{
  "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": 0.6840453486823446,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 2.2499,
      "step": 10
    },
    {
      "epoch": 0.299625468164794,
      "grad_norm": 0.5383635448507048,
      "learning_rate": 1.9995466947279753e-05,
      "loss": 2.108,
      "step": 20
    },
    {
      "epoch": 0.449438202247191,
      "grad_norm": 0.4401013934135884,
      "learning_rate": 1.9914993620144055e-05,
      "loss": 2.1017,
      "step": 30
    },
    {
      "epoch": 0.599250936329588,
      "grad_norm": 0.4423229024539153,
      "learning_rate": 1.9734718376564386e-05,
      "loss": 2.0793,
      "step": 40
    },
    {
      "epoch": 0.7490636704119851,
      "grad_norm": 0.44586620863292237,
      "learning_rate": 1.945645582333587e-05,
      "loss": 2.0429,
      "step": 50
    },
    {
      "epoch": 0.898876404494382,
      "grad_norm": 0.4321055744142107,
      "learning_rate": 1.9083006883701688e-05,
      "loss": 2.0272,
      "step": 60
    },
    {
      "epoch": 1.0599250936329587,
      "grad_norm": 0.4773744957873243,
      "learning_rate": 1.8618130603940386e-05,
      "loss": 2.0306,
      "step": 70
    },
    {
      "epoch": 1.2097378277153559,
      "grad_norm": 0.5195079539448515,
      "learning_rate": 1.806650631571943e-05,
      "loss": 1.4803,
      "step": 80
    },
    {
      "epoch": 1.3595505617977528,
      "grad_norm": 0.5011077528643499,
      "learning_rate": 1.7433686535079736e-05,
      "loss": 1.4548,
      "step": 90
    },
    {
      "epoch": 1.5093632958801497,
      "grad_norm": 0.5049643365004036,
      "learning_rate": 1.672604107215848e-05,
      "loss": 1.4414,
      "step": 100
    },
    {
      "epoch": 1.6591760299625467,
      "grad_norm": 0.5024834597679505,
      "learning_rate": 1.595069291422807e-05,
      "loss": 1.4416,
      "step": 110
    },
    {
      "epoch": 1.8089887640449438,
      "grad_norm": 0.502022317708299,
      "learning_rate": 1.5115446527437193e-05,
      "loss": 1.4621,
      "step": 120
    },
    {
      "epoch": 1.958801498127341,
      "grad_norm": 0.4875127999317042,
      "learning_rate": 1.4228709298950998e-05,
      "loss": 1.4865,
      "step": 130
    },
    {
      "epoch": 2.1198501872659175,
      "grad_norm": 1.086290951197118,
      "learning_rate": 1.3299406910234917e-05,
      "loss": 1.1316,
      "step": 140
    },
    {
      "epoch": 2.2696629213483144,
      "grad_norm": 0.6134042095489988,
      "learning_rate": 1.2336893493313946e-05,
      "loss": 0.8088,
      "step": 150
    },
    {
      "epoch": 2.4194756554307117,
      "grad_norm": 0.570497265695615,
      "learning_rate": 1.1350857474352734e-05,
      "loss": 0.8186,
      "step": 160
    },
    {
      "epoch": 2.5692883895131087,
      "grad_norm": 0.6093429391689572,
      "learning_rate": 1.035122405231209e-05,
      "loss": 0.8078,
      "step": 170
    },
    {
      "epoch": 2.7191011235955056,
      "grad_norm": 0.5714218577537132,
      "learning_rate": 9.348055294308074e-06,
      "loss": 0.8038,
      "step": 180
    },
    {
      "epoch": 2.8689138576779025,
      "grad_norm": 0.6159165930181999,
      "learning_rate": 8.351448853289448e-06,
      "loss": 0.8142,
      "step": 190
    },
    {
      "epoch": 3.0299625468164795,
      "grad_norm": 0.6929188249767834,
      "learning_rate": 7.371436327516854e-06,
      "loss": 0.8166,
      "step": 200
    },
    {
      "epoch": 3.1797752808988764,
      "grad_norm": 0.690263939652076,
      "learning_rate": 6.417882284932373e-06,
      "loss": 0.358,
      "step": 210
    },
    {
      "epoch": 3.3295880149812733,
      "grad_norm": 0.5925427155042732,
      "learning_rate": 5.5003849688157075e-06,
      "loss": 0.3413,
      "step": 220
    },
    {
      "epoch": 3.4794007490636703,
      "grad_norm": 0.5952377022025283,
      "learning_rate": 4.628179684199685e-06,
      "loss": 0.3258,
      "step": 230
    },
    {
      "epoch": 3.629213483146067,
      "grad_norm": 0.5873163995283172,
      "learning_rate": 3.81004583753399e-06,
      "loss": 0.3264,
      "step": 240
    },
    {
      "epoch": 3.7790262172284645,
      "grad_norm": 0.5856393939267419,
      "learning_rate": 3.0542185653132216e-06,
      "loss": 0.3251,
      "step": 250
    },
    {
      "epoch": 3.9288389513108615,
      "grad_norm": 0.5689562422971985,
      "learning_rate": 2.3683058411940563e-06,
      "loss": 0.3221,
      "step": 260
    },
    {
      "epoch": 4.089887640449438,
      "grad_norm": 0.433331633182769,
      "learning_rate": 1.75921189598118e-06,
      "loss": 0.2567,
      "step": 270
    },
    {
      "epoch": 4.239700374531835,
      "grad_norm": 0.41035213632270684,
      "learning_rate": 1.2330677213177034e-06,
      "loss": 0.1505,
      "step": 280
    },
    {
      "epoch": 4.389513108614232,
      "grad_norm": 0.45505684420157144,
      "learning_rate": 7.951693566131325e-07,
      "loss": 0.1439,
      "step": 290
    },
    {
      "epoch": 4.539325842696629,
      "grad_norm": 0.39252824959987115,
      "learning_rate": 4.499245803975927e-07,
      "loss": 0.1378,
      "step": 300
    },
    {
      "epoch": 4.689138576779026,
      "grad_norm": 0.39533237114267095,
      "learning_rate": 2.00808542694233e-07,
      "loss": 0.1425,
      "step": 310
    },
    {
      "epoch": 4.8389513108614235,
      "grad_norm": 0.49144240800963257,
      "learning_rate": 5.032878500355498e-08,
      "loss": 0.1424,
      "step": 320
    },
    {
      "epoch": 4.98876404494382,
      "grad_norm": 0.43561529284798317,
      "learning_rate": 0.0,
      "loss": 0.143,
      "step": 330
    },
    {
      "epoch": 4.98876404494382,
      "step": 330,
      "total_flos": 1979871657984.0,
      "train_loss": 0.9855463316946319,
      "train_runtime": 924.1195,
      "train_samples_per_second": 46.157,
      "train_steps_per_second": 0.357
    }
  ],
  "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": 1979871657984.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}