{
  "best_global_step": 750,
  "best_metric": 3.810453414916992,
  "best_model_checkpoint": "/Users/alexgrigoras/Library/Mobile Documents/com~apple~CloudDocs/[5] Software/github/dif-pi/artifacts/models/sdg_chronos_t5_small_dunnhumby/checkpoint-750",
  "epoch": 0.1045460089561081,
  "eval_steps": 25,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0034848669652036033,
      "grad_norm": 0.2964903712272644,
      "learning_rate": 8.000000000000001e-06,
      "loss": 37.88656494140625,
      "step": 25
    },
    {
      "epoch": 0.0034848669652036033,
      "eval_loss": 4.6062092781066895,
      "eval_runtime": 134.4005,
      "eval_samples_per_second": 94.895,
      "eval_steps_per_second": 47.448,
      "step": 25
    },
    {
      "epoch": 0.006969733930407207,
      "grad_norm": 0.34245482087135315,
      "learning_rate": 1.6333333333333335e-05,
      "loss": 37.61192138671875,
      "step": 50
    },
    {
      "epoch": 0.006969733930407207,
      "eval_loss": 4.552639007568359,
      "eval_runtime": 131.7871,
      "eval_samples_per_second": 96.777,
      "eval_steps_per_second": 48.389,
      "step": 50
    },
    {
      "epoch": 0.01045460089561081,
      "grad_norm": 0.3815608024597168,
      "learning_rate": 2.466666666666667e-05,
      "loss": 37.09659912109375,
      "step": 75
    },
    {
      "epoch": 0.01045460089561081,
      "eval_loss": 4.443544864654541,
      "eval_runtime": 154.9254,
      "eval_samples_per_second": 82.323,
      "eval_steps_per_second": 41.162,
      "step": 75
    },
    {
      "epoch": 0.013939467860814413,
      "grad_norm": 0.3647356331348419,
      "learning_rate": 2.498250672211728e-05,
      "loss": 36.29866943359375,
      "step": 100
    },
    {
      "epoch": 0.013939467860814413,
      "eval_loss": 4.3369669914245605,
      "eval_runtime": 138.8908,
      "eval_samples_per_second": 91.828,
      "eval_steps_per_second": 45.914,
      "step": 100
    },
    {
      "epoch": 0.017424334826018018,
      "grad_norm": 0.3683606684207916,
      "learning_rate": 2.4927134858925575e-05,
      "loss": 35.8759912109375,
      "step": 125
    },
    {
      "epoch": 0.017424334826018018,
      "eval_loss": 4.242681980133057,
      "eval_runtime": 125.8059,
      "eval_samples_per_second": 101.378,
      "eval_steps_per_second": 50.689,
      "step": 125
    },
    {
      "epoch": 0.02090920179122162,
      "grad_norm": 0.41745099425315857,
      "learning_rate": 2.4834022195605383e-05,
      "loss": 34.71609375,
      "step": 150
    },
    {
      "epoch": 0.02090920179122162,
      "eval_loss": 4.15211820602417,
      "eval_runtime": 144.0648,
      "eval_samples_per_second": 88.53,
      "eval_steps_per_second": 44.265,
      "step": 150
    },
    {
      "epoch": 0.024394068756425222,
      "grad_norm": 0.5502339601516724,
      "learning_rate": 2.470345151225491e-05,
      "loss": 34.4389111328125,
      "step": 175
    },
    {
      "epoch": 0.024394068756425222,
      "eval_loss": 4.065174579620361,
      "eval_runtime": 164.1963,
      "eval_samples_per_second": 77.675,
      "eval_steps_per_second": 38.838,
      "step": 175
    },
    {
      "epoch": 0.027878935721628827,
      "grad_norm": 0.5007655024528503,
      "learning_rate": 2.4535819347748074e-05,
      "loss": 33.89746337890625,
      "step": 200
    },
    {
      "epoch": 0.027878935721628827,
      "eval_loss": 3.987807035446167,
      "eval_runtime": 141.6182,
      "eval_samples_per_second": 90.059,
      "eval_steps_per_second": 45.03,
      "step": 200
    },
    {
      "epoch": 0.03136380268683243,
      "grad_norm": 0.48552975058555603,
      "learning_rate": 2.433163479545898e-05,
      "loss": 34.3608935546875,
      "step": 225
    },
    {
      "epoch": 0.03136380268683243,
      "eval_loss": 3.951249361038208,
      "eval_runtime": 178.1207,
      "eval_samples_per_second": 71.603,
      "eval_steps_per_second": 35.802,
      "step": 225
    },
    {
      "epoch": 0.034848669652036035,
      "grad_norm": 0.4646497964859009,
      "learning_rate": 2.4091517957162068e-05,
      "loss": 33.36589599609375,
      "step": 250
    },
    {
      "epoch": 0.034848669652036035,
