{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.23598820058997,
  "eval_steps": 50,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11799410029498525,
      "grad_norm": 2.4879140853881836,
      "learning_rate": 0.0003,
      "loss": 1.8567,
      "step": 10
    },
    {
      "epoch": 0.2359882005899705,
      "grad_norm": 0.8311281204223633,
      "learning_rate": 0.0002963855421686747,
      "loss": 1.3245,
      "step": 20
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 0.6665307879447937,
      "learning_rate": 0.0002927710843373494,
      "loss": 1.1834,
      "step": 30
    },
    {
      "epoch": 0.471976401179941,
      "grad_norm": 0.5632417798042297,
      "learning_rate": 0.0002891566265060241,
      "loss": 1.0915,
      "step": 40
    },
    {
      "epoch": 0.5899705014749262,
      "grad_norm": 0.4381982684135437,
      "learning_rate": 0.00028554216867469873,
      "loss": 1.0438,
      "step": 50
    },
    {
      "epoch": 0.5899705014749262,
      "eval_loss": 1.0292344093322754,
      "eval_runtime": 20.4608,
      "eval_samples_per_second": 8.015,
      "eval_steps_per_second": 0.684,
      "step": 50
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.43256932497024536,
      "learning_rate": 0.0002819277108433735,
      "loss": 1.0156,
      "step": 60
    },
    {
      "epoch": 0.8259587020648967,
      "grad_norm": 0.3582414388656616,
      "learning_rate": 0.0002783132530120482,
      "loss": 0.9793,
      "step": 70
    },
    {
      "epoch": 0.943952802359882,
      "grad_norm": 0.3671708405017853,
      "learning_rate": 0.00027469879518072284,
      "loss": 0.9644,
      "step": 80
    },
    {
      "epoch": 1.0589970501474926,
      "grad_norm": 0.34048739075660706,
      "learning_rate": 0.0002710843373493976,
      "loss": 0.9173,
      "step": 90
    },
    {
      "epoch": 1.176991150442478,
      "grad_norm": 0.29820743203163147,
      "learning_rate": 0.00026746987951807225,
      "loss": 0.8913,
      "step": 100
    },
    {
      "epoch": 1.176991150442478,
      "eval_loss": 0.9288875460624695,
      "eval_runtime": 20.3929,
      "eval_samples_per_second": 8.042,
      "eval_steps_per_second": 0.687,
      "step": 100
    },
    {
      "epoch": 1.294985250737463,
      "grad_norm": 0.31813672184944153,
      "learning_rate": 0.00026385542168674695,
      "loss": 0.8801,
      "step": 110
    },
    {
      "epoch": 1.4129793510324484,
      "grad_norm": 0.2814970016479492,
      "learning_rate": 0.00026024096385542165,
      "loss": 0.875,
      "step": 120
    },
    {
      "epoch": 1.5309734513274336,
      "grad_norm": 0.2815490663051605,
      "learning_rate": 0.00025662650602409636,
      "loss": 0.8642,
      "step": 130
    },
    {
      "epoch": 1.648967551622419,
      "grad_norm": 0.2590789198875427,
      "learning_rate": 0.00025301204819277106,
      "loss": 0.8501,
      "step": 140
    },
    {
      "epoch": 1.7669616519174043,
      "grad_norm": 0.25773778557777405,
      "learning_rate": 0.00024939759036144576,
      "loss": 0.8487,
      "step": 150
    },
    {
      "epoch": 1.7669616519174043,
      "eval_loss": 0.8774459362030029,
      "eval_runtime": 20.4395,
      "eval_samples_per_second": 8.024,
      "eval_steps_per_second": 0.685,
      "step": 150
    },
    {
      "epoch": 1.8849557522123894,
      "grad_norm": 0.2629424035549164,
      "learning_rate": 0.00024578313253012046,
      "loss": 0.8427,
      "step": 160
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2865707278251648,
      "learning_rate": 0.00024216867469879517,
      "loss": 0.8258,
      "step": 170
    },
    {
      "epoch": 2.117994100294985,
      "grad_norm": 0.27073633670806885,
      "learning_rate": 0.00023855421686746987,
      "loss": 0.7835,
      "step": 180
    },
    {
