joelniklaus's picture
Training in progress, step 100000
ab71c8f
raw
history blame
12.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.1,
"global_step": 100000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.0000000000000003e-06,
"loss": 6.7042,
"step": 1000
},
{
"epoch": 0.0,
"learning_rate": 4.000000000000001e-06,
"loss": 5.1179,
"step": 2000
},
{
"epoch": 0.0,
"learning_rate": 6e-06,
"loss": 4.5505,
"step": 3000
},
{
"epoch": 0.0,
"learning_rate": 8.000000000000001e-06,
"loss": 4.3111,
"step": 4000
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 4.0888,
"step": 5000
},
{
"epoch": 0.01,
"learning_rate": 1.2e-05,
"loss": 3.9555,
"step": 6000
},
{
"epoch": 0.01,
"learning_rate": 1.4000000000000001e-05,
"loss": 3.8349,
"step": 7000
},
{
"epoch": 0.01,
"learning_rate": 1.6000000000000003e-05,
"loss": 3.8199,
"step": 8000
},
{
"epoch": 0.01,
"learning_rate": 1.8e-05,
"loss": 3.6237,
"step": 9000
},
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 3.7137,
"step": 10000
},
{
"epoch": 0.01,
"learning_rate": 2.2000000000000003e-05,
"loss": 3.5308,
"step": 11000
},
{
"epoch": 0.01,
"learning_rate": 2.4e-05,
"loss": 3.3471,
"step": 12000
},
{
"epoch": 0.01,
"learning_rate": 2.6000000000000002e-05,
"loss": 3.2095,
"step": 13000
},
{
"epoch": 0.01,
"learning_rate": 2.8000000000000003e-05,
"loss": 3.1049,
"step": 14000
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 2.9958,
"step": 15000
},
{
"epoch": 0.02,
"learning_rate": 3.2000000000000005e-05,
"loss": 2.8518,
"step": 16000
},
{
"epoch": 0.02,
"learning_rate": 3.4000000000000007e-05,
"loss": 2.7929,
"step": 17000
},
{
"epoch": 0.02,
"learning_rate": 3.6e-05,
"loss": 2.6958,
"step": 18000
},
{
"epoch": 0.02,
"learning_rate": 3.8e-05,
"loss": 2.7341,
"step": 19000
},
{
"epoch": 0.02,
"learning_rate": 4e-05,
"loss": 2.6605,
"step": 20000
},
{
"epoch": 0.02,
"learning_rate": 4.2e-05,
"loss": 2.5796,
"step": 21000
},
{
"epoch": 0.02,
"learning_rate": 4.4000000000000006e-05,
"loss": 2.499,
"step": 22000
},
{
"epoch": 0.02,
"learning_rate": 4.600000000000001e-05,
"loss": 2.4217,
"step": 23000
},
{
"epoch": 0.02,
"learning_rate": 4.8e-05,
"loss": 2.285,
"step": 24000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 2.2433,
"step": 25000
},
{
"epoch": 0.03,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.8565,
"step": 26000
},
{
"epoch": 0.03,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.6906,
"step": 27000
},
{
"epoch": 0.03,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.6053,
"step": 28000
},
{
"epoch": 0.03,
"learning_rate": 5.8e-05,
"loss": 1.5208,
"step": 29000
},
{
"epoch": 0.03,
"learning_rate": 6e-05,
"loss": 1.4884,
"step": 30000
},
{
"epoch": 0.03,
"learning_rate": 6.2e-05,
"loss": 1.4536,
"step": 31000
},
{
"epoch": 0.03,
"learning_rate": 6.400000000000001e-05,
"loss": 1.4163,
"step": 32000
},
{
"epoch": 0.03,
"learning_rate": 6.6e-05,
"loss": 1.3619,
"step": 33000
},
{
"epoch": 0.03,
"learning_rate": 6.800000000000001e-05,
"loss": 1.3432,
"step": 34000
},
{
"epoch": 0.04,
"learning_rate": 7e-05,
"loss": 1.3435,
"step": 35000
},
{
"epoch": 0.04,
"learning_rate": 7.2e-05,
"loss": 1.3395,
"step": 36000
},
{
"epoch": 0.04,
"learning_rate": 7.4e-05,
"loss": 1.3372,
"step": 37000
},
{
"epoch": 0.04,
"learning_rate": 7.6e-05,
"loss": 1.3257,
"step": 38000
},
{
"epoch": 0.04,
"learning_rate": 7.800000000000001e-05,
"loss": 1.2969,
"step": 39000
},
{
"epoch": 0.04,
"learning_rate": 8e-05,
"loss": 1.2716,
"step": 40000
},
{
"epoch": 0.04,
"learning_rate": 8.2e-05,
"loss": 1.2637,
"step": 41000
},
{
"epoch": 0.04,
"learning_rate": 8.4e-05,
"loss": 1.2254,
"step": 42000
},
{
"epoch": 0.04,
"learning_rate": 8.6e-05,
"loss": 1.257,
"step": 43000
},
{
"epoch": 0.04,
"learning_rate": 8.800000000000001e-05,
"loss": 1.2555,
"step": 44000
},
{
"epoch": 0.04,
"learning_rate": 9e-05,
"loss": 1.258,
"step": 45000
},
{
"epoch": 0.05,
"learning_rate": 9.200000000000001e-05,
"loss": 1.2429,
"step": 46000
},
{
"epoch": 0.05,
"learning_rate": 9.4e-05,
"loss": 1.2297,
"step": 47000
},
{
"epoch": 0.05,
"learning_rate": 9.6e-05,
"loss": 1.2281,
"step": 48000
},
{
"epoch": 0.05,
"learning_rate": 9.8e-05,
"loss": 1.1976,
"step": 49000
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 1.193,
"step": 50000
},
{
"epoch": 0.05,
"eval_loss": 0.6851979494094849,
"eval_runtime": 114.3167,
"eval_samples_per_second": 43.738,
"eval_steps_per_second": 0.691,
"step": 50000
},
{
"epoch": 0.05,
"learning_rate": 9.999972660400536e-05,
"loss": 1.2195,
"step": 51000
},
{
"epoch": 0.05,
"learning_rate": 9.999890641901125e-05,
"loss": 1.1675,
"step": 52000
},
{
"epoch": 0.05,
"learning_rate": 9.999753945398704e-05,
"loss": 1.1804,
"step": 53000
},
{
"epoch": 0.05,
"learning_rate": 9.99956257238817e-05,
"loss": 1.1654,
"step": 54000
},
{
"epoch": 0.06,
"learning_rate": 9.999316524962345e-05,
"loss": 1.1731,
"step": 55000
},
{
"epoch": 0.06,
"learning_rate": 9.999015805811965e-05,
"loss": 1.1482,
"step": 56000
},
{
"epoch": 0.06,
"learning_rate": 9.998660418225645e-05,
"loss": 1.136,
"step": 57000
},
{
"epoch": 0.06,
"learning_rate": 9.998250366089848e-05,
"loss": 1.1142,
"step": 58000
},
{
"epoch": 0.06,
"learning_rate": 9.997785653888835e-05,
"loss": 1.1169,
"step": 59000
},
{
"epoch": 0.06,
"learning_rate": 9.997266286704631e-05,
"loss": 1.105,
"step": 60000
},
{
"epoch": 0.06,
"learning_rate": 9.996692270216947e-05,
"loss": 1.106,
"step": 61000
},
{
"epoch": 0.06,
"learning_rate": 9.996063610703137e-05,
"loss": 1.1023,
"step": 62000
},
{
"epoch": 0.06,
"learning_rate": 9.995380315038119e-05,
"loss": 1.0824,
"step": 63000
},
{
"epoch": 0.06,
"learning_rate": 9.994642390694308e-05,
"loss": 1.088,
"step": 64000
},
{
"epoch": 0.07,
"learning_rate": 9.993849845741524e-05,
"loss": 1.1121,
"step": 65000
},
{
"epoch": 0.07,
"learning_rate": 9.993002688846913e-05,
"loss": 1.1019,
"step": 66000
},
{
"epoch": 0.07,
"learning_rate": 9.992100929274846e-05,
"loss": 1.1244,
"step": 67000
},
{
"epoch": 0.07,
"learning_rate": 9.991144576886823e-05,
"loss": 1.0794,
"step": 68000
},
{
"epoch": 0.07,
"learning_rate": 9.990133642141359e-05,
"loss": 1.0748,
"step": 69000
},
{
"epoch": 0.07,
"learning_rate": 9.989068136093873e-05,
"loss": 1.0954,
"step": 70000
},
{
"epoch": 0.07,
"learning_rate": 9.987948070396571e-05,
"loss": 1.0871,
"step": 71000
},
{
"epoch": 0.07,
"learning_rate": 9.986773457298311e-05,
"loss": 1.086,
"step": 72000
},
{
"epoch": 0.07,
"learning_rate": 9.985544309644475e-05,
"loss": 1.0842,
"step": 73000
},
{
"epoch": 0.07,
"learning_rate": 9.984260640876821e-05,
"loss": 1.0924,
"step": 74000
},
{
"epoch": 0.07,
"learning_rate": 9.98292246503335e-05,
"loss": 1.0783,
"step": 75000
},
{
"epoch": 0.08,
"learning_rate": 9.981529796748134e-05,
"loss": 1.0547,
"step": 76000
},
{
"epoch": 0.08,
"learning_rate": 9.980082651251175e-05,
"loss": 1.0725,
"step": 77000
},
{
"epoch": 0.08,
"learning_rate": 9.97858104436822e-05,
"loss": 1.0847,
"step": 78000
},
{
"epoch": 0.08,
"learning_rate": 9.977024992520602e-05,
"loss": 1.0695,
"step": 79000
},
{
"epoch": 0.08,
"learning_rate": 9.975414512725057e-05,
"loss": 1.0657,
"step": 80000
},
{
"epoch": 0.08,
"learning_rate": 9.973749622593534e-05,
"loss": 1.0415,
"step": 81000
},
{
"epoch": 0.08,
"learning_rate": 9.972030340333001e-05,
"loss": 1.047,
"step": 82000
},
{
"epoch": 0.08,
"learning_rate": 9.970256684745258e-05,
"loss": 1.0437,
"step": 83000
},
{
"epoch": 0.08,
"learning_rate": 9.968428675226714e-05,
"loss": 1.0484,
"step": 84000
},
{
"epoch": 0.09,
"learning_rate": 9.966546331768191e-05,
"loss": 1.0601,
"step": 85000
},
{
"epoch": 0.09,
"learning_rate": 9.964609674954696e-05,
"loss": 1.0666,
"step": 86000
},
{
"epoch": 0.09,
"learning_rate": 9.962618725965196e-05,
"loss": 1.0594,
"step": 87000
},
{
"epoch": 0.09,
"learning_rate": 9.96057350657239e-05,
"loss": 1.0493,
"step": 88000
},
{
"epoch": 0.09,
"learning_rate": 9.95847403914247e-05,
"loss": 1.0604,
"step": 89000
},
{
"epoch": 0.09,
"learning_rate": 9.956320346634876e-05,
"loss": 1.0533,
"step": 90000
},
{
"epoch": 0.09,
"learning_rate": 9.954112452602045e-05,
"loss": 1.0552,
"step": 91000
},
{
"epoch": 0.09,
"learning_rate": 9.95185038118915e-05,
"loss": 1.0535,
"step": 92000
},
{
"epoch": 0.09,
"learning_rate": 9.949534157133844e-05,
"loss": 1.0618,
"step": 93000
},
{
"epoch": 0.09,
"learning_rate": 9.94716380576598e-05,
"loss": 1.0459,
"step": 94000
},
{
"epoch": 0.1,
"learning_rate": 9.944739353007344e-05,
"loss": 1.0431,
"step": 95000
},
{
"epoch": 0.1,
"learning_rate": 9.942260825371358e-05,
"loss": 1.0274,
"step": 96000
},
{
"epoch": 0.1,
"learning_rate": 9.939728249962807e-05,
"loss": 1.0104,
"step": 97000
},
{
"epoch": 0.1,
"learning_rate": 9.937141654477528e-05,
"loss": 1.0039,
"step": 98000
},
{
"epoch": 0.1,
"learning_rate": 9.934501067202117e-05,
"loss": 1.0206,
"step": 99000
},
{
"epoch": 0.1,
"learning_rate": 9.931806517013612e-05,
"loss": 1.0214,
"step": 100000
},
{
"epoch": 0.1,
"eval_loss": 0.5695434808731079,
"eval_runtime": 114.0507,
"eval_samples_per_second": 43.84,
"eval_steps_per_second": 0.693,
"step": 100000
}
],
"max_steps": 1000000,
"num_train_epochs": 9223372036854775807,
"total_flos": 5.9668772683776e+18,
"trial_name": null,
"trial_params": null
}