{
  "best_metric": 3.5649592876434326,
  "best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained/fr_clm/wikipedia_30/checkpoint-36000",
  "epoch": 68.70638754696726,
  "eval_steps": 2000,
  "global_step": 64000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.1470746108427265,
      "eval_loss": 7.138043403625488,
      "eval_runtime": 0.8415,
      "eval_samples_per_second": 1273.93,
      "eval_steps_per_second": 79.621,
      "step": 2000
    },
    {
      "epoch": 4.294149221685453,
      "grad_norm": 1.455039381980896,
      "learning_rate": 1e-05,
      "loss": 7.213,
      "step": 4000
    },
    {
      "epoch": 4.294149221685453,
      "eval_loss": 5.8541717529296875,
      "eval_runtime": 0.7753,
      "eval_samples_per_second": 1382.676,
      "eval_steps_per_second": 86.417,
      "step": 4000
    },
    {
      "epoch": 6.4412238325281805,
      "eval_loss": 5.403579235076904,
      "eval_runtime": 0.7542,
      "eval_samples_per_second": 1421.437,
      "eval_steps_per_second": 88.84,
      "step": 6000
    },
    {
      "epoch": 8.588298443370906,
      "grad_norm": 3.117489814758301,
      "learning_rate": 1.9997500000000003e-05,
      "loss": 5.4304,
      "step": 8000
    },
    {
      "epoch": 8.588298443370906,
      "eval_loss": 5.049880504608154,
      "eval_runtime": 0.7597,
      "eval_samples_per_second": 1411.127,
      "eval_steps_per_second": 88.195,
      "step": 8000
    },
    {
      "epoch": 10.735373054213634,
      "eval_loss": 4.760603427886963,
      "eval_runtime": 0.7624,
      "eval_samples_per_second": 1406.053,
      "eval_steps_per_second": 87.878,
      "step": 10000
    },
    {
      "epoch": 12.882447665056361,
      "grad_norm": 2.9511141777038574,
      "learning_rate": 2.9995e-05,
      "loss": 4.771,
      "step": 12000
    },
    {
      "epoch": 12.882447665056361,
      "eval_loss": 4.517208576202393,
      "eval_runtime": 0.764,
      "eval_samples_per_second": 1403.097,
      "eval_steps_per_second": 87.694,
      "step": 12000
    },
    {
      "epoch": 15.029522275899087,
      "eval_loss": 4.3206024169921875,
      "eval_runtime": 0.7595,
      "eval_samples_per_second": 1411.435,
      "eval_steps_per_second": 88.215,
      "step": 14000
    },
    {
      "epoch": 17.176596886741816,
      "grad_norm": 2.955515146255493,
      "learning_rate": 3.999e-05,
      "loss": 4.2888,
      "step": 16000
    },
    {
      "epoch": 17.176596886741816,
      "eval_loss": 4.152973175048828,
      "eval_runtime": 0.8247,
      "eval_samples_per_second": 1299.91,
      "eval_steps_per_second": 81.244,
      "step": 16000
    },
    {
      "epoch": 19.32367149758454,
      "eval_loss": 4.015476703643799,
      "eval_runtime": 0.7501,
      "eval_samples_per_second": 1429.237,
      "eval_steps_per_second": 89.327,
      "step": 18000
    },
    {
      "epoch": 21.470746108427267,
      "grad_norm": 3.0531320571899414,
      "learning_rate": 4.99875e-05,
      "loss": 3.9141,
      "step": 20000
    },
    {
      "epoch": 21.470746108427267,
      "eval_loss": 3.896575927734375,
      "eval_runtime": 0.768,
      "eval_samples_per_second": 1395.843,
      "eval_steps_per_second": 87.24,
      "step": 20000
    },
    {
      "epoch": 23.617820719269993,
      "eval_loss": 3.8046905994415283,
      "eval_runtime": 0.7601,
      "eval_samples_per_second": 1410.272,
