{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.926393270241851,
  "eval_steps": 100.0,
  "global_step": 1180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 5e-06,
      "loss": 4.1311,
      "step": 10
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 4.0983,
      "step": 20
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.5e-05,
      "loss": 3.9944,
      "step": 30
    },
    {
      "epoch": 0.34,
      "learning_rate": 2e-05,
      "loss": 3.8495,
      "step": 40
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.5e-05,
      "loss": 3.5944,
      "step": 50
    },
    {
      "epoch": 0.5,
      "learning_rate": 3e-05,
      "loss": 3.1649,
      "step": 60
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.5e-05,
      "loss": 3.0072,
      "step": 70
    },
    {
      "epoch": 0.67,
      "learning_rate": 4e-05,
      "loss": 2.9697,
      "step": 80
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.5e-05,
      "loss": 2.8497,
      "step": 90
    },
    {
      "epoch": 0.84,
      "learning_rate": 5e-05,
      "loss": 2.8376,
      "step": 100
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.998942375205502e-05,
      "loss": 2.8255,
      "step": 110
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.995770395678171e-05,
      "loss": 2.7066,
      "step": 120
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.990486745229364e-05,
      "loss": 2.6717,
      "step": 130
    },
    {
      "epoch": 1.18,
      "learning_rate": 4.983095894354858e-05,
      "loss": 2.6093,
      "step": 140
    },
    {
      "epoch": 1.26,
      "learning_rate": 4.973604096452361e-05,
      "loss": 2.588,
      "step": 150
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.962019382530521e-05,
      "loss": 2.5881,
      "step": 160
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.948351554413879e-05,
      "loss": 2.4645,
      "step": 170
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.9326121764495596e-05,
      "loss": 2.4118,
      "step": 180
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.914814565722671e-05,
      "loss": 2.5078,
      "step": 190
    },
    {
      "epoch": 1.68,
      "learning_rate": 4.894973780788722e-05,
      "loss": 2.3461,
      "step": 200
    },
    {
      "epoch": 1.77,
      "learning_rate": 4.873106608932585e-05,
      "loss": 2.3559,
      "step": 210
    },
    {
      "epoch": 1.85,
      "learning_rate": 4.849231551964771e-05,
      "loss": 2.4097,
      "step": 220
    },
    {
      "epoch": 1.93,
      "learning_rate": 4.823368810567056e-05,
      "loss": 2.2607,
      "step": 230
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.7955402672006854e-05,
      "loss": 2.1208,
      "step": 240
    },
    {
      "epoch": 2.1,
      "learning_rate": 4.765769467591625e-05,
      "loss": 2.112,
      "step": 250
    },
    {
      "epoch": 2.19,
      "learning_rate": 4.734081600808531e-05,
      "loss": 2.1259,
      "step": 260
    },
    {
      "epoch": 2.27,
      "learning_rate": 4.700503477950278e-05,
      "loss": 2.1712,
      "step": 270
    },
    {
      "epoch": 2.36,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.9872,
      "step": 280
    },
    {
      "epoch": 2.44,
      "learning_rate": 4.627791681092499e-05,
      "loss": 1.9918,
      "step": 290
    },
    {
      "epoch": 2.52,
      "learning_rate": 4.588719528532342e-05,
      "loss": 2.0882,
      "step": 300
    },
    {
      "epoch": 2.61,
      "learning_rate": 4.54788011072248e-05,
      "loss": 1.9361,
      "step": 310
    },
    {
