redpajama-3b-evol-coder / trainer_state.json
ray
add file
f3aab75
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.3579935988247023,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 3.0000000000000004e-08,
"loss": 1.3803,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 8e-08,
"loss": 1.3294,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 1.3e-07,
"loss": 1.2867,
"step": 30
},
{
"epoch": 0.07,
"learning_rate": 1.8e-07,
"loss": 1.2626,
"step": 40
},
{
"epoch": 0.08,
"learning_rate": 2.3000000000000002e-07,
"loss": 1.2373,
"step": 50
},
{
"epoch": 0.1,
"learning_rate": 2.8e-07,
"loss": 1.2286,
"step": 60
},
{
"epoch": 0.12,
"learning_rate": 3.3e-07,
"loss": 1.2056,
"step": 70
},
{
"epoch": 0.13,
"learning_rate": 3.8e-07,
"loss": 1.2047,
"step": 80
},
{
"epoch": 0.15,
"learning_rate": 4.3e-07,
"loss": 1.1813,
"step": 90
},
{
"epoch": 0.17,
"learning_rate": 4.800000000000001e-07,
"loss": 1.1672,
"step": 100
},
{
"epoch": 0.18,
"learning_rate": 5.3e-07,
"loss": 1.1585,
"step": 110
},
{
"epoch": 0.2,
"learning_rate": 5.800000000000001e-07,
"loss": 1.1429,
"step": 120
},
{
"epoch": 0.22,
"learning_rate": 6.3e-07,
"loss": 1.1384,
"step": 130
},
{
"epoch": 0.24,
"learning_rate": 6.800000000000001e-07,
"loss": 1.1265,
"step": 140
},
{
"epoch": 0.25,
"learning_rate": 7.3e-07,
"loss": 1.1375,
"step": 150
},
{
"epoch": 0.27,
"learning_rate": 7.8e-07,
"loss": 1.1396,
"step": 160
},
{
"epoch": 0.29,
"learning_rate": 8.300000000000001e-07,
"loss": 1.1302,
"step": 170
},
{
"epoch": 0.3,
"learning_rate": 8.8e-07,
"loss": 1.1213,
"step": 180
},
{
"epoch": 0.32,
"learning_rate": 9.300000000000001e-07,
"loss": 1.1183,
"step": 190
},
{
"epoch": 0.34,
"learning_rate": 9.800000000000001e-07,
"loss": 1.1081,
"step": 200
},
{
"epoch": 0.35,
"learning_rate": 1.03e-06,
"loss": 1.0939,
"step": 210
},
{
"epoch": 0.37,
"learning_rate": 1.08e-06,
"loss": 1.0826,
"step": 220
},
{
"epoch": 0.39,
"learning_rate": 1.1300000000000002e-06,
"loss": 1.1104,
"step": 230
},
{
"epoch": 0.4,
"learning_rate": 1.1800000000000001e-06,
"loss": 1.111,
"step": 240
},
{
"epoch": 0.42,
"learning_rate": 1.23e-06,
"loss": 1.0862,
"step": 250
},
{
"epoch": 0.44,
"learning_rate": 1.28e-06,
"loss": 1.0783,
"step": 260
},
{
"epoch": 0.45,
"learning_rate": 1.3300000000000002e-06,
"loss": 1.0762,
"step": 270
},
{
"epoch": 0.47,
"learning_rate": 1.3800000000000001e-06,
"loss": 1.0928,
"step": 280
},
{
"epoch": 0.49,
"learning_rate": 1.43e-06,
"loss": 1.0884,
"step": 290
},
{
"epoch": 0.5,
"learning_rate": 1.48e-06,
"loss": 1.068,
"step": 300
},
{
"epoch": 0.52,
"learning_rate": 1.5300000000000002e-06,
"loss": 1.0785,
"step": 310
},
{
"epoch": 0.54,
"learning_rate": 1.5800000000000001e-06,
"loss": 1.0538,
"step": 320
},
{
"epoch": 0.55,
"learning_rate": 1.6300000000000003e-06,
"loss": 1.0734,
"step": 330
},
{
"epoch": 0.57,
"learning_rate": 1.6800000000000002e-06,
"loss": 1.0642,
"step": 340
},
{
"epoch": 0.59,