      "eval_steps_per_second": 88.142,
      "step": 22000
    },
    {
      "epoch": 25.764895330112722,
      "grad_norm": 3.089989185333252,
      "learning_rate": 5.998250000000001e-05,
      "loss": 3.6154,
      "step": 24000
    },
    {
      "epoch": 25.764895330112722,
      "eval_loss": 3.7359092235565186,
      "eval_runtime": 0.7778,
      "eval_samples_per_second": 1378.238,
      "eval_steps_per_second": 86.14,
      "step": 24000
    },
    {
      "epoch": 27.911969940955448,
      "eval_loss": 3.6784231662750244,
      "eval_runtime": 0.7541,
      "eval_samples_per_second": 1421.491,
      "eval_steps_per_second": 88.843,
      "step": 26000
    },
    {
      "epoch": 30.059044551798173,
      "grad_norm": 3.3495922088623047,
      "learning_rate": 6.997500000000001e-05,
      "loss": 3.3661,
      "step": 28000
    },
    {
      "epoch": 30.059044551798173,
      "eval_loss": 3.6360318660736084,
      "eval_runtime": 0.7603,
      "eval_samples_per_second": 1409.913,
      "eval_steps_per_second": 88.12,
      "step": 28000
    },
    {
      "epoch": 32.2061191626409,
      "eval_loss": 3.6019041538238525,
      "eval_runtime": 0.7638,
      "eval_samples_per_second": 1403.547,
      "eval_steps_per_second": 87.722,
      "step": 30000
    },
    {
      "epoch": 34.35319377348363,
      "grad_norm": 3.1256051063537598,
      "learning_rate": 7.997250000000001e-05,
      "loss": 3.1473,
      "step": 32000
    },
    {
      "epoch": 34.35319377348363,
      "eval_loss": 3.5816054344177246,
      "eval_runtime": 0.7628,
      "eval_samples_per_second": 1405.391,
      "eval_steps_per_second": 87.837,
      "step": 32000
    },
    {
      "epoch": 36.500268384326354,
      "eval_loss": 3.5698702335357666,
      "eval_runtime": 0.7617,
      "eval_samples_per_second": 1407.381,
      "eval_steps_per_second": 87.961,
      "step": 34000
    },
    {
      "epoch": 38.64734299516908,
      "grad_norm": 2.921318769454956,
      "learning_rate": 8.997000000000001e-05,
      "loss": 2.9533,
      "step": 36000
    },
    {
      "epoch": 38.64734299516908,
      "eval_loss": 3.5649592876434326,
      "eval_runtime": 0.7607,
      "eval_samples_per_second": 1409.149,
      "eval_steps_per_second": 88.072,
      "step": 36000
    },
    {
      "epoch": 40.794417606011805,
      "eval_loss": 3.5666539669036865,
      "eval_runtime": 0.7558,
      "eval_samples_per_second": 1418.297,
      "eval_steps_per_second": 88.644,
      "step": 38000
    },
    {
      "epoch": 42.941492216854535,
      "grad_norm": 3.202237129211426,
      "learning_rate": 9.996500000000001e-05,
      "loss": 2.777,
      "step": 40000
    },
    {
      "epoch": 42.941492216854535,
      "eval_loss": 3.5746841430664062,
      "eval_runtime": 0.7722,
      "eval_samples_per_second": 1388.315,
      "eval_steps_per_second": 86.77,
      "step": 40000
    },
    {
      "epoch": 45.088566827697264,
      "eval_loss": 3.5878281593322754,
      "eval_runtime": 0.7639,
      "eval_samples_per_second": 1403.298,
      "eval_steps_per_second": 87.706,
      "step": 42000
    },
    {
      "epoch": 47.235641438539986,
      "grad_norm": 2.9902379512786865,
      "learning_rate": 9.336e-05,
      "loss": 2.6015,
      "step": 44000
    },
    {
      "epoch": 47.235641438539986,
      "eval_loss": 3.6107263565063477,
      "eval_runtime": 0.7601,
