joelniklaus's picture
Training in progress, step 200000
964178c
raw
history blame
25.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 39.009595,
"global_step": 200000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 5.3348,
"step": 1000
},
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 3.3875,
"step": 2000
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 3.0543,
"step": 3000
},
{
"epoch": 0.02,
"learning_rate": 4e-05,
"loss": 2.7926,
"step": 4000
},
{
"epoch": 0.03,
"learning_rate": 5e-05,
"loss": 2.4529,
"step": 5000
},
{
"epoch": 1.0,
"learning_rate": 6e-05,
"loss": 1.7273,
"step": 6000
},
{
"epoch": 1.01,
"learning_rate": 7e-05,
"loss": 1.5177,
"step": 7000
},
{
"epoch": 1.01,
"learning_rate": 8e-05,
"loss": 1.4508,
"step": 8000
},
{
"epoch": 1.02,
"learning_rate": 9e-05,
"loss": 1.4657,
"step": 9000
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 1.3213,
"step": 10000
},
{
"epoch": 2.0,
"learning_rate": 9.999316524962345e-05,
"loss": 1.1395,
"step": 11000
},
{
"epoch": 2.01,
"learning_rate": 9.997266286704631e-05,
"loss": 1.1372,
"step": 12000
},
{
"epoch": 2.01,
"learning_rate": 9.993849845741524e-05,
"loss": 1.1466,
"step": 13000
},
{
"epoch": 2.02,
"learning_rate": 9.989068136093873e-05,
"loss": 1.2559,
"step": 14000
},
{
"epoch": 2.02,
"learning_rate": 9.98292246503335e-05,
"loss": 1.1492,
"step": 15000
},
{
"epoch": 3.0,
"learning_rate": 9.975414512725057e-05,
"loss": 1.0101,
"step": 16000
},
{
"epoch": 3.01,
"learning_rate": 9.966546331768191e-05,
"loss": 1.018,
"step": 17000
},
{
"epoch": 3.01,
"learning_rate": 9.956320346634876e-05,
"loss": 1.0302,
"step": 18000
},
{
"epoch": 3.02,
"learning_rate": 9.944739353007344e-05,
"loss": 1.1687,
"step": 19000
},
{
"epoch": 3.02,
"learning_rate": 9.931806517013612e-05,
"loss": 1.0713,
"step": 20000
},
{
"epoch": 4.0,
"learning_rate": 9.917525374361912e-05,
"loss": 0.9549,
"step": 21000
},
{
"epoch": 4.01,
"learning_rate": 9.901899829374047e-05,
"loss": 0.9531,
"step": 22000
},
{
"epoch": 4.01,
"learning_rate": 9.884934153917997e-05,
"loss": 0.96,
"step": 23000
},
{
"epoch": 4.02,
"learning_rate": 9.86663298624003e-05,
"loss": 1.1114,
"step": 24000
},
{
"epoch": 4.02,
"learning_rate": 9.847001329696653e-05,
"loss": 1.0257,
"step": 25000
},
{
"epoch": 5.0,
"learning_rate": 9.826044551386744e-05,
"loss": 0.9207,
"step": 26000
},
{
"epoch": 5.01,
"learning_rate": 9.803768380684242e-05,
"loss": 0.9116,
"step": 27000
},
{
"epoch": 5.01,
"learning_rate": 9.780178907671789e-05,
"loss": 0.9103,
"step": 28000
},
{
"epoch": 5.02,
"learning_rate": 9.755282581475769e-05,
"loss": 1.0707,
"step": 29000
},
{
"epoch": 5.02,
"learning_rate": 9.729086208503174e-05,
"loss": 0.9927,
"step": 30000
},
{
