| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 110.0, | |
| "global_step": 962830, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.992000456986176e-05, | |
| "loss": 0.9599, | |
| "step": 3501 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.9476152062416077, | |
| "eval_runtime": 178.6207, | |
| "eval_samples_per_second": 174.224, | |
| "eval_steps_per_second": 10.889, | |
| "step": 3501 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.984000913972353e-05, | |
| "loss": 0.9731, | |
| "step": 7002 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.9536693692207336, | |
| "eval_runtime": 178.7725, | |
| "eval_samples_per_second": 174.076, | |
| "eval_steps_per_second": 10.88, | |
| "step": 7002 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.9760013709585284e-05, | |
| "loss": 0.9745, | |
| "step": 10503 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 0.9530463218688965, | |
| "eval_runtime": 178.7418, | |
| "eval_samples_per_second": 174.106, | |
| "eval_steps_per_second": 10.882, | |
| "step": 10503 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.9680018279447047e-05, | |
| "loss": 0.9747, | |
| "step": 14004 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.9569175839424133, | |
| "eval_runtime": 178.7659, | |
| "eval_samples_per_second": 174.082, | |
| "eval_steps_per_second": 10.88, | |
| "step": 14004 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.960002284930881e-05, | |
| "loss": 0.978, | |
| "step": 17505 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.958555281162262, | |
| "eval_runtime": 178.7319, | |
| "eval_samples_per_second": 174.115, | |
| "eval_steps_per_second": 10.882, | |
| "step": 17505 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.952002741917057e-05, | |
| "loss": 0.9736, | |
| "step": 21006 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.9602962136268616, | |
| "eval_runtime": 178.815, | |
| "eval_samples_per_second": 174.035, | |
| "eval_steps_per_second": 10.877, | |
| "step": 21006 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 4.9440031989032335e-05, | |
| "loss": 0.9772, | |
| "step": 24507 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.9578276872634888, | |
| "eval_runtime": 178.2789, | |
| "eval_samples_per_second": 174.558, | |
| "eval_steps_per_second": 10.91, | |
| "step": 24507 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.93600365588941e-05, | |
| "loss": 0.9771, | |
| "step": 28008 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 0.9583005309104919, | |
| "eval_runtime": 177.473, | |
| "eval_samples_per_second": 175.351, | |
| "eval_steps_per_second": 10.959, | |
| "step": 28008 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 4.928004112875585e-05, | |
| "loss": 0.9773, | |
| "step": 31509 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_loss": 0.9513981938362122, | |
| "eval_runtime": 177.4973, | |
| "eval_samples_per_second": 175.327, | |
| "eval_steps_per_second": 10.958, | |
| "step": 31509 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.920004569861762e-05, | |
| "loss": 0.9802, | |
| "step": 35010 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.9571573138237, | |
| "eval_runtime": 177.3934, | |
| "eval_samples_per_second": 175.429, | |
| "eval_steps_per_second": 10.964, | |
| "step": 35010 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 4.912005026847938e-05, | |
| "loss": 0.9741, | |
| "step": 38511 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "eval_loss": 0.9547442197799683, | |
| "eval_runtime": 177.5692, | |
| "eval_samples_per_second": 175.256, | |
| "eval_steps_per_second": 10.953, | |
| "step": 38511 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.904005483834114e-05, | |
| "loss": 0.9776, | |
| "step": 42012 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_loss": 0.9541487097740173, | |
| "eval_runtime": 177.564, | |
| "eval_samples_per_second": 175.261, | |
| "eval_steps_per_second": 10.954, | |
| "step": 42012 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 4.8960059408202904e-05, | |
| "loss": 0.9737, | |
| "step": 45513 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "eval_loss": 0.9530224204063416, | |
| "eval_runtime": 177.5256, | |
| "eval_samples_per_second": 175.299, | |
| "eval_steps_per_second": 10.956, | |
| "step": 45513 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.888006397806467e-05, | |
| "loss": 0.9758, | |
| "step": 49014 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "eval_loss": 0.9559855461120605, | |
| "eval_runtime": 177.638, | |
| "eval_samples_per_second": 175.188, | |
| "eval_steps_per_second": 10.949, | |
| "step": 49014 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.880006854792642e-05, | |
| "loss": 0.9777, | |
| "step": 52515 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.9567117691040039, | |
| "eval_runtime": 177.402, | |
| "eval_samples_per_second": 175.421, | |
| "eval_steps_per_second": 10.964, | |
| "step": 52515 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.872007311778819e-05, | |
| "loss": 0.9726, | |
| "step": 56016 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "eval_loss": 0.9548764228820801, | |
| "eval_runtime": 177.4726, | |
| "eval_samples_per_second": 175.351, | |
| "eval_steps_per_second": 10.959, | |
| "step": 56016 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 4.864007768764995e-05, | |
| "loss": 0.977, | |
| "step": 59517 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_loss": 0.9567227959632874, | |
| "eval_runtime": 177.3888, | |
| "eval_samples_per_second": 175.434, | |
| "eval_steps_per_second": 10.965, | |
| "step": 59517 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 4.856008225751171e-05, | |
| "loss": 0.9736, | |
| "step": 63018 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "eval_loss": 0.9573630094528198, | |
| "eval_runtime": 177.3454, | |
| "eval_samples_per_second": 175.477, | |
| "eval_steps_per_second": 10.967, | |
| "step": 63018 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 4.8480086827373474e-05, | |
| "loss": 0.9732, | |
| "step": 66519 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "eval_loss": 0.9487555623054504, | |
| "eval_runtime": 177.2246, | |
| "eval_samples_per_second": 175.596, | |
| "eval_steps_per_second": 10.975, | |
| "step": 66519 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.8400091397235236e-05, | |
| "loss": 0.9743, | |
| "step": 70020 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.9511750936508179, | |
| "eval_runtime": 177.2113, | |
| "eval_samples_per_second": 175.61, | |
| "eval_steps_per_second": 10.976, | |
| "step": 70020 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 4.832009596709699e-05, | |
| "loss": 0.9684, | |
| "step": 73521 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "eval_loss": 0.954649031162262, | |
| "eval_runtime": 177.1791, | |
| "eval_samples_per_second": 175.642, | |
| "eval_steps_per_second": 10.978, | |
| "step": 73521 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 4.824010053695876e-05, | |
| "loss": 0.974, | |
| "step": 77022 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "eval_loss": 0.9532359838485718, | |
| "eval_runtime": 177.517, | |
| "eval_samples_per_second": 175.307, | |
| "eval_steps_per_second": 10.957, | |
| "step": 77022 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 4.816010510682052e-05, | |
| "loss": 0.9713, | |
| "step": 80523 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "eval_loss": 0.9548117518424988, | |
| "eval_runtime": 177.4324, | |
| "eval_samples_per_second": 175.391, | |
| "eval_steps_per_second": 10.962, | |
| "step": 80523 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 4.808010967668228e-05, | |
| "loss": 0.9693, | |
| "step": 84024 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "eval_loss": 0.9545753002166748, | |
| "eval_runtime": 177.4929, | |
| "eval_samples_per_second": 175.331, | |
| "eval_steps_per_second": 10.958, | |
| "step": 84024 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.800011424654404e-05, | |
| "loss": 0.9734, | |
| "step": 87525 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.9541465044021606, | |
| "eval_runtime": 177.7477, | |
| "eval_samples_per_second": 175.08, | |
| "eval_steps_per_second": 10.942, | |
| "step": 87525 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 4.7920118816405806e-05, | |
| "loss": 0.9681, | |
| "step": 91026 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "eval_loss": 0.9508066177368164, | |
| "eval_runtime": 177.4879, | |
| "eval_samples_per_second": 175.336, | |
| "eval_steps_per_second": 10.958, | |
| "step": 91026 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 4.784012338626757e-05, | |
| "loss": 0.9713, | |
| "step": 94527 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "eval_loss": 0.953546404838562, | |
| "eval_runtime": 177.5133, | |
| "eval_samples_per_second": 175.311, | |
| "eval_steps_per_second": 10.957, | |
| "step": 94527 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 4.776012795612933e-05, | |
| "loss": 0.9682, | |
| "step": 98028 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "eval_loss": 0.9516591429710388, | |
| "eval_runtime": 177.5065, | |
| "eval_samples_per_second": 175.318, | |
| "eval_steps_per_second": 10.957, | |
| "step": 98028 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 4.768013252599109e-05, | |
| "loss": 0.9678, | |
| "step": 101529 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "eval_loss": 0.9487663507461548, | |
| "eval_runtime": 177.5275, | |
| "eval_samples_per_second": 175.297, | |
| "eval_steps_per_second": 10.956, | |
| "step": 101529 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.760013709585286e-05, | |
| "loss": 0.9692, | |
| "step": 105030 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.9506123065948486, | |
| "eval_runtime": 177.4334, | |
| "eval_samples_per_second": 175.39, | |
| "eval_steps_per_second": 10.962, | |
| "step": 105030 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 4.752014166571461e-05, | |
| "loss": 0.9648, | |
| "step": 108531 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "eval_loss": 0.9482792019844055, | |
| "eval_runtime": 177.4207, | |
| "eval_samples_per_second": 175.402, | |
| "eval_steps_per_second": 10.963, | |
| "step": 108531 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 4.7440146235576376e-05, | |