"learning_rate": 1.73e-06,
"loss": 1.067,
"step": 350
},
{
"epoch": 0.6,
"learning_rate": 1.7800000000000001e-06,
"loss": 1.079,
"step": 360
},
{
"epoch": 0.62,
"learning_rate": 1.83e-06,
"loss": 1.048,
"step": 370
},
{
"epoch": 0.64,
"learning_rate": 1.8800000000000002e-06,
"loss": 1.0571,
"step": 380
},
{
"epoch": 0.65,
"learning_rate": 1.93e-06,
"loss": 1.0617,
"step": 390
},
{
"epoch": 0.67,
"learning_rate": 1.98e-06,
"loss": 1.0644,
"step": 400
},
{
"epoch": 0.69,
"learning_rate": 2.0300000000000005e-06,
"loss": 1.0569,
"step": 410
},
{
"epoch": 0.71,
"learning_rate": 2.08e-06,
"loss": 1.0429,
"step": 420
},
{
"epoch": 0.72,
"learning_rate": 2.13e-06,
"loss": 1.03,
"step": 430
},
{
"epoch": 0.74,
"learning_rate": 2.1800000000000003e-06,
"loss": 1.0449,
"step": 440
},
{
"epoch": 0.76,
"learning_rate": 2.2300000000000002e-06,
"loss": 1.0462,
"step": 450
},
{
"epoch": 0.77,
"learning_rate": 2.28e-06,
"loss": 1.0272,
"step": 460
},
{
"epoch": 0.79,
"learning_rate": 2.33e-06,
"loss": 1.0221,
"step": 470
},
{
"epoch": 0.81,
"learning_rate": 2.38e-06,
"loss": 1.0307,
"step": 480
},
{
"epoch": 0.82,
"learning_rate": 2.43e-06,
"loss": 1.048,
"step": 490
},
{
"epoch": 0.84,
"learning_rate": 2.4800000000000004e-06,
"loss": 1.0376,
"step": 500
},
{
"epoch": 0.84,
"eval_code_evol_accuracy": 0.7292901919811937,
"eval_code_evol_loss": 1.0595703125,
"eval_code_evol_runtime": 44.6855,
"eval_code_evol_samples_per_second": 17.254,
"eval_code_evol_steps_per_second": 2.171,
"step": 500
},
{
"epoch": 0.86,
"learning_rate": 2.5300000000000003e-06,
"loss": 1.0246,
"step": 510
},
{
"epoch": 0.87,
"learning_rate": 2.5800000000000003e-06,
"loss": 1.0309,
"step": 520
},
{
"epoch": 0.89,
"learning_rate": 2.6300000000000002e-06,
"loss": 1.0391,
"step": 530
},
{
"epoch": 0.91,
"learning_rate": 2.68e-06,
"loss": 1.0193,
"step": 540
},
{
"epoch": 0.92,
"learning_rate": 2.7300000000000005e-06,
"loss": 1.0039,
"step": 550
},
{
"epoch": 0.94,
"learning_rate": 2.7800000000000005e-06,
"loss": 1.0271,
"step": 560
},
{
"epoch": 0.96,
"learning_rate": 2.83e-06,
"loss": 1.0269,
"step": 570
},
{
"epoch": 0.97,
"learning_rate": 2.88e-06,
"loss": 1.0103,
"step": 580
},
{
"epoch": 0.99,
"learning_rate": 2.93e-06,
"loss": 1.0012,
"step": 590
},
{
"epoch": 1.01,
"learning_rate": 2.9800000000000003e-06,
"loss": 1.0011,
"step": 600
},
{
"epoch": 1.02,
"learning_rate": 3.0300000000000002e-06,
"loss": 0.9842,
"step": 610
},
{
"epoch": 1.04,
"learning_rate": 3.08e-06,
"loss": 0.9918,
"step": 620
},
{
"epoch": 1.06,
"learning_rate": 3.13e-06,
"loss": 0.985,
"step": 630
},
{
"epoch": 1.07,
"learning_rate": 3.1800000000000005e-06,
"loss": 0.988,
"step": 640
},
{
"epoch": 1.09,
"learning_rate": 3.2300000000000004e-06,
"loss": 0.9832,
"step": 650
},
{
"epoch": 1.11,
"learning_rate": 3.2800000000000004e-06,
"loss": 0.97,
"step": 660
},
{
"epoch": 1.12,
"learning_rate": 3.3300000000000003e-06,
"loss": 0.9699,
"step": 670
},
{
"epoch": 1.14,
