{
  "best_global_step": 200,
  "best_metric": 0.8998275399208069,
  "best_model_checkpoint": "/content/drive/MyDrive/amaru-txt-epoch-6/checkpoint-200",
  "epoch": 0.966183574879227,
  "eval_steps": 10,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04830917874396135,
      "grad_norm": 1.9938534498214722,
      "learning_rate": 3.5389440000000007e-05,
      "loss": 0.8315,
      "step": 10
    },
    {
      "epoch": 0.04830917874396135,
      "eval_loss": 0.9170326590538025,
      "eval_runtime": 89.5861,
      "eval_samples_per_second": 9.778,
      "eval_steps_per_second": 0.156,
      "step": 10
    },
    {
      "epoch": 0.0966183574879227,
      "grad_norm": 2.8435614109039307,
      "learning_rate": 7.471104000000001e-05,
      "loss": 0.7156,
      "step": 20
    },
    {
      "epoch": 0.0966183574879227,
      "eval_loss": 0.92298823595047,
      "eval_runtime": 89.6583,
      "eval_samples_per_second": 9.77,
      "eval_steps_per_second": 0.156,
      "step": 20
    },
    {
      "epoch": 0.14492753623188406,
      "grad_norm": 2.7325339317321777,
      "learning_rate": 7.819458354458255e-05,
      "loss": 0.8015,
      "step": 30
    },
    {
      "epoch": 0.14492753623188406,
      "eval_loss": 0.9262471199035645,
      "eval_runtime": 89.6974,
      "eval_samples_per_second": 9.766,
      "eval_steps_per_second": 0.156,
      "step": 30
    },
    {
      "epoch": 0.1932367149758454,
      "grad_norm": 2.380279779434204,
      "learning_rate": 7.665694808929027e-05,
      "loss": 0.7263,
      "step": 40
    },
    {
      "epoch": 0.1932367149758454,
      "eval_loss": 0.9168504476547241,
      "eval_runtime": 89.6787,
      "eval_samples_per_second": 9.768,
      "eval_steps_per_second": 0.156,
      "step": 40
    },
    {
      "epoch": 0.24154589371980675,
      "grad_norm": 2.8440909385681152,
      "learning_rate": 7.406804077083218e-05,
      "loss": 0.7098,
      "step": 50
    },
    {
      "epoch": 0.24154589371980675,
      "eval_loss": 0.9175106883049011,
      "eval_runtime": 89.6725,
      "eval_samples_per_second": 9.769,
      "eval_steps_per_second": 0.156,
      "step": 50
    },
    {
      "epoch": 0.2898550724637681,
      "grad_norm": 2.432560920715332,
      "learning_rate": 7.050075887179768e-05,
      "loss": 0.7212,
      "step": 60
    },
    {
      "epoch": 0.2898550724637681,
      "eval_loss": 0.9199467301368713,
      "eval_runtime": 89.7174,
      "eval_samples_per_second": 9.764,
      "eval_steps_per_second": 0.156,
      "step": 60
    },
    {
      "epoch": 0.33816425120772947,
      "grad_norm": 3.1470143795013428,
      "learning_rate": 6.605554830418061e-05,
      "loss": 0.7116,
      "step": 70
    },
    {
      "epoch": 0.33816425120772947,
      "eval_loss": 0.9214985966682434,
      "eval_runtime": 89.6568,
      "eval_samples_per_second": 9.771,
      "eval_steps_per_second": 0.156,
      "step": 70
    },
    {
      "epoch": 0.3864734299516908,
      "grad_norm": 3.123927354812622,
      "learning_rate": 6.085757529877134e-05,
      "loss": 0.7162,
      "step": 80
    },
    {
      "epoch": 0.3864734299516908,
      "eval_loss": 0.9215625524520874,
      "eval_runtime": 89.6808,
      "eval_samples_per_second": 9.768,
      "eval_steps_per_second": 0.156,
      "step": 80
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 2.565199851989746,
      "learning_rate": 5.5053202030981025e-05,
      "loss": 0.806,
      "step": 90
    },
    {
      "epoch": 0.43478260869565216,
      "eval_loss": 0.9178029298782349,
      "eval_runtime": 89.7041,
      "eval_samples_per_second": 9.765,
      "eval_steps_per_second": 0.156,
      "step": 90
    },
    {
      "epoch": 0.4830917874396135,
      "grad_norm": 2.8664753437042236,
      "learning_rate": 4.880586542083376e-05,
      "loss": 0.7107,
      "step": 100
    },
    {
      "epoch": 0.4830917874396135,
      "eval_loss": 0.9137737154960632,
      "eval_runtime": 89.6956,
      "eval_samples_per_second": 9.766,
      "eval_steps_per_second": 0.156,