"epoch": 6.0,
"learning_rate": 9.701596950580806e-05,
"loss": 0.905,
"step": 31000
},
{
"epoch": 6.01,
"learning_rate": 9.672822322997305e-05,
"loss": 0.8795,
"step": 32000
},
{
"epoch": 6.01,
"learning_rate": 9.642770192448536e-05,
"loss": 0.8738,
"step": 33000
},
{
"epoch": 6.02,
"learning_rate": 9.611448774886924e-05,
"loss": 1.0339,
"step": 34000
},
{
"epoch": 6.02,
"learning_rate": 9.578866633275288e-05,
"loss": 0.9767,
"step": 35000
},
{
"epoch": 7.0,
"learning_rate": 9.545032675245813e-05,
"loss": 0.8903,
"step": 36000
},
{
"epoch": 7.01,
"learning_rate": 9.509956150664796e-05,
"loss": 0.8514,
"step": 37000
},
{
"epoch": 7.01,
"learning_rate": 9.473646649103818e-05,
"loss": 0.8432,
"step": 38000
},
{
"epoch": 7.02,
"learning_rate": 9.43611409721806e-05,
"loss": 1.0033,
"step": 39000
},
{
"epoch": 7.02,
"learning_rate": 9.397368756032445e-05,
"loss": 0.9656,
"step": 40000
},
{
"epoch": 8.0,
"learning_rate": 9.357421218136386e-05,
"loss": 0.8809,
"step": 41000
},
{
"epoch": 8.01,
"learning_rate": 9.316282404787871e-05,
"loss": 0.8288,
"step": 42000
},
{
"epoch": 8.01,
"learning_rate": 9.273963562927695e-05,
"loss": 0.8188,
"step": 43000
},
{
"epoch": 8.02,
"learning_rate": 9.230476262104677e-05,
"loss": 0.9725,
"step": 44000
},
{
"epoch": 8.02,
"learning_rate": 9.185832391312644e-05,
"loss": 0.9562,
"step": 45000
},
{
"epoch": 9.0,
"learning_rate": 9.140044155740101e-05,
"loss": 0.8758,
"step": 46000
},
{
"epoch": 9.01,
"learning_rate": 9.093124073433463e-05,
"loss": 0.8083,
"step": 47000
},
{
"epoch": 9.01,
"learning_rate": 9.045084971874738e-05,
"loss": 0.7954,
"step": 48000
},
{
"epoch": 9.02,
"learning_rate": 8.995939984474624e-05,
"loss": 0.9468,
"step": 49000
},
{
"epoch": 9.02,
"learning_rate": 8.945702546981969e-05,
"loss": 0.9507,
"step": 50000
},
{
"epoch": 9.02,
"eval_loss": 0.3072759509086609,
"eval_runtime": 16.6446,
"eval_samples_per_second": 300.398,
"eval_steps_per_second": 2.403,
"step": 50000
},
{
"epoch": 10.0,
"learning_rate": 8.894386393810563e-05,
"loss": 0.8711,
"step": 51000
},
{
"epoch": 10.01,
"learning_rate": 8.842005554284296e-05,
"loss": 0.791,
"step": 52000
},
{
"epoch": 10.01,
"learning_rate": 8.788574348801675e-05,
"loss": 0.7827,
"step": 53000
},
{
"epoch": 10.02,
"learning_rate": 8.73410738492077e-05,
"loss": 0.9227,
"step": 54000
},
{
"epoch": 10.02,
"learning_rate": 8.678619553365659e-05,
"loss": 0.9418,
"step": 55000
},
{
"epoch": 11.0,
"learning_rate": 8.622126023955446e-05,
"loss": 0.8834,
"step": 56000
},
{
"epoch": 11.01,
"learning_rate": 8.564642241456986e-05,
"loss": 0.7612,
"step": 57000
},
{
"epoch": 11.01,
"learning_rate": 8.506183921362443e-05,
"loss": 0.7684,
"step": 58000
},
{
"epoch": 11.02,
"learning_rate": 8.44676704559283e-05,
