{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.1213653603034133,
  "eval_steps": 10,
  "global_step": 280,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.116106641292572,
      "epoch": 0.07585335018963338,
      "grad_norm": 1.4921875,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 2.914295959472656,
      "mean_token_accuracy": 0.5410080701112747,
      "num_tokens": 36823.0,
      "step": 10
    },
    {
      "epoch": 0.07585335018963338,
      "eval_entropy": 2.552819073200226,
      "eval_loss": 2.6676909923553467,
      "eval_mean_token_accuracy": 0.5321294479072094,
      "eval_num_tokens": 36823.0,
      "eval_runtime": 14.7674,
      "eval_samples_per_second": 0.542,
      "eval_steps_per_second": 0.542,
      "step": 10
    },
    {
      "entropy": 1.9473248382409414,
      "epoch": 0.15170670037926676,
      "grad_norm": 0.87890625,
      "learning_rate": 9.999152908979117e-05,
      "loss": 1.9090084075927733,
      "mean_token_accuracy": 0.6584314892689387,
      "num_tokens": 65881.0,
      "step": 20
    },
    {
      "epoch": 0.15170670037926676,
      "eval_entropy": 1.8724936991930008,
      "eval_loss": 1.9479429721832275,
      "eval_mean_token_accuracy": 0.6351580396294594,
      "eval_num_tokens": 65881.0,
      "eval_runtime": 14.8467,
      "eval_samples_per_second": 0.539,
      "eval_steps_per_second": 0.539,
      "step": 20
    },
    {
      "entropy": 1.5991886417071024,
      "epoch": 0.22756005056890014,
      "grad_norm": 1.4765625,
      "learning_rate": 9.984101496455829e-05,
      "loss": 1.5578083038330077,
      "mean_token_accuracy": 0.7192381203174592,
      "num_tokens": 89977.0,
      "step": 30
    },
    {
      "epoch": 0.22756005056890014,
      "eval_entropy": 1.6338046044111252,
      "eval_loss": 1.694503903388977,
      "eval_mean_token_accuracy": 0.6637412160634995,
      "eval_num_tokens": 89977.0,
      "eval_runtime": 14.8298,
      "eval_samples_per_second": 0.539,
      "eval_steps_per_second": 0.539,
      "step": 30
    },
    {
      "entropy": 1.6071883370478948,
      "epoch": 0.3034134007585335,
      "grad_norm": 0.71484375,
      "learning_rate": 9.950291051311487e-05,
      "loss": 1.6236091613769532,
      "mean_token_accuracy": 0.6928597639004389,
      "num_tokens": 122672.0,
      "step": 40
    },
    {
      "epoch": 0.3034134007585335,
      "eval_entropy": 1.5961390733718872,
      "eval_loss": 1.5684512853622437,
      "eval_mean_token_accuracy": 0.6787843257188797,
      "eval_num_tokens": 122672.0,
      "eval_runtime": 14.7973,
      "eval_samples_per_second": 0.541,
      "eval_steps_per_second": 0.541,
      "step": 40
    },
    {
      "entropy": 1.3055346330006918,
      "epoch": 0.37926675094816686,
      "grad_norm": 0.9453125,
      "learning_rate": 9.897848828427202e-05,
      "loss": 1.2936326026916505,
      "mean_token_accuracy": 0.7341216415166855,
      "num_tokens": 152626.0,
      "step": 50
    },
    {
      "epoch": 0.37926675094816686,
      "eval_entropy": 1.4331321269273758,
      "eval_loss": 1.410101294517517,
      "eval_mean_token_accuracy": 0.7011745795607567,
      "eval_num_tokens": 152626.0,
      "eval_runtime": 14.7788,
      "eval_samples_per_second": 0.541,
      "eval_steps_per_second": 0.541,
      "step": 50
    },
    {
      "entropy": 1.11328877111276,
      "epoch": 0.45512010113780027,
      "grad_norm": 0.82421875,
      "learning_rate": 9.826972208488447e-05,
      "loss": 1.0861340522766114,
      "mean_token_accuracy": 0.766385022799174,
      "num_tokens": 178156.0,
      "step": 60
    },
    {