"learning_rate": 3.3800000000000007e-06,
"loss": 0.983,
"step": 680
},
{
"epoch": 1.16,
"learning_rate": 3.4300000000000006e-06,
"loss": 0.9789,
"step": 690
},
{
"epoch": 1.18,
"learning_rate": 3.48e-06,
"loss": 0.9783,
"step": 700
},
{
"epoch": 1.19,
"learning_rate": 3.53e-06,
"loss": 0.9805,
"step": 710
},
{
"epoch": 1.21,
"learning_rate": 3.58e-06,
"loss": 0.9764,
"step": 720
},
{
"epoch": 1.23,
"learning_rate": 3.6300000000000004e-06,
"loss": 0.9754,
"step": 730
},
{
"epoch": 1.24,
"learning_rate": 3.6800000000000003e-06,
"loss": 0.9765,
"step": 740
},
{
"epoch": 1.26,
"learning_rate": 3.7300000000000003e-06,
"loss": 0.9637,
"step": 750
},
{
"epoch": 1.28,
"learning_rate": 3.7800000000000002e-06,
"loss": 0.9689,
"step": 760
},
{
"epoch": 1.29,
"learning_rate": 3.830000000000001e-06,
"loss": 0.9847,
"step": 770
},
{
"epoch": 1.31,
"learning_rate": 3.88e-06,
"loss": 0.9646,
"step": 780
},
{
"epoch": 1.33,
"learning_rate": 3.9300000000000005e-06,
"loss": 0.9844,
"step": 790
},
{
"epoch": 1.34,
"learning_rate": 3.980000000000001e-06,
"loss": 0.9678,
"step": 800
},
{
"epoch": 1.36,
"learning_rate": 4.03e-06,
"loss": 0.9597,
"step": 810
},
{
"epoch": 1.38,
"learning_rate": 4.08e-06,
"loss": 0.981,
"step": 820
},
{
"epoch": 1.39,
"learning_rate": 4.13e-06,
"loss": 0.9736,
"step": 830
},
{
"epoch": 1.41,
"learning_rate": 4.18e-06,
"loss": 0.9702,
"step": 840
},
{
"epoch": 1.43,
"learning_rate": 4.23e-06,
"loss": 0.9676,
"step": 850
},
{
"epoch": 1.44,
"learning_rate": 4.2800000000000005e-06,
"loss": 0.975,
"step": 860
},
{
"epoch": 1.46,
"learning_rate": 4.33e-06,
"loss": 0.961,
"step": 870
},
{
"epoch": 1.48,
"learning_rate": 4.38e-06,
"loss": 0.9572,
"step": 880
},
{
"epoch": 1.49,
"learning_rate": 4.430000000000001e-06,
"loss": 0.9637,
"step": 890
},
{
"epoch": 1.51,
"learning_rate": 4.48e-06,
"loss": 0.9625,
"step": 900
},
{
"epoch": 1.53,
"learning_rate": 4.530000000000001e-06,
"loss": 0.9634,
"step": 910
},
{
"epoch": 1.54,
"learning_rate": 4.58e-06,
"loss": 0.9524,
"step": 920
},
{
"epoch": 1.56,
"learning_rate": 4.6300000000000006e-06,
"loss": 0.957,
"step": 930
},
{
"epoch": 1.58,
"learning_rate": 4.680000000000001e-06,
"loss": 0.9609,
"step": 940
},
{
"epoch": 1.6,
"learning_rate": 4.7300000000000005e-06,
"loss": 0.9684,
"step": 950
},
{
"epoch": 1.61,
"learning_rate": 4.78e-06,
"loss": 0.9607,
"step": 960
},
{
"epoch": 1.63,
"learning_rate": 4.83e-06,
"loss": 0.9577,
"step": 970
},
{
"epoch": 1.65,
"learning_rate": 4.880000000000001e-06,
"loss": 0.9614,
"step": 980
},
{
"epoch": 1.66,
"learning_rate": 4.93e-06,
"loss": 0.953,
"step": 990
},
{
"epoch": 1.68,
"learning_rate": 4.980000000000001e-06,
"loss": 0.9679,
"step": 1000
},
{
"epoch": 1.68,
"eval_code_evol_accuracy": 0.7400189369204649,
"eval_code_evol_loss": 1.001953125,
"eval_code_evol_runtime": 44.1999,
"eval_code_evol_samples_per_second": 17.443,
"eval_code_evol_steps_per_second": 2.195,
"step": 1000
},
{
"epoch": 1.7,