| "loss": 0.9664, | |
| "step": 112032 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "eval_loss": 0.9506826400756836, | |
| "eval_runtime": 177.4367, | |
| "eval_samples_per_second": 175.386, | |
| "eval_steps_per_second": 10.962, | |
| "step": 112032 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 4.736015080543814e-05, | |
| "loss": 0.9656, | |
| "step": 115533 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "eval_loss": 0.9522765874862671, | |
| "eval_runtime": 177.6082, | |
| "eval_samples_per_second": 175.217, | |
| "eval_steps_per_second": 10.951, | |
| "step": 115533 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 4.72801553752999e-05, | |
| "loss": 0.9678, | |
| "step": 119034 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "eval_loss": 0.9502620100975037, | |
| "eval_runtime": 177.507, | |
| "eval_samples_per_second": 175.317, | |
| "eval_steps_per_second": 10.957, | |
| "step": 119034 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.720015994516166e-05, | |
| "loss": 0.9652, | |
| "step": 122535 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.9443088173866272, | |
| "eval_runtime": 177.5507, | |
| "eval_samples_per_second": 175.274, | |
| "eval_steps_per_second": 10.955, | |
| "step": 122535 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 4.7120164515023426e-05, | |
| "loss": 0.9624, | |
| "step": 126036 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "eval_loss": 0.9469555020332336, | |
| "eval_runtime": 177.4174, | |
| "eval_samples_per_second": 175.406, | |
| "eval_steps_per_second": 10.963, | |
| "step": 126036 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 4.704016908488518e-05, | |
| "loss": 0.9632, | |
| "step": 129537 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "eval_loss": 0.9473945498466492, | |
| "eval_runtime": 177.5092, | |
| "eval_samples_per_second": 175.315, | |
| "eval_steps_per_second": 10.957, | |
| "step": 129537 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 4.6960173654746945e-05, | |
| "loss": 0.9625, | |
| "step": 133038 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "eval_loss": 0.948591947555542, | |
| "eval_runtime": 177.5625, | |
| "eval_samples_per_second": 175.262, | |
| "eval_steps_per_second": 10.954, | |
| "step": 133038 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 4.688017822460871e-05, | |
| "loss": 0.9606, | |
| "step": 136539 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "eval_loss": 0.9465170502662659, | |
| "eval_runtime": 177.5019, | |
| "eval_samples_per_second": 175.322, | |
| "eval_steps_per_second": 10.958, | |
| "step": 136539 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 4.680018279447047e-05, | |
| "loss": 0.9623, | |
| "step": 140040 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.9485459327697754, | |
| "eval_runtime": 177.4543, | |
| "eval_samples_per_second": 175.369, | |
| "eval_steps_per_second": 10.961, | |
| "step": 140040 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 4.6720187364332226e-05, | |
| "loss": 0.9621, | |
| "step": 143541 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "eval_loss": 0.9435310959815979, | |
| "eval_runtime": 177.7019, | |
| "eval_samples_per_second": 175.125, | |
| "eval_steps_per_second": 10.945, | |
| "step": 143541 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 4.6640191934193996e-05, | |
| "loss": 0.9608, | |
| "step": 147042 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "eval_loss": 0.9458166360855103, | |
| "eval_runtime": 177.4161, | |
| "eval_samples_per_second": 175.407, | |
| "eval_steps_per_second": 10.963, | |
| "step": 147042 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 4.656019650405575e-05, | |
| "loss": 0.9607, | |
| "step": 150543 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "eval_loss": 0.944205641746521, | |
| "eval_runtime": 177.3072, | |
| "eval_samples_per_second": 175.515, | |
| "eval_steps_per_second": 10.97, | |
| "step": 150543 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.6480201073917515e-05, | |
| "loss": 0.9573, | |
| "step": 154044 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "eval_loss": 0.948502242565155, | |
| "eval_runtime": 177.4753, | |
| "eval_samples_per_second": 175.348, | |
| "eval_steps_per_second": 10.959, | |
| "step": 154044 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 4.640020564377928e-05, | |
| "loss": 0.9629, | |
| "step": 157545 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.9456846714019775, | |
| "eval_runtime": 177.5771, | |
| "eval_samples_per_second": 175.248, | |
| "eval_steps_per_second": 10.953, | |
| "step": 157545 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 4.632021021364104e-05, | |
| "loss": 0.9576, | |
| "step": 161046 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "eval_loss": 0.9430428147315979, | |
| "eval_runtime": 177.5195, | |
| "eval_samples_per_second": 175.305, | |
| "eval_steps_per_second": 10.957, | |
| "step": 161046 | |
| }, | |
| { | |
| "epoch": 18.8, | |
| "learning_rate": 4.62402147835028e-05, | |
| "loss": 0.9572, | |
| "step": 164547 | |
| }, | |
| { | |
| "epoch": 18.8, | |
| "eval_loss": 0.945507824420929, | |
| "eval_runtime": 177.5717, | |
| "eval_samples_per_second": 175.253, | |
| "eval_steps_per_second": 10.953, | |
| "step": 164547 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 4.6160219353364566e-05, | |
| "loss": 0.9561, | |
| "step": 168048 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "eval_loss": 0.9430563449859619, | |
| "eval_runtime": 177.639, | |
| "eval_samples_per_second": 175.187, | |
| "eval_steps_per_second": 10.949, | |
| "step": 168048 | |
| }, | |
| { | |
| "epoch": 19.6, | |
| "learning_rate": 4.608022392322632e-05, | |
| "loss": 0.9584, | |
| "step": 171549 | |
| }, | |
| { | |
| "epoch": 19.6, | |
| "eval_loss": 0.944654107093811, | |
| "eval_runtime": 177.2628, | |
| "eval_samples_per_second": 175.559, | |
| "eval_steps_per_second": 10.972, | |
| "step": 171549 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.600022849308809e-05, | |
| "loss": 0.9571, | |
| "step": 175050 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.9449816346168518, | |
| "eval_runtime": 177.5343, | |
| "eval_samples_per_second": 175.29, | |
| "eval_steps_per_second": 10.956, | |
| "step": 175050 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "learning_rate": 4.592023306294985e-05, | |
| "loss": 0.9532, | |
| "step": 178551 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "eval_loss": 0.9422610998153687, | |
| "eval_runtime": 177.5589, | |
| "eval_samples_per_second": 175.266, | |
| "eval_steps_per_second": 10.954, | |
| "step": 178551 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 4.584023763281161e-05, | |
| "loss": 0.955, | |
| "step": 182052 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "eval_loss": 0.9425234794616699, | |
| "eval_runtime": 177.4849, | |
| "eval_samples_per_second": 175.339, | |
| "eval_steps_per_second": 10.959, | |
| "step": 182052 | |
| }, | |
| { | |
| "epoch": 21.2, | |
| "learning_rate": 4.576024220267337e-05, | |
| "loss": 0.9542, | |
| "step": 185553 | |
| }, | |
| { | |
| "epoch": 21.2, | |
| "eval_loss": 0.940060555934906, | |
| "eval_runtime": 177.7301, | |
| "eval_samples_per_second": 175.097, | |
| "eval_steps_per_second": 10.944, | |
| "step": 185553 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 4.5680246772535135e-05, | |
| "loss": 0.9512, | |
| "step": 189054 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "eval_loss": 0.9436028599739075, | |
| "eval_runtime": 177.5045, | |
| "eval_samples_per_second": 175.319, | |
| "eval_steps_per_second": 10.957, | |
| "step": 189054 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 4.560025134239689e-05, | |
| "loss": 0.9556, | |
| "step": 192555 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.9408882260322571, | |
| "eval_runtime": 177.5846, | |
| "eval_samples_per_second": 175.24, | |
| "eval_steps_per_second": 10.953, | |
| "step": 192555 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 4.552025591225866e-05, | |
| "loss": 0.9528, | |
| "step": 196056 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "eval_loss": 0.9434440732002258, | |
| "eval_runtime": 177.5389, | |
| "eval_samples_per_second": 175.286, | |
| "eval_steps_per_second": 10.955, | |
| "step": 196056 | |
| }, | |
| { | |
| "epoch": 22.8, | |
| "learning_rate": 4.5440260482120416e-05, | |
| "loss": 0.9519, | |
| "step": 199557 | |
| }, | |
| { | |
| "epoch": 22.8, | |
| "eval_loss": 0.9397256970405579, | |
| "eval_runtime": 177.7195, | |
| "eval_samples_per_second": 175.107, | |
| "eval_steps_per_second": 10.944, | |
| "step": 199557 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 4.536026505198218e-05, | |
| "loss": 0.9526, | |
| "step": 203058 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "eval_loss": 0.9388800263404846, | |
| "eval_runtime": 177.5696, | |
| "eval_samples_per_second": 175.255, | |
| "eval_steps_per_second": 10.953, | |
| "step": 203058 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "learning_rate": 4.528026962184394e-05, | |
| "loss": 0.9494, | |
| "step": 206559 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "eval_loss": 0.93772292137146, | |
| "eval_runtime": 177.5868, | |
| "eval_samples_per_second": 175.238, | |
| "eval_steps_per_second": 10.952, | |
| "step": 206559 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.5200274191705705e-05, | |
| "loss": 0.953, | |
| "step": 210060 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.9386118054389954, | |
| "eval_runtime": 177.6021, | |
| "eval_samples_per_second": 175.223, | |
| "eval_steps_per_second": 10.951, | |
| "step": 210060 | |
| }, | |
| { | |
| "epoch": 24.4, | |
| "learning_rate": 4.512027876156746e-05, | |
| "loss": 0.9472, | |
| "step": 213561 | |
| }, | |
| { | |
| "epoch": 24.4, | |
| "eval_loss": 0.9392057061195374, | |
| "eval_runtime": 177.5795, | |
| "eval_samples_per_second": 175.245, | |
| "eval_steps_per_second": 10.953, | |
| "step": 213561 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 4.504028333142923e-05, | |
| "loss": 0.9505, | |
| "step": 217062 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "eval_loss": 0.9383804798126221, | |
| "eval_runtime": 177.5958, | |
| "eval_samples_per_second": 175.229, | |