      "epoch": 2.69,
      "learning_rate": 4.50530798188761e-05,
      "loss": 1.9715,
      "step": 320
    },
    {
      "epoch": 2.78,
      "learning_rate": 4.4610391622989396e-05,
      "loss": 1.8659,
      "step": 330
    },
    {
      "epoch": 2.86,
      "learning_rate": 4.415111107797445e-05,
      "loss": 1.8453,
      "step": 340
    },
    {
      "epoch": 2.94,
      "learning_rate": 4.36756267810249e-05,
      "loss": 1.9347,
      "step": 350
    },
    {
      "epoch": 3.03,
      "learning_rate": 4.318434103932622e-05,
      "loss": 1.8471,
      "step": 360
    },
    {
      "epoch": 3.11,
      "learning_rate": 4.267766952966369e-05,
      "loss": 1.7312,
      "step": 370
    },
    {
      "epoch": 3.2,
      "learning_rate": 4.215604094671835e-05,
      "loss": 1.5693,
      "step": 380
    },
    {
      "epoch": 3.28,
      "learning_rate": 4.1619896640348445e-05,
      "loss": 1.7114,
      "step": 390
    },
    {
      "epoch": 3.36,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 1.5693,
      "step": 400
    },
    {
      "epoch": 3.45,
      "learning_rate": 4.05058872817065e-05,
      "loss": 1.588,
      "step": 410
    },
    {
      "epoch": 3.53,
      "learning_rate": 3.9928964792569655e-05,
      "loss": 1.6776,
      "step": 420
    },
    {
      "epoch": 3.62,
      "learning_rate": 3.933941090877615e-05,
      "loss": 1.633,
      "step": 430
    },
    {
      "epoch": 3.7,
      "learning_rate": 3.873772445177015e-05,
      "loss": 1.5435,
      "step": 440
    },
    {
      "epoch": 3.79,
      "learning_rate": 3.8124414508364e-05,
      "loss": 1.522,
      "step": 450
    },
    {
      "epoch": 3.87,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.4307,
      "step": 460
    },
    {
      "epoch": 3.95,
      "learning_rate": 3.686500924369101e-05,
      "loss": 1.6171,
      "step": 470
    },
    {
      "epoch": 4.04,
      "learning_rate": 3.621997950501156e-05,
      "loss": 1.482,
      "step": 480
    },
    {
      "epoch": 4.12,
      "learning_rate": 3.556545654351749e-05,
      "loss": 1.4552,
      "step": 490
    },
    {
      "epoch": 4.21,
      "learning_rate": 3.490199415097892e-05,
      "loss": 1.2726,
      "step": 500
    },
    {
      "epoch": 4.29,
      "learning_rate": 3.423015368281711e-05,
      "loss": 1.312,
      "step": 510
    },
    {
      "epoch": 4.37,
      "learning_rate": 3.355050358314172e-05,
      "loss": 1.3236,
      "step": 520
    },
    {
      "epoch": 4.46,
      "learning_rate": 3.2863618903790346e-05,
      "loss": 1.2786,
      "step": 530
    },
    {
      "epoch": 4.54,
      "learning_rate": 3.217008081777726e-05,
      "loss": 1.2587,
      "step": 540
    },
    {
      "epoch": 4.63,
      "learning_rate": 3.147047612756302e-05,
      "loss": 1.3509,
      "step": 550
    },
    {
      "epoch": 4.71,
      "learning_rate": 3.076539676856101e-05,
      "loss": 1.2632,
      "step": 560
    },
    {
      "epoch": 4.79,
      "learning_rate": 3.0055439308300952e-05,
      "loss": 1.2215,
      "step": 570
    },
    {
      "epoch": 4.88,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 1.2773,
      "step": 580
    },
    {
      "epoch": 4.96,
      "learning_rate": 2.8623296482681166e-05,
      "loss": 1.3122,
      "step": 590
    },
    {
      "epoch": 5.05,
      "learning_rate": 2.7902322853130757e-05,
      "loss": 1.2999,
      "step": 600
    },
    {
      "epoch": 5.13,
      "learning_rate": 2.717889356869146e-05,
      "loss": 1.13,
      "step": 610
    },
    {
      "epoch": 5.22,