      "eval_loss": 3.9345061779022217,
      "eval_runtime": 191.2882,
      "eval_samples_per_second": 66.674,
      "eval_steps_per_second": 33.337,
      "step": 250
    },
    {
      "epoch": 0.038333536617239636,
      "grad_norm": 0.5384636521339417,
      "learning_rate": 2.3816198059803415e-05,
      "loss": 32.43830810546875,
      "step": 275
    },
    {
      "epoch": 0.038333536617239636,
      "eval_loss": 3.919111967086792,
      "eval_runtime": 157.7724,
      "eval_samples_per_second": 80.838,
      "eval_steps_per_second": 40.419,
      "step": 275
    },
    {
      "epoch": 0.04181840358244324,
      "grad_norm": 0.5843191742897034,
      "learning_rate": 2.350651124086246e-05,
      "loss": 33.16199462890625,
      "step": 300
    },
    {
      "epoch": 0.04181840358244324,
      "eval_loss": 3.907341957092285,
      "eval_runtime": 137.2039,
      "eval_samples_per_second": 92.957,
      "eval_steps_per_second": 46.478,
      "step": 300
    },
    {
      "epoch": 0.045303270547646844,
      "grad_norm": 0.6355782151222229,
      "learning_rate": 2.316339800902997e-05,
      "loss": 31.9848095703125,
      "step": 325
    },
    {
      "epoch": 0.045303270547646844,
      "eval_loss": 3.904228925704956,
      "eval_runtime": 142.1459,
      "eval_samples_per_second": 89.725,
      "eval_steps_per_second": 44.862,
      "step": 325
    },
    {
      "epoch": 0.048788137512850445,
      "grad_norm": 0.6354503035545349,
      "learning_rate": 2.2787900387914035e-05,
      "loss": 32.89923095703125,
      "step": 350
    },
    {
      "epoch": 0.048788137512850445,
      "eval_loss": 3.889650344848633,
      "eval_runtime": 135.6805,
      "eval_samples_per_second": 94.0,
      "eval_steps_per_second": 47.0,
      "step": 350
    },
    {
      "epoch": 0.05227300447805405,
      "grad_norm": 0.4500903785228729,
      "learning_rate": 2.238115875144865e-05,
      "loss": 31.9859375,
      "step": 375
    },
    {
      "epoch": 0.05227300447805405,
      "eval_loss": 3.881140947341919,
      "eval_runtime": 137.1013,
      "eval_samples_per_second": 93.026,
      "eval_steps_per_second": 46.513,
      "step": 375
    },
    {
      "epoch": 0.05575787144325765,
      "grad_norm": 0.7105244994163513,
      "learning_rate": 2.1944408360615527e-05,
      "loss": 31.830234375,
      "step": 400
    },
    {
      "epoch": 0.05575787144325765,
      "eval_loss": 3.876532554626465,
      "eval_runtime": 138.0891,
      "eval_samples_per_second": 92.361,
      "eval_steps_per_second": 46.18,
      "step": 400
    },
    {
      "epoch": 0.059242738408461254,
      "grad_norm": 0.5426522493362427,
      "learning_rate": 2.147897561199711e-05,
      "loss": 32.8569921875,
      "step": 425
    },
    {
      "epoch": 0.059242738408461254,
      "eval_loss": 3.869863510131836,
      "eval_runtime": 137.3068,
      "eval_samples_per_second": 92.887,
      "eval_steps_per_second": 46.443,
      "step": 425
    },
    {
      "epoch": 0.06272760537366485,
      "grad_norm": 0.6868773698806763,
      "learning_rate": 2.0986274009553747e-05,
      "loss": 33.1663525390625,
      "step": 450
    },
    {
      "epoch": 0.06272760537366485,
      "eval_loss": 3.858783483505249,
      "eval_runtime": 136.4747,
      "eval_samples_per_second": 93.453,
      "eval_steps_per_second": 46.727,
      "step": 450
    },
    {
      "epoch": 0.06621247233886847,
      "grad_norm": 0.6488957405090332,
      "learning_rate": 2.0467799871858624e-05,
      "loss": 32.170732421875,
      "step": 475
    },
    {
      "epoch": 0.06621247233886847,
      "eval_loss": 3.857388496398926,
      "eval_runtime": 138.5464,
      "eval_samples_per_second": 92.056,
      "eval_steps_per_second": 46.028,
      "step": 475
    },
    {
      "epoch": 0.06969733930407207,
      "grad_norm": 0.5700647830963135,
      "learning_rate": 1.9925127787827415e-05,
      "loss": 32.3882470703125,
      "step": 500
    },
    {
      "epoch": 0.06969733930407207,
      "eval_loss": 3.852177619934082,
      "eval_runtime": 137.7764,
      "eval_samples_per_second": 92.57,
      "eval_steps_per_second": 46.285,
      "step": 500
    },
    {
      "epoch": 0.07318220626927567,
