{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010471752447772134,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010471752447772135,
      "eval_loss": 3.7912585735321045,
      "eval_runtime": 1059.0273,
      "eval_samples_per_second": 15.188,
      "eval_steps_per_second": 1.899,
      "step": 1
    },
    {
      "epoch": 0.000314152573433164,
      "grad_norm": 1.7175657749176025,
      "learning_rate": 1.5e-05,
      "loss": 3.8059,
      "step": 3
    },
    {
      "epoch": 0.000628305146866328,
      "grad_norm": 1.4710763692855835,
      "learning_rate": 3e-05,
      "loss": 3.8095,
      "step": 6
    },
    {
      "epoch": 0.0009424577202994921,
      "grad_norm": 1.8505823612213135,
      "learning_rate": 4.5e-05,
      "loss": 3.5933,
      "step": 9
    },
    {
      "epoch": 0.0009424577202994921,
      "eval_loss": 3.5998284816741943,
      "eval_runtime": 1063.4916,
      "eval_samples_per_second": 15.124,
      "eval_steps_per_second": 1.891,
      "step": 9
    },
    {
      "epoch": 0.001256610293732656,
      "grad_norm": 3.0607101917266846,
      "learning_rate": 4.993910125649561e-05,
      "loss": 3.5482,
      "step": 12
    },
    {
      "epoch": 0.0015707628671658201,
      "grad_norm": 1.9880341291427612,
      "learning_rate": 4.962019382530521e-05,
      "loss": 2.9429,
      "step": 15
    },
    {
      "epoch": 0.0018849154405989842,
      "grad_norm": 1.6317461729049683,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 2.5824,
      "step": 18
    },
    {
      "epoch": 0.0018849154405989842,
      "eval_loss": 2.445322275161743,
      "eval_runtime": 1063.205,
      "eval_samples_per_second": 15.128,
      "eval_steps_per_second": 1.891,
      "step": 18
    },
    {
      "epoch": 0.0021990680140321485,
      "grad_norm": 1.4919593334197998,
      "learning_rate": 4.817959636416969e-05,
      "loss": 2.4754,
      "step": 21
    },
    {
      "epoch": 0.002513220587465312,
      "grad_norm": 1.4782090187072754,
      "learning_rate": 4.707368982147318e-05,
      "loss": 2.2052,
      "step": 24
    },
    {
      "epoch": 0.002827373160898476,
      "grad_norm": 1.4127540588378906,
      "learning_rate": 4.572593931387604e-05,
      "loss": 2.1124,
      "step": 27
    },
    {
      "epoch": 0.002827373160898476,
      "eval_loss": 2.073098659515381,
      "eval_runtime": 1063.9556,
      "eval_samples_per_second": 15.117,
      "eval_steps_per_second": 1.89,
      "step": 27
    },
    {
      "epoch": 0.0031415257343316402,
      "grad_norm": 1.0188194513320923,
      "learning_rate": 4.415111107797445e-05,
      "loss": 2.1222,
      "step": 30
    },
    {
      "epoch": 0.0034556783077648043,
      "grad_norm": 1.1037559509277344,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 2.0357,
      "step": 33
    },
    {
      "epoch": 0.0037698308811979684,
      "grad_norm": 1.4226746559143066,
      "learning_rate": 4.039153688314145e-05,
      "loss": 1.9676,
      "step": 36
    },
    {
      "epoch": 0.0037698308811979684,
      "eval_loss": 1.9431099891662598,
      "eval_runtime": 1064.9541,
      "eval_samples_per_second": 15.103,
      "eval_steps_per_second": 1.888,
      "step": 36
    },
    {
      "epoch": 0.0040839834546311325,
      "grad_norm": 1.024459958076477,
      "learning_rate": 3.824798160583012e-05,
      "loss": 1.9266,
      "step": 39
    },
    {
      "epoch": 0.004398136028064297,
      "grad_norm": 0.8982957601547241,
      "learning_rate": 3.5959278669726935e-05,
      "loss": 1.9038,
      "step": 42
    },
    {
      "epoch": 0.004712288601497461,
      "grad_norm": 1.217470407485962,
      "learning_rate": 3.355050358314172e-05,
      "loss": 2.0108,
      "step": 45
    },
    {
      "epoch": 0.004712288601497461,
      "eval_loss": 1.89578115940094,
      "eval_runtime": 1063.4638,
      "eval_samples_per_second": 15.124,
      "eval_steps_per_second": 1.891,
      "step": 45
    },
    {
      "epoch": 0.005026441174930624,
      "grad_norm": 0.8782138228416443,
      "learning_rate": 3.104804738999169e-05,
      "loss": 1.9465,
      "step": 48
    },
    {
      "epoch": 0.005340593748363789,
      "grad_norm": 0.9445828199386597,
      "learning_rate": 2.8479327524001636e-05,