| "eval_steps_per_second": 10.952, | |
| "step": 217062 | |
| }, | |
| { | |
| "epoch": 25.2, | |
| "learning_rate": 4.4960287901290986e-05, | |
| "loss": 0.9458, | |
| "step": 220563 | |
| }, | |
| { | |
| "epoch": 25.2, | |
| "eval_loss": 0.9350699186325073, | |
| "eval_runtime": 177.4438, | |
| "eval_samples_per_second": 175.379, | |
| "eval_steps_per_second": 10.961, | |
| "step": 220563 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 4.488029247115275e-05, | |
| "loss": 0.9479, | |
| "step": 224064 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "eval_loss": 0.9326021671295166, | |
| "eval_runtime": 177.3212, | |
| "eval_samples_per_second": 175.501, | |
| "eval_steps_per_second": 10.969, | |
| "step": 224064 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 4.480029704101451e-05, | |
| "loss": 0.9495, | |
| "step": 227565 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.9333738088607788, | |
| "eval_runtime": 177.2781, | |
| "eval_samples_per_second": 175.543, | |
| "eval_steps_per_second": 10.971, | |
| "step": 227565 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 4.4720301610876274e-05, | |
| "loss": 0.9434, | |
| "step": 231066 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "eval_loss": 0.9343997836112976, | |
| "eval_runtime": 177.4455, | |
| "eval_samples_per_second": 175.378, | |
| "eval_steps_per_second": 10.961, | |
| "step": 231066 | |
| }, | |
| { | |
| "epoch": 26.8, | |
| "learning_rate": 4.464030618073804e-05, | |
| "loss": 0.9475, | |
| "step": 234567 | |
| }, | |
| { | |
| "epoch": 26.8, | |
| "eval_loss": 0.9394047856330872, | |
| "eval_runtime": 177.4291, | |
| "eval_samples_per_second": 175.394, | |
| "eval_steps_per_second": 10.962, | |
| "step": 234567 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 4.45603107505998e-05, | |
| "loss": 0.9479, | |
| "step": 238068 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "eval_loss": 0.9336209893226624, | |
| "eval_runtime": 177.3352, | |
| "eval_samples_per_second": 175.487, | |
| "eval_steps_per_second": 10.968, | |
| "step": 238068 | |
| }, | |
| { | |
| "epoch": 27.6, | |
| "learning_rate": 4.4480315320461556e-05, | |
| "loss": 0.9453, | |
| "step": 241569 | |
| }, | |
| { | |
| "epoch": 27.6, | |
| "eval_loss": 0.9349226355552673, | |
| "eval_runtime": 177.3043, | |
| "eval_samples_per_second": 175.517, | |
| "eval_steps_per_second": 10.97, | |
| "step": 241569 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 4.4400319890323325e-05, | |
| "loss": 0.9458, | |
| "step": 245070 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.9337905645370483, | |
| "eval_runtime": 177.3396, | |
| "eval_samples_per_second": 175.482, | |
| "eval_steps_per_second": 10.968, | |
| "step": 245070 | |
| }, | |
| { | |
| "epoch": 28.4, | |
| "learning_rate": 4.432032446018508e-05, | |
| "loss": 0.9411, | |
| "step": 248571 | |
| }, | |
| { | |
| "epoch": 28.4, | |
| "eval_loss": 0.9311910271644592, | |
| "eval_runtime": 177.2625, | |
| "eval_samples_per_second": 175.559, | |
| "eval_steps_per_second": 10.972, | |
| "step": 248571 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 4.4240329030046844e-05, | |
| "loss": 0.9443, | |
| "step": 252072 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "eval_loss": 0.930526614189148, | |
| "eval_runtime": 177.3837, | |
| "eval_samples_per_second": 175.439, | |
| "eval_steps_per_second": 10.965, | |
| "step": 252072 | |
| }, | |
| { | |
| "epoch": 29.2, | |
| "learning_rate": 4.4160333599908606e-05, | |
| "loss": 0.9418, | |
| "step": 255573 | |
| }, | |
| { | |
| "epoch": 29.2, | |
| "eval_loss": 0.9349842667579651, | |
| "eval_runtime": 177.3409, | |
| "eval_samples_per_second": 175.481, | |
| "eval_steps_per_second": 10.968, | |
| "step": 255573 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 4.408033816977037e-05, | |
| "loss": 0.9423, | |
| "step": 259074 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "eval_loss": 0.9312747716903687, | |
| "eval_runtime": 177.3094, | |
| "eval_samples_per_second": 175.512, | |
| "eval_steps_per_second": 10.97, | |
| "step": 259074 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 4.4000342739632125e-05, | |
| "loss": 0.9441, | |
| "step": 262575 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.9297969341278076, | |
| "eval_runtime": 177.4784, | |
| "eval_samples_per_second": 175.345, | |
| "eval_steps_per_second": 10.959, | |
| "step": 262575 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "learning_rate": 4.3920347309493895e-05, | |
| "loss": 0.9388, | |
| "step": 266076 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "eval_loss": 0.9298827052116394, | |
| "eval_runtime": 177.3405, | |
| "eval_samples_per_second": 175.482, | |
| "eval_steps_per_second": 10.968, | |
| "step": 266076 | |
| }, | |
| { | |
| "epoch": 30.8, | |
| "learning_rate": 4.384035187935565e-05, | |
| "loss": 0.9418, | |
| "step": 269577 | |
| }, | |
| { | |
| "epoch": 30.8, | |
| "eval_loss": 0.9313934445381165, | |
| "eval_runtime": 177.3424, | |
| "eval_samples_per_second": 175.48, | |
| "eval_steps_per_second": 10.967, | |
| "step": 269577 | |
| }, | |
| { | |
| "epoch": 31.2, | |
| "learning_rate": 4.376035644921741e-05, | |
| "loss": 0.9402, | |
| "step": 273078 | |
| }, | |
| { | |
| "epoch": 31.2, | |
| "eval_loss": 0.933687150478363, | |
| "eval_runtime": 177.2623, | |
| "eval_samples_per_second": 175.559, | |
| "eval_steps_per_second": 10.972, | |
| "step": 273078 | |
| }, | |
| { | |
| "epoch": 31.6, | |
| "learning_rate": 4.3680361019079176e-05, | |
| "loss": 0.9366, | |
| "step": 276579 | |
| }, | |
| { | |
| "epoch": 31.6, | |
| "eval_loss": 0.927956223487854, | |
| "eval_runtime": 177.2474, | |
| "eval_samples_per_second": 175.574, | |
| "eval_steps_per_second": 10.973, | |
| "step": 276579 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 4.360036558894094e-05, | |
| "loss": 0.9406, | |
| "step": 280080 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.9269111156463623, | |
| "eval_runtime": 177.2222, | |
| "eval_samples_per_second": 175.599, | |
| "eval_steps_per_second": 10.975, | |
| "step": 280080 | |
| }, | |
| { | |
| "epoch": 32.4, | |
| "learning_rate": 4.3520370158802695e-05, | |
| "loss": 0.9362, | |
| "step": 283581 | |
| }, | |
| { | |
| "epoch": 32.4, | |
| "eval_loss": 0.9323258399963379, | |
| "eval_runtime": 177.3606, | |
| "eval_samples_per_second": 175.462, | |
| "eval_steps_per_second": 10.966, | |
| "step": 283581 | |
| }, | |
| { | |
| "epoch": 32.8, | |
| "learning_rate": 4.3440374728664464e-05, | |
| "loss": 0.9389, | |
| "step": 287082 | |
| }, | |
| { | |
| "epoch": 32.8, | |
| "eval_loss": 0.9279223084449768, | |
| "eval_runtime": 177.4942, | |
| "eval_samples_per_second": 175.33, | |
| "eval_steps_per_second": 10.958, | |
| "step": 287082 | |
| }, | |
| { | |
| "epoch": 33.2, | |
| "learning_rate": 4.336037929852622e-05, | |
| "loss": 0.9347, | |
| "step": 290583 | |
| }, | |
| { | |
| "epoch": 33.2, | |
| "eval_loss": 0.9276158213615417, | |
| "eval_runtime": 177.5222, | |
| "eval_samples_per_second": 175.302, | |
| "eval_steps_per_second": 10.956, | |
| "step": 290583 | |
| }, | |
| { | |
| "epoch": 33.6, | |
| "learning_rate": 4.328038386838798e-05, | |
| "loss": 0.9361, | |
| "step": 294084 | |
| }, | |
| { | |
| "epoch": 33.6, | |
| "eval_loss": 0.93123459815979, | |
| "eval_runtime": 177.5834, | |
| "eval_samples_per_second": 175.242, | |
| "eval_steps_per_second": 10.953, | |
| "step": 294084 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 4.3200388438249746e-05, | |
| "loss": 0.9382, | |
| "step": 297585 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.928411602973938, | |
| "eval_runtime": 177.6079, | |
| "eval_samples_per_second": 175.217, | |
| "eval_steps_per_second": 10.951, | |
| "step": 297585 | |
| }, | |
| { | |
| "epoch": 34.4, | |
| "learning_rate": 4.312039300811151e-05, | |
| "loss": 0.9319, | |
| "step": 301086 | |
| }, | |
| { | |
| "epoch": 34.4, | |
| "eval_loss": 0.9270405173301697, | |
| "eval_runtime": 177.5221, | |
| "eval_samples_per_second": 175.302, | |
| "eval_steps_per_second": 10.956, | |
| "step": 301086 | |
| }, | |
| { | |
| "epoch": 34.8, | |
| "learning_rate": 4.304039757797327e-05, | |
| "loss": 0.9361, | |
| "step": 304587 | |
| }, | |
| { | |
| "epoch": 34.8, | |
| "eval_loss": 0.9271640777587891, | |
| "eval_runtime": 177.3566, | |
| "eval_samples_per_second": 175.466, | |
| "eval_steps_per_second": 10.967, | |
| "step": 304587 | |
| }, | |
| { | |
| "epoch": 35.2, | |
| "learning_rate": 4.2960402147835034e-05, | |
| "loss": 0.9339, | |
| "step": 308088 | |
| }, | |
| { | |
| "epoch": 35.2, | |
| "eval_loss": 0.9249849319458008, | |
| "eval_runtime": 177.2959, | |
| "eval_samples_per_second": 175.526, | |
| "eval_steps_per_second": 10.97, | |
| "step": 308088 | |
| }, | |
| { | |
| "epoch": 35.6, | |
| "learning_rate": 4.288040671769679e-05, | |
| "loss": 0.9329, | |
| "step": 311589 | |
| }, | |
| { | |
| "epoch": 35.6, | |
| "eval_loss": 0.9226134419441223, | |
| "eval_runtime": 177.4932, | |
| "eval_samples_per_second": 175.331, | |
| "eval_steps_per_second": 10.958, | |
| "step": 311589 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 4.280041128755856e-05, | |
| "loss": 0.9364, | |
| "step": 315090 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 0.9226271510124207, | |
| "eval_runtime": 177.4871, | |
| "eval_samples_per_second": 175.337, | |
| "eval_steps_per_second": 10.959, | |
| "step": 315090 | |
| }, | |
| { | |
| "epoch": 36.4, | |
| "learning_rate": 4.2720415857420315e-05, | |
| "loss": 0.9307, | |
| "step": 318591 | |
| }, | |
| { | |
| "epoch": 36.4, | |
| "eval_loss": 0.9248347878456116, | |
| "eval_runtime": 177.8038, | |
| "eval_samples_per_second": 175.024, | |
| "eval_steps_per_second": 10.939, | |
| "step": 318591 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "learning_rate": 4.264042042728208e-05, | |
| "loss": 0.9326, | |
| "step": 322092 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "eval_loss": 0.9248685836791992, | |
| "eval_runtime": 177.5153, | |
| "eval_samples_per_second": 175.309, | |
| "eval_steps_per_second": 10.957, | |
| "step": 322092 | |
| }, | |
| { | |
| "epoch": 37.2, | |
| "learning_rate": 4.256042499714384e-05, | |
| "loss": 0.932, | |
| "step": 325593 | |
| }, | |
| { | |
| "epoch": 37.2, | |
| "eval_loss": 0.9229134321212769, | |