"learning_rate": 5.03e-06,
"loss": 0.949,
"step": 1010
},
{
"epoch": 1.71,
"learning_rate": 5.0800000000000005e-06,
"loss": 0.9567,
"step": 1020
},
{
"epoch": 1.73,
"learning_rate": 5.130000000000001e-06,
"loss": 0.9527,
"step": 1030
},
{
"epoch": 1.75,
"learning_rate": 5.18e-06,
"loss": 0.9614,
"step": 1040
},
{
"epoch": 1.76,
"learning_rate": 5.230000000000001e-06,
"loss": 0.9595,
"step": 1050
},
{
"epoch": 1.78,
"learning_rate": 5.28e-06,
"loss": 0.9482,
"step": 1060
},
{
"epoch": 1.8,
"learning_rate": 5.330000000000001e-06,
"loss": 0.9403,
"step": 1070
},
{
"epoch": 1.81,
"learning_rate": 5.380000000000001e-06,
"loss": 0.9386,
"step": 1080
},
{
"epoch": 1.83,
"learning_rate": 5.4300000000000005e-06,
"loss": 0.9663,
"step": 1090
},
{
"epoch": 1.85,
"learning_rate": 5.480000000000001e-06,
"loss": 0.9491,
"step": 1100
},
{
"epoch": 1.86,
"learning_rate": 5.530000000000001e-06,
"loss": 0.9638,
"step": 1110
},
{
"epoch": 1.88,
"learning_rate": 5.580000000000001e-06,
"loss": 0.9728,
"step": 1120
},
{
"epoch": 1.9,
"learning_rate": 5.63e-06,
"loss": 0.9551,
"step": 1130
},
{
"epoch": 1.91,
"learning_rate": 5.68e-06,
"loss": 0.9432,
"step": 1140
},
{
"epoch": 1.93,
"learning_rate": 5.73e-06,
"loss": 0.9517,
"step": 1150
},
{
"epoch": 1.95,
"learning_rate": 5.78e-06,
"loss": 0.9448,
"step": 1160
},
{
"epoch": 1.96,
"learning_rate": 5.83e-06,
"loss": 0.954,
"step": 1170
},
{
"epoch": 1.98,
"learning_rate": 5.8800000000000005e-06,
"loss": 0.9402,
"step": 1180
},
{
"epoch": 2.0,
"learning_rate": 5.93e-06,
"loss": 0.9257,
"step": 1190
},
{
"epoch": 2.01,
"learning_rate": 5.98e-06,
"loss": 0.8889,
"step": 1200
},
{
"epoch": 2.03,
"learning_rate": 6.030000000000001e-06,
"loss": 0.8903,
"step": 1210
},
{
"epoch": 2.05,
"learning_rate": 6.08e-06,
"loss": 0.8778,
"step": 1220
},
{
"epoch": 2.07,
"learning_rate": 6.130000000000001e-06,
"loss": 0.8759,
"step": 1230
},
{
"epoch": 2.08,
"learning_rate": 6.18e-06,
"loss": 0.8957,
"step": 1240
},
{
"epoch": 2.1,
"learning_rate": 6.2300000000000005e-06,
"loss": 0.8805,
"step": 1250
},
{
"epoch": 2.12,
"learning_rate": 6.280000000000001e-06,
"loss": 0.882,
"step": 1260
},
{
"epoch": 2.13,
"learning_rate": 6.33e-06,
"loss": 0.8887,
"step": 1270
},
{
"epoch": 2.15,
"learning_rate": 6.380000000000001e-06,
"loss": 0.8692,
"step": 1280
},
{
"epoch": 2.17,
"learning_rate": 6.43e-06,
"loss": 0.896,
"step": 1290
},
{
"epoch": 2.18,
"learning_rate": 6.480000000000001e-06,
"loss": 0.8724,
"step": 1300
},
{
"epoch": 2.2,
"learning_rate": 6.530000000000001e-06,
"loss": 0.8705,
"step": 1310
},
{
"epoch": 2.22,
"learning_rate": 6.5800000000000005e-06,
"loss": 0.8805,
"step": 1320
},
{
"epoch": 2.23,
"learning_rate": 6.630000000000001e-06,
"loss": 0.8804,
"step": 1330
},
{
"epoch": 2.25,
"learning_rate": 6.680000000000001e-06,
"loss": 0.8864,
"step": 1340
},
{
"epoch": 2.27,
"learning_rate": 6.730000000000001e-06,
"loss": 0.8908,
"step": 1350
},
{
"epoch": 2.28,
