| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 19.999983677999577, | |
| "global_step": 612660, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.951082166291254e-05, | |
| "loss": 4.9783, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.902115365782e-05, | |
| "loss": 3.1296, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.853148565272745e-05, | |
| "loss": 2.7383, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.804181764763491e-05, | |
| "loss": 2.5447, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.755231286521073e-05, | |
| "loss": 2.4175, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.706280808278654e-05, | |
| "loss": 2.3285, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.657346652303072e-05, | |
| "loss": 2.2597, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.608396174060654e-05, | |
| "loss": 2.2072, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.559462018085072e-05, | |
| "loss": 2.1601, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.510511539842654e-05, | |
| "loss": 2.125, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.072047233581543, | |
| "eval_runtime": 19.2095, | |
| "eval_samples_per_second": 1536.842, | |
| "eval_steps_per_second": 9.631, | |
| "step": 30633 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 9.461577383867072e-05, | |
| "loss": 2.0771, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 9.412626905624655e-05, | |
| "loss": 2.0514, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 9.363692749649071e-05, | |
| "loss": 2.0297, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 9.314742271406653e-05, | |
| "loss": 2.0123, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 9.265791793164235e-05, | |
| "loss": 1.9955, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.216857637188653e-05, | |
| "loss": 1.9803, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 9.167907158946235e-05, | |
| "loss": 1.9667, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 9.118973002970654e-05, | |
| "loss": 1.9505, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 9.070022524728234e-05, | |
| "loss": 1.9381, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 9.021088368752652e-05, | |
| "loss": 1.9288, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.9032506942749023, | |
| "eval_runtime": 19.1781, | |
| "eval_samples_per_second": 1539.357, | |
| "eval_steps_per_second": 9.646, | |
| "step": 61266 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 8.972137890510235e-05, | |
| "loss": 1.9011, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.923203734534653e-05, | |
| "loss": 1.8834, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 8.874253256292235e-05, | |
| "loss": 1.8807, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 8.825319100316653e-05, | |
| "loss": 1.8737, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 8.776368622074233e-05, | |
| "loss": 1.8686, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.727434466098652e-05, | |
| "loss": 1.861, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 8.678483987856234e-05, | |
| "loss": 1.8549, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 8.629549831880652e-05, | |
| "loss": 1.8503, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 8.580599353638234e-05, | |
| "loss": 1.8446, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 8.531665197662652e-05, | |
| "loss": 1.8387, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.833019733428955, | |
| "eval_runtime": 19.0959, | |
| "eval_samples_per_second": 1545.988, | |
| "eval_steps_per_second": 9.688, | |
| "step": 91899 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 8.482714719420234e-05, | |
| "loss": 1.8222, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 8.433764241177815e-05, | |
| "loss": 1.8037, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 8.384830085202233e-05, | |
| "loss": 1.8017, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 8.335879606959815e-05, | |
| "loss": 1.8018, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 8.286945450984233e-05, | |
| "loss": 1.7984, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 8.237994972741815e-05, | |
| "loss": 1.796, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 8.189060816766233e-05, | |
| "loss": 1.7942, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 8.140110338523814e-05, | |
| "loss": 1.7905, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 8.091176182548232e-05, | |
| "loss": 1.7885, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 8.042225704305814e-05, | |
| "loss": 1.7832, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.7864413261413574, | |
| "eval_runtime": 19.3546, | |
| "eval_samples_per_second": 1525.321, | |
| "eval_steps_per_second": 9.558, | |
| "step": 122532 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 7.993291548330233e-05, | |
| "loss": 1.7754, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 7.944341070087814e-05, | |
| "loss": 1.7507, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 7.895406914112233e-05, | |
| "loss": 1.7526, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 7.846456435869815e-05, | |
| "loss": 1.7541, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 7.797522279894231e-05, | |
