{
  "best_global_step": 1400,
  "best_metric": 1.6602575778961182,
  "best_model_checkpoint": "outputs/checkpoint-1400",
  "epoch": 1.0027855153203342,
  "eval_steps": 200,
  "global_step": 1800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.027855153203342618,
      "grad_norm": 28.48779296875,
      "learning_rate": 9.090909090909091e-07,
      "loss": 6.8261,
      "step": 50
    },
    {
      "epoch": 0.055710306406685235,
      "grad_norm": 16.59324836730957,
      "learning_rate": 1.8367346938775512e-06,
      "loss": 5.5246,
      "step": 100
    },
    {
      "epoch": 0.08356545961002786,
      "grad_norm": 10.027810096740723,
      "learning_rate": 2.764378478664193e-06,
      "loss": 3.4,
      "step": 150
    },
    {
      "epoch": 0.11142061281337047,
      "grad_norm": 16.358600616455078,
      "learning_rate": 3.6920222634508353e-06,
      "loss": 2.6641,
      "step": 200
    },
    {
      "epoch": 0.11142061281337047,
      "eval_loss": 2.535517454147339,
      "eval_runtime": 58.8724,
      "eval_samples_per_second": 46.355,
      "eval_steps_per_second": 5.809,
      "step": 200
    },
    {
      "epoch": 0.1392757660167131,
      "grad_norm": 7.62955904006958,
      "learning_rate": 4.619666048237477e-06,
      "loss": 2.4208,
      "step": 250
    },
    {
      "epoch": 0.1671309192200557,
      "grad_norm": 5.676515579223633,
      "learning_rate": 5.547309833024119e-06,
      "loss": 2.2272,
      "step": 300
    },
    {
      "epoch": 0.19498607242339833,
      "grad_norm": 6.469155788421631,
      "learning_rate": 6.474953617810761e-06,
      "loss": 2.0871,
      "step": 350
    },
    {
      "epoch": 0.22284122562674094,
      "grad_norm": 6.341733455657959,
      "learning_rate": 7.402597402597404e-06,
      "loss": 1.9703,
      "step": 400
    },
    {
      "epoch": 0.22284122562674094,
      "eval_loss": 1.9659122228622437,
      "eval_runtime": 56.3654,
      "eval_samples_per_second": 48.416,
      "eval_steps_per_second": 6.068,
      "step": 400
    },
    {
      "epoch": 0.25069637883008355,
      "grad_norm": 7.506978511810303,
      "learning_rate": 8.330241187384045e-06,
      "loss": 1.8903,
      "step": 450
    },
    {
      "epoch": 0.2785515320334262,
      "grad_norm": 5.684309959411621,
      "learning_rate": 9.257884972170687e-06,
      "loss": 1.8074,
      "step": 500
    },
    {
      "epoch": 0.3064066852367688,
      "grad_norm": 4.537693977355957,
      "learning_rate": 9.999894931770648e-06,
      "loss": 1.7854,
      "step": 550
    },
    {
      "epoch": 0.3342618384401114,
      "grad_norm": 24.553997039794922,
      "learning_rate": 9.996218007374501e-06,
      "loss": 1.7252,
      "step": 600
    },
    {
      "epoch": 0.3342618384401114,
      "eval_loss": 1.74297034740448,
      "eval_runtime": 59.9228,
      "eval_samples_per_second": 45.542,
      "eval_steps_per_second": 5.707,
      "step": 600
    },
    {
      "epoch": 0.362116991643454,
      "grad_norm": 4.550091743469238,
      "learning_rate": 9.987292086409739e-06,
      "loss": 1.6874,
      "step": 650
    },
    {
      "epoch": 0.38997214484679665,
      "grad_norm": 4.49098014831543,
      "learning_rate": 9.973126546395205e-06,
      "loss": 1.6982,
      "step": 700
    },
    {
      "epoch": 0.4178272980501393,
      "grad_norm": 5.295725345611572,
      "learning_rate": 9.953736269561984e-06,
      "loss": 1.6394,
      "step": 750
    },
    {
      "epoch": 0.4456824512534819,
      "grad_norm": 5.552262306213379,
      "learning_rate": 9.929141627218212e-06,
      "loss": 1.6033,
      "step": 800
    },
    {
      "epoch": 0.4456824512534819,
      "eval_loss": 1.6921230554580688,
      "eval_runtime": 59.5066,
      "eval_samples_per_second": 45.86,
      "eval_steps_per_second": 5.747,
      "step": 800
    },
    {
      "epoch": 0.4735376044568245,
      "grad_norm": 7.223403453826904,
      "learning_rate": 9.899368458347117e-06,
      "loss": 1.6089,
      "step": 850
    },
    {
      "epoch": 0.5013927576601671,
      "grad_norm": 4.941762924194336,
      "learning_rate": 9.86444804246072e-06,
      "loss": 1.5874,
      "step": 900
    },
    {
      "epoch": 0.5292479108635098,
      "grad_norm": 6.057460784912109,