      "loss": 1.7905,
      "step": 51
    },
    {
      "epoch": 0.005654746321796952,
      "grad_norm": 0.9831016063690186,
      "learning_rate": 2.587248741756253e-05,
      "loss": 1.8197,
      "step": 54
    },
    {
      "epoch": 0.005654746321796952,
      "eval_loss": 1.8702428340911865,
      "eval_runtime": 1062.5729,
      "eval_samples_per_second": 15.137,
      "eval_steps_per_second": 1.893,
      "step": 54
    },
    {
      "epoch": 0.005968898895230117,
      "grad_norm": 0.8221942186355591,
      "learning_rate": 2.3256088156396868e-05,
      "loss": 1.9312,
      "step": 57
    },
    {
      "epoch": 0.0062830514686632805,
      "grad_norm": 0.9357668161392212,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 1.8986,
      "step": 60
    },
    {
      "epoch": 0.006597204042096445,
      "grad_norm": 0.9517828226089478,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 1.8829,
      "step": 63
    },
    {
      "epoch": 0.006597204042096445,
      "eval_loss": 1.8533341884613037,
      "eval_runtime": 1064.5051,
      "eval_samples_per_second": 15.109,
      "eval_steps_per_second": 1.889,
      "step": 63
    },
    {
      "epoch": 0.006911356615529609,
      "grad_norm": 0.9028967618942261,
      "learning_rate": 1.56348351646022e-05,
      "loss": 1.9189,
      "step": 66
    },
    {
      "epoch": 0.007225509188962773,
      "grad_norm": 0.9823371767997742,
      "learning_rate": 1.3263210930352737e-05,
      "loss": 1.9098,
      "step": 69
    },
    {
      "epoch": 0.007539661762395937,
      "grad_norm": 0.9070382714271545,
      "learning_rate": 1.1020177413231334e-05,
      "loss": 1.7421,
      "step": 72
    },
    {
      "epoch": 0.007539661762395937,
      "eval_loss": 1.845250129699707,
      "eval_runtime": 1065.0809,
      "eval_samples_per_second": 15.101,
      "eval_steps_per_second": 1.888,
      "step": 72
    },
    {
      "epoch": 0.007853814335829101,
      "grad_norm": 0.9094987511634827,
      "learning_rate": 8.930309757836517e-06,
      "loss": 1.7,
      "step": 75
    },
    {
      "epoch": 0.008167966909262265,
      "grad_norm": 0.8672954440116882,
      "learning_rate": 7.016504991533726e-06,
      "loss": 1.7507,
      "step": 78
    },
    {
      "epoch": 0.008482119482695429,
      "grad_norm": 0.8942087888717651,
      "learning_rate": 5.299731159831953e-06,
      "loss": 1.857,
      "step": 81
    },
    {
      "epoch": 0.008482119482695429,
      "eval_loss": 1.8364417552947998,
      "eval_runtime": 1064.7259,
      "eval_samples_per_second": 15.106,
      "eval_steps_per_second": 1.889,
      "step": 81
    },
    {
      "epoch": 0.008796272056128594,
      "grad_norm": 0.7912752628326416,
      "learning_rate": 3.798797596089351e-06,
      "loss": 1.8828,
      "step": 84
    },
    {
      "epoch": 0.009110424629561758,
      "grad_norm": 0.9107024669647217,
      "learning_rate": 2.5301488425208296e-06,
      "loss": 1.8379,
      "step": 87
    },
    {
      "epoch": 0.009424577202994921,
      "grad_norm": 0.9877169132232666,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 1.7811,
      "step": 90
    },
    {
      "epoch": 0.009424577202994921,
      "eval_loss": 1.8339735269546509,
      "eval_runtime": 1063.658,
      "eval_samples_per_second": 15.121,
      "eval_steps_per_second": 1.891,
      "step": 90
    },
    {
      "epoch": 0.009738729776428085,
      "grad_norm": 0.8841791152954102,
      "learning_rate": 7.426068431000882e-07,
      "loss": 1.7551,
      "step": 93
    },
    {
      "epoch": 0.010052882349861248,
      "grad_norm": 1.0488734245300293,
      "learning_rate": 2.4329828146074095e-07,
      "loss": 1.9505,
      "step": 96
    },
    {
      "epoch": 0.010367034923294414,
      "grad_norm": 1.016286849975586,
      "learning_rate": 1.522932452260595e-08,
      "loss": 1.7912,
      "step": 99
    },
    {
      "epoch": 0.010367034923294414,
      "eval_loss": 1.8335013389587402,
      "eval_runtime": 1063.6527,
      "eval_samples_per_second": 15.121,
      "eval_steps_per_second": 1.891,
      "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": 1.306929288708096e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}