| "loss": 1.7537, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 7.748571801651814e-05, | |
| "loss": 1.7541, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 7.699621323409395e-05, | |
| "loss": 1.7505, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 7.650687167433813e-05, | |
| "loss": 1.7475, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 7.601736689191396e-05, | |
| "loss": 1.7477, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 7.552802533215814e-05, | |
| "loss": 1.7461, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 7.503852054973394e-05, | |
| "loss": 1.7445, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.7591967582702637, | |
| "eval_runtime": 19.1359, | |
| "eval_samples_per_second": 1542.756, | |
| "eval_steps_per_second": 9.668, | |
| "step": 153165 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 7.454917898997813e-05, | |
| "loss": 1.7143, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 7.405967420755395e-05, | |
| "loss": 1.7177, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 7.357033264779813e-05, | |
| "loss": 1.7188, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 7.308082786537395e-05, | |
| "loss": 1.7198, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 7.259148630561813e-05, | |
| "loss": 1.7202, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 7.210198152319395e-05, | |
| "loss": 1.7184, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 7.161247674076976e-05, | |
| "loss": 1.719, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 7.112313518101394e-05, | |
| "loss": 1.7173, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 7.063363039858976e-05, | |
| "loss": 1.7176, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 7.014428883883394e-05, | |
| "loss": 1.7152, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.740378975868225, | |
| "eval_runtime": 19.1537, | |
| "eval_samples_per_second": 1541.325, | |
| "eval_steps_per_second": 9.659, | |
| "step": 183798 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 6.965478405640976e-05, | |
| "loss": 1.6926, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 6.916544249665395e-05, | |
| "loss": 1.6889, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 6.867593771422975e-05, | |
| "loss": 1.6923, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 6.818659615447393e-05, | |
| "loss": 1.693, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 6.769709137204976e-05, | |
| "loss": 1.694, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 6.720774981229393e-05, | |
| "loss": 1.6948, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 6.671824502986975e-05, | |
| "loss": 1.6944, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 6.622874024744557e-05, | |
| "loss": 1.6934, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 6.573939868768974e-05, | |
| "loss": 1.6926, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 6.524989390526556e-05, | |
| "loss": 1.6933, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.7208322286605835, | |
| "eval_runtime": 19.2921, | |
| "eval_samples_per_second": 1530.262, | |
| "eval_steps_per_second": 9.589, | |
| "step": 214431 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 6.476055234550975e-05, | |
| "loss": 1.6773, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 6.427104756308556e-05, | |
| "loss": 1.6671, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 6.378170600332975e-05, | |
| "loss": 1.6695, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 6.329220122090557e-05, | |
| "loss": 1.6707, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 6.280285966114975e-05, | |
| "loss": 1.674, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 6.231335487872557e-05, | |
| "loss": 1.6726, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 6.182401331896974e-05, | |
| "loss": 1.6739, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 6.133450853654555e-05, | |
| "loss": 1.6755, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 6.084516697678973e-05, | |
| "loss": 1.6726, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 6.035566219436556e-05, | |
| "loss": 1.6743, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.7004761695861816, | |
| "eval_runtime": 19.351, | |
| "eval_samples_per_second": 1525.608, | |
| "eval_steps_per_second": 9.56, | |
| "step": 245064 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 5.986632063460974e-05, | |
| "loss": 1.6642, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 5.9376815852185555e-05, | |
| "loss": 1.6475, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 5.888747429242973e-05, | |
| "loss": 1.6525, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 5.839796951000556e-05, | |
| "loss": 1.653, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 5.7908627950249736e-05, | |
| "loss": 1.6556, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 5.741912316782555e-05, | |
| "loss": 1.6556, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 5.692961838540136e-05, | |
| "loss": 1.6565, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 5.6440276825645545e-05, | |
| "loss": 1.6567, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 5.5950772043221364e-05, | |
| "loss": 1.6574, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 5.546143048346555e-05, | |
