{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2719033232628398,
  "eval_steps": 21,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012084592145015106,
      "eval_loss": 10.387871742248535,
      "eval_runtime": 0.2615,
      "eval_samples_per_second": 535.336,
      "eval_steps_per_second": 68.829,
      "step": 1
    },
    {
      "epoch": 0.03625377643504532,
      "grad_norm": 0.13119755685329437,
      "learning_rate": 3e-05,
      "loss": 10.3886,
      "step": 3
    },
    {
      "epoch": 0.07250755287009064,
      "grad_norm": 0.10730081051588058,
      "learning_rate": 6e-05,
      "loss": 10.3847,
      "step": 6
    },
    {
      "epoch": 0.10876132930513595,
      "grad_norm": 0.09705545753240585,
      "learning_rate": 9e-05,
      "loss": 10.3871,
      "step": 9
    },
    {
      "epoch": 0.14501510574018128,
      "grad_norm": 0.12139848619699478,
      "learning_rate": 9.998272257842641e-05,
      "loss": 10.3874,
      "step": 12
    },
    {
      "epoch": 0.18126888217522658,
      "grad_norm": 0.11973798274993896,
      "learning_rate": 9.989204876292688e-05,
      "loss": 10.3781,
      "step": 15
    },
    {
      "epoch": 0.2175226586102719,
      "grad_norm": 0.13775140047073364,
      "learning_rate": 9.972379999624936e-05,
      "loss": 10.3777,
      "step": 18
    },
    {
      "epoch": 0.2537764350453172,
      "grad_norm": 0.12977235019207,
      "learning_rate": 9.947823788099753e-05,
      "loss": 10.3796,
      "step": 21
    },
    {
      "epoch": 0.2537764350453172,
      "eval_loss": 10.373146057128906,
      "eval_runtime": 0.2637,
      "eval_samples_per_second": 530.958,
      "eval_steps_per_second": 68.266,
      "step": 21
    },
    {
      "epoch": 0.29003021148036257,
      "grad_norm": 0.16504716873168945,
      "learning_rate": 9.91557442308987e-05,
      "loss": 10.3703,
      "step": 24
    },
    {
      "epoch": 0.32628398791540786,
      "grad_norm": 0.16905713081359863,
      "learning_rate": 9.875682047713846e-05,
      "loss": 10.3718,
      "step": 27
    },
    {
      "epoch": 0.36253776435045315,
      "grad_norm": 0.18219968676567078,
      "learning_rate": 9.828208688870735e-05,
      "loss": 10.3611,
      "step": 30
    },
    {
      "epoch": 0.3987915407854985,
      "grad_norm": 0.2741997241973877,
      "learning_rate": 9.773228160797188e-05,
      "loss": 10.3599,
      "step": 33
    },
    {
      "epoch": 0.4350453172205438,
      "grad_norm": 0.20199109613895416,
      "learning_rate": 9.71082595029695e-05,
      "loss": 10.3536,
      "step": 36
    },
    {
      "epoch": 0.47129909365558914,
      "grad_norm": 0.16347676515579224,
      "learning_rate": 9.64109908382119e-05,
      "loss": 10.3424,
      "step": 39
    },
    {
      "epoch": 0.5075528700906344,
      "grad_norm": 0.15472479164600372,
      "learning_rate": 9.564155976606339e-05,
      "loss": 10.3365,
      "step": 42
    },
    {
      "epoch": 0.5075528700906344,
      "eval_loss": 10.338454246520996,
      "eval_runtime": 0.2615,
      "eval_samples_per_second": 535.377,
      "eval_steps_per_second": 68.834,
      "step": 42
    },
    {
      "epoch": 0.5438066465256798,
      "grad_norm": 0.15116359293460846,
      "learning_rate": 9.480116264104011e-05,
      "loss": 10.3382,
      "step": 45
    },
    {
      "epoch": 0.5800604229607251,
      "grad_norm": 0.20655445754528046,
      "learning_rate": 9.389110615965102e-05,
      "loss": 10.3347,
      "step": 48
    },
    {
      "epoch": 0.6163141993957704,
      "grad_norm": 0.15545906126499176,
      "learning_rate": 9.291280532867302e-05,
      "loss": 10.3275,
      "step": 51
    },
    {
      "epoch": 0.6525679758308157,
      "grad_norm": 0.189162015914917,
      "learning_rate": 9.186778126501916e-05,
      "loss": 10.3294,
      "step": 54
    },
    {
      "epoch": 0.6888217522658611,
      "grad_norm": 0.21338708698749542,
      "learning_rate": 9.075765883062093e-05,
      "loss": 10.3236,
      "step": 57
    },
    {
      "epoch": 0.7250755287009063,
      "grad_norm": 0.23534299433231354,
      "learning_rate": 8.958416410600187e-05,
      "loss": 10.3183,
      "step": 60
    },
    {
      "epoch": 0.7613293051359517,
      "grad_norm": 0.2692500054836273,
      "learning_rate": 8.834912170647101e-05,
      "loss": 10.3116,
      "step": 63
    },
    {
      "epoch": 0.7613293051359517,
      "eval_loss": 10.310102462768555,
      "eval_runtime": 0.2628,
      "eval_samples_per_second": 532.785,
      "eval_steps_per_second": 68.501,
      "step": 63
    },
    {
      "epoch": 0.797583081570997,
      "grad_norm": 0.2844769358634949,
      "learning_rate": 8.705445194510868e-05,
      "loss": 10.3075,
      "step": 66
    },
    {
      "epoch": 0.8338368580060423,
      "grad_norm": 0.2514300048351288,
      "learning_rate": 8.570216784695637e-05,
      "loss": 10.3049,
      "step": 69
    },
    {
      "epoch": 0.8700906344410876,
      "grad_norm": 0.24744316935539246,
      "learning_rate": 8.429437201905254e-05,
      "loss": 10.295,
      "step": 72
    },
    {
      "epoch": 0.9063444108761329,
      "grad_norm": 0.21623125672340393,
      "learning_rate": 8.283325338118153e-05,
      "loss": 10.2903,
      "step": 75
    },
    {
      "epoch": 0.9425981873111783,
      "grad_norm": 0.21527834236621857,
      "learning_rate": 8.132108376241849e-05,
      "loss": 10.2817,
      "step": 78
    },
    {
      "epoch": 0.9788519637462235,
      "grad_norm": 0.2678958475589752,
      "learning_rate": 7.97602143687623e-05,
      "loss": 10.2804,
      "step": 81
    },
    {
      "epoch": 1.0181268882175227,
      "grad_norm": 0.20537346601486206,
      "learning_rate": 7.815307212734888e-05,
      "loss": 11.7642,
      "step": 84
    },
    {
      "epoch": 1.0181268882175227,
      "eval_loss": 10.264846801757812,
      "eval_runtime": 0.2605,
      "eval_samples_per_second": 537.448,
      "eval_steps_per_second": 69.1,
      "step": 84
    },
    {
      "epoch": 1.054380664652568,
      "grad_norm": 0.24083495140075684,
      "learning_rate": 7.650215591292888e-05,
      "loss": 10.8142,
      "step": 87
    },
    {
      "epoch": 1.0906344410876132,
      "grad_norm": 0.20766647160053253,
      "learning_rate": 7.481003266247744e-05,
      "loss": 10.0981,
      "step": 90
    },
    {
      "epoch": 1.1268882175226587,
      "grad_norm": 0.19924764335155487,
      "learning_rate": 7.307933338397667e-05,
      "loss": 10.1149,
      "step": 93
    },
    {
      "epoch": 1.163141993957704,
      "grad_norm": 0.2571873664855957,
      "learning_rate": 7.131274906557725e-05,
      "loss": 10.134,
      "step": 96
    },
    {
      "epoch": 1.1993957703927491,
      "grad_norm": 0.20171616971492767,
      "learning_rate": 6.95130264914993e-05,
      "loss": 10.2961,
      "step": 99
    },
    {
      "epoch": 1.2356495468277946,
      "grad_norm": 0.2096317708492279,
      "learning_rate": 6.768296397117848e-05,
      "loss": 10.2312,
      "step": 102
    },
    {
      "epoch": 1.2719033232628398,
      "grad_norm": 0.28320643305778503,
      "learning_rate": 6.582540698829781e-05,
      "loss": 10.2853,
      "step": 105
    },
    {
      "epoch": 1.2719033232628398,
      "eval_loss": 10.228970527648926,
      "eval_runtime": 0.2716,
      "eval_samples_per_second": 515.557,
      "eval_steps_per_second": 66.286,
      "step": 105
    }
  ],
  "logging_steps": 3,
  "max_steps": 249,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 21,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 11712819363840.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}