{
  "best_metric": 0.4383337870950177,
  "best_model_checkpoint": "videomae-base-finetuned/checkpoint-2236",
  "epoch": 3.2486583184257602,
  "eval_steps": 500,
  "global_step": 2236,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.2321428571428573e-06,
      "loss": 1.2724,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.464285714285715e-06,
      "loss": 1.2558,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.696428571428572e-06,
      "loss": 0.7673,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.92857142857143e-06,
      "loss": 0.7249,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.1160714285714287e-05,
      "loss": 0.7513,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.3392857142857144e-05,
      "loss": 0.8435,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.5625e-05,
      "loss": 0.7557,
      "step": 70
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.785714285714286e-05,
      "loss": 0.7303,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.0089285714285717e-05,
      "loss": 0.6777,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.2321428571428575e-05,
      "loss": 0.6899,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.455357142857143e-05,
      "loss": 0.6762,
      "step": 110
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.6785714285714288e-05,
      "loss": 0.8197,
      "step": 120
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.9017857142857146e-05,
      "loss": 0.7401,
      "step": 130
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.125e-05,
      "loss": 0.6986,
      "step": 140
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.348214285714286e-05,
      "loss": 0.6888,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.2093,
      "step": 160
    },
    {
      "epoch": 0.08,
      "learning_rate": 3.794642857142857e-05,
      "loss": 1.0131,
      "step": 170
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.017857142857143e-05,
      "loss": 0.9455,
      "step": 180
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.2410714285714285e-05,
      "loss": 0.8935,
      "step": 190
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.464285714285715e-05,
      "loss": 0.6467,
      "step": 200
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.6875e-05,
      "loss": 0.7347,
      "step": 210
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.910714285714286e-05,
      "loss": 0.6645,
      "step": 220
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.985089463220676e-05,
      "loss": 0.9226,
      "step": 230
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.9602385685884696e-05,
      "loss": 0.9132,
      "step": 240
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.935387673956263e-05,
      "loss": 0.8685,
      "step": 250
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.910536779324056e-05,
      "loss": 0.9501,
      "step": 260
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.885685884691849e-05,
      "loss": 0.6761,
      "step": 270
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.8608349900596425e-05,
      "loss": 0.8699,
      "step": 280
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.835984095427435e-05,
      "loss": 0.6881,
      "step": 290
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.8111332007952286e-05,
      "loss": 0.6799,
      "step": 300
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.786282306163022e-05,
      "loss": 0.7497,
      "step": 310
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.761431411530815e-05,
      "loss": 0.9132,
      "step": 320
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.736580516898609e-05,
      "loss": 1.1916,
      "step": 330
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.711729622266402e-05,
      "loss": 0.8376,
      "step": 340
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.686878727634195e-05,
      "loss": 0.8276,
      "step": 350
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.6620278330019884e-05,
      "loss": 0.6691,
      "step": 360
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.637176938369782e-05,
      "loss": 0.8195,
      "step": 370
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.6123260437375745e-05,
      "loss": 0.8504,
      "step": 380
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.587475149105368e-05,
      "loss": 1.1144,
      "step": 390
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.562624254473161e-05,
      "loss": 0.5861,
      "step": 400
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.537773359840955e-05,
      "loss": 1.0297,