| "loss": 1.6561, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.6906808614730835, | |
| "eval_runtime": 19.2999, | |
| "eval_samples_per_second": 1529.642, | |
| "eval_steps_per_second": 9.586, | |
| "step": 275697 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 5.497192570104136e-05, | |
| "loss": 1.6546, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 5.4482584141285545e-05, | |
| "loss": 1.6302, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 5.3993079358861364e-05, | |
| "loss": 1.6356, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 5.3503574576437175e-05, | |
| "loss": 1.6375, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 5.301423301668136e-05, | |
| "loss": 1.6399, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 5.252472823425718e-05, | |
| "loss": 1.6404, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 5.203538667450135e-05, | |
| "loss": 1.642, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 5.1545881892077175e-05, | |
| "loss": 1.642, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 5.105654033232135e-05, | |
| "loss": 1.6421, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 5.0567035549897165e-05, | |
| "loss": 1.6417, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 5.007753076747299e-05, | |
| "loss": 1.6431, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.690254807472229, | |
| "eval_runtime": 19.1786, | |
| "eval_samples_per_second": 1539.322, | |
| "eval_steps_per_second": 9.646, | |
| "step": 306330 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 4.9588189207717175e-05, | |
| "loss": 1.6191, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 4.909868442529299e-05, | |
| "loss": 1.6215, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 4.8609342865537165e-05, | |
| "loss": 1.6247, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 4.8119838083112984e-05, | |
| "loss": 1.6244, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 4.76303333006888e-05, | |
| "loss": 1.6261, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "learning_rate": 4.714099174093298e-05, | |
| "loss": 1.6288, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 4.66514869585088e-05, | |
| "loss": 1.6289, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 4.6162145398752984e-05, | |
| "loss": 1.6295, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 10.87, | |
| "learning_rate": 4.5672640616328796e-05, | |
| "loss": 1.6295, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 4.5183135833904614e-05, | |
| "loss": 1.6282, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.6800603866577148, | |
| "eval_runtime": 19.1041, | |
| "eval_samples_per_second": 1545.321, | |
| "eval_steps_per_second": 9.684, | |
| "step": 336963 | |
| }, | |
| { | |
| "epoch": 11.07, | |
| "learning_rate": 4.46937942741488e-05, | |
| "loss": 1.6134, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 4.420428949172462e-05, | |
| "loss": 1.6072, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 11.26, | |
| "learning_rate": 4.371494793196879e-05, | |
| "loss": 1.6099, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 4.322544314954461e-05, | |
| "loss": 1.6137, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 4.273610158978879e-05, | |
| "loss": 1.6136, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 4.224659680736461e-05, | |
| "loss": 1.6151, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 4.175725524760879e-05, | |
| "loss": 1.6166, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "learning_rate": 4.126775046518461e-05, | |
| "loss": 1.6179, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "learning_rate": 4.077840890542879e-05, | |
| "loss": 1.6174, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 4.0288904123004604e-05, | |
| "loss": 1.6173, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.6714136600494385, | |
| "eval_runtime": 19.2107, | |
| "eval_samples_per_second": 1536.747, | |
| "eval_steps_per_second": 9.63, | |
| "step": 367596 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 3.979939934058042e-05, | |
| "loss": 1.6063, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 3.931005778082461e-05, | |
| "loss": 1.5969, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 3.882055299840042e-05, | |
| "loss": 1.5998, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 12.34, | |
| "learning_rate": 3.83312114386446e-05, | |
| "loss": 1.6011, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 3.784154343355205e-05, | |
| "loss": 1.6034, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 12.54, | |
| "learning_rate": 3.7352201873796235e-05, | |
| "loss": 1.6035, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 3.686269709137205e-05, | |
| "loss": 1.6054, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "learning_rate": 3.637335553161623e-05, | |
| "loss": 1.6055, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 3.588385074919205e-05, | |
| "loss": 1.6057, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 3.539434596676787e-05, | |
| "loss": 1.6061, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.6634231805801392, | |
| "eval_runtime": 19.238, | |
| "eval_samples_per_second": 1534.564, | |
| "eval_steps_per_second": 9.616, | |
| "step": 398229 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 3.4905004407012046e-05, | |