      "epoch": 0.45512010113780027,
      "eval_entropy": 1.3111007660627365,
      "eval_loss": 1.2872167825698853,
      "eval_mean_token_accuracy": 0.7273842021822929,
      "eval_num_tokens": 178156.0,
      "eval_runtime": 14.7936,
      "eval_samples_per_second": 0.541,
      "eval_steps_per_second": 0.541,
      "step": 60
    },
    {
      "entropy": 1.3175925850868224,
      "epoch": 0.5309734513274337,
      "grad_norm": 0.625,
      "learning_rate": 9.737927955088705e-05,
      "loss": 1.2941490173339845,
      "mean_token_accuracy": 0.7372792253891627,
      "num_tokens": 209487.0,
      "step": 70
    },
    {
      "epoch": 0.5309734513274337,
      "eval_entropy": 1.2998864650726318,
      "eval_loss": 1.2285542488098145,
      "eval_mean_token_accuracy": 0.7347995787858963,
      "eval_num_tokens": 209487.0,
      "eval_runtime": 14.8531,
      "eval_samples_per_second": 0.539,
      "eval_steps_per_second": 0.539,
      "step": 70
    },
    {
      "entropy": 1.1506140291690827,
      "epoch": 0.606826801517067,
      "grad_norm": 0.828125,
      "learning_rate": 9.631051210691558e-05,
      "loss": 1.134031391143799,
      "mean_token_accuracy": 0.760423094034195,
      "num_tokens": 239555.0,
      "step": 80
    },
    {
      "epoch": 0.606826801517067,
      "eval_entropy": 1.2010595947504044,
      "eval_loss": 1.1256182193756104,
      "eval_mean_token_accuracy": 0.7571268677711487,
      "eval_num_tokens": 239555.0,
      "eval_runtime": 15.6324,
      "eval_samples_per_second": 0.512,
      "eval_steps_per_second": 0.512,
      "step": 80
    },
    {
      "entropy": 0.9923018544912339,
      "epoch": 0.6826801517067004,
      "grad_norm": 1.0078125,
      "learning_rate": 9.50674423523011e-05,
      "loss": 0.9289534568786622,
      "mean_token_accuracy": 0.7951417863368988,
      "num_tokens": 265306.0,
      "step": 90
    },
    {
      "epoch": 0.6826801517067004,
      "eval_entropy": 1.0992150977253914,
      "eval_loss": 1.0379621982574463,
      "eval_mean_token_accuracy": 0.7777058333158493,
      "eval_num_tokens": 265306.0,
      "eval_runtime": 15.7361,
      "eval_samples_per_second": 0.508,
      "eval_steps_per_second": 0.508,
      "step": 90
    },
    {
      "entropy": 1.0375868437190852,
      "epoch": 0.7585335018963337,
      "grad_norm": 0.609375,
      "learning_rate": 9.365474892091451e-05,
      "loss": 1.0106287956237794,
      "mean_token_accuracy": 0.7893585612376531,
      "num_tokens": 292993.0,
      "step": 100
    },
    {
      "epoch": 0.7585335018963337,
      "eval_entropy": 1.072925515472889,
      "eval_loss": 1.0008392333984375,
      "eval_mean_token_accuracy": 0.7823155149817467,
      "eval_num_tokens": 292993.0,
      "eval_runtime": 15.602,
      "eval_samples_per_second": 0.513,
      "eval_steps_per_second": 0.513,
      "step": 100
    },
    {
      "entropy": 1.0960371459523837,
      "epoch": 0.8343868520859671,
      "grad_norm": 0.7890625,
      "learning_rate": 9.207774887184493e-05,
      "loss": 1.0759888648986817,
      "mean_token_accuracy": 0.7768891970316569,
      "num_tokens": 324472.0,
      "step": 110
    },
    {
      "epoch": 0.8343868520859671,
      "eval_entropy": 0.9983096048235893,
      "eval_loss": 0.965083658695221,
      "eval_mean_token_accuracy": 0.7886351868510246,
      "eval_num_tokens": 324472.0,
      "eval_runtime": 15.6552,
      "eval_samples_per_second": 0.511,
      "eval_steps_per_second": 0.511,
      "step": 110
    },
    {
      "entropy": 0.8683194468418757,
      "epoch": 0.9102402022756005,
      "grad_norm": 0.859375,
