{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 260,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07736943907156674,
      "grad_norm": 1.0296438932418823,
      "learning_rate": 0.0001930769230769231,
      "loss": 2.7908,
      "step": 10
    },
    {
      "epoch": 0.15473887814313347,
      "grad_norm": 0.9864906668663025,
      "learning_rate": 0.0001853846153846154,
      "loss": 1.9878,
      "step": 20
    },
    {
      "epoch": 0.23210831721470018,
      "grad_norm": 0.8276298642158508,
      "learning_rate": 0.0001776923076923077,
      "loss": 1.8722,
      "step": 30
    },
    {
      "epoch": 0.30947775628626695,
      "grad_norm": 0.9250670075416565,
      "learning_rate": 0.00017,
      "loss": 1.7767,
      "step": 40
    },
    {
      "epoch": 0.38684719535783363,
      "grad_norm": 0.8650696277618408,
      "learning_rate": 0.0001623076923076923,
      "loss": 1.8079,
      "step": 50
    },
    {
      "epoch": 0.46421663442940037,
      "grad_norm": 0.8957677483558655,
      "learning_rate": 0.00015461538461538464,
      "loss": 1.786,
      "step": 60
    },
    {
      "epoch": 0.5415860735009671,
      "grad_norm": 0.7478697299957275,
      "learning_rate": 0.00014692307692307693,
      "loss": 1.7628,
      "step": 70
    },
    {
      "epoch": 0.6189555125725339,
      "grad_norm": 0.7914655804634094,
      "learning_rate": 0.00013923076923076923,
      "loss": 1.712,
      "step": 80
    },
    {
      "epoch": 0.6963249516441006,
      "grad_norm": 0.8356083631515503,
      "learning_rate": 0.00013153846153846156,
      "loss": 1.7362,
      "step": 90
    },
    {
      "epoch": 0.7736943907156673,
      "grad_norm": 0.8357738256454468,
      "learning_rate": 0.00012384615384615385,
      "loss": 1.7215,
      "step": 100
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.8000754714012146,
      "learning_rate": 0.00011615384615384617,
      "loss": 1.6271,
      "step": 110
    },
    {
      "epoch": 0.9284332688588007,
      "grad_norm": 0.7836863994598389,
      "learning_rate": 0.00010846153846153846,
      "loss": 1.7314,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.5980422496795654,
      "learning_rate": 0.00010076923076923077,
      "loss": 1.6623,
      "step": 130
    },
    {
      "epoch": 1.0773694390715667,
      "grad_norm": 0.8195829391479492,
      "learning_rate": 9.307692307692309e-05,
      "loss": 1.5811,
      "step": 140
    },
    {
      "epoch": 1.1547388781431334,
      "grad_norm": 0.824920654296875,
      "learning_rate": 8.538461538461538e-05,
      "loss": 1.5525,
      "step": 150
    },
    {
      "epoch": 1.2321083172147003,
      "grad_norm": 0.9823306798934937,
      "learning_rate": 7.76923076923077e-05,
      "loss": 1.6602,
      "step": 160
    },
    {
      "epoch": 1.309477756286267,
      "grad_norm": 0.8831573724746704,
      "learning_rate": 7e-05,
      "loss": 1.5839,
      "step": 170
    },
    {
      "epoch": 1.3868471953578336,
      "grad_norm": 1.0566450357437134,
      "learning_rate": 6.23076923076923e-05,
      "loss": 1.6407,
      "step": 180
    },
    {
      "epoch": 1.4642166344294003,
      "grad_norm": 0.8523500561714172,
      "learning_rate": 5.461538461538461e-05,
      "loss": 1.5857,
      "step": 190
    },
    {
      "epoch": 1.5415860735009672,
      "grad_norm": 0.9045595526695251,
      "learning_rate": 4.692307692307693e-05,
      "loss": 1.5332,
      "step": 200
    },
    {
      "epoch": 1.618955512572534,
      "grad_norm": 0.941744863986969,
      "learning_rate": 3.923076923076923e-05,
      "loss": 1.5534,
      "step": 210
    },
    {
      "epoch": 1.6963249516441006,
      "grad_norm": 0.8504011631011963,
      "learning_rate": 3.153846153846154e-05,
      "loss": 1.5462,
      "step": 220
    },
    {
      "epoch": 1.7736943907156673,
      "grad_norm": 0.8891894817352295,
      "learning_rate": 2.384615384615385e-05,
      "loss": 1.6007,
      "step": 230
    },
    {
      "epoch": 1.851063829787234,
      "grad_norm": 0.8817383050918579,
      "learning_rate": 1.6153846153846154e-05,
      "loss": 1.5908,
      "step": 240
    },
    {
      "epoch": 1.9284332688588006,
      "grad_norm": 0.9529927372932434,
      "learning_rate": 8.461538461538462e-06,
      "loss": 1.5941,
      "step": 250
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.8291347026824951,
      "learning_rate": 7.692307692307694e-07,
      "loss": 1.5418,
      "step": 260
    }
  ],
  "logging_steps": 10,
  "max_steps": 260,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.2925171077384038e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}