"loss": 0.8967,
"step": 59000
},
{
"epoch": 11.02,
"learning_rate": 8.386407858128706e-05,
"loss": 0.9378,
"step": 60000
},
{
"epoch": 12.0,
"learning_rate": 8.32512286056924e-05,
"loss": 0.8882,
"step": 61000
},
{
"epoch": 12.01,
"learning_rate": 8.262928807620843e-05,
"loss": 0.7426,
"step": 62000
},
{
"epoch": 12.01,
"learning_rate": 8.199842702516583e-05,
"loss": 0.7592,
"step": 63000
},
{
"epoch": 12.02,
"learning_rate": 8.135881792367686e-05,
"loss": 0.8699,
"step": 64000
},
{
"epoch": 12.02,
"learning_rate": 8.07106356344834e-05,
"loss": 0.9352,
"step": 65000
},
{
"epoch": 12.03,
"learning_rate": 8.005405736415126e-05,
"loss": 0.8901,
"step": 66000
},
{
"epoch": 13.0,
"learning_rate": 7.938926261462366e-05,
"loss": 0.7242,
"step": 67000
},
{
"epoch": 13.01,
"learning_rate": 7.871643313414718e-05,
"loss": 0.7627,
"step": 68000
},
{
"epoch": 13.01,
"learning_rate": 7.803575286758364e-05,
"loss": 0.8369,
"step": 69000
},
{
"epoch": 13.02,
"learning_rate": 7.734740790612136e-05,
"loss": 0.9364,
"step": 70000
},
{
"epoch": 13.02,
"learning_rate": 7.66515864363997e-05,
"loss": 0.872,
"step": 71000
},
{
"epoch": 14.0,
"learning_rate": 7.594847868906076e-05,
"loss": 0.727,
"step": 72000
},
{
"epoch": 14.01,
"learning_rate": 7.52382768867422e-05,
"loss": 0.7649,
"step": 73000
},
{
"epoch": 14.01,
"learning_rate": 7.452117519152542e-05,
"loss": 0.8039,
"step": 74000
},
{
"epoch": 14.02,
"learning_rate": 7.379736965185368e-05,
"loss": 0.9335,
"step": 75000
},
{
"epoch": 14.02,
"learning_rate": 7.30670581489344e-05,
"loss": 0.856,
"step": 76000
},
{
"epoch": 15.0,
"learning_rate": 7.233044034264034e-05,
"loss": 0.7324,
"step": 77000
},
{
"epoch": 15.01,
"learning_rate": 7.158771761692464e-05,
"loss": 0.7571,
"step": 78000
},
{
"epoch": 15.01,
"learning_rate": 7.083909302476453e-05,
"loss": 0.7826,
"step": 79000
},
{
"epoch": 15.02,
"learning_rate": 7.008477123264848e-05,
"loss": 0.9303,
"step": 80000
},
{
"epoch": 15.02,
"learning_rate": 6.932495846462261e-05,
"loss": 0.8436,
"step": 81000
},
{
"epoch": 16.0,
"learning_rate": 6.855986244591104e-05,
"loss": 0.7372,
"step": 82000
},
{
"epoch": 16.01,
"learning_rate": 6.778969234612584e-05,
"loss": 0.7497,
"step": 83000
},
{
"epoch": 16.01,
"learning_rate": 6.701465872208216e-05,
"loss": 0.7654,
"step": 84000
},
{
"epoch": 16.02,
"learning_rate": 6.623497346023418e-05,
"loss": 0.9188,
"step": 85000
},
{
"epoch": 16.02,
"learning_rate": 6.545084971874738e-05,
"loss": 0.8375,
"step": 86000
},
{
"epoch": 17.0,
"learning_rate": 6.466250186922325e-05,
"loss": 0.7431,
"step": 87000
},
{
"epoch": 17.01,
"learning_rate": 6.387014543809223e-05,
"loss": 0.7417,
"step": 88000
},
{
"epoch": 17.01,
"learning_rate": 6.307399704769099e-05,