      "learning_rate": 9.034237767718997e-05,
      "loss": 0.839997386932373,
      "mean_token_accuracy": 0.8105442355076472,
      "num_tokens": 350423.0,
      "step": 120
    },
    {
      "epoch": 0.9102402022756005,
      "eval_entropy": 0.9654994606971741,
      "eval_loss": 0.9282829761505127,
      "eval_mean_token_accuracy": 0.8008697852492332,
      "eval_num_tokens": 350423.0,
      "eval_runtime": 15.7206,
      "eval_samples_per_second": 0.509,
      "eval_steps_per_second": 0.509,
      "step": 120
    },
    {
      "entropy": 0.8921634897589683,
      "epoch": 0.9860935524652339,
      "grad_norm": 0.66015625,
      "learning_rate": 8.8455166882279e-05,
      "loss": 0.8713577270507813,
      "mean_token_accuracy": 0.805043849349022,
      "num_tokens": 374888.0,
      "step": 130
    },
    {
      "epoch": 0.9860935524652339,
      "eval_entropy": 0.925379566848278,
      "eval_loss": 0.9301751852035522,
      "eval_mean_token_accuracy": 0.8013799041509628,
      "eval_num_tokens": 374888.0,
      "eval_runtime": 15.7302,
      "eval_samples_per_second": 0.509,
      "eval_steps_per_second": 0.509,
      "step": 130
    },
    {
      "entropy": 1.1222206217757726,
      "epoch": 1.0606826801517066,
      "grad_norm": 0.65625,
      "learning_rate": 8.642321952241126e-05,
      "loss": 1.0791142463684082,
      "mean_token_accuracy": 0.779176946413719,
      "num_tokens": 408924.0,
      "step": 140
    },
    {
      "epoch": 1.0606826801517066,
      "eval_entropy": 0.9091628380119801,
      "eval_loss": 0.9220267534255981,
      "eval_mean_token_accuracy": 0.8066961765289307,
      "eval_num_tokens": 408924.0,
      "eval_runtime": 15.6764,
      "eval_samples_per_second": 0.51,
      "eval_steps_per_second": 0.51,
      "step": 140
    },
    {
      "entropy": 0.7742048308253289,
      "epoch": 1.13653603034134,
      "grad_norm": 0.74609375,
      "learning_rate": 8.425418338863502e-05,
      "loss": 0.7456035137176513,
      "mean_token_accuracy": 0.8373923808336258,
      "num_tokens": 437721.0,
      "step": 150
    },
    {
      "epoch": 1.13653603034134,
      "eval_entropy": 0.8886274918913841,
      "eval_loss": 0.8979178071022034,
      "eval_mean_token_accuracy": 0.8057176694273949,
      "eval_num_tokens": 437721.0,
      "eval_runtime": 15.6592,
      "eval_samples_per_second": 0.511,
      "eval_steps_per_second": 0.511,
      "step": 150
    },
    {
      "entropy": 0.7018384074171384,
      "epoch": 1.2123893805309733,
      "grad_norm": 0.6484375,
      "learning_rate": 8.195622224318879e-05,
      "loss": 0.6607318878173828,
      "mean_token_accuracy": 0.8447161267201105,
      "num_tokens": 462626.0,
      "step": 160
    },
    {
      "epoch": 1.2123893805309733,
      "eval_entropy": 0.8706388957798481,
      "eval_loss": 0.9000320434570312,
      "eval_mean_token_accuracy": 0.8101153001189232,
      "eval_num_tokens": 462626.0,
      "eval_runtime": 15.6367,
      "eval_samples_per_second": 0.512,
      "eval_steps_per_second": 0.512,
      "step": 160
    },
    {
      "entropy": 0.9497246752182643,
      "epoch": 1.2882427307206068,
      "grad_norm": 0.64453125,
      "learning_rate": 7.953798509294372e-05,
      "loss": 0.9422295570373536,
      "mean_token_accuracy": 0.8010553220907847,
      "num_tokens": 492653.0,
      "step": 170
    },
    {
      "epoch": 1.2882427307206068,
      "eval_entropy": 0.9001824222505093,
      "eval_loss": 0.9093658924102783,
      "eval_mean_token_accuracy": 0.8088075593113899,
      "eval_num_tokens": 492653.0,
      "eval_runtime": 15.6666,
      "eval_samples_per_second": 0.511,