      "epoch": 2.2359882005899703,
      "grad_norm": 0.2692751884460449,
      "learning_rate": 0.00023493975903614455,
      "loss": 0.7804,
      "step": 190
    },
    {
      "epoch": 2.353982300884956,
      "grad_norm": 0.2548248767852783,
      "learning_rate": 0.00023132530120481928,
      "loss": 0.7756,
      "step": 200
    },
    {
      "epoch": 2.353982300884956,
      "eval_loss": 0.8462932109832764,
      "eval_runtime": 20.4134,
      "eval_samples_per_second": 8.034,
      "eval_steps_per_second": 0.686,
      "step": 200
    },
    {
      "epoch": 2.471976401179941,
      "grad_norm": 0.21938325464725494,
      "learning_rate": 0.00022771084337349395,
      "loss": 0.7695,
      "step": 210
    },
    {
      "epoch": 2.589970501474926,
      "grad_norm": 0.23754891753196716,
      "learning_rate": 0.00022409638554216866,
      "loss": 0.7771,
      "step": 220
    },
    {
      "epoch": 2.7079646017699117,
      "grad_norm": 0.2382248044013977,
      "learning_rate": 0.00022048192771084336,
      "loss": 0.7672,
      "step": 230
    },
    {
      "epoch": 2.825958702064897,
      "grad_norm": 0.2536454200744629,
      "learning_rate": 0.00021686746987951806,
      "loss": 0.7645,
      "step": 240
    },
    {
      "epoch": 2.943952802359882,
      "grad_norm": 0.21255475282669067,
      "learning_rate": 0.00021325301204819274,
      "loss": 0.7667,
      "step": 250
    },
    {
      "epoch": 2.943952802359882,
      "eval_loss": 0.8220995664596558,
      "eval_runtime": 20.3922,
      "eval_samples_per_second": 8.042,
      "eval_steps_per_second": 0.687,
      "step": 250
    },
    {
      "epoch": 3.0589970501474926,
      "grad_norm": 0.2579372227191925,
      "learning_rate": 0.00020963855421686747,
      "loss": 0.7418,
      "step": 260
    },
    {
      "epoch": 3.1769911504424777,
      "grad_norm": 0.2223750501871109,
      "learning_rate": 0.00020602409638554214,
      "loss": 0.7198,
      "step": 270
    },
    {
      "epoch": 3.2949852507374633,
      "grad_norm": 0.26154494285583496,
      "learning_rate": 0.00020240963855421685,
      "loss": 0.7188,
      "step": 280
    },
    {
      "epoch": 3.4129793510324484,
      "grad_norm": 0.2428540140390396,
      "learning_rate": 0.00019879518072289155,
      "loss": 0.7158,
      "step": 290
    },
    {
      "epoch": 3.5309734513274336,
      "grad_norm": 0.2056645303964615,
      "learning_rate": 0.00019518072289156625,
      "loss": 0.7103,
      "step": 300
    },
    {
      "epoch": 3.5309734513274336,
      "eval_loss": 0.8080394864082336,
      "eval_runtime": 20.4084,
      "eval_samples_per_second": 8.036,
      "eval_steps_per_second": 0.686,
      "step": 300
    },
    {
      "epoch": 3.6489675516224187,
      "grad_norm": 0.21578620374202728,
      "learning_rate": 0.00019156626506024093,
      "loss": 0.7133,
      "step": 310
    },
    {
      "epoch": 3.7669616519174043,
      "grad_norm": 0.21399493515491486,
      "learning_rate": 0.00018795180722891566,
      "loss": 0.7146,
      "step": 320
    },
    {
      "epoch": 3.8849557522123894,
      "grad_norm": 0.22075815498828888,
      "learning_rate": 0.00018433734939759034,
      "loss": 0.7183,
      "step": 330
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2605201005935669,
      "learning_rate": 0.00018072289156626507,
      "loss": 0.7142,
      "step": 340
    },
    {
      "epoch": 4.117994100294985,
      "grad_norm": 0.21863675117492676,
      "learning_rate": 0.00017710843373493974,
      "loss": 0.6761,
      "step": 350
    },
    {
      "epoch": 4.117994100294985,
      "eval_loss": 0.8006919026374817,
      "eval_runtime": 20.379,
      "eval_samples_per_second": 8.047,
      "eval_steps_per_second": 0.687,
      "step": 350
    },
    {
      "epoch": 4.23598820058997,