"loss": 0.7483,
"step": 89000
},
{
"epoch": 17.02,
"learning_rate": 6.227427435703997e-05,
"loss": 0.9084,
"step": 90000
},
{
"epoch": 17.02,
"learning_rate": 6.147119600233758e-05,
"loss": 0.8333,
"step": 91000
},
{
"epoch": 18.0,
"learning_rate": 6.066498153718735e-05,
"loss": 0.7456,
"step": 92000
},
{
"epoch": 18.01,
"learning_rate": 5.985585137257401e-05,
"loss": 0.7344,
"step": 93000
},
{
"epoch": 18.01,
"learning_rate": 5.90440267166055e-05,
"loss": 0.7345,
"step": 94000
},
{
"epoch": 18.02,
"learning_rate": 5.8229729514036705e-05,
"loss": 0.8943,
"step": 95000
},
{
"epoch": 18.02,
"learning_rate": 5.74131823855921e-05,
"loss": 0.8304,
"step": 96000
},
{
"epoch": 19.0,
"learning_rate": 5.6594608567103456e-05,
"loss": 0.7531,
"step": 97000
},
{
"epoch": 19.01,
"learning_rate": 5.577423184847932e-05,
"loss": 0.724,
"step": 98000
},
{
"epoch": 19.01,
"learning_rate": 5.495227651252315e-05,
"loss": 0.722,
"step": 99000
},
{
"epoch": 19.02,
"learning_rate": 5.4128967273616625e-05,
"loss": 0.8777,
"step": 100000
},
{
"epoch": 19.02,
"eval_loss": 0.2591562867164612,
"eval_runtime": 10.3781,
"eval_samples_per_second": 481.783,
"eval_steps_per_second": 3.854,
"step": 100000
},
{
"epoch": 19.02,
"learning_rate": 5.330452921628497e-05,
"loss": 0.8354,
"step": 101000
},
{
"epoch": 20.0,
"learning_rate": 5.247918773366112e-05,
"loss": 0.7591,
"step": 102000
},
{
"epoch": 20.01,
"learning_rate": 5.165316846586541e-05,
"loss": 0.7138,
"step": 103000
},
{
"epoch": 20.01,
"learning_rate": 5.0826697238317935e-05,
"loss": 0.7078,
"step": 104000
},
{
"epoch": 20.02,
"learning_rate": 5e-05,
"loss": 0.8641,
"step": 105000
},
{
"epoch": 20.02,
"learning_rate": 4.917330276168208e-05,
"loss": 0.8378,
"step": 106000
},
{
"epoch": 21.0,
"learning_rate": 4.834683153413459e-05,
"loss": 0.7606,
"step": 107000
},
{
"epoch": 21.01,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.7069,
"step": 108000
},
{
"epoch": 21.01,
"learning_rate": 4.669547078371504e-05,
"loss": 0.6973,
"step": 109000
},
{
"epoch": 21.02,
"learning_rate": 4.5871032726383386e-05,
"loss": 0.8465,
"step": 110000
},
{
"epoch": 21.02,
"learning_rate": 4.504772348747687e-05,
"loss": 0.8413,
"step": 111000
},
{
"epoch": 22.0,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.7666,
"step": 112000
},
{
"epoch": 22.01,
"learning_rate": 4.3405391432896555e-05,
"loss": 0.6977,
"step": 113000
},
{
"epoch": 22.01,
"learning_rate": 4.2586817614407895e-05,
"loss": 0.6884,
"step": 114000
},
{
"epoch": 22.02,
"learning_rate": 4.17702704859633e-05,
"loss": 0.8303,
"step": 115000
},
{
"epoch": 22.02,
"learning_rate": 4.095597328339452e-05,
"loss": 0.8452,
"step": 116000
},
{
"epoch": 23.0,
"learning_rate": 4.0144148627425993e-05,