      "learning_rate": 9.824417066737782e-06,
      "loss": 1.5895,
      "step": 950
    },
    {
      "epoch": 0.5571030640668524,
      "grad_norm": 6.217402935028076,
      "learning_rate": 9.779317587480471e-06,
      "loss": 1.5377,
      "step": 1000
    },
    {
      "epoch": 0.5571030640668524,
      "eval_loss": 1.6874749660491943,
      "eval_runtime": 59.8971,
      "eval_samples_per_second": 45.561,
      "eval_steps_per_second": 5.71,
      "step": 1000
    },
    {
      "epoch": 0.584958217270195,
      "grad_norm": 6.518588542938232,
      "learning_rate": 9.729196985930261e-06,
      "loss": 1.5332,
      "step": 1050
    },
    {
      "epoch": 0.6128133704735376,
      "grad_norm": 5.452282905578613,
      "learning_rate": 9.674107918489489e-06,
      "loss": 1.515,
      "step": 1100
    },
    {
      "epoch": 0.6406685236768802,
      "grad_norm": 5.754498481750488,
      "learning_rate": 9.61410826140085e-06,
      "loss": 1.5108,
      "step": 1150
    },
    {
      "epoch": 0.6685236768802229,
      "grad_norm": 5.382887840270996,
      "learning_rate": 9.549261049942972e-06,
      "loss": 1.4732,
      "step": 1200
    },
    {
      "epoch": 0.6685236768802229,
      "eval_loss": 1.6714078187942505,
      "eval_runtime": 58.2937,
      "eval_samples_per_second": 46.815,
      "eval_steps_per_second": 5.867,
      "step": 1200
    },
    {
      "epoch": 0.6963788300835655,
      "grad_norm": 5.8490891456604,
      "learning_rate": 9.479634412205929e-06,
      "loss": 1.4491,
      "step": 1250
    },
    {
      "epoch": 0.724233983286908,
      "grad_norm": 6.567768096923828,
      "learning_rate": 9.405301497516274e-06,
      "loss": 1.4845,
      "step": 1300
    },
    {
      "epoch": 0.7520891364902507,
      "grad_norm": 6.346134662628174,
      "learning_rate": 9.326340399586805e-06,
      "loss": 1.4787,
      "step": 1350
    },
    {
      "epoch": 0.7799442896935933,
      "grad_norm": 6.748211860656738,
      "learning_rate": 9.24283407447178e-06,
      "loss": 1.47,
      "step": 1400
    },
    {
      "epoch": 0.7799442896935933,
      "eval_loss": 1.6602575778961182,
      "eval_runtime": 61.3099,
      "eval_samples_per_second": 44.512,
      "eval_steps_per_second": 5.578,
      "step": 1400
    },
    {
      "epoch": 0.807799442896936,
      "grad_norm": 6.448507308959961,
      "learning_rate": 9.154870253413776e-06,
      "loss": 1.3974,
      "step": 1450
    },
    {
      "epoch": 0.8356545961002786,
      "grad_norm": 6.654584884643555,
      "learning_rate": 9.062541350673782e-06,
      "loss": 1.3915,
      "step": 1500
    },
    {
      "epoch": 0.8635097493036211,
      "grad_norm": 7.59186315536499,
      "learning_rate": 8.965944366441332e-06,
      "loss": 1.3932,
      "step": 1550
    },
    {
      "epoch": 0.8913649025069638,
      "grad_norm": 7.587399005889893,
      "learning_rate": 8.86518078492669e-06,
      "loss": 1.3702,
      "step": 1600
    },
    {
      "epoch": 0.8913649025069638,
      "eval_loss": 1.6901545524597168,
      "eval_runtime": 58.7741,
      "eval_samples_per_second": 46.432,
      "eval_steps_per_second": 5.819,
      "step": 1600
    },
    {
      "epoch": 0.9192200557103064,
      "grad_norm": 8.80136489868164,
      "learning_rate": 8.760356467742144e-06,
      "loss": 1.3641,
      "step": 1650
    },
    {
      "epoch": 0.947075208913649,
      "grad_norm": 7.431648254394531,
      "learning_rate": 8.651581542684438e-06,
      "loss": 1.3336,
      "step": 1700
    },
    {
      "epoch": 0.9749303621169917,
      "grad_norm": 13.54917049407959,
      "learning_rate": 8.538970288035174e-06,
      "loss": 1.3335,
      "step": 1750
    },
    {
      "epoch": 1.0027855153203342,
      "grad_norm": 7.557823657989502,
      "learning_rate": 8.42264101250073e-06,
      "loss": 1.2826,
      "step": 1800
    },
    {
      "epoch": 1.0027855153203342,
      "eval_loss": 1.6702473163604736,
      "eval_runtime": 61.0186,
      "eval_samples_per_second": 44.724,
      "eval_steps_per_second": 5.605,
      "step": 1800
    }
  ],
  "logging_steps": 50,
  "max_steps": 5385,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.19765988253696e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}