      "eval_samples_per_second": 1410.262,
      "eval_steps_per_second": 88.141,
      "step": 44000
    },
    {
      "epoch": 49.382716049382715,
      "eval_loss": 3.6260793209075928,
      "eval_runtime": 0.7605,
      "eval_samples_per_second": 1409.681,
      "eval_steps_per_second": 88.105,
      "step": 46000
    },
    {
      "epoch": 51.529790660225444,
      "grad_norm": 3.1626901626586914,
      "learning_rate": 8.669833333333334e-05,
      "loss": 2.4429,
      "step": 48000
    },
    {
      "epoch": 51.529790660225444,
      "eval_loss": 3.6414248943328857,
      "eval_runtime": 0.7596,
      "eval_samples_per_second": 1411.254,
      "eval_steps_per_second": 88.203,
      "step": 48000
    },
    {
      "epoch": 53.676865271068166,
      "eval_loss": 3.6636786460876465,
      "eval_runtime": 0.7637,
      "eval_samples_per_second": 1403.705,
      "eval_steps_per_second": 87.732,
      "step": 50000
    },
    {
      "epoch": 55.823939881910896,
      "grad_norm": 3.162830114364624,
      "learning_rate": 8.003333333333333e-05,
      "loss": 2.3125,
      "step": 52000
    },
    {
      "epoch": 55.823939881910896,
      "eval_loss": 3.6777544021606445,
      "eval_runtime": 0.7597,
      "eval_samples_per_second": 1411.137,
      "eval_steps_per_second": 88.196,
      "step": 52000
    },
    {
      "epoch": 57.971014492753625,
      "eval_loss": 3.703284502029419,
      "eval_runtime": 0.757,
      "eval_samples_per_second": 1416.089,
      "eval_steps_per_second": 88.506,
      "step": 54000
    },
    {
      "epoch": 60.11808910359635,
      "grad_norm": 3.4666566848754883,
      "learning_rate": 7.337000000000001e-05,
      "loss": 2.1989,
      "step": 56000
    },
    {
      "epoch": 60.11808910359635,
      "eval_loss": 3.7409818172454834,
      "eval_runtime": 0.7476,
      "eval_samples_per_second": 1433.993,
      "eval_steps_per_second": 89.625,
      "step": 56000
    },
    {
      "epoch": 62.265163714439076,
      "eval_loss": 3.7754786014556885,
      "eval_runtime": 0.7506,
      "eval_samples_per_second": 1428.237,
      "eval_steps_per_second": 89.265,
      "step": 58000
    },
    {
      "epoch": 64.4122383252818,
      "grad_norm": 3.3885388374328613,
      "learning_rate": 6.670666666666668e-05,
      "loss": 2.1044,
      "step": 60000
    },
    {
      "epoch": 64.4122383252818,
      "eval_loss": 3.7875912189483643,
      "eval_runtime": 0.7543,
      "eval_samples_per_second": 1421.139,
      "eval_steps_per_second": 88.821,
      "step": 60000
    },
    {
      "epoch": 66.55931293612453,
      "eval_loss": 3.8081138134002686,
      "eval_runtime": 0.7633,
      "eval_samples_per_second": 1404.466,
      "eval_steps_per_second": 87.779,
      "step": 62000
    },
    {
      "epoch": 68.70638754696726,
      "grad_norm": 3.763136148452759,
      "learning_rate": 6.004333333333334e-05,
      "loss": 2.0257,
      "step": 64000
    },
    {
      "epoch": 68.70638754696726,
      "eval_loss": 3.822213649749756,
      "eval_runtime": 0.7598,
      "eval_samples_per_second": 1410.912,
      "eval_steps_per_second": 88.182,
      "step": 64000
    }
  ],
  "logging_steps": 4000,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 108,
  "save_steps": 4000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6543844929634304e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}