      "step": 410
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.5129224652087475e-05,
      "loss": 1.0822,
      "step": 420
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.488071570576541e-05,
      "loss": 0.942,
      "step": 430
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.463220675944334e-05,
      "loss": 0.6496,
      "step": 440
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.438369781312127e-05,
      "loss": 0.9284,
      "step": 450
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.4135188866799204e-05,
      "loss": 0.9135,
      "step": 460
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.3886679920477145e-05,
      "loss": 0.4698,
      "step": 470
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.363817097415507e-05,
      "loss": 0.9779,
      "step": 480
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.3389662027833006e-05,
      "loss": 0.9089,
      "step": 490
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.314115308151094e-05,
      "loss": 0.9272,
      "step": 500
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.289264413518887e-05,
      "loss": 0.7273,
      "step": 510
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.26441351888668e-05,
      "loss": 0.8869,
      "step": 520
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.2395626242544736e-05,
      "loss": 0.8218,
      "step": 530
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.214711729622266e-05,
      "loss": 1.034,
      "step": 540
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.18986083499006e-05,
      "loss": 0.5722,
      "step": 550
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.165009940357853e-05,
      "loss": 0.5277,
      "step": 560
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.39150558126871765,
      "eval_loss": 1.0346124172210693,
      "eval_runtime": 758.0472,
      "eval_samples_per_second": 4.845,
      "eval_steps_per_second": 0.607,
      "step": 560
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.140159045725646e-05,
      "loss": 0.9766,
      "step": 570
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.115308151093439e-05,
      "loss": 1.2514,
      "step": 580
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.0904572564612327e-05,
      "loss": 0.5766,
      "step": 590
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.065606361829026e-05,
      "loss": 0.4935,
      "step": 600
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.0407554671968195e-05,
      "loss": 0.7871,
      "step": 610
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.015904572564613e-05,
      "loss": 0.8886,
      "step": 620
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.9910536779324056e-05,
      "loss": 0.8568,
      "step": 630
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.966202783300199e-05,
      "loss": 1.2222,
      "step": 640
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.9413518886679924e-05,
      "loss": 0.8227,
      "step": 650
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.916500994035786e-05,
      "loss": 0.8264,
      "step": 660
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.8916500994035785e-05,
      "loss": 0.607,
      "step": 670
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.866799204771372e-05,
      "loss": 0.6223,
      "step": 680
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.8419483101391654e-05,
      "loss": 0.7475,
      "step": 690
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.817097415506958e-05,
      "loss": 0.7546,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.7922465208747515e-05,
      "loss": 0.8668,
      "step": 710
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.767395626242545e-05,
      "loss": 0.7125,
      "step": 720
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.7425447316103376e-05,
      "loss": 0.9261,
      "step": 730
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.717693836978131e-05,
      "loss": 0.6339,
      "step": 740
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.692842942345925e-05,
      "loss": 0.6737,
      "step": 750
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.667992047713718e-05,
      "loss": 0.9312,
      "step": 760
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.643141153081511e-05,
      "loss": 0.6546,
      "step": 770
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.6182902584493047e-05,
      "loss": 0.7337,
      "step": 780
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.5934393638170974e-05,
      "loss": 0.5808,
      "step": 790
