{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 237,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06369426751592357,
      "grad_norm": 1.8735829591751099,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.2478,
      "step": 5
    },
    {
      "epoch": 0.12738853503184713,
      "grad_norm": 1.7458922863006592,
      "learning_rate": 1.9655172413793106e-05,
      "loss": 3.1764,
      "step": 10
    },
    {
      "epoch": 0.1910828025477707,
      "grad_norm": 1.80453622341156,
      "learning_rate": 1.9224137931034484e-05,
      "loss": 2.9433,
      "step": 15
    },
    {
      "epoch": 0.25477707006369427,
      "grad_norm": 1.8682630062103271,
      "learning_rate": 1.8793103448275863e-05,
      "loss": 2.5689,
      "step": 20
    },
    {
      "epoch": 0.3184713375796178,
      "grad_norm": 2.233153820037842,
      "learning_rate": 1.8362068965517245e-05,
      "loss": 2.1608,
      "step": 25
    },
    {
      "epoch": 0.3821656050955414,
      "grad_norm": 1.8297864198684692,
      "learning_rate": 1.7931034482758623e-05,
      "loss": 1.7308,
      "step": 30
    },
    {
      "epoch": 0.445859872611465,
      "grad_norm": 1.6991928815841675,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 1.3536,
      "step": 35
    },
    {
      "epoch": 0.5095541401273885,
      "grad_norm": 1.4975662231445312,
      "learning_rate": 1.706896551724138e-05,
      "loss": 1.0481,
      "step": 40
    },
    {
      "epoch": 0.5732484076433121,
      "grad_norm": 1.4604802131652832,
      "learning_rate": 1.663793103448276e-05,
      "loss": 0.8506,
      "step": 45
    },
    {
      "epoch": 0.6369426751592356,
      "grad_norm": 0.740442156791687,
      "learning_rate": 1.6206896551724137e-05,
      "loss": 0.7286,
      "step": 50
    },
    {
      "epoch": 0.7006369426751592,
      "grad_norm": 0.5034754276275635,
      "learning_rate": 1.577586206896552e-05,
      "loss": 0.6376,
      "step": 55
    },
    {
      "epoch": 0.7643312101910829,
      "grad_norm": 0.5653797388076782,
      "learning_rate": 1.5344827586206898e-05,
      "loss": 0.5873,
      "step": 60
    },
    {
      "epoch": 0.8280254777070064,
      "grad_norm": 0.6510421633720398,
      "learning_rate": 1.4913793103448278e-05,
      "loss": 0.5896,
      "step": 65
    },
    {
      "epoch": 0.89171974522293,
      "grad_norm": 0.4169202148914337,
      "learning_rate": 1.4482758620689657e-05,
      "loss": 0.5866,
      "step": 70
    },
    {
      "epoch": 0.9554140127388535,
      "grad_norm": 0.5169458985328674,
      "learning_rate": 1.4051724137931035e-05,
      "loss": 0.6369,
      "step": 75
    },
    {
      "epoch": 1.0127388535031847,
      "grad_norm": 0.5400104522705078,
      "learning_rate": 1.3620689655172414e-05,
      "loss": 0.5814,
      "step": 80
    },
    {
      "epoch": 1.0764331210191083,
      "grad_norm": 0.44644486904144287,
      "learning_rate": 1.3189655172413794e-05,
      "loss": 0.5647,
      "step": 85
    },
    {
      "epoch": 1.1401273885350318,
      "grad_norm": 0.5076264142990112,
      "learning_rate": 1.2758620689655174e-05,
      "loss": 0.5476,
      "step": 90
    },
    {
      "epoch": 1.2038216560509554,
      "grad_norm": 0.46874696016311646,
      "learning_rate": 1.2327586206896553e-05,
      "loss": 0.4927,
      "step": 95
    },
    {
      "epoch": 1.267515923566879,
      "grad_norm": 0.5135082006454468,
      "learning_rate": 1.1896551724137933e-05,
      "loss": 0.5551,
      "step": 100
    },
    {
      "epoch": 1.3312101910828025,
      "grad_norm": 0.5747122168540955,
      "learning_rate": 1.1465517241379311e-05,
      "loss": 0.5505,
      "step": 105
    },
    {
      "epoch": 1.394904458598726,
      "grad_norm": 0.5480216145515442,
      "learning_rate": 1.103448275862069e-05,
      "loss": 0.5135,
      "step": 110
    },
    {
      "epoch": 1.4585987261146496,
      "grad_norm": 0.5516991019248962,
      "learning_rate": 1.060344827586207e-05,
      "loss": 0.5969,
      "step": 115
    },
    {
      "epoch": 1.5222929936305731,
      "grad_norm": 0.6291227340698242,
      "learning_rate": 1.0172413793103449e-05,
