{
  "best_metric": 0.04320823773741722,
  "best_model_checkpoint": "./xlam_lora_new_1024_2_delete_over_size_3epoch/checkpoint-789",
  "epoch": 1.000316906987799,
  "eval_steps": 263,
  "global_step": 789,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02535255902392648,
      "grad_norm": 0.515038788318634,
      "learning_rate": 5.633802816901409e-06,
      "loss": 0.4826,
      "step": 20
    },
    {
      "epoch": 0.05070511804785296,
      "grad_norm": 1.2124691009521484,
      "learning_rate": 1.1267605633802819e-05,
      "loss": 0.337,
      "step": 40
    },
    {
      "epoch": 0.07605767707177943,
      "grad_norm": 0.562520444393158,
      "learning_rate": 1.6901408450704228e-05,
      "loss": 0.1167,
      "step": 60
    },
    {
      "epoch": 0.10141023609570592,
      "grad_norm": 0.1530018150806427,
      "learning_rate": 1.9999239776734535e-05,
      "loss": 0.0444,
      "step": 80
    },
    {
      "epoch": 0.1267627951196324,
      "grad_norm": 0.43701356649398804,
      "learning_rate": 1.9992107756032603e-05,
      "loss": 0.0941,
      "step": 100
    },
    {
      "epoch": 0.15211535414355887,
      "grad_norm": 0.26956745982170105,
      "learning_rate": 1.997747365756147e-05,
      "loss": 0.0722,
      "step": 120
    },
    {
      "epoch": 0.17746791316748534,
      "grad_norm": 0.38304299116134644,
      "learning_rate": 1.995534846860705e-05,
      "loss": 0.0664,
      "step": 140
    },
    {
      "epoch": 0.20282047219141183,
      "grad_norm": 0.24561983346939087,
      "learning_rate": 1.9925748800768444e-05,
      "loss": 0.0474,
      "step": 160
    },
    {
      "epoch": 0.2281730312153383,
      "grad_norm": 0.26263824105262756,
      "learning_rate": 1.9888696877485937e-05,
      "loss": 0.0364,
      "step": 180
    },
    {
      "epoch": 0.2535255902392648,
      "grad_norm": 0.2551981210708618,
      "learning_rate": 1.984422051735564e-05,
      "loss": 0.0276,
      "step": 200
    },
    {
      "epoch": 0.27887814926319127,
      "grad_norm": 0.16999328136444092,
      "learning_rate": 1.979235311324328e-05,
      "loss": 0.039,
      "step": 220
    },
    {
      "epoch": 0.30423070828711773,
      "grad_norm": 0.2080262005329132,
      "learning_rate": 1.973313360721281e-05,
      "loss": 0.0353,
      "step": 240
    },
    {
      "epoch": 0.3295832673110442,
      "grad_norm": 0.19375990331172943,
      "learning_rate": 1.9666606461288728e-05,
      "loss": 0.0509,
      "step": 260
    },
    {
      "epoch": 0.33338615116463316,
      "eval_loss": 0.04866104573011398,
      "eval_runtime": 144.4235,
      "eval_samples_per_second": 4.618,
      "eval_steps_per_second": 2.313,
      "step": 263
    },
    {
      "epoch": 0.35493582633497067,
      "grad_norm": 0.3100409209728241,
      "learning_rate": 1.959282162407392e-05,
      "loss": 0.0317,
      "step": 280
    },
    {
      "epoch": 0.38028838535889714,
      "grad_norm": 0.49380865693092346,
      "learning_rate": 1.9511834493248303e-05,
      "loss": 0.0513,
      "step": 300
    },
    {
      "epoch": 0.40564094438282366,
      "grad_norm": 0.18333816528320312,
      "learning_rate": 1.9423705873976156e-05,
      "loss": 0.0449,
      "step": 320
    },
    {
      "epoch": 0.43099350340675013,
      "grad_norm": 0.3562432825565338,
      "learning_rate": 1.9328501933253643e-05,
      "loss": 0.028,
      "step": 340
    },
    {
      "epoch": 0.4563460624306766,
      "grad_norm": 0.341875821352005,
      "learning_rate": 1.9226294150230573e-05,
      "loss": 0.0361,
      "step": 360
    },
    {
      "epoch": 0.48169862145460307,
      "grad_norm": 0.259799987077713,
      "learning_rate": 1.9117159262543844e-05,
      "loss": 0.0454,
      "step": 380
    },
    {
      "epoch": 0.5070511804785296,
      "grad_norm": 0.4206746518611908,
      "learning_rate": 1.9001179208702812e-05,
      "loss": 0.0333,
      "step": 400
    },
    {