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.568588469184891e-05,
      "loss": 1.0989,
      "step": 800
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.543737574552684e-05,
      "loss": 0.8446,
      "step": 810
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.5188866799204776e-05,
      "loss": 0.6314,
      "step": 820
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.49403578528827e-05,
      "loss": 0.9441,
      "step": 830
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.469184890656064e-05,
      "loss": 0.6362,
      "step": 840
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.444333996023857e-05,
      "loss": 0.6164,
      "step": 850
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.41948310139165e-05,
      "loss": 0.6472,
      "step": 860
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.394632206759443e-05,
      "loss": 0.5832,
      "step": 870
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.369781312127237e-05,
      "loss": 0.5978,
      "step": 880
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.34493041749503e-05,
      "loss": 0.7464,
      "step": 890
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.3200795228628235e-05,
      "loss": 0.6589,
      "step": 900
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.295228628230617e-05,
      "loss": 0.6176,
      "step": 910
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.2703777335984096e-05,
      "loss": 0.9792,
      "step": 920
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.245526838966203e-05,
      "loss": 0.6343,
      "step": 930
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.2206759443339964e-05,
      "loss": 0.6519,
      "step": 940
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.195825049701789e-05,
      "loss": 0.8736,
      "step": 950
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.1709741550695826e-05,
      "loss": 0.6899,
      "step": 960
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.146123260437376e-05,
      "loss": 0.758,
      "step": 970
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.121272365805169e-05,
      "loss": 0.5085,
      "step": 980
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.096421471172962e-05,
      "loss": 0.9265,
      "step": 990
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.0715705765407555e-05,
      "loss": 0.8784,
      "step": 1000
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.0467196819085486e-05,
      "loss": 0.9509,
      "step": 1010
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.0218687872763416e-05,
      "loss": 0.6804,
      "step": 1020
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.9970178926441357e-05,
      "loss": 0.6791,
      "step": 1030
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.9721669980119288e-05,
      "loss": 0.5747,
      "step": 1040
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.947316103379722e-05,
      "loss": 0.5537,
      "step": 1050
    },
    {
      "epoch": 1.22,
      "learning_rate": 2.9224652087475153e-05,
      "loss": 0.7963,
      "step": 1060
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.8976143141153083e-05,
      "loss": 0.6961,
      "step": 1070
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.8727634194831014e-05,
      "loss": 0.885,
      "step": 1080
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.8479125248508948e-05,
      "loss": 0.6771,
      "step": 1090
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.823061630218688e-05,
      "loss": 0.6592,
      "step": 1100
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.7982107355864813e-05,
      "loss": 0.6657,
      "step": 1110
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.7733598409542744e-05,
      "loss": 0.9442,
      "step": 1120
    },
    {
      "epoch": 1.25,
      "eval_accuracy": 0.337054179145113,
      "eval_loss": 0.9560135006904602,
      "eval_runtime": 786.5921,
      "eval_samples_per_second": 4.67,
      "eval_steps_per_second": 0.585,
      "step": 1120
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.7485089463220674e-05,
      "loss": 0.4543,
      "step": 1130
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.7236580516898608e-05,
      "loss": 0.4966,
      "step": 1140
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.698807157057654e-05,
      "loss": 0.7272,
      "step": 1150
    },
    {
      "epoch": 2.02,
      "learning_rate": 2.6739562624254473e-05,
      "loss": 0.7418,
      "step": 1160
    },
    {
      "epoch": 2.02,
      "learning_rate": 2.649105367793241e-05,
      "loss": 0.7824,