      "loss": 0.521,
      "step": 120
    },
    {
      "epoch": 1.5859872611464967,
      "grad_norm": 0.5867863893508911,
      "learning_rate": 9.741379310344829e-06,
      "loss": 0.5218,
      "step": 125
    },
    {
      "epoch": 1.6496815286624202,
      "grad_norm": 0.6907349824905396,
      "learning_rate": 9.310344827586207e-06,
      "loss": 0.5387,
      "step": 130
    },
    {
      "epoch": 1.7133757961783438,
      "grad_norm": 0.7726341485977173,
      "learning_rate": 8.879310344827588e-06,
      "loss": 0.4955,
      "step": 135
    },
    {
      "epoch": 1.7770700636942676,
      "grad_norm": 0.6937519907951355,
      "learning_rate": 8.448275862068966e-06,
      "loss": 0.522,
      "step": 140
    },
    {
      "epoch": 1.8407643312101911,
      "grad_norm": 0.7441688776016235,
      "learning_rate": 8.017241379310345e-06,
      "loss": 0.4902,
      "step": 145
    },
    {
      "epoch": 1.9044585987261147,
      "grad_norm": 0.6664876937866211,
      "learning_rate": 7.586206896551724e-06,
      "loss": 0.5205,
      "step": 150
    },
    {
      "epoch": 1.9681528662420382,
      "grad_norm": 0.6684409976005554,
      "learning_rate": 7.155172413793104e-06,
      "loss": 0.5223,
      "step": 155
    },
    {
      "epoch": 2.0254777070063694,
      "grad_norm": 0.7442811727523804,
      "learning_rate": 6.724137931034484e-06,
      "loss": 0.5559,
      "step": 160
    },
    {
      "epoch": 2.089171974522293,
      "grad_norm": 0.7137691974639893,
      "learning_rate": 6.293103448275862e-06,
      "loss": 0.4983,
      "step": 165
    },
    {
      "epoch": 2.1528662420382165,
      "grad_norm": 0.7240712642669678,
      "learning_rate": 5.862068965517242e-06,
      "loss": 0.5343,
      "step": 170
    },
    {
      "epoch": 2.21656050955414,
      "grad_norm": 0.8344106078147888,
      "learning_rate": 5.431034482758621e-06,
      "loss": 0.4778,
      "step": 175
    },
    {
      "epoch": 2.2802547770700636,
      "grad_norm": 0.8354288935661316,
      "learning_rate": 5e-06,
      "loss": 0.4551,
      "step": 180
    },
    {
      "epoch": 2.343949044585987,
      "grad_norm": 0.8019914627075195,
      "learning_rate": 4.56896551724138e-06,
      "loss": 0.4619,
      "step": 185
    },
    {
      "epoch": 2.4076433121019107,
      "grad_norm": 0.8863728642463684,
      "learning_rate": 4.137931034482759e-06,
      "loss": 0.4663,
      "step": 190
    },
    {
      "epoch": 2.4713375796178343,
      "grad_norm": 0.8233481645584106,
      "learning_rate": 3.7068965517241385e-06,
      "loss": 0.4788,
      "step": 195
    },
    {
      "epoch": 2.535031847133758,
      "grad_norm": 0.9060497283935547,
      "learning_rate": 3.2758620689655175e-06,
      "loss": 0.4514,
      "step": 200
    },
    {
      "epoch": 2.5987261146496814,
      "grad_norm": 0.8957809805870056,
      "learning_rate": 2.844827586206897e-06,
      "loss": 0.4729,
      "step": 205
    },
    {
      "epoch": 2.662420382165605,
      "grad_norm": 0.9156747460365295,
      "learning_rate": 2.4137931034482762e-06,
      "loss": 0.5263,
      "step": 210
    },
    {
      "epoch": 2.7261146496815285,
      "grad_norm": 0.9548827409744263,
      "learning_rate": 1.982758620689655e-06,
      "loss": 0.4613,
      "step": 215
    },
    {
      "epoch": 2.789808917197452,
      "grad_norm": 0.9629204273223877,
      "learning_rate": 1.5517241379310346e-06,
      "loss": 0.507,
      "step": 220
    },
    {
      "epoch": 2.853503184713376,
      "grad_norm": 0.9625599980354309,
      "learning_rate": 1.120689655172414e-06,
      "loss": 0.4884,
      "step": 225
    },
    {
      "epoch": 2.917197452229299,
      "grad_norm": 0.9648425579071045,
      "learning_rate": 6.896551724137931e-07,
      "loss": 0.467,
      "step": 230
    },
    {
      "epoch": 2.980891719745223,
      "grad_norm": 0.93361496925354,
      "learning_rate": 2.5862068965517245e-07,
      "loss": 0.4868,
      "step": 235
    }
  ],
  "logging_steps": 5,
  "max_steps": 237,
  "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": 1.973223653835571e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}