      "epoch": 0.532403739502456,
      "grad_norm": 0.3466087877750397,
      "learning_rate": 1.88784410665698e-05,
      "loss": 0.0292,
      "step": 420
    },
    {
      "epoch": 0.5577562985263825,
      "grad_norm": 0.5302783846855164,
      "learning_rate": 1.8749036987982047e-05,
      "loss": 0.0319,
      "step": 440
    },
    {
      "epoch": 0.583108857550309,
      "grad_norm": 0.3487597107887268,
      "learning_rate": 1.861306412956404e-05,
      "loss": 0.037,
      "step": 460
    },
    {
      "epoch": 0.6084614165742355,
      "grad_norm": 0.4753687381744385,
      "learning_rate": 1.8470624579782338e-05,
      "loss": 0.029,
      "step": 480
    },
    {
      "epoch": 0.633813975598162,
      "grad_norm": 0.20097890496253967,
      "learning_rate": 1.8321825282297467e-05,
      "loss": 0.0432,
      "step": 500
    },
    {
      "epoch": 0.6591665346220884,
      "grad_norm": 0.33282265067100525,
      "learning_rate": 1.8166777955670616e-05,
      "loss": 0.0414,
      "step": 520
    },
    {
      "epoch": 0.6667723023292663,
      "eval_loss": 0.045147210359573364,
      "eval_runtime": 144.4317,
      "eval_samples_per_second": 4.618,
      "eval_steps_per_second": 2.313,
      "step": 526
    },
    {
      "epoch": 0.6845190936460149,
      "grad_norm": 0.17276500165462494,
      "learning_rate": 1.800559900948529e-05,
      "loss": 0.046,
      "step": 540
    },
    {
      "epoch": 0.7098716526699413,
      "grad_norm": 0.17020255327224731,
      "learning_rate": 1.7838409456946973e-05,
      "loss": 0.0273,
      "step": 560
    },
    {
      "epoch": 0.7352242116938679,
      "grad_norm": 0.09968056529760361,
      "learning_rate": 1.7665334824026358e-05,
      "loss": 0.0265,
      "step": 580
    },
    {
      "epoch": 0.7605767707177943,
      "grad_norm": 0.3242018520832062,
      "learning_rate": 1.7486505055214405e-05,
      "loss": 0.0269,
      "step": 600
    },
    {
      "epoch": 0.7859293297417208,
      "grad_norm": 0.2690919041633606,
      "learning_rate": 1.7302054415959994e-05,
      "loss": 0.0247,
      "step": 620
    },
    {
      "epoch": 0.8112818887656473,
      "grad_norm": 0.5220848321914673,
      "learning_rate": 1.7112121391863367e-05,
      "loss": 0.0389,
      "step": 640
    },
    {
      "epoch": 0.8366344477895737,
      "grad_norm": 0.26270976662635803,
      "learning_rate": 1.6916848584701092e-05,
      "loss": 0.0281,
      "step": 660
    },
    {
      "epoch": 0.8619870068135003,
      "grad_norm": 0.32137855887413025,
      "learning_rate": 1.671638260536062e-05,
      "loss": 0.0365,
      "step": 680
    },
    {
      "epoch": 0.8873395658374267,
      "grad_norm": 0.5726165175437927,
      "learning_rate": 1.6510873963764754e-05,
      "loss": 0.0468,
      "step": 700
    },
    {
      "epoch": 0.9126921248613532,
      "grad_norm": 0.7382823824882507,
      "learning_rate": 1.6300476955868785e-05,
      "loss": 0.0365,
      "step": 720
    },
    {
      "epoch": 0.9380446838852796,
      "grad_norm": 0.3500744104385376,
      "learning_rate": 1.6085349547815002e-05,
      "loss": 0.027,
      "step": 740
    },
    {
      "epoch": 0.9633972429092061,
      "grad_norm": 0.2678811252117157,
      "learning_rate": 1.5865653257331697e-05,
      "loss": 0.0483,
      "step": 760
    },
    {
      "epoch": 0.9887498019331327,
      "grad_norm": 0.22900326550006866,
      "learning_rate": 1.564155303246556e-05,
      "loss": 0.0508,
      "step": 780
    },
    {
      "epoch": 1.000316906987799,
      "eval_loss": 0.04320823773741722,
      "eval_runtime": 144.4268,
      "eval_samples_per_second": 4.618,
      "eval_steps_per_second": 2.313,
      "step": 789
    }
  ],
  "logging_steps": 20,
  "max_steps": 2364,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 263,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.876643611330478e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}