      "step": 1170
    },
    {
      "epoch": 2.03,
      "learning_rate": 2.624254473161034e-05,
      "loss": 0.7431,
      "step": 1180
    },
    {
      "epoch": 2.03,
      "learning_rate": 2.5994035785288272e-05,
      "loss": 0.8001,
      "step": 1190
    },
    {
      "epoch": 2.04,
      "learning_rate": 2.5745526838966206e-05,
      "loss": 0.6027,
      "step": 1200
    },
    {
      "epoch": 2.04,
      "learning_rate": 2.5497017892644136e-05,
      "loss": 0.9076,
      "step": 1210
    },
    {
      "epoch": 2.04,
      "learning_rate": 2.524850894632207e-05,
      "loss": 0.6438,
      "step": 1220
    },
    {
      "epoch": 2.05,
      "learning_rate": 2.5e-05,
      "loss": 0.6609,
      "step": 1230
    },
    {
      "epoch": 2.05,
      "learning_rate": 2.4751491053677932e-05,
      "loss": 0.7644,
      "step": 1240
    },
    {
      "epoch": 2.06,
      "learning_rate": 2.4502982107355866e-05,
      "loss": 0.5369,
      "step": 1250
    },
    {
      "epoch": 2.06,
      "learning_rate": 2.4254473161033797e-05,
      "loss": 0.5679,
      "step": 1260
    },
    {
      "epoch": 2.07,
      "learning_rate": 2.400596421471173e-05,
      "loss": 0.7206,
      "step": 1270
    },
    {
      "epoch": 2.07,
      "learning_rate": 2.3757455268389665e-05,
      "loss": 0.5578,
      "step": 1280
    },
    {
      "epoch": 2.08,
      "learning_rate": 2.3508946322067595e-05,
      "loss": 0.4818,
      "step": 1290
    },
    {
      "epoch": 2.08,
      "learning_rate": 2.326043737574553e-05,
      "loss": 0.7293,
      "step": 1300
    },
    {
      "epoch": 2.08,
      "learning_rate": 2.301192842942346e-05,
      "loss": 0.5929,
      "step": 1310
    },
    {
      "epoch": 2.09,
      "learning_rate": 2.276341948310139e-05,
      "loss": 0.4792,
      "step": 1320
    },
    {
      "epoch": 2.09,
      "learning_rate": 2.2514910536779325e-05,
      "loss": 0.5766,
      "step": 1330
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.226640159045726e-05,
      "loss": 0.6679,
      "step": 1340
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.201789264413519e-05,
      "loss": 0.5128,
      "step": 1350
    },
    {
      "epoch": 2.11,
      "learning_rate": 2.1769383697813124e-05,
      "loss": 0.5404,
      "step": 1360
    },
    {
      "epoch": 2.11,
      "learning_rate": 2.1520874751491054e-05,
      "loss": 0.9508,
      "step": 1370
    },
    {
      "epoch": 2.12,
      "learning_rate": 2.127236580516899e-05,
      "loss": 0.8586,
      "step": 1380
    },
    {
      "epoch": 2.12,
      "learning_rate": 2.102385685884692e-05,
      "loss": 0.6006,
      "step": 1390
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.077534791252485e-05,
      "loss": 0.7293,
      "step": 1400
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.0526838966202787e-05,
      "loss": 0.8965,
      "step": 1410
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.0278330019880718e-05,
      "loss": 0.5134,
      "step": 1420
    },
    {
      "epoch": 2.14,
      "learning_rate": 2.002982107355865e-05,
      "loss": 0.7787,
      "step": 1430
    },
    {
      "epoch": 2.14,
      "learning_rate": 1.9781312127236583e-05,
      "loss": 0.7198,
      "step": 1440
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.9532803180914513e-05,
      "loss": 0.9,
      "step": 1450
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.9284294234592444e-05,
      "loss": 0.7677,
      "step": 1460
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.9035785288270378e-05,
      "loss": 0.5368,
      "step": 1470
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.8787276341948312e-05,
      "loss": 0.4846,
      "step": 1480
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.8538767395626243e-05,
      "loss": 0.6272,
      "step": 1490
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.8290258449304177e-05,
      "loss": 0.6104,
      "step": 1500
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.8041749502982107e-05,
      "loss": 0.6732,
      "step": 1510
    },
    {
      "epoch": 2.18,
      "learning_rate": 1.779324055666004e-05,
      "loss": 0.6708,
      "step": 1520
    },
    {
      "epoch": 2.18,
      "learning_rate": 1.7544731610337972e-05,
      "loss": 0.5534,
      "step": 1530
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.7296222664015903e-05,
      "loss": 0.6177,
      "step": 1540
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.704771371769384e-05,
      "loss": 0.6893,
      "step": 1550
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.679920477137177e-05,
