{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02543558438255119,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002543558438255119,
      "eval_loss": 5.598480701446533,
      "eval_runtime": 320.3837,
      "eval_samples_per_second": 20.669,
      "eval_steps_per_second": 2.584,
      "step": 1
    },
    {
      "epoch": 0.0007630675314765357,
      "grad_norm": 23.70137596130371,
      "learning_rate": 3e-05,
      "loss": 5.7078,
      "step": 3
    },
    {
      "epoch": 0.0015261350629530714,
      "grad_norm": 11.249475479125977,
      "learning_rate": 6e-05,
      "loss": 3.5538,
      "step": 6
    },
    {
      "epoch": 0.002289202594429607,
      "grad_norm": 7.258395671844482,
      "learning_rate": 9e-05,
      "loss": 2.0523,
      "step": 9
    },
    {
      "epoch": 0.002289202594429607,
      "eval_loss": 1.837152123451233,
      "eval_runtime": 321.8836,
      "eval_samples_per_second": 20.573,
      "eval_steps_per_second": 2.572,
      "step": 9
    },
    {
      "epoch": 0.003052270125906143,
      "grad_norm": 8.19688606262207,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.8409,
      "step": 12
    },
    {
      "epoch": 0.0038153376573826785,
      "grad_norm": 3.2697651386260986,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.7495,
      "step": 15
    },
    {
      "epoch": 0.004578405188859214,
      "grad_norm": 3.1090781688690186,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7031,
      "step": 18
    },
    {
      "epoch": 0.004578405188859214,
      "eval_loss": 1.6593525409698486,
      "eval_runtime": 321.5875,
      "eval_samples_per_second": 20.592,
      "eval_steps_per_second": 2.575,
      "step": 18
    },
    {
      "epoch": 0.00534147272033575,
      "grad_norm": 2.3846840858459473,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.6711,
      "step": 21
    },
    {
      "epoch": 0.006104540251812286,
      "grad_norm": 1.8909103870391846,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.6372,
      "step": 24
    },
    {
      "epoch": 0.006867607783288821,
      "grad_norm": 3.047074794769287,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.6429,
      "step": 27
    },
    {
      "epoch": 0.006867607783288821,
      "eval_loss": 1.627792239189148,
      "eval_runtime": 321.6005,
      "eval_samples_per_second": 20.591,
      "eval_steps_per_second": 2.575,
      "step": 27
    },
    {
      "epoch": 0.007630675314765357,
      "grad_norm": 2.153074264526367,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.6103,
      "step": 30
    },
    {
      "epoch": 0.008393742846241892,
      "grad_norm": 1.5520834922790527,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.5756,
      "step": 33
    },
    {
      "epoch": 0.009156810377718427,
      "grad_norm": 1.3303474187850952,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.5947,
      "step": 36
    },
    {
      "epoch": 0.009156810377718427,
      "eval_loss": 1.596153974533081,
      "eval_runtime": 321.4648,
      "eval_samples_per_second": 20.599,
      "eval_steps_per_second": 2.576,
      "step": 36
    },
    {
      "epoch": 0.009919877909194963,
      "grad_norm": 1.5800137519836426,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.6058,
      "step": 39
    },
    {
      "epoch": 0.0106829454406715,
      "grad_norm": 1.3730175495147705,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.5432,
      "step": 42
    },
    {
      "epoch": 0.011446012972148036,
      "grad_norm": 1.8071743249893188,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5758,
      "step": 45
    },
    {
      "epoch": 0.011446012972148036,
      "eval_loss": 1.5650079250335693,
      "eval_runtime": 321.4815,
      "eval_samples_per_second": 20.598,
      "eval_steps_per_second": 2.576,
      "step": 45
    },
    {
      "epoch": 0.012209080503624571,
      "grad_norm": 1.7138389348983765,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.4889,
      "step": 48
    },
    {
      "epoch": 0.012972148035101107,
      "grad_norm": 1.4016435146331787,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.5086,
      "step": 51
    },
    {
      "epoch": 0.013735215566577643,
      "grad_norm": 1.3536241054534912,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.5789,
      "step": 54
    },
    {
      "epoch": 0.013735215566577643,
      "eval_loss": 1.5569493770599365,
      "eval_runtime": 321.523,
      "eval_samples_per_second": 20.596,
      "eval_steps_per_second": 2.575,
      "step": 54
    },
    {
      "epoch": 0.014498283098054178,
      "grad_norm": 1.2225385904312134,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.5789,
      "step": 57
    },
    {
      "epoch": 0.015261350629530714,
      "grad_norm": 1.0706034898757935,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.5548,
      "step": 60
    },
    {
      "epoch": 0.016024418161007248,
      "grad_norm": 0.9136539101600647,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.5457,
      "step": 63
    },
    {
      "epoch": 0.016024418161007248,
      "eval_loss": 1.5255224704742432,
      "eval_runtime": 321.5153,
      "eval_samples_per_second": 20.596,
      "eval_steps_per_second": 2.575,
      "step": 63
    },
    {
      "epoch": 0.016787485692483783,
      "grad_norm": 1.1234185695648193,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.532,
      "step": 66
    },
    {
      "epoch": 0.01755055322396032,
      "grad_norm": 1.1647182703018188,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.4708,
      "step": 69
    },
    {
      "epoch": 0.018313620755436855,
      "grad_norm": 1.3128389120101929,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.5735,
      "step": 72
    },
    {
      "epoch": 0.018313620755436855,
      "eval_loss": 1.5191624164581299,
      "eval_runtime": 321.4932,
      "eval_samples_per_second": 20.598,
      "eval_steps_per_second": 2.575,
      "step": 72
    },
    {
      "epoch": 0.01907668828691339,
      "grad_norm": 1.3198413848876953,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.5235,
      "step": 75
    },
    {
      "epoch": 0.019839755818389926,
      "grad_norm": 1.1952508687973022,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.5038,
      "step": 78
    },
    {
      "epoch": 0.02060282334986646,
      "grad_norm": 1.0137096643447876,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.4952,
      "step": 81
    },
    {
      "epoch": 0.02060282334986646,
      "eval_loss": 1.5108598470687866,
      "eval_runtime": 321.4625,
      "eval_samples_per_second": 20.6,
      "eval_steps_per_second": 2.576,
      "step": 81
    },
    {
      "epoch": 0.021365890881343,
      "grad_norm": 2.021695613861084,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.5211,
      "step": 84
    },
    {
      "epoch": 0.022128958412819536,
      "grad_norm": 0.9883065223693848,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.5691,
      "step": 87
    },
    {
      "epoch": 0.022892025944296072,
      "grad_norm": 1.4156526327133179,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.498,
      "step": 90
    },
    {
      "epoch": 0.022892025944296072,
      "eval_loss": 1.5057381391525269,
      "eval_runtime": 321.4316,
      "eval_samples_per_second": 20.602,
      "eval_steps_per_second": 2.576,
      "step": 90
    },
    {
      "epoch": 0.023655093475772607,
      "grad_norm": 1.0483613014221191,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.5108,
      "step": 93
    },
    {
      "epoch": 0.024418161007249143,
      "grad_norm": 1.0317051410675049,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.4549,
      "step": 96
    },
    {
      "epoch": 0.02518122853872568,
      "grad_norm": 0.9832442998886108,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.4761,
      "step": 99
    },
    {
      "epoch": 0.02518122853872568,
      "eval_loss": 1.5044512748718262,
      "eval_runtime": 321.63,
      "eval_samples_per_second": 20.589,
      "eval_steps_per_second": 2.574,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.14368026066944e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}