| "eval_runtime": 177.4978, | |
| "eval_samples_per_second": 175.326, | |
| "eval_steps_per_second": 10.958, | |
| "step": 325593 | |
| }, | |
| { | |
| "epoch": 37.6, | |
| "learning_rate": 4.2480429567005596e-05, | |
| "loss": 0.9321, | |
| "step": 329094 | |
| }, | |
| { | |
| "epoch": 37.6, | |
| "eval_loss": 0.9236814975738525, | |
| "eval_runtime": 178.5737, | |
| "eval_samples_per_second": 174.27, | |
| "eval_steps_per_second": 10.892, | |
| "step": 329094 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 4.240043413686736e-05, | |
| "loss": 0.9315, | |
| "step": 332595 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.9243875741958618, | |
| "eval_runtime": 178.4244, | |
| "eval_samples_per_second": 174.416, | |
| "eval_steps_per_second": 10.901, | |
| "step": 332595 | |
| }, | |
| { | |
| "epoch": 38.4, | |
| "learning_rate": 4.232043870672912e-05, | |
| "loss": 0.9277, | |
| "step": 336096 | |
| }, | |
| { | |
| "epoch": 38.4, | |
| "eval_loss": 0.921384334564209, | |
| "eval_runtime": 178.5199, | |
| "eval_samples_per_second": 174.322, | |
| "eval_steps_per_second": 10.895, | |
| "step": 336096 | |
| }, | |
| { | |
| "epoch": 38.8, | |
| "learning_rate": 4.2240443276590885e-05, | |
| "loss": 0.9305, | |
| "step": 339597 | |
| }, | |
| { | |
| "epoch": 38.8, | |
| "eval_loss": 0.924416184425354, | |
| "eval_runtime": 178.4499, | |
| "eval_samples_per_second": 174.391, | |
| "eval_steps_per_second": 10.899, | |
| "step": 339597 | |
| }, | |
| { | |
| "epoch": 39.2, | |
| "learning_rate": 4.216044784645265e-05, | |
| "loss": 0.9264, | |
| "step": 343098 | |
| }, | |
| { | |
| "epoch": 39.2, | |
| "eval_loss": 0.9202448725700378, | |
| "eval_runtime": 178.5894, | |
| "eval_samples_per_second": 174.254, | |
| "eval_steps_per_second": 10.891, | |
| "step": 343098 | |
| }, | |
| { | |
| "epoch": 39.6, | |
| "learning_rate": 4.208045241631441e-05, | |
| "loss": 0.9272, | |
| "step": 346599 | |
| }, | |
| { | |
| "epoch": 39.6, | |
| "eval_loss": 0.9173216223716736, | |
| "eval_runtime": 178.587, | |
| "eval_samples_per_second": 174.257, | |
| "eval_steps_per_second": 10.891, | |
| "step": 346599 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 4.2000456986176166e-05, | |
| "loss": 0.9292, | |
| "step": 350100 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.9211925268173218, | |
| "eval_runtime": 177.5554, | |
| "eval_samples_per_second": 175.269, | |
| "eval_steps_per_second": 10.954, | |
| "step": 350100 | |
| }, | |
| { | |
| "epoch": 40.4, | |
| "learning_rate": 4.1920461556037935e-05, | |
| "loss": 0.9237, | |
| "step": 353601 | |
| }, | |
| { | |
| "epoch": 40.4, | |
| "eval_loss": 0.9185072183609009, | |
| "eval_runtime": 177.3103, | |
| "eval_samples_per_second": 175.512, | |
| "eval_steps_per_second": 10.969, | |
| "step": 353601 | |
| }, | |
| { | |
| "epoch": 40.8, | |
| "learning_rate": 4.184046612589969e-05, | |
| "loss": 0.9277, | |
| "step": 357102 | |
| }, | |
| { | |
| "epoch": 40.8, | |
| "eval_loss": 0.9214913845062256, | |
| "eval_runtime": 177.444, | |
| "eval_samples_per_second": 175.379, | |
| "eval_steps_per_second": 10.961, | |
| "step": 357102 | |
| }, | |
| { | |
| "epoch": 41.2, | |
| "learning_rate": 4.1760470695761454e-05, | |
| "loss": 0.9262, | |
| "step": 360603 | |
| }, | |
| { | |
| "epoch": 41.2, | |
| "eval_loss": 0.9183996319770813, | |
| "eval_runtime": 177.4174, | |
| "eval_samples_per_second": 175.406, | |
| "eval_steps_per_second": 10.963, | |
| "step": 360603 | |
| }, | |
| { | |
| "epoch": 41.6, | |
| "learning_rate": 4.168047526562322e-05, | |
| "loss": 0.9247, | |
| "step": 364104 | |
| }, | |
| { | |
| "epoch": 41.6, | |
| "eval_loss": 0.921753466129303, | |
| "eval_runtime": 177.4686, | |
| "eval_samples_per_second": 175.355, | |
| "eval_steps_per_second": 10.96, | |
| "step": 364104 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 4.160047983548498e-05, | |
| "loss": 0.9265, | |
| "step": 367605 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 0.9194549918174744, | |
| "eval_runtime": 177.4828, | |
| "eval_samples_per_second": 175.341, | |
| "eval_steps_per_second": 10.959, | |
| "step": 367605 | |
| }, | |
| { | |
| "epoch": 42.4, | |
| "learning_rate": 4.1520484405346736e-05, | |
| "loss": 0.9228, | |
| "step": 371106 | |
| }, | |
| { | |
| "epoch": 42.4, | |
| "eval_loss": 0.9182046055793762, | |
| "eval_runtime": 177.5745, | |
| "eval_samples_per_second": 175.25, | |
| "eval_steps_per_second": 10.953, | |
| "step": 371106 | |
| }, | |
| { | |
| "epoch": 42.8, | |
| "learning_rate": 4.1440488975208505e-05, | |
| "loss": 0.9239, | |
| "step": 374607 | |
| }, | |
| { | |
| "epoch": 42.8, | |
| "eval_loss": 0.9209604859352112, | |
| "eval_runtime": 177.5469, | |
| "eval_samples_per_second": 175.278, | |
| "eval_steps_per_second": 10.955, | |
| "step": 374607 | |
| }, | |
| { | |
| "epoch": 43.2, | |
| "learning_rate": 4.136049354507026e-05, | |
| "loss": 0.9234, | |
| "step": 378108 | |
| }, | |
| { | |
| "epoch": 43.2, | |
| "eval_loss": 0.9235459566116333, | |
| "eval_runtime": 177.4486, | |
| "eval_samples_per_second": 175.375, | |
| "eval_steps_per_second": 10.961, | |
| "step": 378108 | |
| }, | |
| { | |
| "epoch": 43.6, | |
| "learning_rate": 4.1280498114932024e-05, | |
| "loss": 0.9235, | |
| "step": 381609 | |
| }, | |
| { | |
| "epoch": 43.6, | |
| "eval_loss": 0.9178280234336853, | |
| "eval_runtime": 177.5134, | |
| "eval_samples_per_second": 175.311, | |
| "eval_steps_per_second": 10.957, | |
| "step": 381609 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 4.1200502684793786e-05, | |
| "loss": 0.9251, | |
| "step": 385110 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 0.913722574710846, | |
| "eval_runtime": 177.523, | |
| "eval_samples_per_second": 175.301, | |
| "eval_steps_per_second": 10.956, | |
| "step": 385110 | |
| }, | |
| { | |
| "epoch": 44.4, | |
| "learning_rate": 4.112050725465555e-05, | |
| "loss": 0.9188, | |
| "step": 388611 | |
| }, | |
| { | |
| "epoch": 44.4, | |
| "eval_loss": 0.9187389612197876, | |
| "eval_runtime": 177.5478, | |
| "eval_samples_per_second": 175.277, | |
| "eval_steps_per_second": 10.955, | |
| "step": 388611 | |
| }, | |
| { | |
| "epoch": 44.8, | |
| "learning_rate": 4.1040511824517305e-05, | |
| "loss": 0.9215, | |
| "step": 392112 | |
| }, | |
| { | |
| "epoch": 44.8, | |
| "eval_loss": 0.9166533946990967, | |
| "eval_runtime": 177.4821, | |
| "eval_samples_per_second": 175.342, | |
| "eval_steps_per_second": 10.959, | |
| "step": 392112 | |
| }, | |
| { | |
| "epoch": 45.2, | |
| "learning_rate": 4.0960516394379075e-05, | |
| "loss": 0.9203, | |
| "step": 395613 | |
| }, | |
| { | |
| "epoch": 45.2, | |
| "eval_loss": 0.9170865416526794, | |
| "eval_runtime": 177.4835, | |
| "eval_samples_per_second": 175.34, | |
| "eval_steps_per_second": 10.959, | |
| "step": 395613 | |
| }, | |
| { | |
| "epoch": 45.6, | |
| "learning_rate": 4.088052096424083e-05, | |
| "loss": 0.9206, | |
| "step": 399114 | |
| }, | |
| { | |
| "epoch": 45.6, | |
| "eval_loss": 0.9114164113998413, | |
| "eval_runtime": 177.3931, | |
| "eval_samples_per_second": 175.43, | |
| "eval_steps_per_second": 10.964, | |
| "step": 399114 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 4.080052553410259e-05, | |
| "loss": 0.9226, | |
| "step": 402615 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 0.9157847762107849, | |
| "eval_runtime": 177.4174, | |
| "eval_samples_per_second": 175.406, | |
| "eval_steps_per_second": 10.963, | |
| "step": 402615 | |
| }, | |
| { | |
| "epoch": 46.4, | |
| "learning_rate": 4.0720530103964356e-05, | |
| "loss": 0.9172, | |
| "step": 406116 | |
| }, | |
| { | |
| "epoch": 46.4, | |
| "eval_loss": 0.9159908294677734, | |
| "eval_runtime": 177.5134, | |
| "eval_samples_per_second": 175.311, | |
| "eval_steps_per_second": 10.957, | |
| "step": 406116 | |
| }, | |
| { | |
| "epoch": 46.8, | |
| "learning_rate": 4.064053467382612e-05, | |
| "loss": 0.918, | |
| "step": 409617 | |
| }, | |
| { | |
| "epoch": 46.8, | |
| "eval_loss": 0.9126763343811035, | |
| "eval_runtime": 177.4115, | |
| "eval_samples_per_second": 175.411, | |
| "eval_steps_per_second": 10.963, | |
| "step": 409617 | |
| }, | |
| { | |
| "epoch": 47.2, | |
| "learning_rate": 4.056053924368788e-05, | |
| "loss": 0.9177, | |
| "step": 413118 | |
| }, | |
| { | |
| "epoch": 47.2, | |
| "eval_loss": 0.9146538376808167, | |
| "eval_runtime": 177.5159, | |
| "eval_samples_per_second": 175.308, | |
| "eval_steps_per_second": 10.957, | |
| "step": 413118 | |
| }, | |
| { | |
| "epoch": 47.6, | |
| "learning_rate": 4.0480543813549644e-05, | |
| "loss": 0.918, | |
| "step": 416619 | |
| }, | |
| { | |
| "epoch": 47.6, | |
| "eval_loss": 0.9144261479377747, | |
| "eval_runtime": 177.4299, | |
| "eval_samples_per_second": 175.393, | |
| "eval_steps_per_second": 10.962, | |
| "step": 416619 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 4.04005483834114e-05, | |
| "loss": 0.9186, | |
| "step": 420120 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 0.9152446389198303, | |
| "eval_runtime": 177.4928, | |
| "eval_samples_per_second": 175.331, | |
| "eval_steps_per_second": 10.958, | |
| "step": 420120 | |
| }, | |
| { | |
| "epoch": 48.4, | |
| "learning_rate": 4.032055295327317e-05, | |
| "loss": 0.9145, | |
| "step": 423621 | |
| }, | |
| { | |
| "epoch": 48.4, | |
| "eval_loss": 0.9146500825881958, | |
| "eval_runtime": 177.6162, | |
| "eval_samples_per_second": 175.209, | |
| "eval_steps_per_second": 10.951, | |
| "step": 423621 | |
| }, | |
| { | |
| "epoch": 48.8, | |
| "learning_rate": 4.0240557523134926e-05, | |
| "loss": 0.9176, | |
| "step": 427122 | |
| }, | |
| { | |
| "epoch": 48.8, | |
| "eval_loss": 0.91416335105896, | |
| "eval_runtime": 177.5943, | |
| "eval_samples_per_second": 175.231, | |
| "eval_steps_per_second": 10.952, | |
| "step": 427122 | |
| }, | |
| { | |
| "epoch": 49.2, | |
| "learning_rate": 4.016056209299669e-05, | |
| "loss": 0.9146, | |
| "step": 430623 | |
| }, | |
| { | |
| "epoch": 49.2, | |
| "eval_loss": 0.9143691658973694, | |
| "eval_runtime": 177.6008, | |
| "eval_samples_per_second": 175.224, | |
| "eval_steps_per_second": 10.952, | |
| "step": 430623 | |
| }, | |
| { | |
| "epoch": 49.6, | |
| "learning_rate": 4.008056666285845e-05, | |
| "loss": 0.9163, | |
| "step": 434124 | |
| }, | |
| { | |