      "eval_steps_per_second": 0.511,
      "step": 170
    },
    {
      "entropy": 0.8425602326790492,
      "epoch": 1.3640960809102403,
      "grad_norm": 0.609375,
      "learning_rate": 7.700857363649465e-05,
      "loss": 0.8109879493713379,
      "mean_token_accuracy": 0.8285688976446788,
      "num_tokens": 523035.0,
      "step": 180
    },
    {
      "epoch": 1.3640960809102403,
      "eval_entropy": 0.8594749756157398,
      "eval_loss": 0.8847923278808594,
      "eval_mean_token_accuracy": 0.8098366558551788,
      "eval_num_tokens": 523035.0,
      "eval_runtime": 15.7401,
      "eval_samples_per_second": 0.508,
      "eval_steps_per_second": 0.508,
      "step": 180
    },
    {
      "entropy": 0.7103817813098431,
      "epoch": 1.4399494310998735,
      "grad_norm": 0.625,
      "learning_rate": 7.43775080074218e-05,
      "loss": 0.6827019214630127,
      "mean_token_accuracy": 0.8422260383764902,
      "num_tokens": 548885.0,
      "step": 190
    },
    {
      "epoch": 1.4399494310998735,
      "eval_entropy": 0.8456171080470085,
      "eval_loss": 0.8787115812301636,
      "eval_mean_token_accuracy": 0.8125583752989769,
      "eval_num_tokens": 548885.0,
      "eval_runtime": 15.8473,
      "eval_samples_per_second": 0.505,
      "eval_steps_per_second": 0.505,
      "step": 190
    },
    {
      "entropy": 0.9479823822776476,
      "epoch": 1.515802781289507,
      "grad_norm": 0.734375,
      "learning_rate": 7.16546909426576e-05,
      "loss": 0.949166202545166,
      "mean_token_accuracy": 0.7941406567891439,
      "num_tokens": 577576.0,
      "step": 200
    },
    {
      "epoch": 1.515802781289507,
      "eval_entropy": 0.8673977516591549,
      "eval_loss": 0.8828094005584717,
      "eval_mean_token_accuracy": 0.8098664358258247,
      "eval_num_tokens": 577576.0,
      "eval_runtime": 15.5839,
      "eval_samples_per_second": 0.513,
      "eval_steps_per_second": 0.513,
      "step": 200
    },
    {
      "entropy": 1.0111428305506707,
      "epoch": 1.5916561314791404,
      "grad_norm": 0.7265625,
      "learning_rate": 6.885037051082091e-05,
      "loss": 0.9710953712463379,
      "mean_token_accuracy": 0.7993101666371027,
      "num_tokens": 609960.0,
      "step": 210
    },
    {
      "epoch": 1.5916561314791404,
      "eval_entropy": 0.856759961694479,
      "eval_loss": 0.8776929378509521,
      "eval_mean_token_accuracy": 0.8108815997838974,
      "eval_num_tokens": 609960.0,
      "eval_runtime": 15.6851,
      "eval_samples_per_second": 0.51,
      "eval_steps_per_second": 0.51,
      "step": 210
    },
    {
      "entropy": 0.6799834683537483,
      "epoch": 1.6675094816687737,
      "grad_norm": 0.7109375,
      "learning_rate": 6.597510154080078e-05,
      "loss": 0.6525429248809814,
      "mean_token_accuracy": 0.8495604753494262,
      "num_tokens": 636497.0,
      "step": 220
    },
    {
      "epoch": 1.6675094816687737,
      "eval_entropy": 0.8356063477694988,
      "eval_loss": 0.8647487759590149,
      "eval_mean_token_accuracy": 0.8143020421266556,
      "eval_num_tokens": 636497.0,
      "eval_runtime": 15.8097,
      "eval_samples_per_second": 0.506,
      "eval_steps_per_second": 0.506,
      "step": 220
    },
    {
      "entropy": 0.8049038504560788,
      "epoch": 1.7433628318584071,
      "grad_norm": 0.76171875,
      "learning_rate": 6.303970589576378e-05,
      "loss": 0.7930676937103271,
      "mean_token_accuracy": 0.8221095313628515,
      "num_tokens": 662413.0,
      "step": 230
    },
    {
      "epoch": 1.7433628318584071,
      "eval_entropy": 0.8299686685204506,