"loss": 0.775,
"step": 117000
},
{
"epoch": 23.01,
"learning_rate": 3.933501846281267e-05,
"loss": 0.6885,
"step": 118000
},
{
"epoch": 23.01,
"learning_rate": 3.852880399766243e-05,
"loss": 0.6849,
"step": 119000
},
{
"epoch": 23.02,
"learning_rate": 3.772572564296005e-05,
"loss": 0.8159,
"step": 120000
},
{
"epoch": 23.02,
"learning_rate": 3.6926002952309016e-05,
"loss": 0.8458,
"step": 121000
},
{
"epoch": 24.0,
"learning_rate": 3.612985456190778e-05,
"loss": 0.7978,
"step": 122000
},
{
"epoch": 24.01,
"learning_rate": 3.533749813077677e-05,
"loss": 0.6638,
"step": 123000
},
{
"epoch": 24.01,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.6798,
"step": 124000
},
{
"epoch": 24.02,
"learning_rate": 3.3765026539765834e-05,
"loss": 0.7968,
"step": 125000
},
{
"epoch": 24.02,
"learning_rate": 3.298534127791785e-05,
"loss": 0.8487,
"step": 126000
},
{
"epoch": 25.0,
"learning_rate": 3.221030765387417e-05,
"loss": 0.8085,
"step": 127000
},
{
"epoch": 25.01,
"learning_rate": 3.144013755408895e-05,
"loss": 0.6488,
"step": 128000
},
{
"epoch": 25.01,
"learning_rate": 3.0675041535377405e-05,
"loss": 0.682,
"step": 129000
},
{
"epoch": 25.02,
"learning_rate": 2.991522876735154e-05,
"loss": 0.7755,
"step": 130000
},
{
"epoch": 25.02,
"learning_rate": 2.916090697523549e-05,
"loss": 0.852,
"step": 131000
},
{
"epoch": 25.03,
"learning_rate": 2.8412282383075363e-05,
"loss": 0.806,
"step": 132000
},
{
"epoch": 26.0,
"learning_rate": 2.766955965735968e-05,
"loss": 0.6503,
"step": 133000
},
{
"epoch": 26.01,
"learning_rate": 2.693294185106562e-05,
"loss": 0.6906,
"step": 134000
},
{
"epoch": 26.01,
"learning_rate": 2.6202630348146324e-05,
"loss": 0.748,
"step": 135000
},
{
"epoch": 26.02,
"learning_rate": 2.547882480847461e-05,
"loss": 0.8586,
"step": 136000
},
{
"epoch": 26.02,
"learning_rate": 2.476172311325783e-05,
"loss": 0.7917,
"step": 137000
},
{
"epoch": 27.0,
"learning_rate": 2.405152131093926e-05,
"loss": 0.659,
"step": 138000
},
{
"epoch": 27.01,
"learning_rate": 2.3348413563600325e-05,
"loss": 0.6941,
"step": 139000
},
{
"epoch": 27.01,
"learning_rate": 2.2652592093878666e-05,
"loss": 0.7248,
"step": 140000
},
{
"epoch": 27.02,
"learning_rate": 2.196424713241637e-05,
"loss": 0.861,
"step": 141000
},
{
"epoch": 27.02,
"learning_rate": 2.128356686585282e-05,
"loss": 0.7822,
"step": 142000
},
{
"epoch": 28.0,
"learning_rate": 2.061073738537635e-05,
"loss": 0.6697,
"step": 143000
},
{
"epoch": 28.01,
"learning_rate": 1.9945942635848748e-05,
"loss": 0.6906,
"step": 144000
},
{
"epoch": 28.01,
"learning_rate": 1.928936436551661e-05,
"loss": 0.7105,
"step": 145000
},
{
"epoch": 28.02,
"learning_rate": 1.8641182076323148e-05,
"loss": 0.861,
"step": 146000
},
{