| "epoch": 49.6, | |
| "eval_loss": 0.9136433601379395, | |
| "eval_runtime": 177.4417, | |
| "eval_samples_per_second": 175.382, | |
| "eval_steps_per_second": 10.961, | |
| "step": 434124 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 4.0000571232720214e-05, | |
| "loss": 0.9164, | |
| "step": 437625 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 0.9115509390830994, | |
| "eval_runtime": 178.4645, | |
| "eval_samples_per_second": 174.376, | |
| "eval_steps_per_second": 10.899, | |
| "step": 437625 | |
| }, | |
| { | |
| "epoch": 50.4, | |
| "learning_rate": 3.992057580258197e-05, | |
| "loss": 0.9102, | |
| "step": 441126 | |
| }, | |
| { | |
| "epoch": 50.4, | |
| "eval_loss": 0.9133750796318054, | |
| "eval_runtime": 178.2605, | |
| "eval_samples_per_second": 174.576, | |
| "eval_steps_per_second": 10.911, | |
| "step": 441126 | |
| }, | |
| { | |
| "epoch": 50.8, | |
| "learning_rate": 3.984058037244374e-05, | |
| "loss": 0.9149, | |
| "step": 444627 | |
| }, | |
| { | |
| "epoch": 50.8, | |
| "eval_loss": 0.9099620580673218, | |
| "eval_runtime": 177.7712, | |
| "eval_samples_per_second": 175.056, | |
| "eval_steps_per_second": 10.941, | |
| "step": 444627 | |
| }, | |
| { | |
| "epoch": 51.2, | |
| "learning_rate": 3.9760584942305495e-05, | |
| "loss": 0.9155, | |
| "step": 448128 | |
| }, | |
| { | |
| "epoch": 51.2, | |
| "eval_loss": 0.9076240658760071, | |
| "eval_runtime": 177.4509, | |
| "eval_samples_per_second": 175.372, | |
| "eval_steps_per_second": 10.961, | |
| "step": 448128 | |
| }, | |
| { | |
| "epoch": 51.6, | |
| "learning_rate": 3.968058951216726e-05, | |
| "loss": 0.9128, | |
| "step": 451629 | |
| }, | |
| { | |
| "epoch": 51.6, | |
| "eval_loss": 0.9097868204116821, | |
| "eval_runtime": 177.4759, | |
| "eval_samples_per_second": 175.348, | |
| "eval_steps_per_second": 10.959, | |
| "step": 451629 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 3.960059408202902e-05, | |
| "loss": 0.9128, | |
| "step": 455130 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_loss": 0.9142981171607971, | |
| "eval_runtime": 177.8314, | |
| "eval_samples_per_second": 174.997, | |
| "eval_steps_per_second": 10.937, | |
| "step": 455130 | |
| }, | |
| { | |
| "epoch": 52.4, | |
| "learning_rate": 3.952059865189078e-05, | |
| "loss": 0.9098, | |
| "step": 458631 | |
| }, | |
| { | |
| "epoch": 52.4, | |
| "eval_loss": 0.9127160310745239, | |
| "eval_runtime": 177.596, | |
| "eval_samples_per_second": 175.229, | |
| "eval_steps_per_second": 10.952, | |
| "step": 458631 | |
| }, | |
| { | |
| "epoch": 52.8, | |
| "learning_rate": 3.944060322175254e-05, | |
| "loss": 0.9121, | |
| "step": 462132 | |
| }, | |
| { | |
| "epoch": 52.8, | |
| "eval_loss": 0.911176323890686, | |
| "eval_runtime": 177.6183, | |
| "eval_samples_per_second": 175.207, | |
| "eval_steps_per_second": 10.95, | |
| "step": 462132 | |
| }, | |
| { | |
| "epoch": 53.2, | |
| "learning_rate": 3.936060779161431e-05, | |
| "loss": 0.9128, | |
| "step": 465633 | |
| }, | |
| { | |
| "epoch": 53.2, | |
| "eval_loss": 0.9088250398635864, | |
| "eval_runtime": 177.3192, | |
| "eval_samples_per_second": 175.503, | |
| "eval_steps_per_second": 10.969, | |
| "step": 465633 | |
| }, | |
| { | |
| "epoch": 53.6, | |
| "learning_rate": 3.9280612361476065e-05, | |
| "loss": 0.9068, | |
| "step": 469134 | |
| }, | |
| { | |
| "epoch": 53.6, | |
| "eval_loss": 0.9073150157928467, | |
| "eval_runtime": 177.6629, | |
| "eval_samples_per_second": 175.163, | |
| "eval_steps_per_second": 10.948, | |
| "step": 469134 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "learning_rate": 3.920061693133783e-05, | |
| "loss": 0.9116, | |
| "step": 472635 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_loss": 0.9075030088424683, | |
| "eval_runtime": 177.5925, | |
| "eval_samples_per_second": 175.233, | |
| "eval_steps_per_second": 10.952, | |
| "step": 472635 | |
| }, | |
| { | |
| "epoch": 54.4, | |
| "learning_rate": 3.912062150119959e-05, | |
| "loss": 0.9071, | |
| "step": 476136 | |
| }, | |
| { | |
| "epoch": 54.4, | |
| "eval_loss": 0.9067005515098572, | |
| "eval_runtime": 177.5266, | |
| "eval_samples_per_second": 175.298, | |
| "eval_steps_per_second": 10.956, | |
| "step": 476136 | |
| }, | |
| { | |
| "epoch": 54.8, | |
| "learning_rate": 3.904062607106135e-05, | |
| "loss": 0.9104, | |
| "step": 479637 | |
| }, | |
| { | |
| "epoch": 54.8, | |
| "eval_loss": 0.9073493480682373, | |
| "eval_runtime": 177.4472, | |
| "eval_samples_per_second": 175.376, | |
| "eval_steps_per_second": 10.961, | |
| "step": 479637 | |
| }, | |
| { | |
| "epoch": 55.2, | |
| "learning_rate": 3.8960630640923115e-05, | |
| "loss": 0.9054, | |
| "step": 483138 | |
| }, | |
| { | |
| "epoch": 55.2, | |
| "eval_loss": 0.9102022051811218, | |
| "eval_runtime": 177.6725, | |
| "eval_samples_per_second": 175.154, | |
| "eval_steps_per_second": 10.947, | |
| "step": 483138 | |
| }, | |
| { | |
| "epoch": 55.6, | |
| "learning_rate": 3.888063521078488e-05, | |
| "loss": 0.9097, | |
| "step": 486639 | |
| }, | |
| { | |
| "epoch": 55.6, | |
| "eval_loss": 0.9054126143455505, | |
| "eval_runtime": 177.6461, | |
| "eval_samples_per_second": 175.18, | |
| "eval_steps_per_second": 10.949, | |
| "step": 486639 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 3.8800639780646634e-05, | |
| "loss": 0.9091, | |
| "step": 490140 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_loss": 0.9067865014076233, | |
| "eval_runtime": 177.5605, | |
| "eval_samples_per_second": 175.264, | |
| "eval_steps_per_second": 10.954, | |
| "step": 490140 | |
| }, | |
| { | |
| "epoch": 56.4, | |
| "learning_rate": 3.8720644350508404e-05, | |
| "loss": 0.9047, | |
| "step": 493641 | |
| }, | |
| { | |
| "epoch": 56.4, | |
| "eval_loss": 0.9057883024215698, | |
| "eval_runtime": 177.3995, | |
| "eval_samples_per_second": 175.423, | |
| "eval_steps_per_second": 10.964, | |
| "step": 493641 | |
| }, | |
| { | |
| "epoch": 56.8, | |
| "learning_rate": 3.864064892037016e-05, | |
| "loss": 0.9076, | |
| "step": 497142 | |
| }, | |
| { | |
| "epoch": 56.8, | |
| "eval_loss": 0.9096718430519104, | |
| "eval_runtime": 177.7746, | |
| "eval_samples_per_second": 175.053, | |
| "eval_steps_per_second": 10.941, | |
| "step": 497142 | |
| }, | |
| { | |
| "epoch": 57.2, | |
| "learning_rate": 3.856065349023192e-05, | |
| "loss": 0.9052, | |
| "step": 500643 | |
| }, | |
| { | |
| "epoch": 57.2, | |
| "eval_loss": 0.9001969695091248, | |
| "eval_runtime": 177.6819, | |
| "eval_samples_per_second": 175.144, | |
| "eval_steps_per_second": 10.947, | |
| "step": 500643 | |
| }, | |
| { | |
| "epoch": 57.6, | |
| "learning_rate": 3.8480658060093685e-05, | |
| "loss": 0.9047, | |
| "step": 504144 | |
| }, | |
| { | |
| "epoch": 57.6, | |
| "eval_loss": 0.9067962765693665, | |
| "eval_runtime": 177.5691, | |
| "eval_samples_per_second": 175.256, | |
| "eval_steps_per_second": 10.953, | |
| "step": 504144 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "learning_rate": 3.840066262995545e-05, | |
| "loss": 0.9061, | |
| "step": 507645 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_loss": 0.9069446921348572, | |
| "eval_runtime": 177.6225, | |
| "eval_samples_per_second": 175.203, | |
| "eval_steps_per_second": 10.95, | |
| "step": 507645 | |
| }, | |
| { | |
| "epoch": 58.4, | |
| "learning_rate": 3.8320667199817204e-05, | |
| "loss": 0.9004, | |
| "step": 511146 | |
| }, | |
| { | |
| "epoch": 58.4, | |
| "eval_loss": 0.9056394696235657, | |
| "eval_runtime": 177.6384, | |
| "eval_samples_per_second": 175.187, | |
| "eval_steps_per_second": 10.949, | |
| "step": 511146 | |
| }, | |
| { | |
| "epoch": 58.8, | |
| "learning_rate": 3.824067176967897e-05, | |
| "loss": 0.9056, | |
| "step": 514647 | |
| }, | |
| { | |
| "epoch": 58.8, | |
| "eval_loss": 0.9041665196418762, | |
| "eval_runtime": 177.5114, | |
| "eval_samples_per_second": 175.313, | |
| "eval_steps_per_second": 10.957, | |
| "step": 514647 | |
| }, | |
| { | |
| "epoch": 59.2, | |
| "learning_rate": 3.816067633954073e-05, | |
| "loss": 0.9038, | |
| "step": 518148 | |
| }, | |
| { | |
| "epoch": 59.2, | |
| "eval_loss": 0.9006583094596863, | |
| "eval_runtime": 177.5976, | |
| "eval_samples_per_second": 175.228, | |
| "eval_steps_per_second": 10.952, | |
| "step": 518148 | |
| }, | |
| { | |
| "epoch": 59.6, | |
| "learning_rate": 3.808068090940249e-05, | |
| "loss": 0.9033, | |
| "step": 521649 | |
| }, | |
| { | |
| "epoch": 59.6, | |
| "eval_loss": 0.905081570148468, | |
| "eval_runtime": 177.5456, | |
| "eval_samples_per_second": 175.279, | |
| "eval_steps_per_second": 10.955, | |
| "step": 521649 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 3.8000685479264255e-05, | |
| "loss": 0.903, | |
| "step": 525150 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_loss": 0.9015125632286072, | |
| "eval_runtime": 177.5682, | |
| "eval_samples_per_second": 175.257, | |
| "eval_steps_per_second": 10.954, | |
| "step": 525150 | |
| }, | |
| { | |
| "epoch": 60.4, | |
| "learning_rate": 3.792069004912602e-05, | |
| "loss": 0.9001, | |
| "step": 528651 | |
| }, | |
| { | |
| "epoch": 60.4, | |
| "eval_loss": 0.9008970856666565, | |
| "eval_runtime": 177.5673, | |
| "eval_samples_per_second": 175.258, | |
| "eval_steps_per_second": 10.954, | |
| "step": 528651 | |
| }, | |
| { | |
| "epoch": 60.8, | |
| "learning_rate": 3.784069461898777e-05, | |
| "loss": 0.9039, | |
| "step": 532152 | |
| }, | |
| { | |
| "epoch": 60.8, | |
| "eval_loss": 0.8996139764785767, | |
| "eval_runtime": 177.5892, | |
| "eval_samples_per_second": 175.236, | |
| "eval_steps_per_second": 10.952, | |
| "step": 532152 | |
| }, | |
| { | |
| "epoch": 61.2, | |
| "learning_rate": 3.776069918884954e-05, | |
| "loss": 0.9026, | |
| "step": 535653 | |
| }, | |
| { | |
| "epoch": 61.2, | |
| "eval_loss": 0.9031299948692322, | |
| "eval_runtime": 177.6018, | |
| "eval_samples_per_second": 175.223, | |
| "eval_steps_per_second": 10.951, | |
| "step": 535653 | |
| }, | |
| { | |
| "epoch": 61.6, | |
| "learning_rate": 3.76807037587113e-05, | |
| "loss": 0.901, | |
| "step": 539154 | |
| }, | |
| { | |
| "epoch": 61.6, | |
| "eval_loss": 0.9000225067138672, | |
| "eval_runtime": 177.4957, | |
| "eval_samples_per_second": 175.328, | |
| "eval_steps_per_second": 10.958, | |
