{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.98876404494382,
  "eval_steps": 500,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.149812734082397,
      "grad_norm": 0.39764611674179245,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 2.0748,
      "step": 10
    },
    {
      "epoch": 0.299625468164794,
      "grad_norm": 0.33418274433633427,
      "learning_rate": 1.9995466947279753e-05,
      "loss": 1.9357,
      "step": 20
    },
    {
      "epoch": 0.449438202247191,
      "grad_norm": 0.30596977211848336,
      "learning_rate": 1.9914993620144055e-05,
      "loss": 1.9244,
      "step": 30
    },
    {
      "epoch": 0.599250936329588,
      "grad_norm": 0.3036736282799432,
      "learning_rate": 1.9734718376564386e-05,
      "loss": 1.9022,
      "step": 40
    },
    {
      "epoch": 0.7490636704119851,
      "grad_norm": 0.284655188047816,
      "learning_rate": 1.945645582333587e-05,
      "loss": 1.8668,
      "step": 50
    },
    {
      "epoch": 0.898876404494382,
      "grad_norm": 0.2931958833021133,
      "learning_rate": 1.9083006883701688e-05,
      "loss": 1.8554,
      "step": 60
    },
    {
      "epoch": 1.0599250936329587,
      "grad_norm": 0.28840358163197843,
      "learning_rate": 1.8618130603940386e-05,
      "loss": 1.9266,
      "step": 70
    },
    {
      "epoch": 1.2097378277153559,
      "grad_norm": 0.31273069573948475,
      "learning_rate": 1.806650631571943e-05,
      "loss": 1.519,
      "step": 80
    },
    {
      "epoch": 1.3595505617977528,
      "grad_norm": 0.30148793981942584,
      "learning_rate": 1.7433686535079736e-05,
      "loss": 1.496,
      "step": 90
    },
    {
      "epoch": 1.5093632958801497,
      "grad_norm": 0.31527683785379346,
      "learning_rate": 1.672604107215848e-05,
      "loss": 1.4866,
      "step": 100
    },
    {
      "epoch": 1.6591760299625467,
      "grad_norm": 0.3218815018280702,
      "learning_rate": 1.595069291422807e-05,
      "loss": 1.4836,
      "step": 110
    },
    {
      "epoch": 1.8089887640449438,
      "grad_norm": 0.30720857355248626,
      "learning_rate": 1.5115446527437193e-05,
      "loss": 1.5032,
      "step": 120
    },
    {
      "epoch": 1.958801498127341,
      "grad_norm": 0.3059430053565084,
      "learning_rate": 1.4228709298950998e-05,
      "loss": 1.5188,
      "step": 130
    },
    {
      "epoch": 2.1198501872659175,
      "grad_norm": 0.5090068117726075,
      "learning_rate": 1.3299406910234917e-05,
      "loss": 1.317,
      "step": 140
    },
    {
      "epoch": 2.2696629213483144,
      "grad_norm": 0.3740747992666989,
      "learning_rate": 1.2336893493313946e-05,
      "loss": 1.0373,
      "step": 150
    },
    {
      "epoch": 2.4194756554307117,
      "grad_norm": 0.33275358849197795,
      "learning_rate": 1.1350857474352734e-05,
      "loss": 1.0568,
      "step": 160
    },
    {
      "epoch": 2.5692883895131087,
      "grad_norm": 0.3477818652467414,
      "learning_rate": 1.035122405231209e-05,
      "loss": 1.042,
      "step": 170
    },
    {
      "epoch": 2.7191011235955056,
      "grad_norm": 0.3503138385013982,
      "learning_rate": 9.348055294308074e-06,
      "loss": 1.0395,
      "step": 180
    },
    {
      "epoch": 2.8689138576779025,
      "grad_norm": 0.3495123000295199,
      "learning_rate": 8.351448853289448e-06,
      "loss": 1.0483,
      "step": 190
    },
    {
      "epoch": 3.0299625468164795,
      "grad_norm": 0.4114432810528054,
      "learning_rate": 7.371436327516854e-06,
      "loss": 1.0911,
      "step": 200
    },
    {
      "epoch": 3.1797752808988764,
      "grad_norm": 0.39068294679147425,
      "learning_rate": 6.417882284932373e-06,
      "loss": 0.6599,
      "step": 210
    },
    {
      "epoch": 3.3295880149812733,
      "grad_norm": 0.41116943497926467,
      "learning_rate": 5.5003849688157075e-06,
      "loss": 0.6496,
      "step": 220
    },
    {
      "epoch": 3.4794007490636703,
      "grad_norm": 0.4229247504320466,
      "learning_rate": 4.628179684199685e-06,
      "loss": 0.6365,
      "step": 230
    },
    {
      "epoch": 3.629213483146067,
      "grad_norm": 0.42509915295838896,
      "learning_rate": 3.81004583753399e-06,
      "loss": 0.6389,
      "step": 240
    },
    {
      "epoch": 3.7790262172284645,
      "grad_norm": 0.40983402774794686,
      "learning_rate": 3.0542185653132216e-06,
      "loss": 0.6375,
      "step": 250
    },
    {
      "epoch": 3.9288389513108615,
      "grad_norm": 0.40311017410118993,
      "learning_rate": 2.3683058411940563e-06,
      "loss": 0.6373,
      "step": 260
    },
    {
      "epoch": 4.089887640449438,
      "grad_norm": 0.39450951459446526,
      "learning_rate": 1.75921189598118e-06,
      "loss": 0.5717,
      "step": 270
    },
    {
      "epoch": 4.239700374531835,
      "grad_norm": 0.4397758073037085,
      "learning_rate": 1.2330677213177034e-06,
      "loss": 0.4204,
      "step": 280
    },
    {
      "epoch": 4.389513108614232,
      "grad_norm": 0.3951998169809048,
      "learning_rate": 7.951693566131325e-07,
      "loss": 0.4112,
      "step": 290
    },
    {
      "epoch": 4.539325842696629,
      "grad_norm": 0.3666261066362723,
      "learning_rate": 4.499245803975927e-07,
      "loss": 0.3975,
      "step": 300
    },
    {
      "epoch": 4.689138576779026,
      "grad_norm": 0.37380319557930475,
      "learning_rate": 2.00808542694233e-07,
      "loss": 0.4066,
      "step": 310
    },
    {
      "epoch": 4.8389513108614235,
      "grad_norm": 0.3833202977830408,
      "learning_rate": 5.032878500355498e-08,
      "loss": 0.4091,
      "step": 320
    },
    {
      "epoch": 4.98876404494382,
      "grad_norm": 0.4161935621630781,
      "learning_rate": 0.0,
      "loss": 0.4116,
      "step": 330
    },
    {
      "epoch": 4.98876404494382,
      "step": 330,
      "total_flos": 4662359162880.0,
      "train_loss": 1.1215998179984816,
      "train_runtime": 1366.2967,
      "train_samples_per_second": 31.219,
      "train_steps_per_second": 0.242
    }
  ],
  "logging_steps": 10,
  "max_steps": 330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4662359162880.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}