"learning_rate": 6.780000000000001e-06,
"loss": 0.8836,
"step": 1360
},
{
"epoch": 2.3,
"learning_rate": 6.830000000000001e-06,
"loss": 0.8817,
"step": 1370
},
{
"epoch": 2.32,
"learning_rate": 6.88e-06,
"loss": 0.8825,
"step": 1380
},
{
"epoch": 2.33,
"learning_rate": 6.93e-06,
"loss": 0.8928,
"step": 1390
},
{
"epoch": 2.35,
"learning_rate": 6.98e-06,
"loss": 0.885,
"step": 1400
},
{
"epoch": 2.37,
"learning_rate": 7.0300000000000005e-06,
"loss": 0.8756,
"step": 1410
},
{
"epoch": 2.38,
"learning_rate": 7.08e-06,
"loss": 0.8945,
"step": 1420
},
{
"epoch": 2.4,
"learning_rate": 7.13e-06,
"loss": 0.8712,
"step": 1430
},
{
"epoch": 2.42,
"learning_rate": 7.180000000000001e-06,
"loss": 0.8992,
"step": 1440
},
{
"epoch": 2.43,
"learning_rate": 7.23e-06,
"loss": 0.8687,
"step": 1450
},
{
"epoch": 2.45,
"learning_rate": 7.280000000000001e-06,
"loss": 0.8896,
"step": 1460
},
{
"epoch": 2.47,
"learning_rate": 7.33e-06,
"loss": 0.8853,
"step": 1470
},
{
"epoch": 2.48,
"learning_rate": 7.3800000000000005e-06,
"loss": 0.866,
"step": 1480
},
{
"epoch": 2.5,
"learning_rate": 7.430000000000001e-06,
"loss": 0.8834,
"step": 1490
},
{
"epoch": 2.52,
"learning_rate": 7.48e-06,
"loss": 0.8657,
"step": 1500
},
{
"epoch": 2.52,
"eval_code_evol_accuracy": 0.7452004701580254,
"eval_code_evol_loss": 0.98095703125,
"eval_code_evol_runtime": 43.1875,
"eval_code_evol_samples_per_second": 17.852,
"eval_code_evol_steps_per_second": 2.246,
"step": 1500
},
{
"epoch": 2.54,
"learning_rate": 7.530000000000001e-06,
"loss": 0.8986,
"step": 1510
},
{
"epoch": 2.55,
"learning_rate": 7.58e-06,
"loss": 0.8768,
"step": 1520
},
{
"epoch": 2.57,
"learning_rate": 7.630000000000001e-06,
"loss": 0.8873,
"step": 1530
},
{
"epoch": 2.59,
"learning_rate": 7.680000000000001e-06,
"loss": 0.8836,
"step": 1540
},
{
"epoch": 2.6,
"learning_rate": 7.73e-06,
"loss": 0.8689,
"step": 1550
},
{
"epoch": 2.62,
"learning_rate": 7.78e-06,
"loss": 0.8896,
"step": 1560
},
{
"epoch": 2.64,
"learning_rate": 7.830000000000001e-06,
"loss": 0.8916,
"step": 1570
},
{
"epoch": 2.65,
"learning_rate": 7.88e-06,
"loss": 0.8654,
"step": 1580
},
{
"epoch": 2.67,
"learning_rate": 7.93e-06,
"loss": 0.8742,
"step": 1590
},
{
"epoch": 2.69,
"learning_rate": 7.980000000000002e-06,
"loss": 0.8822,
"step": 1600
},
{
"epoch": 2.7,
"learning_rate": 8.030000000000001e-06,
"loss": 0.8699,
"step": 1610
},
{
"epoch": 2.72,
"learning_rate": 8.08e-06,
"loss": 0.8759,
"step": 1620
},
{
"epoch": 2.74,
"learning_rate": 8.13e-06,
"loss": 0.879,
"step": 1630
},
{
"epoch": 2.75,
"learning_rate": 8.18e-06,
"loss": 0.8819,
"step": 1640
},
{
"epoch": 2.77,
"learning_rate": 8.23e-06,
"loss": 0.8797,
"step": 1650
},
{
"epoch": 2.79,
"learning_rate": 8.28e-06,
"loss": 0.8706,
"step": 1660
},
{
"epoch": 2.8,
"learning_rate": 8.33e-06,
"loss": 0.8732,
"step": 1670
},
{
"epoch": 2.82,
"learning_rate": 8.380000000000001e-06,
"loss": 0.8829,
"step": 1680
},
{
"epoch": 2.84,
"learning_rate": 8.43e-06,
