trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.045882083046570314,
  "eval_steps": 5,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011470520761642578,
      "eval_loss": 2.755366325378418,
      "eval_runtime": 14.0088,
      "eval_samples_per_second": 469.989,
      "eval_steps_per_second": 3.712,
      "step": 5
    },
    {
      "epoch": 0.0022941041523285156,
      "eval_loss": 2.750617027282715,
      "eval_runtime": 14.0654,
      "eval_samples_per_second": 468.099,
      "eval_steps_per_second": 3.697,
      "step": 10
    },
    {
      "epoch": 0.0034411562284927736,
      "eval_loss": 2.7424304485321045,
      "eval_runtime": 14.1186,
      "eval_samples_per_second": 466.336,
      "eval_steps_per_second": 3.683,
      "step": 15
    },
    {
      "epoch": 0.004588208304657031,
      "eval_loss": 2.730889081954956,
      "eval_runtime": 14.2451,
      "eval_samples_per_second": 462.193,
      "eval_steps_per_second": 3.65,
      "step": 20
    },
    {
      "epoch": 0.005735260380821289,
      "eval_loss": 2.7159576416015625,
      "eval_runtime": 14.245,
      "eval_samples_per_second": 462.199,
      "eval_steps_per_second": 3.65,
      "step": 25
    },
    {
      "epoch": 0.006882312456985547,
      "eval_loss": 2.6975343227386475,
      "eval_runtime": 14.3448,
      "eval_samples_per_second": 458.981,
      "eval_steps_per_second": 3.625,
      "step": 30
    },
    {
      "epoch": 0.008029364533149804,
      "eval_loss": 2.675693988800049,
      "eval_runtime": 16.965,
      "eval_samples_per_second": 388.094,
      "eval_steps_per_second": 3.065,
      "step": 35
    },
    {
      "epoch": 0.009176416609314062,
      "eval_loss": 2.650242328643799,
      "eval_runtime": 14.2414,
      "eval_samples_per_second": 462.315,
      "eval_steps_per_second": 3.651,
      "step": 40
    },
    {
      "epoch": 0.01032346868547832,
      "eval_loss": 2.6213560104370117,
      "eval_runtime": 14.4168,
      "eval_samples_per_second": 456.689,
      "eval_steps_per_second": 3.607,
      "step": 45
    },
    {
      "epoch": 0.011470520761642579,
      "eval_loss": 2.5892951488494873,
      "eval_runtime": 14.3332,
      "eval_samples_per_second": 459.353,
      "eval_steps_per_second": 3.628,
      "step": 50
    },
    {
      "epoch": 0.012617572837806837,
      "eval_loss": 2.5538384914398193,
      "eval_runtime": 14.4067,
      "eval_samples_per_second": 457.01,
      "eval_steps_per_second": 3.609,
      "step": 55
    },
    {
      "epoch": 0.013764624913971095,
      "eval_loss": 2.51452374458313,
      "eval_runtime": 14.4948,
      "eval_samples_per_second": 454.233,
      "eval_steps_per_second": 3.588,
      "step": 60
    },
    {
      "epoch": 0.014911676990135353,
      "eval_loss": 2.4726295471191406,
      "eval_runtime": 14.3162,
      "eval_samples_per_second": 459.898,
      "eval_steps_per_second": 3.632,
      "step": 65
    },
    {
      "epoch": 0.01605872906629961,
      "eval_loss": 2.428196668624878,
      "eval_runtime": 14.3204,
      "eval_samples_per_second": 459.763,
      "eval_steps_per_second": 3.631,
      "step": 70
    },
    {
      "epoch": 0.017205781142463867,
      "eval_loss": 2.379453659057617,
      "eval_runtime": 14.3796,
      "eval_samples_per_second": 457.872,
      "eval_steps_per_second": 3.616,
      "step": 75
    },
    {
      "epoch": 0.018352833218628125,
      "eval_loss": 2.327221393585205,
      "eval_runtime": 14.3415,
      "eval_samples_per_second": 459.089,
      "eval_steps_per_second": 3.626,
      "step": 80
    },
    {
      "epoch": 0.019499885294792383,
      "eval_loss": 2.2712388038635254,
      "eval_runtime": 14.462,
      "eval_samples_per_second": 455.263,
      "eval_steps_per_second": 3.596,
      "step": 85
    },
    {
      "epoch": 0.02064693737095664,
      "eval_loss": 2.2120068073272705,
      "eval_runtime": 14.334,
      "eval_samples_per_second": 459.326,
      "eval_steps_per_second": 3.628,
      "step": 90
    },
    {
      "epoch": 0.0217939894471209,
      "eval_loss": 2.1501331329345703,
      "eval_runtime": 14.3506,
      "eval_samples_per_second": 458.796,
      "eval_steps_per_second": 3.624,
      "step": 95
    },
    {
      "epoch": 0.022941041523285157,
      "grad_norm": 19.895355224609375,
      "learning_rate": 7.645259938837921e-07,
      "loss": 3.6197,
      "step": 100
    },
    {
      "epoch": 0.022941041523285157,
      "eval_loss": 2.086596727371216,
      "eval_runtime": 16.6465,
      "eval_samples_per_second": 395.519,
      "eval_steps_per_second": 3.124,
      "step": 100