| "loss": 1.5995, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 3.4415499624587865e-05, | |
| "loss": 1.5849, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 13.22, | |
| "learning_rate": 3.392615806483205e-05, | |
| "loss": 1.5894, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 13.32, | |
| "learning_rate": 3.343665328240786e-05, | |
| "loss": 1.5914, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "learning_rate": 3.294731172265204e-05, | |
| "loss": 1.5917, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 13.51, | |
| "learning_rate": 3.245780694022786e-05, | |
| "loss": 1.5933, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 3.196830215780368e-05, | |
| "loss": 1.5926, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 3.1478960598047855e-05, | |
| "loss": 1.5956, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "learning_rate": 3.0989455815623674e-05, | |
| "loss": 1.5953, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "learning_rate": 3.0500114255867855e-05, | |
| "loss": 1.5971, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.6542909145355225, | |
| "eval_runtime": 19.1669, | |
| "eval_samples_per_second": 1540.259, | |
| "eval_steps_per_second": 9.652, | |
| "step": 428862 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.0010609473443674e-05, | |
| "loss": 1.5959, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 2.9521267913687855e-05, | |
| "loss": 1.5752, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 2.9031763131263674e-05, | |
| "loss": 1.5775, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 2.854225834883949e-05, | |
| "loss": 1.5814, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.8052916789083673e-05, | |
| "loss": 1.5814, | |
| "step": 441000 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 2.7563412006659482e-05, | |
| "loss": 1.5837, | |
| "step": 444000 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 2.7074070446903667e-05, | |
| "loss": 1.585, | |
| "step": 447000 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 2.6584565664479482e-05, | |
| "loss": 1.5868, | |
| "step": 450000 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 2.60950608820553e-05, | |
| "loss": 1.5854, | |
| "step": 453000 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 2.5605719322299482e-05, | |
| "loss": 1.5864, | |
| "step": 456000 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "learning_rate": 2.51162145398753e-05, | |
| "loss": 1.5867, | |
| "step": 459000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.6488285064697266, | |
| "eval_runtime": 19.1177, | |
| "eval_samples_per_second": 1544.224, | |
| "eval_steps_per_second": 9.677, | |
| "step": 459495 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 2.4626709757451116e-05, | |
| "loss": 1.5695, | |
| "step": 462000 | |
| }, | |
| { | |
| "epoch": 15.18, | |
| "learning_rate": 2.4137368197695297e-05, | |
| "loss": 1.5714, | |
| "step": 465000 | |
| }, | |
| { | |
| "epoch": 15.28, | |
| "learning_rate": 2.3647863415271113e-05, | |
| "loss": 1.5721, | |
| "step": 468000 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 2.315835863284693e-05, | |
| "loss": 1.5729, | |
| "step": 471000 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 2.2669017073091113e-05, | |
| "loss": 1.5728, | |
| "step": 474000 | |
| }, | |
| { | |
| "epoch": 15.57, | |
| "learning_rate": 2.2179512290666928e-05, | |
| "loss": 1.5739, | |
| "step": 477000 | |
| }, | |
| { | |
| "epoch": 15.67, | |
| "learning_rate": 2.1690007508242746e-05, | |
| "loss": 1.5756, | |
| "step": 480000 | |
| }, | |
| { | |
| "epoch": 15.77, | |
| "learning_rate": 2.1200665948486928e-05, | |
| "loss": 1.5774, | |
| "step": 483000 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 2.0711161166062743e-05, | |
| "loss": 1.5772, | |
| "step": 486000 | |
| }, | |
| { | |
| "epoch": 15.96, | |
| "learning_rate": 2.022165638363856e-05, | |
| "loss": 1.5781, | |
| "step": 489000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.6446890830993652, | |
| "eval_runtime": 19.0262, | |
| "eval_samples_per_second": 1551.652, | |
| "eval_steps_per_second": 9.723, | |
| "step": 490128 | |
| }, | |
| { | |
| "epoch": 16.06, | |
| "learning_rate": 1.9732314823882743e-05, | |
| "loss": 1.5652, | |
| "step": 492000 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 1.924281004145856e-05, | |
| "loss": 1.5612, | |
| "step": 495000 | |
| }, | |
| { | |
| "epoch": 16.26, | |
| "learning_rate": 1.8753305259034377e-05, | |
| "loss": 1.5634, | |
| "step": 498000 | |
| }, | |
| { | |
| "epoch": 16.35, | |
| "learning_rate": 1.8263800476610192e-05, | |
| "loss": 1.5648, | |
| "step": 501000 | |
| }, | |
| { | |
| "epoch": 16.45, | |
| "learning_rate": 1.7774458916854374e-05, | |
| "loss": 1.5664, | |
| "step": 504000 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 1.728495413443019e-05, | |
| "loss": 1.5656, | |
| "step": 507000 | |
| }, | |
| { | |
| "epoch": 16.65, | |
| "learning_rate": 1.679561257467437e-05, | |
| "loss": 1.5676, | |
| "step": 510000 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "learning_rate": 1.630610779225019e-05, | |
| "loss": 1.566, | |
| "step": 513000 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "learning_rate": 1.5816603009826008e-05, | |
