05,
      "loss": 0.0001,
      "step": 400
    },
    {
      "epoch": 0.8411214953271028,
      "grad_norm": 0.004236909560859203,
      "learning_rate": 3.5981308411214956e-05,
      "loss": 0.0034,
      "step": 450
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 0.004730775952339172,
      "learning_rate": 3.442367601246106e-05,
      "loss": 0.0035,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_loss": 8.711264610290527,
      "eval_runtime": 0.6907,
      "eval_samples_per_second": 7.239,
      "eval_steps_per_second": 1.448,
      "step": 535
    },
    {
      "epoch": 1.02803738317757,
      "grad_norm": 0.022852910682559013,
      "learning_rate": 3.286604361370716e-05,
      "loss": 0.003,
      "step": 550
    },
    {
      "epoch": 1.1214953271028036,
      "grad_norm": 0.0033658354077488184,
      "learning_rate": 3.130841121495327e-05,
      "loss": 0.0003,
      "step": 600
    },
    {
      "epoch": 1.2149532710280373,
      "grad_norm": 0.003417043248191476,
      "learning_rate": 2.9750778816199376e-05,
      "loss": 0.0001,
      "step": 650
    },
    {
      "epoch": 1.308411214953271,
      "grad_norm": 0.002329085720703006,
      "learning_rate": 2.8193146417445482e-05,
      "loss": 0.0001,
      "step": 700
    },
    {
      "epoch": 1.4018691588785046,
      "grad_norm": 0.003157567698508501,
      "learning_rate": 2.663551401869159e-05,
      "loss": 0.0036,
      "step": 750
    },
    {
      "epoch": 1.4953271028037383,
      "grad_norm": 0.002345046494156122,
      "learning_rate": 2.5077881619937692e-05,
      "loss": 0.002,
      "step": 800
    },
    {
      "epoch": 1.588785046728972,
      "grad_norm": 0.0028426579665392637,
      "learning_rate": 2.3520249221183802e-05,
      "loss": 0.0001,
      "step": 850
    },
    {
      "epoch": 1.6822429906542056,
      "grad_norm": 0.0021719676442444324,
      "learning_rate": 2.196261682242991e-05,
      "loss": 0.001,
      "step": 900
    },
    {
      "epoch": 1.7757009345794392,
      "grad_norm": 0.0028401941526681185,
      "learning_rate": 2.0404984423676012e-05,
      "loss": 0.0021,
      "step": 950
    },
    {
      "epoch": 1.8691588785046729,
      "grad_norm": 0.0017638171557337046,
      "learning_rate": 1.884735202492212e-05,
      "loss": 0.0001,
      "step": 1000
    },
    {
      "epoch": 1.9626168224299065,
      "grad_norm": 0.0020422961097210646,
      "learning_rate": 1.7289719626168225e-05,
      "loss": 0.001,
      "step": 1050
    },
    {
      "epoch": 2.0,
      "eval_loss": 5.994241237640381,
      "eval_runtime": 0.3635,
      "eval_samples_per_second": 13.756,
      "eval_steps_per_second": 2.751,
      "step": 1070
    },
    {
      "epoch": 2.05607476635514,
      "grad_norm": 0.0015974253183230758,
      "learning_rate": 1.573208722741433e-05,
      "loss": 0.0004,
      "step": 1100
    },
    {
      "epoch": 2.149532710280374,
      "grad_norm": 0.0014293135609477758,
      "learning_rate": 1.4174454828660435e-05,
      "loss": 0.0008,
      "step": 1150
    },
    {
      "epoch": 2.2429906542056073,
      "grad_norm": 0.0013810868840664625,
      "learning_rate": 1.2616822429906542e-05,
      "loss": 0.0001,
      "step": 1200
    },
    {
      "epoch": 2.336448598130841,
      "grad_norm": 0.0013669389300048351,
      "learning_rate": 1.1059190031152649e-05,
      "loss": 0.0007,
      "step": 1250
    },
    {
      "epoch": 2.4299065420560746,
      "grad_norm": 0.0012841916177421808,
      "learning_rate": 9.501557632398754e-06,
      "loss": 0.0001,
      "step": 1300
    },
    {
      "epoch": 2.5233644859813085,
      "grad_norm": 0.0013251251075416803,
      "learning_rate": 7.94392523364486e-06,
      "loss": 0.0001,
      "step": 1350
    },
    {
      "epoch": 2.616822429906542,
      "grad_norm": 0.001289376406930387,
      "learning_rate": 6.386292834890965e-06,
      "loss": 0.0008,
      "step": 1400
    },
    {
      "epoch": 2.710280373831776,
      "grad_norm": 0.0012487081112340093,
      "learning_rate": 4.828660436137072e-06,
      "loss": 0.0,
      "step": 1450
    },
    {
      "epoch": 2.803738317757009,
      "grad_norm": 0.0013417797163128853,
      "learning_rate": 3.2710280373831774e-06,
      "loss": 0.0019,
      "step": 1500
    },
    {
      "epoch": 2.897196261682243,
      "grad_norm": 0.001086659263819456,
      "learning_rate": 1.7133956386292835e-06,
      "loss": 0.0006,
      "step": 1550
    },
    {
      "epoch": 2.9906542056074765,
      "grad_norm": 0.001263592392206192,
      "learning_rate": 1.5576323987538942e-07,
      "loss": 0.0007,
      "step": 1600
    },
    {
      "epoch": 3.0,
      "eval_loss": 6.119048595428467,
      "eval_runtime": 0.3387,
      "eval_samples_per_second": 14.762,
      "eval_steps_per_second": 2.952,
      "step": 1605
    }
  ],
  "logging_steps": 50,
  "max_steps": 1605,
  "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": 6748570106652672.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}