    },
    {
      "epoch": 0.024088093599449415,
      "eval_loss": 2.0223236083984375,
      "eval_runtime": 14.471,
      "eval_samples_per_second": 454.979,
      "eval_steps_per_second": 3.593,
      "step": 105
    },
    {
      "epoch": 0.025235145675613673,
      "eval_loss": 1.9571231603622437,
      "eval_runtime": 14.3783,
      "eval_samples_per_second": 457.913,
      "eval_steps_per_second": 3.617,
      "step": 110
    },
    {
      "epoch": 0.02638219775177793,
      "eval_loss": 1.890655517578125,
      "eval_runtime": 14.288,
      "eval_samples_per_second": 460.805,
      "eval_steps_per_second": 3.639,
      "step": 115
    },
    {
      "epoch": 0.02752924982794219,
      "eval_loss": 1.823920488357544,
      "eval_runtime": 14.3764,
      "eval_samples_per_second": 457.972,
      "eval_steps_per_second": 3.617,
      "step": 120
    },
    {
      "epoch": 0.028676301904106447,
      "eval_loss": 1.758331298828125,
      "eval_runtime": 14.2666,
      "eval_samples_per_second": 461.499,
      "eval_steps_per_second": 3.645,
      "step": 125
    },
    {
      "epoch": 0.029823353980270705,
      "eval_loss": 1.6937522888183594,
      "eval_runtime": 14.2522,
      "eval_samples_per_second": 461.963,
      "eval_steps_per_second": 3.649,
      "step": 130
    },
    {
      "epoch": 0.030970406056434963,
      "eval_loss": 1.6316019296646118,
      "eval_runtime": 16.3104,
      "eval_samples_per_second": 403.67,
      "eval_steps_per_second": 3.188,
      "step": 135
    },
    {
      "epoch": 0.03211745813259922,
      "eval_loss": 1.571895718574524,
      "eval_runtime": 14.2422,
      "eval_samples_per_second": 462.288,
      "eval_steps_per_second": 3.651,
      "step": 140
    },
    {
      "epoch": 0.033264510208763476,
      "eval_loss": 1.5148202180862427,
      "eval_runtime": 14.3624,
      "eval_samples_per_second": 458.418,
      "eval_steps_per_second": 3.621,
      "step": 145
    },
    {
      "epoch": 0.034411562284927734,
      "eval_loss": 1.459762454032898,
      "eval_runtime": 14.3035,
      "eval_samples_per_second": 460.308,
      "eval_steps_per_second": 3.635,
      "step": 150
    },
    {
      "epoch": 0.03555861436109199,
      "eval_loss": 1.4081143140792847,
      "eval_runtime": 14.2988,
      "eval_samples_per_second": 460.46,
      "eval_steps_per_second": 3.637,
      "step": 155
    },
    {
      "epoch": 0.03670566643725625,
      "eval_loss": 1.3612124919891357,
      "eval_runtime": 14.2569,
      "eval_samples_per_second": 461.812,
      "eval_steps_per_second": 3.647,
      "step": 160
    },
    {
      "epoch": 0.03785271851342051,
      "eval_loss": 1.318212866783142,
      "eval_runtime": 14.282,
      "eval_samples_per_second": 460.999,
      "eval_steps_per_second": 3.641,
      "step": 165
    },
    {
      "epoch": 0.038999770589584766,
      "eval_loss": 1.2802687883377075,
      "eval_runtime": 14.4058,
      "eval_samples_per_second": 457.038,
      "eval_steps_per_second": 3.61,
      "step": 170
    },
    {
      "epoch": 0.040146822665749024,
      "eval_loss": 1.246294617652893,
      "eval_runtime": 14.2804,
      "eval_samples_per_second": 461.051,
      "eval_steps_per_second": 3.641,
      "step": 175
    },
    {
      "epoch": 0.04129387474191328,
      "eval_loss": 1.2160167694091797,
      "eval_runtime": 14.3449,
      "eval_samples_per_second": 458.977,
      "eval_steps_per_second": 3.625,
      "step": 180
    },
    {
      "epoch": 0.04244092681807754,
      "eval_loss": 1.189509630203247,
      "eval_runtime": 14.2361,
      "eval_samples_per_second": 462.486,
      "eval_steps_per_second": 3.653,
      "step": 185
    },
    {
      "epoch": 0.0435879788942418,
      "eval_loss": 1.1653709411621094,
      "eval_runtime": 14.3748,
      "eval_samples_per_second": 458.025,
      "eval_steps_per_second": 3.617,
      "step": 190
    },
    {
      "epoch": 0.044735030970406056,
      "eval_loss": 1.143513798713684,
      "eval_runtime": 14.25,
      "eval_samples_per_second": 462.035,
      "eval_steps_per_second": 3.649,
      "step": 195
    },
    {
      "epoch": 0.045882083046570314,
      "grad_norm": 8.192963600158691,
      "learning_rate": 1.5290519877675841e-06,
      "loss": 2.292,
      "step": 200
    },
    {
      "epoch": 0.045882083046570314,
      "eval_loss": 1.1239805221557617,
      "eval_runtime": 16.3012,
      "eval_samples_per_second": 403.896,
      "eval_steps_per_second": 3.19,
      "step": 200
    }
  ],
  "logging_steps": 100,
  "max_steps": 13077,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}