{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 79.55762481689453,
      "learning_rate": 4.9786121534345265e-05,
      "loss": 45.253,
      "num_input_tokens_seen": 47512,
      "step": 5
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 17.002260208129883,
      "learning_rate": 4.914814565722671e-05,
      "loss": 3.0254,
      "num_input_tokens_seen": 94536,
      "step": 10
    },
    {
      "epoch": 1.0,
      "grad_norm": 35.45703887939453,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 3.1619,
      "num_input_tokens_seen": 141336,
      "step": 15
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 32.79413604736328,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.7871,
      "num_input_tokens_seen": 188368,
      "step": 20
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 57.80039978027344,
      "learning_rate": 4.4833833507280884e-05,
      "loss": 2.643,
      "num_input_tokens_seen": 235128,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.35395622253418,
      "learning_rate": 4.267766952966369e-05,
      "loss": 2.3801,
      "num_input_tokens_seen": 282672,
      "step": 30
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 13.160042762756348,
      "learning_rate": 4.021903572521802e-05,
      "loss": 1.6999,
      "num_input_tokens_seen": 329864,
      "step": 35
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 31.193811416625977,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.5571,
      "num_input_tokens_seen": 377952,
      "step": 40
    },
    {
      "epoch": 3.0,
      "grad_norm": 57.113609313964844,
      "learning_rate": 3.456708580912725e-05,
      "loss": 1.7335,
      "num_input_tokens_seen": 424008,
      "step": 45
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 26.844955444335938,
      "learning_rate": 3.147047612756302e-05,
      "loss": 1.1859,
      "num_input_tokens_seen": 471344,
      "step": 50
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 19.28535270690918,
      "learning_rate": 2.8263154805501297e-05,
      "loss": 0.9846,
      "num_input_tokens_seen": 517832,
      "step": 55
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.303863525390625,
      "learning_rate": 2.5e-05,
      "loss": 0.901,
      "num_input_tokens_seen": 565344,
      "step": 60
    },
    {
      "epoch": 4.333333333333333,
      "grad_norm": 38.277183532714844,
      "learning_rate": 2.173684519449872e-05,
      "loss": 0.4142,
      "num_input_tokens_seen": 612336,
      "step": 65
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 16.51125144958496,
      "learning_rate": 1.852952387243698e-05,
      "loss": 0.6221,
      "num_input_tokens_seen": 659560,
      "step": 70
    },
    {
      "epoch": 5.0,
      "grad_norm": 55.58554458618164,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.7115,
      "num_input_tokens_seen": 706680,
      "step": 75
    },
    {
      "epoch": 5.333333333333333,
      "grad_norm": 7.757297992706299,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.1582,
      "num_input_tokens_seen": 754048,
      "step": 80
    },
    {
      "epoch": 5.666666666666667,
      "grad_norm": 6.108384609222412,
      "learning_rate": 9.780964274781984e-06,
      "loss": 0.1891,
      "num_input_tokens_seen": 800984,
      "step": 85
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.9440665245056152,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.2214,
      "num_input_tokens_seen": 848016,
      "step": 90
    },
    {
      "epoch": 6.333333333333333,
      "grad_norm": 0.9317387342453003,
      "learning_rate": 5.166166492719124e-06,
      "loss": 0.0135,
      "num_input_tokens_seen": 895040,
      "step": 95
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.1581590473651886,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.0055,
      "num_input_tokens_seen": 941960,
      "step": 100
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.00675368309021,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.031,
      "num_input_tokens_seen": 989352,
      "step": 105
    },
    {
      "epoch": 7.333333333333333,
      "grad_norm": 0.6310182213783264,
      "learning_rate": 8.51854342773295e-07,
      "loss": 0.0085,
      "num_input_tokens_seen": 1035760,
      "step": 110
    },
    {
      "epoch": 7.666666666666667,
      "grad_norm": 0.24195235967636108,
      "learning_rate": 2.1387846565474045e-07,
      "loss": 0.0032,
      "num_input_tokens_seen": 1083624,
      "step": 115
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.020462460815906525,
      "learning_rate": 0.0,
      "loss": 0.0005,
      "num_input_tokens_seen": 1130688,
      "step": 120
    },
    {
      "epoch": 8.0,
      "num_input_tokens_seen": 1130688,
      "step": 120,
      "total_flos": 1.7959027775641805e+17,
      "train_loss": 2.86213872662629,
      "train_runtime": 778.6794,
      "train_samples_per_second": 1.233,
      "train_steps_per_second": 0.154
    }
  ],
  "logging_steps": 5,
  "max_steps": 120,
  "num_input_tokens_seen": 1130688,
  "num_train_epochs": 8,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7959027775641805e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}