prateeky2806's picture
Training in progress, step 2000
107ffcc
raw
history blame
23.5 kB
{
"best_metric": 0.39367392659187317,
"best_model_checkpoint": "./output_v2/7b_cluster00_Nous-Hermes-llama-2-7b_partitioned_v3_standardized_00/checkpoint-1800",
"epoch": 2.1208907741251326,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5637,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.4775,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5079,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.4849,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.4587,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.4867,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 0.0002,
"loss": 0.4578,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 0.0002,
"loss": 0.4665,
"step": 80
},
{
"epoch": 0.1,
"learning_rate": 0.0002,
"loss": 0.5044,
"step": 90
},
{
"epoch": 0.11,
"learning_rate": 0.0002,
"loss": 0.4979,
"step": 100
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 0.4715,
"step": 110
},
{
"epoch": 0.13,
"learning_rate": 0.0002,
"loss": 0.4717,
"step": 120
},
{
"epoch": 0.14,
"learning_rate": 0.0002,
"loss": 0.4419,
"step": 130
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 0.4671,
"step": 140
},
{
"epoch": 0.16,
"learning_rate": 0.0002,
"loss": 0.4503,
"step": 150
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 0.4878,
"step": 160
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 0.4648,
"step": 170
},
{
"epoch": 0.19,
"learning_rate": 0.0002,
"loss": 0.4625,
"step": 180
},
{
"epoch": 0.2,
"learning_rate": 0.0002,
"loss": 0.4473,
"step": 190
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 0.4585,
"step": 200
},
{
"epoch": 0.21,
"eval_loss": 0.4498298466205597,
"eval_runtime": 253.5551,
"eval_samples_per_second": 3.944,
"eval_steps_per_second": 0.986,
"step": 200
},
{
"epoch": 0.22,
"learning_rate": 0.0002,
"loss": 0.4396,
"step": 210
},
{
"epoch": 0.23,
"learning_rate": 0.0002,
"loss": 0.4545,
"step": 220
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 0.4632,
"step": 230
},
{
"epoch": 0.25,
"learning_rate": 0.0002,
"loss": 0.4458,
"step": 240
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 0.4612,
"step": 250
},
{
"epoch": 0.28,
"learning_rate": 0.0002,
"loss": 0.4493,
"step": 260
},
{
"epoch": 0.29,
"learning_rate": 0.0002,
"loss": 0.4652,
"step": 270
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 0.4596,
"step": 280
},
{
"epoch": 0.31,
"learning_rate": 0.0002,
"loss": 0.4483,
"step": 290
},
{
"epoch": 0.32,
"learning_rate": 0.0002,
"loss": 0.4386,
"step": 300
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 0.4746,
"step": 310
},
{
"epoch": 0.34,
"learning_rate": 0.0002,
"loss": 0.4299,
"step": 320
},
{
"epoch": 0.35,
"learning_rate": 0.0002,
"loss": 0.4462,
"step": 330
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 0.4346,
"step": 340
},
{
"epoch": 0.37,
"learning_rate": 0.0002,
"loss": 0.4425,
"step": 350
},
{
"epoch": 0.38,
"learning_rate": 0.0002,
"loss": 0.4356,
"step": 360
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 0.4647,
"step": 370
},
{
"epoch": 0.4,
"learning_rate": 0.0002,
"loss": 0.4448,
"step": 380
},
{
"epoch": 0.41,
"learning_rate": 0.0002,
"loss": 0.4208,
"step": 390
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 0.4095,
"step": 400
},
{
"epoch": 0.42,