      "eval_loss": 0.8727775812149048,
      "eval_mean_token_accuracy": 0.811675526201725,
      "eval_num_tokens": 662413.0,
      "eval_runtime": 15.6522,
      "eval_samples_per_second": 0.511,
      "eval_steps_per_second": 0.511,
      "step": 230
    },
    {
      "entropy": 1.0564268256227176,
      "epoch": 1.8192161820480406,
      "grad_norm": 0.578125,
      "learning_rate": 6.00552317421046e-05,
      "loss": 1.028653335571289,
      "mean_token_accuracy": 0.790699835618337,
      "num_tokens": 696264.0,
      "step": 240
    },
    {
      "epoch": 1.8192161820480406,
      "eval_entropy": 0.8743892759084702,
      "eval_loss": 0.8777971267700195,
      "eval_mean_token_accuracy": 0.8138757944107056,
      "eval_num_tokens": 696264.0,
      "eval_runtime": 15.7076,
      "eval_samples_per_second": 0.509,
      "eval_steps_per_second": 0.509,
      "step": 240
    },
    {
      "entropy": 0.7534422516822815,
      "epoch": 1.8950695322376738,
      "grad_norm": 0.578125,
      "learning_rate": 5.703291196664247e-05,
      "loss": 0.7200803279876709,
      "mean_token_accuracy": 0.841905082265536,
      "num_tokens": 724679.0,
      "step": 250
    },
    {
      "epoch": 1.8950695322376738,
      "eval_entropy": 0.8260066509246826,
      "eval_loss": 0.8556550741195679,
      "eval_mean_token_accuracy": 0.8176052942872047,
      "eval_num_tokens": 724679.0,
      "eval_runtime": 15.5383,
      "eval_samples_per_second": 0.515,
      "eval_steps_per_second": 0.515,
      "step": 250
    },
    {
      "entropy": 0.6556119327743848,
      "epoch": 1.970922882427307,
      "grad_norm": 0.90625,
      "learning_rate": 5.39841218985715e-05,
      "loss": 0.6228540897369385,
      "mean_token_accuracy": 0.8531604041655858,
      "num_tokens": 747645.0,
      "step": 260
    },
    {
      "epoch": 1.970922882427307,
      "eval_entropy": 0.7757505960762501,
      "eval_loss": 0.8425352573394775,
      "eval_mean_token_accuracy": 0.8199078440666199,
      "eval_num_tokens": 747645.0,
      "eval_runtime": 15.5078,
      "eval_samples_per_second": 0.516,
      "eval_steps_per_second": 0.516,
      "step": 260
    },
    {
      "entropy": 0.9678725031977993,
      "epoch": 2.04551201011378,
      "grad_norm": 0.66015625,
      "learning_rate": 5.0920336495290244e-05,
      "loss": 0.9681121826171875,
      "mean_token_accuracy": 0.7974661972563145,
      "num_tokens": 782139.0,
      "step": 270
    },
    {
      "epoch": 2.04551201011378,
      "eval_entropy": 0.80567791685462,
      "eval_loss": 0.8436932563781738,
      "eval_mean_token_accuracy": 0.8152260556817055,
      "eval_num_tokens": 782139.0,
      "eval_runtime": 15.8016,
      "eval_samples_per_second": 0.506,
      "eval_steps_per_second": 0.506,
      "step": 270
    },
    {
      "entropy": 0.8536191220084827,
      "epoch": 2.1213653603034133,
      "grad_norm": 0.5546875,
      "learning_rate": 4.785308715325296e-05,
      "loss": 0.7874747276306152,
      "mean_token_accuracy": 0.8298017164071401,
      "num_tokens": 813720.0,
      "step": 280
    },
    {
      "epoch": 2.1213653603034133,
      "eval_entropy": 0.7856072653084993,
      "eval_loss": 0.846335232257843,
      "eval_mean_token_accuracy": 0.819606214761734,
      "eval_num_tokens": 813720.0,
      "eval_runtime": 15.6923,
      "eval_samples_per_second": 0.51,
      "eval_steps_per_second": 0.51,
      "step": 280
    }
  ],
  "logging_steps": 10,
  "max_steps": 528,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.399944281776128e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}