      "grad_norm": 0.19717003405094147,
      "learning_rate": 0.00017349397590361444,
      "loss": 0.6741,
      "step": 360
    },
    {
      "epoch": 4.353982300884955,
      "grad_norm": 0.21431218087673187,
      "learning_rate": 0.00016987951807228915,
      "loss": 0.6767,
      "step": 370
    },
    {
      "epoch": 4.4719764011799406,
      "grad_norm": 0.21559002995491028,
      "learning_rate": 0.00016626506024096385,
      "loss": 0.6775,
      "step": 380
    },
    {
      "epoch": 4.589970501474927,
      "grad_norm": 0.22161749005317688,
      "learning_rate": 0.00016265060240963853,
      "loss": 0.6754,
      "step": 390
    },
    {
      "epoch": 4.707964601769912,
      "grad_norm": 0.23757950961589813,
      "learning_rate": 0.00015903614457831326,
      "loss": 0.6718,
      "step": 400
    },
    {
      "epoch": 4.707964601769912,
      "eval_loss": 0.7892524003982544,
      "eval_runtime": 20.3783,
      "eval_samples_per_second": 8.048,
      "eval_steps_per_second": 0.687,
      "step": 400
    },
    {
      "epoch": 4.825958702064897,
      "grad_norm": 0.2082790583372116,
      "learning_rate": 0.00015542168674698793,
      "loss": 0.6774,
      "step": 410
    },
    {
      "epoch": 4.943952802359882,
      "grad_norm": 0.22040750086307526,
      "learning_rate": 0.00015180722891566264,
      "loss": 0.6708,
      "step": 420
    },
    {
      "epoch": 5.058997050147493,
      "grad_norm": 0.20725864171981812,
      "learning_rate": 0.00014819277108433734,
      "loss": 0.6561,
      "step": 430
    },
    {
      "epoch": 5.176991150442478,
      "grad_norm": 0.20603080093860626,
      "learning_rate": 0.00014457831325301204,
      "loss": 0.642,
      "step": 440
    },
    {
      "epoch": 5.294985250737463,
      "grad_norm": 0.21384873986244202,
      "learning_rate": 0.00014096385542168674,
      "loss": 0.6424,
      "step": 450
    },
    {
      "epoch": 5.294985250737463,
      "eval_loss": 0.7870513200759888,
      "eval_runtime": 20.3804,
      "eval_samples_per_second": 8.047,
      "eval_steps_per_second": 0.687,
      "step": 450
    },
    {
      "epoch": 5.412979351032448,
      "grad_norm": 0.20905406773090363,
      "learning_rate": 0.00013734939759036142,
      "loss": 0.6388,
      "step": 460
    },
    {
      "epoch": 5.530973451327434,
      "grad_norm": 0.20094947516918182,
      "learning_rate": 0.00013373493975903612,
      "loss": 0.643,
      "step": 470
    },
    {
      "epoch": 5.648967551622419,
      "grad_norm": 0.19701030850410461,
      "learning_rate": 0.00013012048192771083,
      "loss": 0.639,
      "step": 480
    },
    {
      "epoch": 5.766961651917404,
      "grad_norm": 0.2031456083059311,
      "learning_rate": 0.00012650602409638553,
      "loss": 0.6417,
      "step": 490
    },
    {
      "epoch": 5.88495575221239,
      "grad_norm": 0.20272108912467957,
      "learning_rate": 0.00012289156626506023,
      "loss": 0.6374,
      "step": 500
    },
    {
      "epoch": 5.88495575221239,
      "eval_loss": 0.7786917686462402,
      "eval_runtime": 20.3582,
      "eval_samples_per_second": 8.056,
      "eval_steps_per_second": 0.688,
      "step": 500
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.2726292312145233,
      "learning_rate": 0.00011927710843373494,
      "loss": 0.6404,
      "step": 510
    },
    {
      "epoch": 6.117994100294985,
      "grad_norm": 0.19304881989955902,
      "learning_rate": 0.00011566265060240964,
      "loss": 0.6101,
      "step": 520
    },
    {
      "epoch": 6.23598820058997,
      "grad_norm": 0.18884815275669098,
      "learning_rate": 0.00011204819277108433,
      "loss": 0.6131,
      "step": 530
    },
    {
      "epoch": 6.353982300884955,
      "grad_norm": 0.19081687927246094,
      "learning_rate": 0.00010843373493975903,