      "step": 100
    },
    {
      "epoch": 0.5314009661835749,
      "grad_norm": 2.94624400138855,
      "learning_rate": 4.229147515001422e-05,
      "loss": 0.7115,
      "step": 110
    },
    {
      "epoch": 0.5314009661835749,
      "eval_loss": 0.913902223110199,
      "eval_runtime": 89.6611,
      "eval_samples_per_second": 9.77,
      "eval_steps_per_second": 0.156,
      "step": 110
    },
    {
      "epoch": 0.5797101449275363,
      "grad_norm": 3.233154296875,
      "learning_rate": 3.569346047652783e-05,
      "loss": 0.7752,
      "step": 120
    },
    {
      "epoch": 0.5797101449275363,
      "eval_loss": 0.9105567336082458,
      "eval_runtime": 89.6726,
      "eval_samples_per_second": 9.769,
      "eval_steps_per_second": 0.156,
      "step": 120
    },
    {
      "epoch": 0.6280193236714976,
      "grad_norm": 2.791991949081421,
      "learning_rate": 2.9197605316528352e-05,
      "loss": 0.8082,
      "step": 130
    },
    {
      "epoch": 0.6280193236714976,
      "eval_loss": 0.9074307084083557,
      "eval_runtime": 89.6733,
      "eval_samples_per_second": 9.769,
      "eval_steps_per_second": 0.156,
      "step": 130
    },
    {
      "epoch": 0.6763285024154589,
      "grad_norm": 2.9703595638275146,
      "learning_rate": 2.2986817024745032e-05,
      "loss": 0.8185,
      "step": 140
    },
    {
      "epoch": 0.6763285024154589,
      "eval_loss": 0.9059156775474548,
      "eval_runtime": 89.6839,
      "eval_samples_per_second": 9.768,
      "eval_steps_per_second": 0.156,
      "step": 140
    },
    {
      "epoch": 0.7246376811594203,
      "grad_norm": 2.797487735748291,
      "learning_rate": 1.7235976171826803e-05,
      "loss": 0.8013,
      "step": 150
    },
    {
      "epoch": 0.7246376811594203,
      "eval_loss": 0.9037850499153137,
      "eval_runtime": 89.6764,
      "eval_samples_per_second": 9.768,
      "eval_steps_per_second": 0.156,
      "step": 150
    },
    {
      "epoch": 0.7729468599033816,
      "grad_norm": 2.6389381885528564,
      "learning_rate": 1.210701233624601e-05,
      "loss": 0.8531,
      "step": 160
    },
    {
      "epoch": 0.7729468599033816,
      "eval_loss": 0.9019114971160889,
      "eval_runtime": 89.6735,
      "eval_samples_per_second": 9.769,
      "eval_steps_per_second": 0.156,
      "step": 160
    },
    {
      "epoch": 0.821256038647343,
      "grad_norm": 2.7340869903564453,
      "learning_rate": 7.744344564388566e-06,
      "loss": 0.8288,
      "step": 170
    },
    {
      "epoch": 0.821256038647343,
      "eval_loss": 0.9006927609443665,
      "eval_runtime": 89.6331,
      "eval_samples_per_second": 9.773,
      "eval_steps_per_second": 0.156,
      "step": 170
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 2.7714426517486572,
      "learning_rate": 4.270814884295176e-06,
      "loss": 0.8686,
      "step": 180
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 0.8999435901641846,
      "eval_runtime": 89.7018,
      "eval_samples_per_second": 9.766,
      "eval_steps_per_second": 0.156,
      "step": 180
    },
    {
      "epoch": 0.9178743961352657,
      "grad_norm": 3.1497857570648193,
      "learning_rate": 1.7842293753365276e-06,
      "loss": 0.8859,
      "step": 190
    },
    {
      "epoch": 0.9178743961352657,
      "eval_loss": 0.9000065326690674,
      "eval_runtime": 89.6862,
      "eval_samples_per_second": 9.767,
      "eval_steps_per_second": 0.156,
      "step": 190
    },
    {
      "epoch": 0.966183574879227,
      "grad_norm": 2.9853219985961914,
      "learning_rate": 3.546041888197535e-07,
      "loss": 0.8611,
      "step": 200
    },
    {
      "epoch": 0.966183574879227,
      "eval_loss": 0.8998275399208069,
      "eval_runtime": 89.6735,
      "eval_samples_per_second": 9.769,
      "eval_steps_per_second": 0.156,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 207,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.99869509435392e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}