"loss": 0.8914,
"step": 1690
},
{
"epoch": 2.85,
"learning_rate": 8.48e-06,
"loss": 0.8692,
"step": 1700
},
{
"epoch": 2.87,
"learning_rate": 8.530000000000001e-06,
"loss": 0.8975,
"step": 1710
},
{
"epoch": 2.89,
"learning_rate": 8.580000000000001e-06,
"loss": 0.8762,
"step": 1720
},
{
"epoch": 2.9,
"learning_rate": 8.63e-06,
"loss": 0.8955,
"step": 1730
},
{
"epoch": 2.92,
"learning_rate": 8.68e-06,
"loss": 0.8853,
"step": 1740
},
{
"epoch": 2.94,
"learning_rate": 8.730000000000001e-06,
"loss": 0.8702,
"step": 1750
},
{
"epoch": 2.96,
"learning_rate": 8.78e-06,
"loss": 0.8824,
"step": 1760
},
{
"epoch": 2.97,
"learning_rate": 8.83e-06,
"loss": 0.8839,
"step": 1770
},
{
"epoch": 2.99,
"learning_rate": 8.880000000000001e-06,
"loss": 0.885,
"step": 1780
},
{
"epoch": 3.01,
"learning_rate": 8.930000000000001e-06,
"loss": 0.8535,
"step": 1790
},
{
"epoch": 3.02,
"learning_rate": 8.98e-06,
"loss": 0.7718,
"step": 1800
},
{
"epoch": 3.04,
"learning_rate": 9.030000000000002e-06,
"loss": 0.7874,
"step": 1810
},
{
"epoch": 3.06,
"learning_rate": 9.080000000000001e-06,
"loss": 0.7935,
"step": 1820
},
{
"epoch": 3.07,
"learning_rate": 9.13e-06,
"loss": 0.7874,
"step": 1830
},
{
"epoch": 3.09,
"learning_rate": 9.180000000000002e-06,
"loss": 0.7963,
"step": 1840
},
{
"epoch": 3.11,
"learning_rate": 9.230000000000001e-06,
"loss": 0.7788,
"step": 1850
},
{
"epoch": 3.12,
"learning_rate": 9.280000000000001e-06,
"loss": 0.7856,
"step": 1860
},
{
"epoch": 3.14,
"learning_rate": 9.33e-06,
"loss": 0.7824,
"step": 1870
},
{
"epoch": 3.16,
"learning_rate": 9.38e-06,
"loss": 0.7942,
"step": 1880
},
{
"epoch": 3.17,
"learning_rate": 9.43e-06,
"loss": 0.7846,
"step": 1890
},
{
"epoch": 3.19,
"learning_rate": 9.48e-06,
"loss": 0.7971,
"step": 1900
},
{
"epoch": 3.21,
"learning_rate": 9.53e-06,
"loss": 0.7914,
"step": 1910
},
{
"epoch": 3.22,
"learning_rate": 9.58e-06,
"loss": 0.7873,
"step": 1920
},
{
"epoch": 3.24,
"learning_rate": 9.630000000000001e-06,
"loss": 0.7815,
"step": 1930
},
{
"epoch": 3.26,
"learning_rate": 9.68e-06,
"loss": 0.7958,
"step": 1940
},
{
"epoch": 3.27,
"learning_rate": 9.73e-06,
"loss": 0.7875,
"step": 1950
},
{
"epoch": 3.29,
"learning_rate": 9.780000000000001e-06,
"loss": 0.7968,
"step": 1960
},
{
"epoch": 3.31,
"learning_rate": 9.83e-06,
"loss": 0.7834,
"step": 1970
},
{
"epoch": 3.32,
"learning_rate": 9.88e-06,
"loss": 0.7935,
"step": 1980
},
{
"epoch": 3.34,
"learning_rate": 9.930000000000001e-06,
"loss": 0.7894,
"step": 1990
},
{
"epoch": 3.36,
"learning_rate": 9.980000000000001e-06,
"loss": 0.7908,
"step": 2000
},
{
"epoch": 3.36,
"eval_code_evol_accuracy": 0.7468688781507118,
"eval_code_evol_loss": 0.9775390625,
"eval_code_evol_runtime": 44.2366,
"eval_code_evol_samples_per_second": 17.429,
"eval_code_evol_steps_per_second": 2.193,
"step": 2000
}
],
"max_steps": 4760,
"num_train_epochs": 8,
"total_flos": 832756800815104.0,
"trial_name": null,
"trial_params": null
}