      "learning_rate": 2.6453620722761896e-05,
      "loss": 1.1283,
      "step": 620
    },
    {
      "epoch": 5.3,
      "learning_rate": 2.5727117968577784e-05,
      "loss": 1.0922,
      "step": 630
    },
    {
      "epoch": 5.38,
      "learning_rate": 2.5e-05,
      "loss": 1.0549,
      "step": 640
    },
    {
      "epoch": 5.47,
      "learning_rate": 2.4272882031422215e-05,
      "loss": 1.0966,
      "step": 650
    },
    {
      "epoch": 5.55,
      "learning_rate": 2.3546379277238107e-05,
      "loss": 1.2114,
      "step": 660
    },
    {
      "epoch": 5.64,
      "learning_rate": 2.2821106431308544e-05,
      "loss": 0.9685,
      "step": 670
    },
    {
      "epoch": 5.72,
      "learning_rate": 2.2097677146869242e-05,
      "loss": 0.9688,
      "step": 680
    },
    {
      "epoch": 5.8,
      "learning_rate": 2.1376703517318837e-05,
      "loss": 1.0943,
      "step": 690
    },
    {
      "epoch": 5.89,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 0.9363,
      "step": 700
    },
    {
      "epoch": 5.97,
      "learning_rate": 1.9944560691699057e-05,
      "loss": 1.1054,
      "step": 710
    },
    {
      "epoch": 6.06,
      "learning_rate": 1.9234603231438995e-05,
      "loss": 1.0781,
      "step": 720
    },
    {
      "epoch": 6.14,
      "learning_rate": 1.852952387243698e-05,
      "loss": 0.8869,
      "step": 730
    },
    {
      "epoch": 6.23,
      "learning_rate": 1.7829919182222752e-05,
      "loss": 0.8957,
      "step": 740
    },
    {
      "epoch": 6.31,
      "learning_rate": 1.7136381096209664e-05,
      "loss": 1.0628,
      "step": 750
    },
    {
      "epoch": 6.39,
      "learning_rate": 1.6449496416858284e-05,
      "loss": 1.0005,
      "step": 760
    },
    {
      "epoch": 6.48,
      "learning_rate": 1.5769846317182893e-05,
      "loss": 0.9747,
      "step": 770
    },
    {
      "epoch": 6.56,
      "learning_rate": 1.509800584902108e-05,
      "loss": 1.0524,
      "step": 780
    },
    {
      "epoch": 6.65,
      "learning_rate": 1.443454345648252e-05,
      "loss": 1.0064,
      "step": 790
    },
    {
      "epoch": 6.73,
      "learning_rate": 1.3780020494988446e-05,
      "loss": 0.979,
      "step": 800
    },
    {
      "epoch": 6.81,
      "learning_rate": 1.313499075630899e-05,
      "loss": 0.9495,
      "step": 810
    },
    {
      "epoch": 6.9,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.8098,
      "step": 820
    },
    {
      "epoch": 6.98,
      "learning_rate": 1.1875585491636e-05,
      "loss": 0.9074,
      "step": 830
    },
    {
      "epoch": 7.07,
      "learning_rate": 1.126227554822985e-05,
      "loss": 0.8522,
      "step": 840
    },
    {
      "epoch": 7.15,
      "learning_rate": 1.0660589091223855e-05,
      "loss": 0.8949,
      "step": 850
    },
    {
      "epoch": 7.23,
      "learning_rate": 1.0071035207430352e-05,
      "loss": 0.9344,
      "step": 860
    },
    {
      "epoch": 7.32,
      "learning_rate": 9.494112718293501e-06,
      "loss": 0.7258,
      "step": 870
    },
    {
      "epoch": 7.4,
      "learning_rate": 8.930309757836517e-06,
      "loss": 0.8315,
      "step": 880
    },
    {
      "epoch": 7.49,
      "learning_rate": 8.380103359651553e-06,
      "loss": 0.9103,
      "step": 890
    },
    {
      "epoch": 7.57,
      "learning_rate": 7.843959053281663e-06,
      "loss": 0.8161,
      "step": 900
    },
    {
      "epoch": 7.66,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.8657,
      "step": 910
    },
    {
      "epoch": 7.74,
      "learning_rate": 6.815658960673782e-06,