      "loss": 0.6119,
      "step": 540
    },
    {
      "epoch": 6.4719764011799406,
      "grad_norm": 0.19593416154384613,
      "learning_rate": 0.00010481927710843373,
      "loss": 0.615,
      "step": 550
    },
    {
      "epoch": 6.4719764011799406,
      "eval_loss": 0.7764475345611572,
      "eval_runtime": 20.3753,
      "eval_samples_per_second": 8.049,
      "eval_steps_per_second": 0.687,
      "step": 550
    },
    {
      "epoch": 6.589970501474927,
      "grad_norm": 0.19110922515392303,
      "learning_rate": 0.00010120481927710842,
      "loss": 0.6135,
      "step": 560
    },
    {
      "epoch": 6.707964601769912,
      "grad_norm": 0.19444629549980164,
      "learning_rate": 9.759036144578313e-05,
      "loss": 0.6128,
      "step": 570
    },
    {
      "epoch": 6.825958702064897,
      "grad_norm": 0.19284790754318237,
      "learning_rate": 9.397590361445783e-05,
      "loss": 0.6126,
      "step": 580
    },
    {
      "epoch": 6.943952802359882,
      "grad_norm": 0.19341598451137543,
      "learning_rate": 9.036144578313253e-05,
      "loss": 0.6136,
      "step": 590
    },
    {
      "epoch": 7.058997050147493,
      "grad_norm": 0.18730440735816956,
      "learning_rate": 8.674698795180722e-05,
      "loss": 0.5993,
      "step": 600
    },
    {
      "epoch": 7.058997050147493,
      "eval_loss": 0.7759349942207336,
      "eval_runtime": 20.3649,
      "eval_samples_per_second": 8.053,
      "eval_steps_per_second": 0.687,
      "step": 600
    },
    {
      "epoch": 7.176991150442478,
      "grad_norm": 0.1910707950592041,
      "learning_rate": 8.313253012048193e-05,
      "loss": 0.5895,
      "step": 610
    },
    {
      "epoch": 7.294985250737463,
      "grad_norm": 0.18417201936244965,
      "learning_rate": 7.951807228915663e-05,
      "loss": 0.591,
      "step": 620
    },
    {
      "epoch": 7.412979351032448,
      "grad_norm": 0.19250455498695374,
      "learning_rate": 7.590361445783132e-05,
      "loss": 0.5864,
      "step": 630
    },
    {
      "epoch": 7.530973451327434,
      "grad_norm": 0.18243682384490967,
      "learning_rate": 7.228915662650602e-05,
      "loss": 0.5918,
      "step": 640
    },
    {
      "epoch": 7.648967551622419,
      "grad_norm": 0.20162852108478546,
      "learning_rate": 6.867469879518071e-05,
      "loss": 0.5903,
      "step": 650
    },
    {
      "epoch": 7.648967551622419,
      "eval_loss": 0.7702756524085999,
      "eval_runtime": 20.3772,
      "eval_samples_per_second": 8.048,
      "eval_steps_per_second": 0.687,
      "step": 650
    },
    {
      "epoch": 7.766961651917404,
      "grad_norm": 0.2087647020816803,
      "learning_rate": 6.506024096385541e-05,
      "loss": 0.5909,
      "step": 660
    },
    {
      "epoch": 7.88495575221239,
      "grad_norm": 0.1935969889163971,
      "learning_rate": 6.144578313253012e-05,
      "loss": 0.5883,
      "step": 670
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.24114122986793518,
      "learning_rate": 5.783132530120482e-05,
      "loss": 0.5859,
      "step": 680
    },
    {
      "epoch": 8.117994100294986,
      "grad_norm": 0.19360019266605377,
      "learning_rate": 5.4216867469879516e-05,
      "loss": 0.5739,
      "step": 690
    },
    {
      "epoch": 8.23598820058997,
      "grad_norm": 0.19802173972129822,
      "learning_rate": 5.060240963855421e-05,
      "loss": 0.5755,
      "step": 700
    },
    {
      "epoch": 8.23598820058997,
      "eval_loss": 0.7725194692611694,
      "eval_runtime": 20.3781,
      "eval_samples_per_second": 8.048,
      "eval_steps_per_second": 0.687,
      "step": 700
    }
  ],
  "logging_steps": 10,
  "max_steps": 840,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2674273049671893e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}