"epoch": 28.02,
"learning_rate": 1.800157297483417e-05,
"loss": 0.7773,
"step": 147000
},
{
"epoch": 29.0,
"learning_rate": 1.7370711923791567e-05,
"loss": 0.6785,
"step": 148000
},
{
"epoch": 29.01,
"learning_rate": 1.6748771394307585e-05,
"loss": 0.6872,
"step": 149000
},
{
"epoch": 29.01,
"learning_rate": 1.6135921418712956e-05,
"loss": 0.6977,
"step": 150000
},
{
"epoch": 29.01,
"eval_loss": 0.2398204356431961,
"eval_runtime": 10.7073,
"eval_samples_per_second": 466.973,
"eval_steps_per_second": 3.736,
"step": 150000
},
{
"epoch": 29.02,
"learning_rate": 1.553232954407171e-05,
"loss": 0.8544,
"step": 151000
},
{
"epoch": 29.02,
"learning_rate": 1.4938160786375572e-05,
"loss": 0.7749,
"step": 152000
},
{
"epoch": 30.0,
"learning_rate": 1.435357758543015e-05,
"loss": 0.6875,
"step": 153000
},
{
"epoch": 30.01,
"learning_rate": 1.3778739760445552e-05,
"loss": 0.6832,
"step": 154000
},
{
"epoch": 30.01,
"learning_rate": 1.3213804466343421e-05,
"loss": 0.6868,
"step": 155000
},
{
"epoch": 30.02,
"learning_rate": 1.2658926150792322e-05,
"loss": 0.8447,
"step": 156000
},
{
"epoch": 30.02,
"learning_rate": 1.2114256511983274e-05,
"loss": 0.7752,
"step": 157000
},
{
"epoch": 31.0,
"learning_rate": 1.157994445715706e-05,
"loss": 0.6962,
"step": 158000
},
{
"epoch": 31.01,
"learning_rate": 1.1056136061894384e-05,
"loss": 0.6789,
"step": 159000
},
{
"epoch": 31.01,
"learning_rate": 1.0542974530180327e-05,
"loss": 0.6788,
"step": 160000
},
{
"epoch": 31.02,
"learning_rate": 1.0040600155253765e-05,
"loss": 0.8362,
"step": 161000
},
{
"epoch": 31.02,
"learning_rate": 9.549150281252633e-06,
"loss": 0.781,
"step": 162000
},
{
"epoch": 32.0,
"learning_rate": 9.068759265665384e-06,
"loss": 0.7037,
"step": 163000
},
{
"epoch": 32.01,
"learning_rate": 8.599558442598998e-06,
"loss": 0.6753,
"step": 164000
},
{
"epoch": 32.01,
"learning_rate": 8.141676086873572e-06,
"loss": 0.6692,
"step": 165000
},
{
"epoch": 32.02,
"learning_rate": 7.695237378953223e-06,
"loss": 0.8246,
"step": 166000
},
{
"epoch": 32.02,
"learning_rate": 7.260364370723044e-06,
"loss": 0.7892,
"step": 167000
},
{
"epoch": 33.0,
"learning_rate": 6.837175952121306e-06,
"loss": 0.7146,
"step": 168000
},
{
"epoch": 33.01,
"learning_rate": 6.425787818636131e-06,
"loss": 0.6683,
"step": 169000
},
{
"epoch": 33.01,
"learning_rate": 6.026312439675552e-06,
"loss": 0.6613,
"step": 170000
},
{
"epoch": 33.02,
"learning_rate": 5.6388590278194096e-06,
"loss": 0.8125,
"step": 171000
},
{
"epoch": 33.02,
"learning_rate": 5.263533508961827e-06,
"loss": 0.7963,
"step": 172000
},
{
"epoch": 34.0,
"learning_rate": 4.900438493352055e-06,
"loss": 0.7243,
"step": 173000
},
{
"epoch": 34.01,
"learning_rate": 4.549673247541875e-06,
"loss": 0.6625,