| "step": 539154 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "learning_rate": 3.760070832857306e-05, | |
| "loss": 0.9026, | |
| "step": 542655 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_loss": 0.8991663455963135, | |
| "eval_runtime": 177.5752, | |
| "eval_samples_per_second": 175.25, | |
| "eval_steps_per_second": 10.953, | |
| "step": 542655 | |
| }, | |
| { | |
| "epoch": 62.4, | |
| "learning_rate": 3.7520712898434824e-05, | |
| "loss": 0.8988, | |
| "step": 546156 | |
| }, | |
| { | |
| "epoch": 62.4, | |
| "eval_loss": 0.9008954763412476, | |
| "eval_runtime": 177.533, | |
| "eval_samples_per_second": 175.291, | |
| "eval_steps_per_second": 10.956, | |
| "step": 546156 | |
| }, | |
| { | |
| "epoch": 62.8, | |
| "learning_rate": 3.744071746829659e-05, | |
| "loss": 0.8994, | |
| "step": 549657 | |
| }, | |
| { | |
| "epoch": 62.8, | |
| "eval_loss": 0.9005922675132751, | |
| "eval_runtime": 177.6151, | |
| "eval_samples_per_second": 175.21, | |
| "eval_steps_per_second": 10.951, | |
| "step": 549657 | |
| }, | |
| { | |
| "epoch": 63.2, | |
| "learning_rate": 3.736072203815835e-05, | |
| "loss": 0.8983, | |
| "step": 553158 | |
| }, | |
| { | |
| "epoch": 63.2, | |
| "eval_loss": 0.9030284881591797, | |
| "eval_runtime": 177.5458, | |
| "eval_samples_per_second": 175.279, | |
| "eval_steps_per_second": 10.955, | |
| "step": 553158 | |
| }, | |
| { | |
| "epoch": 63.6, | |
| "learning_rate": 3.728072660802011e-05, | |
| "loss": 0.9, | |
| "step": 556659 | |
| }, | |
| { | |
| "epoch": 63.6, | |
| "eval_loss": 0.8991916179656982, | |
| "eval_runtime": 177.4727, | |
| "eval_samples_per_second": 175.351, | |
| "eval_steps_per_second": 10.959, | |
| "step": 556659 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "learning_rate": 3.720073117788187e-05, | |
| "loss": 0.8994, | |
| "step": 560160 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 0.8985081315040588, | |
| "eval_runtime": 177.5551, | |
| "eval_samples_per_second": 175.27, | |
| "eval_steps_per_second": 10.954, | |
| "step": 560160 | |
| }, | |
| { | |
| "epoch": 64.4, | |
| "learning_rate": 3.712073574774364e-05, | |
| "loss": 0.8953, | |
| "step": 563661 | |
| }, | |
| { | |
| "epoch": 64.4, | |
| "eval_loss": 0.900728166103363, | |
| "eval_runtime": 177.7452, | |
| "eval_samples_per_second": 175.082, | |
| "eval_steps_per_second": 10.943, | |
| "step": 563661 | |
| }, | |
| { | |
| "epoch": 64.8, | |
| "learning_rate": 3.7040740317605394e-05, | |
| "loss": 0.8991, | |
| "step": 567162 | |
| }, | |
| { | |
| "epoch": 64.8, | |
| "eval_loss": 0.902450680732727, | |
| "eval_runtime": 177.6955, | |
| "eval_samples_per_second": 175.131, | |
| "eval_steps_per_second": 10.946, | |
| "step": 567162 | |
| }, | |
| { | |
| "epoch": 65.2, | |
| "learning_rate": 3.6960744887467156e-05, | |
| "loss": 0.8964, | |
| "step": 570663 | |
| }, | |
| { | |
| "epoch": 65.2, | |
| "eval_loss": 0.8983866572380066, | |
| "eval_runtime": 177.5924, | |
| "eval_samples_per_second": 175.233, | |
| "eval_steps_per_second": 10.952, | |
| "step": 570663 | |
| }, | |
| { | |
| "epoch": 65.6, | |
| "learning_rate": 3.688074945732892e-05, | |
| "loss": 0.8959, | |
| "step": 574164 | |
| }, | |
| { | |
| "epoch": 65.6, | |
| "eval_loss": 0.9006548523902893, | |
| "eval_runtime": 177.7333, | |
| "eval_samples_per_second": 175.094, | |
| "eval_steps_per_second": 10.943, | |
| "step": 574164 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "learning_rate": 3.680075402719068e-05, | |
| "loss": 0.8981, | |
| "step": 577665 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_loss": 0.8985300064086914, | |
| "eval_runtime": 177.5714, | |
| "eval_samples_per_second": 175.253, | |
| "eval_steps_per_second": 10.953, | |
| "step": 577665 | |
| }, | |
| { | |
| "epoch": 66.4, | |
| "learning_rate": 3.672075859705244e-05, | |
| "loss": 0.8922, | |
| "step": 581166 | |
| }, | |
| { | |
| "epoch": 66.4, | |
| "eval_loss": 0.8925117254257202, | |
| "eval_runtime": 177.5096, | |
| "eval_samples_per_second": 175.314, | |
| "eval_steps_per_second": 10.957, | |
| "step": 581166 | |
| }, | |
| { | |
| "epoch": 66.8, | |
| "learning_rate": 3.664076316691421e-05, | |
| "loss": 0.896, | |
| "step": 584667 | |
| }, | |
| { | |
| "epoch": 66.8, | |
| "eval_loss": 0.8964714407920837, | |
| "eval_runtime": 177.5858, | |
| "eval_samples_per_second": 175.239, | |
| "eval_steps_per_second": 10.952, | |
| "step": 584667 | |
| }, | |
| { | |
| "epoch": 67.2, | |
| "learning_rate": 3.656076773677596e-05, | |
| "loss": 0.8942, | |
| "step": 588168 | |
| }, | |
| { | |
| "epoch": 67.2, | |
| "eval_loss": 0.8949043154716492, | |
| "eval_runtime": 177.7347, | |
| "eval_samples_per_second": 175.092, | |
| "eval_steps_per_second": 10.943, | |
| "step": 588168 | |
| }, | |
| { | |
| "epoch": 67.6, | |
| "learning_rate": 3.6480772306637726e-05, | |
| "loss": 0.8937, | |
| "step": 591669 | |
| }, | |
| { | |
| "epoch": 67.6, | |
| "eval_loss": 0.8952317237854004, | |
| "eval_runtime": 177.6327, | |
| "eval_samples_per_second": 175.193, | |
| "eval_steps_per_second": 10.95, | |
| "step": 591669 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "learning_rate": 3.640077687649949e-05, | |
| "loss": 0.8953, | |
| "step": 595170 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_loss": 0.894290566444397, | |
| "eval_runtime": 177.4358, | |
| "eval_samples_per_second": 175.387, | |
| "eval_steps_per_second": 10.962, | |
| "step": 595170 | |
| }, | |
| { | |
| "epoch": 68.4, | |
| "learning_rate": 3.632078144636125e-05, | |
| "loss": 0.8907, | |
| "step": 598671 | |
| }, | |
| { | |
| "epoch": 68.4, | |
| "eval_loss": 0.8952488899230957, | |
| "eval_runtime": 177.6568, | |
| "eval_samples_per_second": 175.169, | |
| "eval_steps_per_second": 10.948, | |
| "step": 598671 | |
| }, | |
| { | |
| "epoch": 68.8, | |
| "learning_rate": 3.624078601622301e-05, | |
| "loss": 0.8919, | |
| "step": 602172 | |
| }, | |
| { | |
| "epoch": 68.8, | |
| "eval_loss": 0.8931904435157776, | |
| "eval_runtime": 177.5937, | |
| "eval_samples_per_second": 175.231, | |
| "eval_steps_per_second": 10.952, | |
| "step": 602172 | |
| }, | |
| { | |
| "epoch": 69.2, | |
| "learning_rate": 3.616079058608478e-05, | |
| "loss": 0.8933, | |
| "step": 605673 | |
| }, | |
| { | |
| "epoch": 69.2, | |
| "eval_loss": 0.89773029088974, | |
| "eval_runtime": 177.7324, | |
| "eval_samples_per_second": 175.095, | |
| "eval_steps_per_second": 10.943, | |
| "step": 605673 | |
| }, | |
| { | |
| "epoch": 69.6, | |
| "learning_rate": 3.608079515594653e-05, | |
| "loss": 0.891, | |
| "step": 609174 | |
| }, | |
| { | |
| "epoch": 69.6, | |
| "eval_loss": 0.894548773765564, | |
| "eval_runtime": 177.5908, | |
| "eval_samples_per_second": 175.234, | |
| "eval_steps_per_second": 10.952, | |
| "step": 609174 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 3.6000799725808295e-05, | |
| "loss": 0.8932, | |
| "step": 612675 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_loss": 0.8936890959739685, | |
| "eval_runtime": 177.5711, | |
| "eval_samples_per_second": 175.254, | |
| "eval_steps_per_second": 10.953, | |
| "step": 612675 | |
| }, | |
| { | |
| "epoch": 70.4, | |
| "learning_rate": 3.592080429567006e-05, | |
| "loss": 0.8882, | |
| "step": 616176 | |
| }, | |
| { | |
| "epoch": 70.4, | |
| "eval_loss": 0.8970974683761597, | |
| "eval_runtime": 177.5388, | |
| "eval_samples_per_second": 175.286, | |
| "eval_steps_per_second": 10.955, | |
| "step": 616176 | |
| }, | |
| { | |
| "epoch": 70.8, | |
| "learning_rate": 3.584080886553182e-05, | |
| "loss": 0.8907, | |
| "step": 619677 | |
| }, | |
| { | |
| "epoch": 70.8, | |
| "eval_loss": 0.8894772529602051, | |
| "eval_runtime": 178.5288, | |
| "eval_samples_per_second": 174.314, | |
| "eval_steps_per_second": 10.895, | |
| "step": 619677 | |
| }, | |
| { | |
| "epoch": 71.2, | |
| "learning_rate": 3.5760813435393584e-05, | |
| "loss": 0.8893, | |
| "step": 623178 | |
| }, | |
| { | |
| "epoch": 71.2, | |
| "eval_loss": 0.8943666219711304, | |
| "eval_runtime": 177.452, | |
| "eval_samples_per_second": 175.371, | |
| "eval_steps_per_second": 10.961, | |
| "step": 623178 | |
| }, | |
| { | |
| "epoch": 71.6, | |
| "learning_rate": 3.5680818005255346e-05, | |
| "loss": 0.8883, | |
| "step": 626679 | |
| }, | |
| { | |
| "epoch": 71.6, | |
| "eval_loss": 0.892691969871521, | |
| "eval_runtime": 177.2653, | |
| "eval_samples_per_second": 175.556, | |
| "eval_steps_per_second": 10.972, | |
| "step": 626679 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "learning_rate": 3.56008225751171e-05, | |
| "loss": 0.8917, | |
| "step": 630180 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 0.890504777431488, | |
| "eval_runtime": 177.5314, | |
| "eval_samples_per_second": 175.293, | |
| "eval_steps_per_second": 10.956, | |
| "step": 630180 | |
| }, | |
| { | |
| "epoch": 72.4, | |
| "learning_rate": 3.552082714497887e-05, | |
| "loss": 0.8862, | |
| "step": 633681 | |
| }, | |
| { | |
| "epoch": 72.4, | |
| "eval_loss": 0.8900084495544434, | |
| "eval_runtime": 177.3085, | |
| "eval_samples_per_second": 175.513, | |
| "eval_steps_per_second": 10.97, | |
| "step": 633681 | |
| }, | |
| { | |
| "epoch": 72.8, | |
| "learning_rate": 3.544083171484063e-05, | |
| "loss": 0.8886, | |
| "step": 637182 | |
| }, | |
| { | |
| "epoch": 72.8, | |
| "eval_loss": 0.8953748941421509, | |
| "eval_runtime": 177.334, | |
| "eval_samples_per_second": 175.488, | |
| "eval_steps_per_second": 10.968, | |
| "step": 637182 | |
| }, | |
| { | |
| "epoch": 73.2, | |
| "learning_rate": 3.536083628470239e-05, | |
| "loss": 0.8874, | |
| "step": 640683 | |
| }, | |
| { | |
| "epoch": 73.2, | |
| "eval_loss": 0.8892679810523987, | |
| "eval_runtime": 177.3431, | |
| "eval_samples_per_second": 175.479, | |
| "eval_steps_per_second": 10.967, | |
| "step": 640683 | |
| }, | |
| { | |
| "epoch": 73.6, | |
| "learning_rate": 3.528084085456415e-05, | |
| "loss": 0.8866, | |
| "step": 644184 | |
| }, | |
| { | |
| "epoch": 73.6, | |
| "eval_loss": 0.8939085602760315, | |
| "eval_runtime": 177.3428, | |
| "eval_samples_per_second": 175.479, | |
| "eval_steps_per_second": 10.967, | |
| "step": 644184 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "learning_rate": 3.520084542442591e-05, | |
| "loss": 0.8893, | |
| "step": 647685 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 0.8904389142990112, | |