"eval_loss": 0.43381235003471375,
"eval_runtime": 253.5754,
"eval_samples_per_second": 3.944,
"eval_steps_per_second": 0.986,
"step": 400
},
{
"epoch": 0.43,
"learning_rate": 0.0002,
"loss": 0.4181,
"step": 410
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 0.445,
"step": 420
},
{
"epoch": 0.46,
"learning_rate": 0.0002,
"loss": 0.417,
"step": 430
},
{
"epoch": 0.47,
"learning_rate": 0.0002,
"loss": 0.438,
"step": 440
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 0.4376,
"step": 450
},
{
"epoch": 0.49,
"learning_rate": 0.0002,
"loss": 0.4249,
"step": 460
},
{
"epoch": 0.5,
"learning_rate": 0.0002,
"loss": 0.4407,
"step": 470
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 0.4506,
"step": 480
},
{
"epoch": 0.52,
"learning_rate": 0.0002,
"loss": 0.4289,
"step": 490
},
{
"epoch": 0.53,
"learning_rate": 0.0002,
"loss": 0.4596,
"step": 500
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 0.4174,
"step": 510
},
{
"epoch": 0.55,
"learning_rate": 0.0002,
"loss": 0.4373,
"step": 520
},
{
"epoch": 0.56,
"learning_rate": 0.0002,
"loss": 0.4253,
"step": 530
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 0.4243,
"step": 540
},
{
"epoch": 0.58,
"learning_rate": 0.0002,
"loss": 0.4455,
"step": 550
},
{
"epoch": 0.59,
"learning_rate": 0.0002,
"loss": 0.4362,
"step": 560
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 0.4364,
"step": 570
},
{
"epoch": 0.62,
"learning_rate": 0.0002,
"loss": 0.4257,
"step": 580
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 0.4193,
"step": 590
},
{
"epoch": 0.64,
"learning_rate": 0.0002,
"loss": 0.4233,
"step": 600
},
{
"epoch": 0.64,
"eval_loss": 0.42340007424354553,
"eval_runtime": 253.6896,
"eval_samples_per_second": 3.942,
"eval_steps_per_second": 0.985,
"step": 600
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 0.4047,
"step": 610
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 0.4329,
"step": 620
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 0.4423,
"step": 630
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 0.4192,
"step": 640
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 0.4183,
"step": 650
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 0.4268,
"step": 660
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 0.425,
"step": 670
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 0.4353,
"step": 680
},
{
"epoch": 0.73,
"learning_rate": 0.0002,
"loss": 0.411,
"step": 690
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 0.4155,
"step": 700
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 0.4066,
"step": 710
},
{
"epoch": 0.76,
"learning_rate": 0.0002,
"loss": 0.4216,
"step": 720
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 0.4294,
"step": 730
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 0.427,
"step": 740
},
{
"epoch": 0.8,
"learning_rate": 0.0002,
"loss": 0.4276,
"step": 750
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 0.4397,
"step": 760
},
{
"epoch": 0.82,
"learning_rate": 0.0002,
"loss": 0.4264,
"step": 770
},
{
"epoch": 0.83,
"learning_rate": 0.0002,
"loss": 0.4021,
"step": 780
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 0.4132,
"step": 790
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 0.4167,
"step": 800
},
{
"epoch": 0.85,
"eval_loss": 0.4146576523780823,
"eval_runtime": 253.792,
"eval_samples_per_second": 3.94,
"eval_steps_per_second": 0.985,
"step": 800
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 0.4234,
"step": 810
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 0.4192,
"step": 820
},
{
"epoch": 0.88,
"learning_rate": 0.0002,
"loss": 0.4132,
"step": 830
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 0.4091,
"step": 840
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 0.4153,
"step": 850
},
{
"epoch": 0.91,
"learning_rate": 0.0002,
"loss": 0.417,
"step": 860
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 0.4004,
"step": 870
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 0.4282,
"step": 880
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 0.4334,
"step": 890
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 0.4042,
"step": 900
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 0.4159,
"step": 910
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 0.3986,
"step": 920
},
{
"epoch": 0.99,
"learning_rate": 0.0002,
"loss": 0.4207,
"step": 930
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 0.4144,
"step": 940
},
{
"epoch": 1.01,
"learning_rate": 0.0002,
"loss": 0.3744,
"step": 950
},
{
"epoch": 1.02,
"learning_rate": 0.0002,
"loss": 0.3685,
"step": 960
},
{
"epoch": 1.03,
"learning_rate": 0.0002,
"loss": 0.3812,
"step": 970
},
{
"epoch": 1.04,
"learning_rate": 0.0002,
"loss": 0.3604,
"step": 980
},
{
"epoch": 1.05,
"learning_rate": 0.0002,
"loss": 0.3595,
"step": 990
},
{
"epoch": 1.06,
"learning_rate": 0.0002,
"loss": 0.3659,
"step": 1000
},
{
"epoch": 1.06,
"eval_loss": 0.4106157422065735,
"eval_runtime": 253.7163,
"eval_samples_per_second": 3.941,
"eval_steps_per_second": 0.985,
"step": 1000
},
{
"epoch": 1.07,
"learning_rate": 0.0002,
"loss": 0.3586,
"step": 1010
},
{
"epoch": 1.08,
"learning_rate": 0.0002,
"loss": 0.3645,
"step": 1020
},
{
"epoch": 1.09,
"learning_rate": 0.0002,
"loss": 0.3894,
"step": 1030
},
{
"epoch": 1.1,
"learning_rate": 0.0002,
"loss": 0.3591,
"step": 1040
},
{
"epoch": 1.11,
"learning_rate": 0.0002,
"loss": 0.363,
"step": 1050
},
{
"epoch": 1.12,
"learning_rate": 0.0002,
"loss": 0.3654,
"step": 1060
},
{
"epoch": 1.13,
"learning_rate": 0.0002,
"loss": 0.3903,
"step": 1070
},
{
"epoch": 1.15,
"learning_rate": 0.0002,
"loss": 0.3521,
"step": 1080
},
{
"epoch": 1.16,
"learning_rate": 0.0002,
"loss": 0.3698,
"step": 1090
},
{
"epoch": 1.17,
"learning_rate": 0.0002,
"loss": 0.3525,
"step": 1100
},
{
"epoch": 1.18,
"learning_rate": 0.0002,
"loss": 0.3749,
"step": 1110
},
{
"epoch": 1.19,
"learning_rate": 0.0002,
"loss": 0.357,
"step": 1120
},
{
"epoch": 1.2,
"learning_rate": 0.0002,
"loss": 0.3733,
"step": 1130
},
{
"epoch": 1.21,
"learning_rate": 0.0002,
"loss": 0.3956,
"step": 1140
},
{
"epoch": 1.22,
"learning_rate": 0.0002,
"loss": 0.3666,
"step": 1150
},
{
"epoch": 1.23,
"learning_rate": 0.0002,
"loss": 0.3694,
"step": 1160
},
{
"epoch": 1.24,
"learning_rate": 0.0002,
"loss": 0.3737,
"step": 1170
},
{
"epoch": 1.25,
"learning_rate": 0.0002,
"loss": 0.3623,
"step": 1180
},
{
"epoch": 1.26,
"learning_rate": 0.0002,
"loss": 0.3588,
"step": 1190
},
{
"epoch": 1.27,
"learning_rate": 0.0002,
"loss": 0.3494,
"step": 1200
},
{
"epoch": 1.27,
"eval_loss": 0.40632152557373047,
"eval_runtime": 253.8741,
"eval_samples_per_second": 3.939,
"eval_steps_per_second": 0.985,
"step": 1200
},
{
"epoch": 1.28,
"learning_rate": 0.0002,
"loss": 0.3791,
"step": 1210
},
{
"epoch": 1.29,
"learning_rate": 0.0002,
"loss": 0.3709,
"step": 1220
},
{
"epoch": 1.3,
"learning_rate": 0.0002,
"loss": 0.3647,
"step": 1230
},
{
"epoch": 1.31,
"learning_rate": 0.0002,
"loss": 0.3702,
"step": 1240
},
{
"epoch": 1.33,
"learning_rate": 0.0002,
"loss": 0.3774,
"step": 1250
},
{
"epoch": 1.34,
"learning_rate": 0.0002,
"loss": 0.3608,
"step": 1260
},
{
"epoch": 1.35,
"learning_rate": 0.0002,
"loss": 0.358,
"step": 1270
},
{
"epoch": 1.36,
"learning_rate": 0.0002,
"loss": 0.3576,
"step": 1280
},
{
"epoch": 1.37,
"learning_rate": 0.0002,
"loss": 0.3781,
"step": 1290
},
{
"epoch": 1.38,
"learning_rate": 0.0002,
"loss": 0.3658,
"step": 1300
},
{
"epoch": 1.39,
"learning_rate": 0.0002,
"loss": 0.3473,
"step": 1310
},
{
"epoch": 1.4,
"learning_rate": 0.0002,
"loss": 0.3546,
"step": 1320
},
{
"epoch": 1.41,
"learning_rate": 0.0002,
"loss": 0.3681,
"step": 1330
},
{
"epoch": 1.42,
"learning_rate": 0.0002,
"loss": 0.3491,
"step": 1340
},
{
"epoch": 1.43,
"learning_rate": 0.0002,
"loss": 0.3454,
"step": 1350
},
{
"epoch": 1.44,
"learning_rate": 0.0002,
"loss": 0.3786,
"step": 1360
},
{
"epoch": 1.45,
"learning_rate": 0.0002,
"loss": 0.3536,
"step": 1370
},
{
"epoch": 1.46,
"learning_rate": 0.0002,
"loss": 0.3607,
"step": 1380
},
{
"epoch": 1.47,
"learning_rate": 0.0002,
"loss": 0.372,
"step": 1390
},
{
"epoch": 1.48,
"learning_rate": 0.0002,
"loss": 0.3621,
"step": 1400
},
{
"epoch": 1.48,
"eval_loss": 0.40282392501831055,
"eval_runtime": 253.8219,
"eval_samples_per_second": 3.94,
"eval_steps_per_second": 0.985,
"step": 1400
},
{
"epoch": 1.5,
"learning_rate": 0.0002,
"loss": 0.3644,
"step": 1410
},
{
"epoch": 1.51,
"learning_rate": 0.0002,
"loss": 0.351,
"step": 1420
},
{
"epoch": 1.52,
"learning_rate": 0.0002,
"loss": 0.381,
"step": 1430
},
{
"epoch": 1.53,
"learning_rate": 0.0002,
"loss": 0.3589,
"step": 1440
},
{
"epoch": 1.54,
"learning_rate": 0.0002,
"loss": 0.3528,
"step": 1450
},
{
"epoch": 1.55,
"learning_rate": 0.0002,
"loss": 0.3597,
"step": 1460
},
{
"epoch": 1.56,
"learning_rate": 0.0002,
"loss": 0.3577,
"step": 1470
},
{
"epoch": 1.57,
"learning_rate": 0.0002,
"loss": 0.3595,
"step": 1480
},
{
"epoch": 1.58,
"learning_rate": 0.0002,
"loss": 0.3507,
"step": 1490
},
{
"epoch": 1.59,
"learning_rate": 0.0002,
"loss": 0.3478,
"step": 1500
},
{
"epoch": 1.6,
"learning_rate": 0.0002,
"loss": 0.363,
"step": 1510
},
{
"epoch": 1.61,
"learning_rate": 0.0002,
"loss": 0.3594,
"step": 1520
},
{
"epoch": 1.62,
"learning_rate": 0.0002,
"loss": 0.3531,
"step": 1530
},
{
"epoch": 1.63,
"learning_rate": 0.0002,
"loss": 0.3616,
"step": 1540
},
{
"epoch": 1.64,
"learning_rate": 0.0002,
"loss": 0.3534,
"step": 1550
},
{
"epoch": 1.65,
"learning_rate": 0.0002,
"loss": 0.3657,
"step": 1560
},
{
"epoch": 1.66,
"learning_rate": 0.0002,
"loss": 0.3859,
"step": 1570
},
{
"epoch": 1.68,
"learning_rate": 0.0002,
"loss": 0.3647,
"step": 1580
},
{
"epoch": 1.69,
"learning_rate": 0.0002,
"loss": 0.3659,
"step": 1590
},
{
"epoch": 1.7,
"learning_rate": 0.0002,
"loss": 0.3625,
"step": 1600
},
{
"epoch": 1.7,
"eval_loss": 0.3978842794895172,
"eval_runtime": 253.9522,
"eval_samples_per_second": 3.938,
"eval_steps_per_second": 0.984,
"step": 1600
},
{
"epoch": 1.71,
"learning_rate": 0.0002,
"loss": 0.3542,
"step": 1610
},
{
"epoch": 1.72,
"learning_rate": 0.0002,
"loss": 0.3683,
"step": 1620
},
{
"epoch": 1.73,
"learning_rate": 0.0002,
"loss": 0.3604,
"step": 1630
},
{
"epoch": 1.74,
"learning_rate": 0.0002,
"loss": 0.3709,
"step": 1640
},
{
"epoch": 1.75,
"learning_rate": 0.0002,
"loss": 0.3685,
"step": 1650
},
{
"epoch": 1.76,
"learning_rate": 0.0002,
"loss": 0.3584,
"step": 1660
},
{
"epoch": 1.77,
"learning_rate": 0.0002,
"loss": 0.3475,
"step": 1670
},
{
"epoch": 1.78,
"learning_rate": 0.0002,
"loss": 0.3759,
"step": 1680
},
{
"epoch": 1.79,
"learning_rate": 0.0002,
"loss": 0.3779,
"step": 1690
},
{
"epoch": 1.8,
"learning_rate": 0.0002,
"loss": 0.3607,
"step": 1700
},
{
"epoch": 1.81,
"learning_rate": 0.0002,
"loss": 0.3639,
"step": 1710
},
{
"epoch": 1.82,
"learning_rate": 0.0002,
"loss": 0.3451,
"step": 1720
},
{
"epoch": 1.83,
"learning_rate": 0.0002,
"loss": 0.3738,
"step": 1730
},
{
"epoch": 1.85,
"learning_rate": 0.0002,
"loss": 0.3384,
"step": 1740
},
{
"epoch": 1.86,
"learning_rate": 0.0002,
"loss": 0.3548,
"step": 1750
},
{
"epoch": 1.87,
"learning_rate": 0.0002,
"loss": 0.3633,
"step": 1760
},
{
"epoch": 1.88,
"learning_rate": 0.0002,
"loss": 0.3658,
"step": 1770
},
{
"epoch": 1.89,
"learning_rate": 0.0002,
"loss": 0.3422,
"step": 1780
},
{
"epoch": 1.9,
"learning_rate": 0.0002,
"loss": 0.3682,
"step": 1790
},
{
"epoch": 1.91,
"learning_rate": 0.0002,
"loss": 0.3397,
"step": 1800
},
{
"epoch": 1.91,
"eval_loss": 0.39367392659187317,
"eval_runtime": 254.0031,
"eval_samples_per_second": 3.937,
"eval_steps_per_second": 0.984,
"step": 1800
},
{
"epoch": 1.92,
"learning_rate": 0.0002,
"loss": 0.3424,
"step": 1810
},
{
"epoch": 1.93,
"learning_rate": 0.0002,
"loss": 0.3644,
"step": 1820
},
{
"epoch": 1.94,
"learning_rate": 0.0002,
"loss": 0.3605,
"step": 1830
},
{
"epoch": 1.95,
"learning_rate": 0.0002,
"loss": 0.3532,
"step": 1840
},
{
"epoch": 1.96,
"learning_rate": 0.0002,
"loss": 0.3598,
"step": 1850
},
{
"epoch": 1.97,
"learning_rate": 0.0002,
"loss": 0.3512,
"step": 1860
},
{
"epoch": 1.98,
"learning_rate": 0.0002,
"loss": 0.3539,
"step": 1870
},
{
"epoch": 1.99,
"learning_rate": 0.0002,
"loss": 0.3527,
"step": 1880
},
{
"epoch": 2.0,
"learning_rate": 0.0002,
"loss": 0.3396,
"step": 1890
},
{
"epoch": 2.01,
"learning_rate": 0.0002,
"loss": 0.2891,
"step": 1900
},
{
"epoch": 2.03,
"learning_rate": 0.0002,
"loss": 0.2841,
"step": 1910
},
{
"epoch": 2.04,
"learning_rate": 0.0002,
"loss": 0.2833,
"step": 1920
},
{
"epoch": 2.05,
"learning_rate": 0.0002,
"loss": 0.2818,
"step": 1930
},
{
"epoch": 2.06,
"learning_rate": 0.0002,
"loss": 0.3051,
"step": 1940
},
{
"epoch": 2.07,
"learning_rate": 0.0002,
"loss": 0.2943,
"step": 1950
},
{
"epoch": 2.08,
"learning_rate": 0.0002,
"loss": 0.2801,
"step": 1960
},
{
"epoch": 2.09,
"learning_rate": 0.0002,
"loss": 0.2891,
"step": 1970
},
{
"epoch": 2.1,
"learning_rate": 0.0002,
"loss": 0.2887,
"step": 1980
},
{
"epoch": 2.11,
"learning_rate": 0.0002,
"loss": 0.292,
"step": 1990
},
{
"epoch": 2.12,
"learning_rate": 0.0002,
"loss": 0.2921,
"step": 2000
},
{
"epoch": 2.12,
"eval_loss": 0.4052470624446869,
"eval_runtime": 253.9413,
"eval_samples_per_second": 3.938,
"eval_steps_per_second": 0.984,
"step": 2000
}
],
"max_steps": 5000,
"num_train_epochs": 6,
"total_flos": 5.497566144534282e+17,
"trial_name": null,
"trial_params": null
}