| "loss": 1.5691, | |
| "step": 516000 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 1.5327098227401823e-05, | |
| "loss": 1.5684, | |
| "step": 519000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.6387931108474731, | |
| "eval_runtime": 19.1639, | |
| "eval_samples_per_second": 1540.501, | |
| "eval_steps_per_second": 9.654, | |
| "step": 520761 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "learning_rate": 1.4837756667646002e-05, | |
| "loss": 1.5616, | |
| "step": 522000 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 1.434825188522182e-05, | |
| "loss": 1.5545, | |
| "step": 525000 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "learning_rate": 1.3858747102797636e-05, | |
| "loss": 1.5551, | |
| "step": 528000 | |
| }, | |
| { | |
| "epoch": 17.33, | |
| "learning_rate": 1.3369405543041818e-05, | |
| "loss": 1.5558, | |
| "step": 531000 | |
| }, | |
| { | |
| "epoch": 17.43, | |
| "learning_rate": 1.2879900760617636e-05, | |
| "loss": 1.5587, | |
| "step": 534000 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 1.2390559200861816e-05, | |
| "loss": 1.5585, | |
| "step": 537000 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 1.1901054418437633e-05, | |
| "loss": 1.5579, | |
| "step": 540000 | |
| }, | |
| { | |
| "epoch": 17.73, | |
| "learning_rate": 1.141154963601345e-05, | |
| "loss": 1.5586, | |
| "step": 543000 | |
| }, | |
| { | |
| "epoch": 17.82, | |
| "learning_rate": 1.0922208076257631e-05, | |
| "loss": 1.559, | |
| "step": 546000 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 1.0432703293833448e-05, | |
| "loss": 1.5597, | |
| "step": 549000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.6415975093841553, | |
| "eval_runtime": 19.1825, | |
| "eval_samples_per_second": 1539.008, | |
| "eval_steps_per_second": 9.644, | |
| "step": 551394 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 9.94336173407763e-06, | |
| "loss": 1.5579, | |
| "step": 552000 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "learning_rate": 9.453856951653447e-06, | |
| "loss": 1.5465, | |
| "step": 555000 | |
| }, | |
| { | |
| "epoch": 18.22, | |
| "learning_rate": 8.964352169229264e-06, | |
| "loss": 1.5491, | |
| "step": 558000 | |
| }, | |
| { | |
| "epoch": 18.31, | |
| "learning_rate": 8.475010609473443e-06, | |
| "loss": 1.5495, | |
| "step": 561000 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 7.985505827049262e-06, | |
| "loss": 1.5498, | |
| "step": 564000 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 7.496001044625078e-06, | |
| "loss": 1.5514, | |
| "step": 567000 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 7.006659484869258e-06, | |
| "loss": 1.5508, | |
| "step": 570000 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 6.517154702445076e-06, | |
| "loss": 1.5516, | |
| "step": 573000 | |
| }, | |
| { | |
| "epoch": 18.8, | |
| "learning_rate": 6.027649920020892e-06, | |
| "loss": 1.5508, | |
| "step": 576000 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 5.538308360265074e-06, | |
| "loss": 1.5515, | |
| "step": 579000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 5.048803577840891e-06, | |
| "loss": 1.5521, | |
| "step": 582000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.6370400190353394, | |
| "eval_runtime": 19.1163, | |
| "eval_samples_per_second": 1544.337, | |
| "eval_steps_per_second": 9.678, | |
| "step": 582027 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 4.559298795416708e-06, | |
| "loss": 1.5413, | |
| "step": 585000 | |
| }, | |
| { | |
| "epoch": 19.19, | |
| "learning_rate": 4.069957235660889e-06, | |
| "loss": 1.5435, | |
| "step": 588000 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 3.580452453236706e-06, | |
| "loss": 1.5432, | |
| "step": 591000 | |
| }, | |
| { | |
| "epoch": 19.39, | |
| "learning_rate": 3.091110893480887e-06, | |
| "loss": 1.5437, | |
| "step": 594000 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 2.6016061110567034e-06, | |
| "loss": 1.5431, | |
| "step": 597000 | |
| }, | |
| { | |
| "epoch": 19.59, | |
| "learning_rate": 2.1121013286325204e-06, | |
| "loss": 1.5431, | |
| "step": 600000 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 1.6225965462083374e-06, | |
| "loss": 1.5441, | |
| "step": 603000 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "learning_rate": 1.1332549864525185e-06, | |
| "loss": 1.544, | |
| "step": 606000 | |
| }, | |
| { | |
| "epoch": 19.88, | |
| "learning_rate": 6.437502040283355e-07, | |
| "loss": 1.5469, | |
| "step": 609000 | |
| }, | |
| { | |
| "epoch": 19.98, | |
| "learning_rate": 1.5440864427251657e-07, | |
| "loss": 1.5438, | |
| "step": 612000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.636548638343811, | |
| "eval_runtime": 19.1335, | |
| "eval_samples_per_second": 1542.949, | |
| "eval_steps_per_second": 9.669, | |
| "step": 612660 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 612660, | |
| "total_flos": 3.3229272051886326e+18, | |
| "train_loss": 1.7127611959194204, | |
| "train_runtime": 370998.644, | |
| "train_samples_per_second": 528.445, | |
| "train_steps_per_second": 1.651 | |
| } | |
| ], | |
| "max_steps": 612660, | |
| "num_train_epochs": 20, | |
| "total_flos": 3.3229272051886326e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |