{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0178117048346056,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05089058524173028,
      "grad_norm": 2.2103662490844727,
      "learning_rate": 0.0001999771640780308,
      "loss": 3.0938,
      "num_input_tokens_seen": 190176,
      "step": 5
    },
    {
      "epoch": 0.10178117048346055,
      "grad_norm": 0.8035047054290771,
      "learning_rate": 0.0001998844110196681,
      "loss": 1.471,
      "num_input_tokens_seen": 378656,
      "step": 10
    },
    {
      "epoch": 0.15267175572519084,
      "grad_norm": 0.44624239206314087,
      "learning_rate": 0.00019972037971811802,
      "loss": 1.2452,
      "num_input_tokens_seen": 570208,
      "step": 15
    },
    {
      "epoch": 0.2035623409669211,
      "grad_norm": 0.41621240973472595,
      "learning_rate": 0.00019948518722731206,
      "loss": 1.1957,
      "num_input_tokens_seen": 763040,
      "step": 20
    },
    {
      "epoch": 0.2544529262086514,
      "grad_norm": 0.3875686824321747,
      "learning_rate": 0.0001991790013823246,
      "loss": 1.1319,
      "num_input_tokens_seen": 959200,
      "step": 25
    },
    {
      "epoch": 0.3053435114503817,
      "grad_norm": 0.4382984936237335,
      "learning_rate": 0.00019880204067960472,
      "loss": 1.1209,
      "num_input_tokens_seen": 1153728,
      "step": 30
    },
    {
      "epoch": 0.356234096692112,
      "grad_norm": 0.45683977007865906,
      "learning_rate": 0.00019835457412105528,
      "loss": 1.123,
      "num_input_tokens_seen": 1351616,
      "step": 35
    },
    {
      "epoch": 0.4071246819338422,
      "grad_norm": 0.4628298580646515,
      "learning_rate": 0.00019783692102207155,
      "loss": 1.0532,
      "num_input_tokens_seen": 1537696,
      "step": 40
    },
    {
      "epoch": 0.4580152671755725,
      "grad_norm": 0.5620412826538086,
      "learning_rate": 0.00019724945078367513,
      "loss": 1.0805,
      "num_input_tokens_seen": 1730144,
      "step": 45
    },
    {
      "epoch": 0.5089058524173028,
      "grad_norm": 0.4734291732311249,
      "learning_rate": 0.00019659258262890683,
      "loss": 1.0572,
      "num_input_tokens_seen": 1916608,
      "step": 50
    },
    {
      "epoch": 0.5597964376590331,
      "grad_norm": 0.46405333280563354,
      "learning_rate": 0.00019586678530366606,
      "loss": 1.0069,
      "num_input_tokens_seen": 2103712,
      "step": 55
    },
    {
      "epoch": 0.6106870229007634,
      "grad_norm": 0.4856356084346771,
      "learning_rate": 0.00019507257674221027,
      "loss": 1.0293,
      "num_input_tokens_seen": 2289888,
      "step": 60
    },
    {
      "epoch": 0.6615776081424937,
      "grad_norm": 0.4761466085910797,
      "learning_rate": 0.00019421052369755334,
      "loss": 0.9994,
      "num_input_tokens_seen": 2477888,
      "step": 65
    },
    {
      "epoch": 0.712468193384224,
      "grad_norm": 0.5239170789718628,
      "learning_rate": 0.0001932812413370265,
      "loss": 1.0159,
      "num_input_tokens_seen": 2662848,
      "step": 70
    },
    {
      "epoch": 0.7633587786259542,
      "grad_norm": 0.4161457419395447,
      "learning_rate": 0.00019228539280329038,
      "loss": 1.0233,
      "num_input_tokens_seen": 2861024,
      "step": 75
    },
    {
      "epoch": 0.8142493638676844,
      "grad_norm": 0.5579718351364136,
      "learning_rate": 0.00019122368874111172,
      "loss": 1.0109,
      "num_input_tokens_seen": 3043712,
      "step": 80
    },
    {
      "epoch": 0.8651399491094147,
      "grad_norm": 0.4595694839954376,
      "learning_rate": 0.0001900968867902419,
      "loss": 1.0132,
      "num_input_tokens_seen": 3231840,
      "step": 85
    },
    {
      "epoch": 0.916030534351145,
      "grad_norm": 0.49271535873413086,
      "learning_rate": 0.00018890579104475995,
      "loss": 1.0079,
      "num_input_tokens_seen": 3429632,
      "step": 90
    },
    {
      "epoch": 0.9669211195928753,
      "grad_norm": 0.5259862542152405,
      "learning_rate": 0.00018765125147926476,
      "loss": 0.9515,
      "num_input_tokens_seen": 3620000,
      "step": 95
    },
    {
      "epoch": 1.0178117048346056,
      "grad_norm": 0.444477379322052,
      "learning_rate": 0.00018633416334232753,
      "loss": 0.93,
      "num_input_tokens_seen": 3809824,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 588,
  "num_input_tokens_seen": 3809824,
  "num_train_epochs": 6,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7203403994169344e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}