{
  "best_global_step": 300,
  "best_metric": 4.177750110626221,
  "best_model_checkpoint": "/Users/alexgrigoras/Library/Mobile Documents/com~apple~CloudDocs/[5] Software/github/dif-pi/artifacts/models/sdg_chronos_t5_small_dunnhumby/checkpoint-300",
  "epoch": 0.04181840358244324,
  "eval_steps": 25,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0034848669652036033,
      "grad_norm": 0.2658565640449524,
      "learning_rate": 2.4938536281812643e-05,
      "loss": 50.4958984375,
      "step": 25
    },
    {
      "epoch": 0.0034848669652036033,
      "eval_loss": 4.513997554779053,
      "eval_runtime": 126.0711,
      "eval_samples_per_second": 101.165,
      "eval_steps_per_second": 50.583,
      "step": 25
    },
    {
      "epoch": 0.006969733930407207,
      "grad_norm": 0.3027424216270447,
      "learning_rate": 2.4132322535191482e-05,
      "loss": 49.5675048828125,
      "step": 50
    },
    {
      "epoch": 0.006969733930407207,
      "eval_loss": 4.422898769378662,
      "eval_runtime": 135.5543,
      "eval_samples_per_second": 94.088,
      "eval_steps_per_second": 47.044,
      "step": 50
    },
    {
      "epoch": 0.01045460089561081,
      "grad_norm": 0.34238171577453613,
      "learning_rate": 2.2448287207969232e-05,
      "loss": 48.3637109375,
      "step": 75
    },
    {
      "epoch": 0.01045460089561081,
      "eval_loss": 4.359263896942139,
      "eval_runtime": 138.5997,
      "eval_samples_per_second": 92.02,
      "eval_steps_per_second": 46.01,
      "step": 75
    },
    {
      "epoch": 0.013939467860814413,
      "grad_norm": 0.3021143674850464,
      "learning_rate": 2.0013514341037815e-05,
      "loss": 47.3734521484375,
      "step": 100
    },
    {
      "epoch": 0.013939467860814413,
      "eval_loss": 4.318150997161865,
      "eval_runtime": 136.3222,
      "eval_samples_per_second": 93.558,
      "eval_steps_per_second": 46.779,
      "step": 100
    },
    {
      "epoch": 0.017424334826018018,
      "grad_norm": 0.28853410482406616,
      "learning_rate": 1.7011741632521437e-05,
      "loss": 48.521357421875,
      "step": 125
    },
    {
      "epoch": 0.017424334826018018,
      "eval_loss": 4.282954692840576,
      "eval_runtime": 132.1879,
      "eval_samples_per_second": 96.484,
      "eval_steps_per_second": 48.242,
      "step": 125
    },
    {
      "epoch": 0.02090920179122162,
      "grad_norm": 0.3650856614112854,
      "learning_rate": 1.3669494856238973e-05,
      "loss": 47.43091796875,
      "step": 150
    },
    {
      "epoch": 0.02090920179122162,
      "eval_loss": 4.249988555908203,
      "eval_runtime": 145.2659,
      "eval_samples_per_second": 87.798,
      "eval_steps_per_second": 43.899,
      "step": 150
    },
    {
      "epoch": 0.024394068756425222,
      "grad_norm": 0.3505313992500305,
      "learning_rate": 1.023899332084863e-05,
      "loss": 46.525419921875,
      "step": 175
    },
    {
      "epoch": 0.024394068756425222,
      "eval_loss": 4.218865871429443,
      "eval_runtime": 137.0969,
      "eval_samples_per_second": 93.029,
      "eval_steps_per_second": 46.515,
      "step": 175
    },
    {
      "epoch": 0.027878935721628827,
      "grad_norm": 0.3190622925758362,
      "learning_rate": 6.979116392095325e-06,
      "loss": 46.60708984375,
      "step": 200
    },
    {
      "epoch": 0.027878935721628827,
      "eval_loss": 4.196957588195801,
      "eval_runtime": 140.7578,
      "eval_samples_per_second": 90.61,
      "eval_steps_per_second": 45.305,
      "step": 200
    },
    {
      "epoch": 0.03136380268683243,
      "grad_norm": 0.3062129318714142,
      "learning_rate": 4.1358674205142765e-06,
      "loss": 48.300791015625,
      "step": 225
    },
    {
      "epoch": 0.03136380268683243,
      "eval_loss": 4.185319900512695,
      "eval_runtime": 134.3944,
      "eval_samples_per_second": 94.9,
      "eval_steps_per_second": 47.45,
      "step": 225
    },
    {
      "epoch": 0.034848669652036035,
      "grad_norm": 0.30869823694229126,
      "learning_rate": 1.923809344738306e-06,
      "loss": 47.4475341796875,
      "step": 250
    },
    {
      "epoch": 0.034848669652036035,
      "eval_loss": 4.180154323577881,
      "eval_runtime": 142.7493,
      "eval_samples_per_second": 89.345,
      "eval_steps_per_second": 44.673,
      "step": 250
    },
    {
      "epoch": 0.038333536617239636,
      "grad_norm": 0.30447155237197876,
      "learning_rate": 5.098729140296271e-07,
      "loss": 47.397509765625,
      "step": 275
    },
    {
      "epoch": 0.038333536617239636,
      "eval_loss": 4.1781206130981445,
      "eval_runtime": 150.242,
      "eval_samples_per_second": 84.89,
      "eval_steps_per_second": 42.445,
      "step": 275
    },
    {
      "epoch": 0.04181840358244324,
      "grad_norm": 0.3095584213733673,
      "learning_rate": 7.594263207122421e-10,
      "loss": 46.36583984375,
      "step": 300
    },
    {
      "epoch": 0.04181840358244324,
      "eval_loss": 4.177750110626221,
      "eval_runtime": 144.6681,
      "eval_samples_per_second": 88.16,
      "eval_steps_per_second": 44.08,
      "step": 300
    }
  ],
  "logging_steps": 25,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 229911035904000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}