      "loss": 0.8315,
      "step": 920
    },
    {
      "epoch": 7.82,
      "learning_rate": 6.324373218975105e-06,
      "loss": 0.8273,
      "step": 930
    },
    {
      "epoch": 7.91,
      "learning_rate": 5.848888922025553e-06,
      "loss": 0.8765,
      "step": 940
    },
    {
      "epoch": 7.99,
      "learning_rate": 5.389608377010608e-06,
      "loss": 0.8816,
      "step": 950
    },
    {
      "epoch": 8.08,
      "learning_rate": 4.946920181123904e-06,
      "loss": 0.8582,
      "step": 960
    },
    {
      "epoch": 8.16,
      "learning_rate": 4.521198892775203e-06,
      "loss": 0.7583,
      "step": 970
    },
    {
      "epoch": 8.24,
      "learning_rate": 4.112804714676594e-06,
      "loss": 0.862,
      "step": 980
    },
    {
      "epoch": 8.33,
      "learning_rate": 3.7220831890750067e-06,
      "loss": 0.8618,
      "step": 990
    },
    {
      "epoch": 8.41,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.6312,
      "step": 1000
    },
    {
      "epoch": 8.5,
      "learning_rate": 2.9949652204972254e-06,
      "loss": 0.8316,
      "step": 1010
    },
    {
      "epoch": 8.58,
      "learning_rate": 2.659183991914696e-06,
      "loss": 0.8118,
      "step": 1020
    },
    {
      "epoch": 8.66,
      "learning_rate": 2.3423053240837515e-06,
      "loss": 0.8255,
      "step": 1030
    },
    {
      "epoch": 8.75,
      "learning_rate": 2.044597327993153e-06,
      "loss": 0.7131,
      "step": 1040
    },
    {
      "epoch": 8.83,
      "learning_rate": 1.7663118943294366e-06,
      "loss": 0.8605,
      "step": 1050
    },
    {
      "epoch": 8.92,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 0.7849,
      "step": 1060
    },
    {
      "epoch": 9.0,
      "learning_rate": 1.2689339106741527e-06,
      "loss": 0.8457,
      "step": 1070
    },
    {
      "epoch": 9.09,
      "learning_rate": 1.0502621921127776e-06,
      "loss": 0.7074,
      "step": 1080
    },
    {
      "epoch": 9.17,
      "learning_rate": 8.51854342773295e-07,
      "loss": 0.7921,
      "step": 1090
    },
    {
      "epoch": 9.25,
      "learning_rate": 6.738782355044049e-07,
      "loss": 0.7745,
      "step": 1100
    },
    {
      "epoch": 9.34,
      "learning_rate": 5.164844558612131e-07,
      "loss": 0.8488,
      "step": 1110
    },
    {
      "epoch": 9.42,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 0.7559,
      "step": 1120
    },
    {
      "epoch": 9.51,
      "learning_rate": 2.6395903547638825e-07,
      "loss": 0.8448,
      "step": 1130
    },
    {
      "epoch": 9.59,
      "learning_rate": 1.6904105645142444e-07,
      "loss": 0.7632,
      "step": 1140
    },
    {
      "epoch": 9.67,
      "learning_rate": 9.513254770636137e-08,
      "loss": 0.6902,
      "step": 1150
    },
    {
      "epoch": 9.76,
      "learning_rate": 4.229604321829561e-08,
      "loss": 0.8562,
      "step": 1160
    },
    {
      "epoch": 9.84,
      "learning_rate": 1.0576247944985018e-08,
      "loss": 0.8078,
      "step": 1170
    },
    {
      "epoch": 9.93,
      "learning_rate": 0.0,
      "loss": 0.7809,
      "step": 1180
    },
    {
      "epoch": 9.93,
      "step": 1180,
      "total_flos": 1.0185645586201313e+18,
      "train_loss": 1.5241096448090117,
      "train_runtime": 23566.1012,
      "train_samples_per_second": 1.614,
      "train_steps_per_second": 0.05
    }
  ],
  "logging_steps": 10,
  "max_steps": 1180,
  "num_train_epochs": 10,
  "save_steps": 100,
  "total_flos": 1.0185645586201313e+18,
  "trial_name": null,
  "trial_params": null
}