| "eval_runtime": 177.4175, | |
| "eval_samples_per_second": 175.406, | |
| "eval_steps_per_second": 10.963, | |
| "step": 647685 | |
| }, | |
| { | |
| "epoch": 74.4, | |
| "learning_rate": 3.512084999428767e-05, | |
| "loss": 0.8838, | |
| "step": 651186 | |
| }, | |
| { | |
| "epoch": 74.4, | |
| "eval_loss": 0.8905112743377686, | |
| "eval_runtime": 177.3904, | |
| "eval_samples_per_second": 175.432, | |
| "eval_steps_per_second": 10.965, | |
| "step": 651186 | |
| }, | |
| { | |
| "epoch": 74.8, | |
| "learning_rate": 3.5040854564149435e-05, | |
| "loss": 0.8846, | |
| "step": 654687 | |
| }, | |
| { | |
| "epoch": 74.8, | |
| "eval_loss": 0.8922948241233826, | |
| "eval_runtime": 177.434, | |
| "eval_samples_per_second": 175.389, | |
| "eval_steps_per_second": 10.962, | |
| "step": 654687 | |
| }, | |
| { | |
| "epoch": 75.2, | |
| "learning_rate": 3.49608591340112e-05, | |
| "loss": 0.8862, | |
| "step": 658188 | |
| }, | |
| { | |
| "epoch": 75.2, | |
| "eval_loss": 0.8935458660125732, | |
| "eval_runtime": 178.2544, | |
| "eval_samples_per_second": 174.582, | |
| "eval_steps_per_second": 10.911, | |
| "step": 658188 | |
| }, | |
| { | |
| "epoch": 75.6, | |
| "learning_rate": 3.488086370387296e-05, | |
| "loss": 0.8832, | |
| "step": 661689 | |
| }, | |
| { | |
| "epoch": 75.6, | |
| "eval_loss": 0.8909444808959961, | |
| "eval_runtime": 177.513, | |
| "eval_samples_per_second": 175.311, | |
| "eval_steps_per_second": 10.957, | |
| "step": 661689 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "learning_rate": 3.480086827373472e-05, | |
| "loss": 0.8843, | |
| "step": 665190 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_loss": 0.8939051032066345, | |
| "eval_runtime": 177.5511, | |
| "eval_samples_per_second": 175.273, | |
| "eval_steps_per_second": 10.955, | |
| "step": 665190 | |
| }, | |
| { | |
| "epoch": 76.4, | |
| "learning_rate": 3.472087284359648e-05, | |
| "loss": 0.8819, | |
| "step": 668691 | |
| }, | |
| { | |
| "epoch": 76.4, | |
| "eval_loss": 0.8863644599914551, | |
| "eval_runtime": 177.5405, | |
| "eval_samples_per_second": 175.284, | |
| "eval_steps_per_second": 10.955, | |
| "step": 668691 | |
| }, | |
| { | |
| "epoch": 76.8, | |
| "learning_rate": 3.464087741345825e-05, | |
| "loss": 0.8848, | |
| "step": 672192 | |
| }, | |
| { | |
| "epoch": 76.8, | |
| "eval_loss": 0.8871325850486755, | |
| "eval_runtime": 177.6785, | |
| "eval_samples_per_second": 175.148, | |
| "eval_steps_per_second": 10.947, | |
| "step": 672192 | |
| }, | |
| { | |
| "epoch": 77.2, | |
| "learning_rate": 3.4560881983320004e-05, | |
| "loss": 0.8825, | |
| "step": 675693 | |
| }, | |
| { | |
| "epoch": 77.2, | |
| "eval_loss": 0.8879318237304688, | |
| "eval_runtime": 177.5519, | |
| "eval_samples_per_second": 175.273, | |
| "eval_steps_per_second": 10.955, | |
| "step": 675693 | |
| }, | |
| { | |
| "epoch": 77.6, | |
| "learning_rate": 3.448088655318177e-05, | |
| "loss": 0.8812, | |
| "step": 679194 | |
| }, | |
| { | |
| "epoch": 77.6, | |
| "eval_loss": 0.88758385181427, | |
| "eval_runtime": 177.5541, | |
| "eval_samples_per_second": 175.271, | |
| "eval_steps_per_second": 10.954, | |
| "step": 679194 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "learning_rate": 3.440089112304353e-05, | |
| "loss": 0.8833, | |
| "step": 682695 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_loss": 0.8914999961853027, | |
| "eval_runtime": 178.2748, | |
| "eval_samples_per_second": 174.562, | |
| "eval_steps_per_second": 10.91, | |
| "step": 682695 | |
| }, | |
| { | |
| "epoch": 78.4, | |
| "learning_rate": 3.432089569290529e-05, | |
| "loss": 0.8817, | |
| "step": 686196 | |
| }, | |
| { | |
| "epoch": 78.4, | |
| "eval_loss": 0.8898407816886902, | |
| "eval_runtime": 178.1701, | |
| "eval_samples_per_second": 174.665, | |
| "eval_steps_per_second": 10.917, | |
| "step": 686196 | |
| }, | |
| { | |
| "epoch": 78.8, | |
| "learning_rate": 3.424090026276705e-05, | |
| "loss": 0.8834, | |
| "step": 689697 | |
| }, | |
| { | |
| "epoch": 78.8, | |
| "eval_loss": 0.8876122236251831, | |
| "eval_runtime": 178.2895, | |
| "eval_samples_per_second": 174.548, | |
| "eval_steps_per_second": 10.909, | |
| "step": 689697 | |
| }, | |
| { | |
| "epoch": 79.2, | |
| "learning_rate": 3.416090483262882e-05, | |
| "loss": 0.8808, | |
| "step": 693198 | |
| }, | |
| { | |
| "epoch": 79.2, | |
| "eval_loss": 0.8858633041381836, | |
| "eval_runtime": 177.9937, | |
| "eval_samples_per_second": 174.838, | |
| "eval_steps_per_second": 10.927, | |
| "step": 693198 | |
| }, | |
| { | |
| "epoch": 79.6, | |
| "learning_rate": 3.4080909402490574e-05, | |
| "loss": 0.8801, | |
| "step": 696699 | |
| }, | |
| { | |
| "epoch": 79.6, | |
| "eval_loss": 0.8899697661399841, | |
| "eval_runtime": 178.1844, | |
| "eval_samples_per_second": 174.651, | |
| "eval_steps_per_second": 10.916, | |
| "step": 696699 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 3.4000913972352336e-05, | |
| "loss": 0.8799, | |
| "step": 700200 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 0.887626051902771, | |
| "eval_runtime": 178.2075, | |
| "eval_samples_per_second": 174.628, | |
| "eval_steps_per_second": 10.914, | |
| "step": 700200 | |
| }, | |
| { | |
| "epoch": 80.4, | |
| "learning_rate": 3.39209185422141e-05, | |
| "loss": 0.8774, | |
| "step": 703701 | |
| }, | |
| { | |
| "epoch": 80.4, | |
| "eval_loss": 0.8899440169334412, | |
| "eval_runtime": 178.0542, | |
| "eval_samples_per_second": 174.778, | |
| "eval_steps_per_second": 10.924, | |
| "step": 703701 | |
| }, | |
| { | |
| "epoch": 80.8, | |
| "learning_rate": 3.384092311207586e-05, | |
| "loss": 0.8798, | |
| "step": 707202 | |
| }, | |
| { | |
| "epoch": 80.8, | |
| "eval_loss": 0.8822316527366638, | |
| "eval_runtime": 178.2892, | |
| "eval_samples_per_second": 174.548, | |
| "eval_steps_per_second": 10.909, | |
| "step": 707202 | |
| }, | |
| { | |
| "epoch": 81.2, | |
| "learning_rate": 3.376092768193762e-05, | |
| "loss": 0.8783, | |
| "step": 710703 | |
| }, | |
| { | |
| "epoch": 81.2, | |
| "eval_loss": 0.889187216758728, | |
| "eval_runtime": 177.9073, | |
| "eval_samples_per_second": 174.923, | |
| "eval_steps_per_second": 10.933, | |
| "step": 710703 | |
| }, | |
| { | |
| "epoch": 81.6, | |
| "learning_rate": 3.368093225179939e-05, | |
| "loss": 0.879, | |
| "step": 714204 | |
| }, | |
| { | |
| "epoch": 81.6, | |
| "eval_loss": 0.8858596086502075, | |
| "eval_runtime": 177.9871, | |
| "eval_samples_per_second": 174.844, | |
| "eval_steps_per_second": 10.928, | |
| "step": 714204 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "learning_rate": 3.360093682166114e-05, | |
| "loss": 0.8805, | |
| "step": 717705 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_loss": 0.8828133940696716, | |
| "eval_runtime": 178.0841, | |
| "eval_samples_per_second": 174.749, | |
| "eval_steps_per_second": 10.922, | |
| "step": 717705 | |
| }, | |
| { | |
| "epoch": 82.4, | |
| "learning_rate": 3.3520941391522906e-05, | |
| "loss": 0.8745, | |
| "step": 721206 | |
| }, | |
| { | |
| "epoch": 82.4, | |
| "eval_loss": 0.8833040595054626, | |
| "eval_runtime": 178.3724, | |
| "eval_samples_per_second": 174.466, | |
| "eval_steps_per_second": 10.904, | |
| "step": 721206 | |
| }, | |
| { | |
| "epoch": 82.8, | |
| "learning_rate": 3.344094596138467e-05, | |
| "loss": 0.8779, | |
| "step": 724707 | |
| }, | |
| { | |
| "epoch": 82.8, | |
| "eval_loss": 0.8839106559753418, | |
| "eval_runtime": 178.0087, | |
| "eval_samples_per_second": 174.823, | |
| "eval_steps_per_second": 10.926, | |
| "step": 724707 | |
| }, | |
| { | |
| "epoch": 83.2, | |
| "learning_rate": 3.336095053124643e-05, | |
| "loss": 0.8758, | |
| "step": 728208 | |
| }, | |
| { | |
| "epoch": 83.2, | |
| "eval_loss": 0.8863241076469421, | |
| "eval_runtime": 178.0608, | |
| "eval_samples_per_second": 174.772, | |
| "eval_steps_per_second": 10.923, | |
| "step": 728208 | |
| }, | |
| { | |
| "epoch": 83.6, | |
| "learning_rate": 3.3280955101108194e-05, | |
| "loss": 0.8747, | |
| "step": 731709 | |
| }, | |
| { | |
| "epoch": 83.6, | |
| "eval_loss": 0.8861810564994812, | |
| "eval_runtime": 178.0994, | |
| "eval_samples_per_second": 174.734, | |
| "eval_steps_per_second": 10.921, | |
| "step": 731709 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "learning_rate": 3.320095967096996e-05, | |
| "loss": 0.8768, | |
| "step": 735210 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_loss": 0.8819161653518677, | |
| "eval_runtime": 178.1304, | |
| "eval_samples_per_second": 174.703, | |
| "eval_steps_per_second": 10.919, | |
| "step": 735210 | |
| }, | |
| { | |
| "epoch": 84.4, | |
| "learning_rate": 3.312096424083171e-05, | |
| "loss": 0.8721, | |
| "step": 738711 | |
| }, | |
| { | |
| "epoch": 84.4, | |
| "eval_loss": 0.8827645778656006, | |
| "eval_runtime": 178.1975, | |
| "eval_samples_per_second": 174.638, | |
| "eval_steps_per_second": 10.915, | |
| "step": 738711 | |
| }, | |
| { | |
| "epoch": 84.8, | |
| "learning_rate": 3.304096881069348e-05, | |
| "loss": 0.8762, | |
| "step": 742212 | |
| }, | |
| { | |
| "epoch": 84.8, | |
| "eval_loss": 0.8821256160736084, | |
| "eval_runtime": 178.2935, | |
| "eval_samples_per_second": 174.544, | |
| "eval_steps_per_second": 10.909, | |
| "step": 742212 | |
| }, | |
| { | |
| "epoch": 85.2, | |
| "learning_rate": 3.296097338055524e-05, | |
| "loss": 0.8745, | |
| "step": 745713 | |
| }, | |
| { | |
| "epoch": 85.2, | |
| "eval_loss": 0.8844091296195984, | |
| "eval_runtime": 178.1959, | |
| "eval_samples_per_second": 174.639, | |
| "eval_steps_per_second": 10.915, | |
| "step": 745713 | |
| }, | |
| { | |
| "epoch": 85.6, | |
| "learning_rate": 3.2880977950417e-05, | |
| "loss": 0.8718, | |
| "step": 749214 | |
| }, | |
| { | |
| "epoch": 85.6, | |
| "eval_loss": 0.8821405172348022, | |
| "eval_runtime": 178.5043, | |
| "eval_samples_per_second": 174.338, | |
| "eval_steps_per_second": 10.896, | |
| "step": 749214 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "learning_rate": 3.2800982520278764e-05, | |
| "loss": 0.8753, | |
| "step": 752715 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_loss": 0.8849576711654663, | |
| "eval_runtime": 178.2889, | |
| "eval_samples_per_second": 174.548, | |
| "eval_steps_per_second": 10.909, | |
| "step": 752715 | |
| }, | |
| { | |
| "epoch": 86.4, | |