      "grad_norm": 0.6471461653709412,
      "learning_rate": 1.9359905834743513e-05,
      "loss": 32.83000244140625,
      "step": 525
    },
    {
      "epoch": 0.07318220626927567,
      "eval_loss": 3.8465960025787354,
      "eval_runtime": 137.4128,
      "eval_samples_per_second": 92.815,
      "eval_steps_per_second": 46.408,
      "step": 525
    },
    {
      "epoch": 0.07666707323447927,
      "grad_norm": 0.6369190812110901,
      "learning_rate": 1.8773850573101503e-05,
      "loss": 32.35257080078125,
      "step": 550
    },
    {
      "epoch": 0.07666707323447927,
      "eval_loss": 3.842385768890381,
      "eval_runtime": 140.2355,
      "eval_samples_per_second": 90.947,
      "eval_steps_per_second": 45.474,
      "step": 550
    },
    {
      "epoch": 0.08015194019968287,
      "grad_norm": 0.5800191164016724,
      "learning_rate": 1.8168741833469327e-05,
      "loss": 31.9875244140625,
      "step": 575
    },
    {
      "epoch": 0.08015194019968287,
      "eval_loss": 3.8325023651123047,
      "eval_runtime": 137.4074,
      "eval_samples_per_second": 92.819,
      "eval_steps_per_second": 46.409,
      "step": 575
    },
    {
      "epoch": 0.08363680716488649,
      "grad_norm": 0.655426025390625,
      "learning_rate": 1.7546417311201357e-05,
      "loss": 31.470654296875,
      "step": 600
    },
    {
      "epoch": 0.08363680716488649,
      "eval_loss": 3.82979416847229,
      "eval_runtime": 136.3318,
      "eval_samples_per_second": 93.551,
      "eval_steps_per_second": 46.776,
      "step": 600
    },
    {
      "epoch": 0.08712167413009009,
      "grad_norm": 0.5678662657737732,
      "learning_rate": 1.690876698541802e-05,
      "loss": 32.25173828125,
      "step": 625
    },
    {
      "epoch": 0.08712167413009009,
      "eval_loss": 3.828555107116699,
      "eval_runtime": 142.3008,
      "eval_samples_per_second": 89.627,
      "eval_steps_per_second": 44.814,
      "step": 625
    },
    {
      "epoch": 0.09060654109529369,
      "grad_norm": 0.6696360111236572,
      "learning_rate": 1.625772737920128e-05,
      "loss": 32.847529296875,
      "step": 650
    },
    {
      "epoch": 0.09060654109529369,
      "eval_loss": 3.8212130069732666,
      "eval_runtime": 145.4915,
      "eval_samples_per_second": 87.661,
      "eval_steps_per_second": 43.831,
      "step": 650
    },
    {
      "epoch": 0.09409140806049729,
      "grad_norm": 0.6813345551490784,
      "learning_rate": 1.5595275678437756e-05,
      "loss": 32.22562744140625,
      "step": 675
    },
    {
      "epoch": 0.09409140806049729,
      "eval_loss": 3.8163504600524902,
      "eval_runtime": 135.9053,
      "eval_samples_per_second": 93.845,
      "eval_steps_per_second": 46.922,
      "step": 675
    },
    {
      "epoch": 0.09757627502570089,
      "grad_norm": 0.6201620101928711,
      "learning_rate": 1.4923423727170106e-05,
      "loss": 32.73896240234375,
      "step": 700
    },
    {
      "epoch": 0.09757627502570089,
      "eval_loss": 3.8148138523101807,
      "eval_runtime": 140.771,
      "eval_samples_per_second": 90.601,
      "eval_steps_per_second": 45.301,
      "step": 700
    },
    {
      "epoch": 0.10106114199090449,
      "grad_norm": 0.6953298449516296,
      "learning_rate": 1.4244211917692812e-05,
      "loss": 32.32746826171875,
      "step": 725
    },
    {
      "epoch": 0.10106114199090449,
      "eval_loss": 3.8123884201049805,
      "eval_runtime": 141.0245,
      "eval_samples_per_second": 90.438,
      "eval_steps_per_second": 45.219,
      "step": 725
    },
    {
      "epoch": 0.1045460089561081,
      "grad_norm": 0.7098183035850525,
      "learning_rate": 1.355970299394786e-05,
      "loss": 32.90800048828125,
      "step": 750
    },
    {
      "epoch": 0.1045460089561081,
      "eval_loss": 3.810453414916992,
      "eval_runtime": 138.6332,
      "eval_samples_per_second": 91.998,
      "eval_steps_per_second": 45.999,
      "step": 750
    }
  ],
  "logging_steps": 25,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 750,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 574777589760000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}