      "loss": 0.7224,
      "step": 1560
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.65506958250497e-05,
      "loss": 0.5848,
      "step": 1570
    },
    {
      "epoch": 2.21,
      "learning_rate": 1.6302186878727636e-05,
      "loss": 0.5624,
      "step": 1580
    },
    {
      "epoch": 2.21,
      "learning_rate": 1.6053677932405566e-05,
      "loss": 0.6792,
      "step": 1590
    },
    {
      "epoch": 2.21,
      "learning_rate": 1.58051689860835e-05,
      "loss": 1.6715,
      "step": 1600
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.555666003976143e-05,
      "loss": 0.8796,
      "step": 1610
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.5308151093439365e-05,
      "loss": 0.656,
      "step": 1620
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.5059642147117297e-05,
      "loss": 0.7348,
      "step": 1630
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.481113320079523e-05,
      "loss": 0.6974,
      "step": 1640
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.4562624254473162e-05,
      "loss": 0.7363,
      "step": 1650
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.4314115308151095e-05,
      "loss": 0.6796,
      "step": 1660
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.4065606361829025e-05,
      "loss": 0.6237,
      "step": 1670
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.3817097415506958e-05,
      "loss": 0.4539,
      "step": 1680
    },
    {
      "epoch": 2.25,
      "eval_accuracy": 0.4097468009801252,
      "eval_loss": 0.9267099499702454,
      "eval_runtime": 716.8759,
      "eval_samples_per_second": 5.124,
      "eval_steps_per_second": 0.642,
      "step": 1680
    },
    {
      "epoch": 3.0,
      "learning_rate": 1.3568588469184893e-05,
      "loss": 0.4844,
      "step": 1690
    },
    {
      "epoch": 3.01,
      "learning_rate": 1.3320079522862824e-05,
      "loss": 0.5648,
      "step": 1700
    },
    {
      "epoch": 3.01,
      "learning_rate": 1.3071570576540756e-05,
      "loss": 0.8101,
      "step": 1710
    },
    {
      "epoch": 3.02,
      "learning_rate": 1.2823061630218689e-05,
      "loss": 0.604,
      "step": 1720
    },
    {
      "epoch": 3.02,
      "learning_rate": 1.2574552683896621e-05,
      "loss": 0.6577,
      "step": 1730
    },
    {
      "epoch": 3.03,
      "learning_rate": 1.2326043737574553e-05,
      "loss": 0.6786,
      "step": 1740
    },
    {
      "epoch": 3.03,
      "learning_rate": 1.2077534791252486e-05,
      "loss": 0.5483,
      "step": 1750
    },
    {
      "epoch": 3.04,
      "learning_rate": 1.1829025844930418e-05,
      "loss": 0.739,
      "step": 1760
    },
    {
      "epoch": 3.04,
      "learning_rate": 1.158051689860835e-05,
      "loss": 0.9266,
      "step": 1770
    },
    {
      "epoch": 3.04,
      "learning_rate": 1.1332007952286283e-05,
      "loss": 0.6817,
      "step": 1780
    },
    {
      "epoch": 3.05,
      "learning_rate": 1.1083499005964215e-05,
      "loss": 0.5696,
      "step": 1790
    },
    {
      "epoch": 3.05,
      "learning_rate": 1.0834990059642148e-05,
      "loss": 1.0031,
      "step": 1800
    },
    {
      "epoch": 3.06,
      "learning_rate": 1.058648111332008e-05,
      "loss": 0.85,
      "step": 1810
    },
    {
      "epoch": 3.06,
      "learning_rate": 1.0337972166998012e-05,
      "loss": 0.584,
      "step": 1820
    },
    {
      "epoch": 3.07,
      "learning_rate": 1.0089463220675945e-05,
      "loss": 0.6634,
      "step": 1830
    },
    {
      "epoch": 3.07,
      "learning_rate": 9.840954274353877e-06,
      "loss": 0.897,
      "step": 1840
    },
    {
      "epoch": 3.08,
      "learning_rate": 9.59244532803181e-06,
      "loss": 0.4782,
      "step": 1850
    },
    {
      "epoch": 3.08,
      "learning_rate": 9.343936381709742e-06,
      "loss": 0.5902,
      "step": 1860
    },
    {
      "epoch": 3.08,
      "learning_rate": 9.095427435387674e-06,
      "loss": 0.6974,
      "step": 1870
    },
    {
      "epoch": 3.09,
      "learning_rate": 8.846918489065607e-06,
      "loss": 0.9892,
      "step": 1880
    },
    {
      "epoch": 3.09,
      "learning_rate": 8.598409542743539e-06,
      "loss": 0.6206,
      "step": 1890
    },
    {
      "epoch": 3.1,
      "learning_rate": 8.349900596421471e-06,
      "loss": 0.5937,
      "step": 1900
    },
    {
      "epoch": 3.1,
      "learning_rate": 8.101391650099404e-06,
      "loss": 0.6497,
      "step": 1910
    },
    {
      "epoch": 3.11,
      "learning_rate": 7.852882703777336e-06,
      "loss": 0.5911,
      "step": 1920
    },
    {
      "epoch": 3.11,