"step": 174000
},
{
"epoch": 34.01,
"learning_rate": 4.2113336672471245e-06,
"loss": 0.6554,
"step": 175000
},
{
"epoch": 34.02,
"learning_rate": 3.885512251130763e-06,
"loss": 0.8013,
"step": 176000
},
{
"epoch": 34.02,
"learning_rate": 3.5722980755146517e-06,
"loss": 0.8046,
"step": 177000
},
{
"epoch": 35.0,
"learning_rate": 3.271776770026963e-06,
"loss": 0.732,
"step": 178000
},
{
"epoch": 35.01,
"learning_rate": 2.9840304941919415e-06,
"loss": 0.6575,
"step": 179000
},
{
"epoch": 35.01,
"learning_rate": 2.7091379149682685e-06,
"loss": 0.6533,
"step": 180000
},
{
"epoch": 35.02,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.7892,
"step": 181000
},
{
"epoch": 35.02,
"learning_rate": 2.1982109232821178e-06,
"loss": 0.8077,
"step": 182000
},
{
"epoch": 36.0,
"learning_rate": 1.962316193157593e-06,
"loss": 0.7468,
"step": 183000
},
{
"epoch": 36.01,
"learning_rate": 1.7395544861325718e-06,
"loss": 0.6475,
"step": 184000
},
{
"epoch": 36.01,
"learning_rate": 1.5299867030334814e-06,
"loss": 0.6511,
"step": 185000
},
{
"epoch": 36.02,
"learning_rate": 1.333670137599713e-06,
"loss": 0.7758,
"step": 186000
},
{
"epoch": 36.02,
"learning_rate": 1.1506584608200367e-06,
"loss": 0.8151,
"step": 187000
},
{
"epoch": 37.0,
"learning_rate": 9.810017062595322e-07,
"loss": 0.7692,
"step": 188000
},
{
"epoch": 37.01,
"learning_rate": 8.247462563808817e-07,
"loss": 0.6325,
"step": 189000
},
{
"epoch": 37.01,
"learning_rate": 6.819348298638839e-07,
"loss": 0.6538,
"step": 190000
},
{
"epoch": 37.02,
"learning_rate": 5.526064699265753e-07,
"loss": 0.7594,
"step": 191000
},
{
"epoch": 37.02,
"learning_rate": 4.367965336512403e-07,
"loss": 0.8223,
"step": 192000
},
{
"epoch": 37.03,
"learning_rate": 3.3453668231809286e-07,
"loss": 0.7867,
"step": 193000
},
{
"epoch": 38.0,
"learning_rate": 2.458548727494292e-07,
"loss": 0.6194,
"step": 194000
},
{
"epoch": 38.01,
"learning_rate": 1.7077534966650766e-07,
"loss": 0.6619,
"step": 195000
},
{
"epoch": 38.01,
"learning_rate": 1.0931863906127327e-07,
"loss": 0.7407,
"step": 196000
},
{
"epoch": 38.02,
"learning_rate": 6.150154258476315e-08,
"loss": 0.8314,
"step": 197000
},
{
"epoch": 38.02,
"learning_rate": 2.7337132953697554e-08,
"loss": 0.7785,
"step": 198000
},
{
"epoch": 39.0,
"learning_rate": 6.834750376549792e-09,
"loss": 0.6307,
"step": 199000
},
{
"epoch": 39.01,
"learning_rate": 0.0,
"loss": 0.6732,
"step": 200000
},
{
"epoch": 39.01,
"eval_loss": 0.2364628165960312,
"eval_runtime": 10.9271,
"eval_samples_per_second": 457.577,
"eval_steps_per_second": 3.661,
"step": 200000
}
],
"max_steps": 200000,
"num_train_epochs": 9223372036854775807,
"total_flos": 3.3695724490740204e+18,
"trial_name": null,
"trial_params": null
}