      "learning_rate": 7.604373757455268e-06,
      "loss": 0.4621,
      "step": 1930
    },
    {
      "epoch": 3.12,
      "learning_rate": 7.355864811133201e-06,
      "loss": 0.7211,
      "step": 1940
    },
    {
      "epoch": 3.12,
      "learning_rate": 7.107355864811134e-06,
      "loss": 0.6791,
      "step": 1950
    },
    {
      "epoch": 3.13,
      "learning_rate": 6.858846918489066e-06,
      "loss": 0.7411,
      "step": 1960
    },
    {
      "epoch": 3.13,
      "learning_rate": 6.610337972166998e-06,
      "loss": 0.5481,
      "step": 1970
    },
    {
      "epoch": 3.13,
      "learning_rate": 6.36182902584493e-06,
      "loss": 0.4477,
      "step": 1980
    },
    {
      "epoch": 3.14,
      "learning_rate": 6.113320079522863e-06,
      "loss": 0.6457,
      "step": 1990
    },
    {
      "epoch": 3.14,
      "learning_rate": 5.864811133200796e-06,
      "loss": 0.5761,
      "step": 2000
    },
    {
      "epoch": 3.15,
      "learning_rate": 5.616302186878728e-06,
      "loss": 0.52,
      "step": 2010
    },
    {
      "epoch": 3.15,
      "learning_rate": 5.3677932405566604e-06,
      "loss": 0.673,
      "step": 2020
    },
    {
      "epoch": 3.16,
      "learning_rate": 5.119284294234593e-06,
      "loss": 0.7666,
      "step": 2030
    },
    {
      "epoch": 3.16,
      "learning_rate": 4.870775347912525e-06,
      "loss": 0.8006,
      "step": 2040
    },
    {
      "epoch": 3.17,
      "learning_rate": 4.6222664015904575e-06,
      "loss": 0.6396,
      "step": 2050
    },
    {
      "epoch": 3.17,
      "learning_rate": 4.37375745526839e-06,
      "loss": 0.6268,
      "step": 2060
    },
    {
      "epoch": 3.17,
      "learning_rate": 4.125248508946322e-06,
      "loss": 0.4449,
      "step": 2070
    },
    {
      "epoch": 3.18,
      "learning_rate": 3.876739562624255e-06,
      "loss": 0.8862,
      "step": 2080
    },
    {
      "epoch": 3.18,
      "learning_rate": 3.628230616302187e-06,
      "loss": 0.7243,
      "step": 2090
    },
    {
      "epoch": 3.19,
      "learning_rate": 3.3797216699801198e-06,
      "loss": 0.5405,
      "step": 2100
    },
    {
      "epoch": 3.19,
      "learning_rate": 3.1312127236580517e-06,
      "loss": 0.6213,
      "step": 2110
    },
    {
      "epoch": 3.2,
      "learning_rate": 2.882703777335984e-06,
      "loss": 0.4473,
      "step": 2120
    },
    {
      "epoch": 3.2,
      "learning_rate": 2.6341948310139164e-06,
      "loss": 0.8773,
      "step": 2130
    },
    {
      "epoch": 3.21,
      "learning_rate": 2.385685884691849e-06,
      "loss": 0.6047,
      "step": 2140
    },
    {
      "epoch": 3.21,
      "learning_rate": 2.137176938369781e-06,
      "loss": 0.7478,
      "step": 2150
    },
    {
      "epoch": 3.21,
      "learning_rate": 1.8886679920477135e-06,
      "loss": 0.6613,
      "step": 2160
    },
    {
      "epoch": 3.22,
      "learning_rate": 1.6401590457256463e-06,
      "loss": 0.6787,
      "step": 2170
    },
    {
      "epoch": 3.22,
      "learning_rate": 1.3916500994035787e-06,
      "loss": 0.8131,
      "step": 2180
    },
    {
      "epoch": 3.23,
      "learning_rate": 1.143141153081511e-06,
      "loss": 0.5204,
      "step": 2190
    },
    {
      "epoch": 3.23,
      "learning_rate": 8.946322067594434e-07,
      "loss": 0.5376,
      "step": 2200
    },
    {
      "epoch": 3.24,
      "learning_rate": 6.461232604373758e-07,
      "loss": 0.9021,
      "step": 2210
    },
    {
      "epoch": 3.24,
      "learning_rate": 3.9761431411530813e-07,
      "loss": 0.9006,
      "step": 2220
    },
    {
      "epoch": 3.25,
      "learning_rate": 1.4910536779324055e-07,
      "loss": 0.4548,
      "step": 2230
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.4383337870950177,
      "eval_loss": 0.9206746816635132,
      "eval_runtime": 739.7014,
      "eval_samples_per_second": 4.966,
      "eval_steps_per_second": 0.622,
      "step": 2236
    },
    {
      "epoch": 3.25,
      "step": 2236,
      "total_flos": 2.227130963787999e+19,
      "train_loss": 0.7353641163684388,
      "train_runtime": 8458.1965,
      "train_samples_per_second": 2.115,
      "train_steps_per_second": 0.264
    },
    {
      "epoch": 3.25,
      "eval_accuracy": 0.44131334022750773,
      "eval_loss": 0.9065404534339905,
      "eval_runtime": 794.9863,
      "eval_samples_per_second": 4.865,
      "eval_steps_per_second": 0.609,
      "step": 2236
    }
  ],
  "logging_steps": 10,
  "max_steps": 2236,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 2.227130963787999e+19,
  "trial_name": null,
  "trial_params": null
}