| "learning_rate": 3.2720987090140526e-05, | |
| "loss": 0.8702, | |
| "step": 756216 | |
| }, | |
| { | |
| "epoch": 86.4, | |
| "eval_loss": 0.8836557865142822, | |
| "eval_runtime": 178.073, | |
| "eval_samples_per_second": 174.76, | |
| "eval_steps_per_second": 10.922, | |
| "step": 756216 | |
| }, | |
| { | |
| "epoch": 86.8, | |
| "learning_rate": 3.264099166000228e-05, | |
| "loss": 0.8745, | |
| "step": 759717 | |
| }, | |
| { | |
| "epoch": 86.8, | |
| "eval_loss": 0.8812028765678406, | |
| "eval_runtime": 178.1701, | |
| "eval_samples_per_second": 174.665, | |
| "eval_steps_per_second": 10.917, | |
| "step": 759717 | |
| }, | |
| { | |
| "epoch": 87.2, | |
| "learning_rate": 3.256099622986405e-05, | |
| "loss": 0.8726, | |
| "step": 763218 | |
| }, | |
| { | |
| "epoch": 87.2, | |
| "eval_loss": 0.8863665461540222, | |
| "eval_runtime": 178.1003, | |
| "eval_samples_per_second": 174.733, | |
| "eval_steps_per_second": 10.921, | |
| "step": 763218 | |
| }, | |
| { | |
| "epoch": 87.59, | |
| "learning_rate": 3.248100079972581e-05, | |
| "loss": 0.8731, | |
| "step": 766719 | |
| }, | |
| { | |
| "epoch": 87.59, | |
| "eval_loss": 0.8802133798599243, | |
| "eval_runtime": 177.7361, | |
| "eval_samples_per_second": 175.091, | |
| "eval_steps_per_second": 10.943, | |
| "step": 766719 | |
| }, | |
| { | |
| "epoch": 87.99, | |
| "learning_rate": 3.240100536958757e-05, | |
| "loss": 0.8735, | |
| "step": 770220 | |
| }, | |
| { | |
| "epoch": 87.99, | |
| "eval_loss": 0.87850421667099, | |
| "eval_runtime": 178.0197, | |
| "eval_samples_per_second": 174.812, | |
| "eval_steps_per_second": 10.926, | |
| "step": 770220 | |
| }, | |
| { | |
| "epoch": 88.39, | |
| "learning_rate": 3.232100993944933e-05, | |
| "loss": 0.8684, | |
| "step": 773721 | |
| }, | |
| { | |
| "epoch": 88.39, | |
| "eval_loss": 0.8797884583473206, | |
| "eval_runtime": 177.9064, | |
| "eval_samples_per_second": 174.923, | |
| "eval_steps_per_second": 10.933, | |
| "step": 773721 | |
| }, | |
| { | |
| "epoch": 88.79, | |
| "learning_rate": 3.2241014509311096e-05, | |
| "loss": 0.8727, | |
| "step": 777222 | |
| }, | |
| { | |
| "epoch": 88.79, | |
| "eval_loss": 0.8834565281867981, | |
| "eval_runtime": 178.2741, | |
| "eval_samples_per_second": 174.563, | |
| "eval_steps_per_second": 10.91, | |
| "step": 777222 | |
| }, | |
| { | |
| "epoch": 89.19, | |
| "learning_rate": 3.216101907917285e-05, | |
| "loss": 0.8704, | |
| "step": 780723 | |
| }, | |
| { | |
| "epoch": 89.19, | |
| "eval_loss": 0.8808990120887756, | |
| "eval_runtime": 177.9944, | |
| "eval_samples_per_second": 174.837, | |
| "eval_steps_per_second": 10.927, | |
| "step": 780723 | |
| }, | |
| { | |
| "epoch": 89.59, | |
| "learning_rate": 3.208102364903462e-05, | |
| "loss": 0.8691, | |
| "step": 784224 | |
| }, | |
| { | |
| "epoch": 89.59, | |
| "eval_loss": 0.8784425854682922, | |
| "eval_runtime": 177.87, | |
| "eval_samples_per_second": 174.959, | |
| "eval_steps_per_second": 10.935, | |
| "step": 784224 | |
| }, | |
| { | |
| "epoch": 89.99, | |
| "learning_rate": 3.200102821889638e-05, | |
| "loss": 0.8718, | |
| "step": 787725 | |
| }, | |
| { | |
| "epoch": 89.99, | |
| "eval_loss": 0.8777753114700317, | |
| "eval_runtime": 178.0354, | |
| "eval_samples_per_second": 174.797, | |
| "eval_steps_per_second": 10.925, | |
| "step": 787725 | |
| }, | |
| { | |
| "epoch": 90.39, | |
| "learning_rate": 3.192103278875814e-05, | |
| "loss": 0.8685, | |
| "step": 791226 | |
| }, | |
| { | |
| "epoch": 90.39, | |
| "eval_loss": 0.8818721175193787, | |
| "eval_runtime": 177.85, | |
| "eval_samples_per_second": 174.979, | |
| "eval_steps_per_second": 10.936, | |
| "step": 791226 | |
| }, | |
| { | |
| "epoch": 90.79, | |
| "learning_rate": 3.18410373586199e-05, | |
| "loss": 0.8686, | |
| "step": 794727 | |
| }, | |
| { | |
| "epoch": 90.79, | |
| "eval_loss": 0.878167450428009, | |
| "eval_runtime": 177.8069, | |
| "eval_samples_per_second": 175.021, | |
| "eval_steps_per_second": 10.939, | |
| "step": 794727 | |
| }, | |
| { | |
| "epoch": 91.19, | |
| "learning_rate": 3.1761041928481665e-05, | |
| "loss": 0.8692, | |
| "step": 798228 | |
| }, | |
| { | |
| "epoch": 91.19, | |
| "eval_loss": 0.8786768913269043, | |
| "eval_runtime": 177.7581, | |
| "eval_samples_per_second": 175.069, | |
| "eval_steps_per_second": 10.942, | |
| "step": 798228 | |
| }, | |
| { | |
| "epoch": 91.59, | |
| "learning_rate": 3.168104649834343e-05, | |
| "loss": 0.8649, | |
| "step": 801729 | |
| }, | |
| { | |
| "epoch": 91.59, | |
| "eval_loss": 0.8777763247489929, | |
| "eval_runtime": 178.0586, | |
| "eval_samples_per_second": 174.774, | |
| "eval_steps_per_second": 10.923, | |
| "step": 801729 | |
| }, | |
| { | |
| "epoch": 91.99, | |
| "learning_rate": 3.160105106820519e-05, | |
| "loss": 0.8699, | |
| "step": 805230 | |
| }, | |
| { | |
| "epoch": 91.99, | |
| "eval_loss": 0.8764858841896057, | |
| "eval_runtime": 178.3307, | |
| "eval_samples_per_second": 174.507, | |
| "eval_steps_per_second": 10.907, | |
| "step": 805230 | |
| }, | |
| { | |
| "epoch": 92.39, | |
| "learning_rate": 3.152105563806695e-05, | |
| "loss": 0.8734, | |
| "step": 808731 | |
| }, | |
| { | |
| "epoch": 92.39, | |
| "eval_loss": 0.8796523809432983, | |
| "eval_runtime": 178.1053, | |
| "eval_samples_per_second": 174.728, | |
| "eval_steps_per_second": 10.921, | |
| "step": 808731 | |
| }, | |
| { | |
| "epoch": 92.79, | |
| "learning_rate": 3.1441060207928716e-05, | |
| "loss": 0.8762, | |
| "step": 812232 | |
| }, | |
| { | |
| "epoch": 92.79, | |
| "eval_loss": 0.873812198638916, | |
| "eval_runtime": 177.9129, | |
| "eval_samples_per_second": 174.917, | |
| "eval_steps_per_second": 10.932, | |
| "step": 812232 | |
| }, | |
| { | |
| "epoch": 93.19, | |
| "learning_rate": 3.136106477779047e-05, | |
| "loss": 0.875, | |
| "step": 815733 | |
| }, | |
| { | |
| "epoch": 93.19, | |
| "eval_loss": 0.8739504814147949, | |
| "eval_runtime": 178.3464, | |
| "eval_samples_per_second": 174.492, | |
| "eval_steps_per_second": 10.906, | |
| "step": 815733 | |
| }, | |
| { | |
| "epoch": 93.59, | |
| "learning_rate": 3.1281069347652235e-05, | |
| "loss": 0.8749, | |
| "step": 819234 | |
| }, | |
| { | |
| "epoch": 93.59, | |
| "eval_loss": 0.877826988697052, | |
| "eval_runtime": 177.9396, | |
| "eval_samples_per_second": 174.891, | |
| "eval_steps_per_second": 10.931, | |
| "step": 819234 | |
| }, | |
| { | |
| "epoch": 93.99, | |
| "learning_rate": 3.1201073917514e-05, | |
| "loss": 0.8766, | |
| "step": 822735 | |
| }, | |
| { | |
| "epoch": 93.99, | |
| "eval_loss": 0.8729666471481323, | |
| "eval_runtime": 178.2108, | |
| "eval_samples_per_second": 174.625, | |
| "eval_steps_per_second": 10.914, | |
| "step": 822735 | |
| }, | |
| { | |
| "epoch": 94.39, | |
| "learning_rate": 3.112107848737576e-05, | |
| "loss": 0.8726, | |
| "step": 826236 | |
| }, | |
| { | |
| "epoch": 94.39, | |
| "eval_loss": 0.8738223910331726, | |
| "eval_runtime": 177.8319, | |
| "eval_samples_per_second": 174.997, | |
| "eval_steps_per_second": 10.937, | |
| "step": 826236 | |
| }, | |
| { | |
| "epoch": 94.79, | |
| "learning_rate": 3.1041083057237516e-05, | |
| "loss": 0.8752, | |
| "step": 829737 | |
| }, | |
| { | |
| "epoch": 94.79, | |
| "eval_loss": 0.8740049600601196, | |
| "eval_runtime": 178.0665, | |
| "eval_samples_per_second": 174.766, | |
| "eval_steps_per_second": 10.923, | |
| "step": 829737 | |
| }, | |
| { | |
| "epoch": 95.19, | |
| "learning_rate": 3.0961087627099286e-05, | |
| "loss": 0.8737, | |
| "step": 833238 | |
| }, | |
| { | |
| "epoch": 95.19, | |
| "eval_loss": 0.871174693107605, | |
| "eval_runtime": 177.988, | |
| "eval_samples_per_second": 174.843, | |
| "eval_steps_per_second": 10.928, | |
| "step": 833238 | |
| }, | |
| { | |
| "epoch": 95.59, | |
| "learning_rate": 3.088109219696104e-05, | |
| "loss": 0.8723, | |
| "step": 836739 | |
| }, | |
| { | |
| "epoch": 95.59, | |
| "eval_loss": 0.8785658478736877, | |
| "eval_runtime": 178.1263, | |
| "eval_samples_per_second": 174.707, | |
| "eval_steps_per_second": 10.919, | |
| "step": 836739 | |
| }, | |
| { | |
| "epoch": 95.99, | |
| "learning_rate": 3.0801096766822805e-05, | |
| "loss": 0.8749, | |
| "step": 840240 | |
| }, | |
| { | |
| "epoch": 95.99, | |
| "eval_loss": 0.8714969158172607, | |
| "eval_runtime": 178.1533, | |
| "eval_samples_per_second": 174.681, | |
| "eval_steps_per_second": 10.918, | |
| "step": 840240 | |
| }, | |
| { | |
| "epoch": 96.39, | |
| "learning_rate": 3.072110133668457e-05, | |
| "loss": 0.8707, | |
| "step": 843741 | |
| }, | |
| { | |
| "epoch": 96.39, | |
| "eval_loss": 0.8721190094947815, | |
| "eval_runtime": 177.9697, | |
| "eval_samples_per_second": 174.861, | |
| "eval_steps_per_second": 10.929, | |
| "step": 843741 | |
| }, | |
| { | |
| "epoch": 96.79, | |
| "learning_rate": 3.064110590654633e-05, | |
| "loss": 0.8718, | |
| "step": 847242 | |
| }, | |
| { | |
| "epoch": 96.79, | |
| "eval_loss": 0.8713057637214661, | |
| "eval_runtime": 178.2884, | |
| "eval_samples_per_second": 174.549, | |
| "eval_steps_per_second": 10.909, | |
| "step": 847242 | |
| }, | |
| { | |
| "epoch": 97.19, | |
| "learning_rate": 3.0561110476408086e-05, | |
| "loss": 0.8731, | |
| "step": 850743 | |
| }, | |
| { | |
| "epoch": 97.19, | |
| "eval_loss": 0.8710973858833313, | |
| "eval_runtime": 178.0006, | |
| "eval_samples_per_second": 174.831, | |
| "eval_steps_per_second": 10.927, | |
| "step": 850743 | |
| }, | |
| { | |
| "epoch": 97.59, | |
| "learning_rate": 3.0481115046269852e-05, | |
| "loss": 0.872, | |
| "step": 854244 | |
| }, | |
| { | |
| "epoch": 97.59, | |
| "eval_loss": 0.8724552989006042, | |
| "eval_runtime": 177.9577, | |
| "eval_samples_per_second": 174.873, | |
| "eval_steps_per_second": 10.93, | |
| "step": 854244 | |
| }, | |
| { | |
| "epoch": 97.99, | |
| "learning_rate": 3.040111961613161e-05, | |
| "loss": 0.872, | |
| "step": 857745 | |
| }, | |
| { | |
| "epoch": 97.99, | |
| "eval_loss": 0.8701831698417664, | |
| "eval_runtime": 177.9492, | |
| "eval_samples_per_second": 174.881, | |
| "eval_steps_per_second": 10.93, | |
| "step": 857745 | |
| }, | |
| { | |
| "epoch": 98.39, | |
| "learning_rate": 3.0321124185993377e-05, | |
| "loss": 0.8688, | |
| "step": 861246 | |
| }, | |
| { | |
| "epoch": 98.39, | |
| "eval_loss": 0.868754506111145, | |
| "eval_runtime": 178.1695, | |
| "eval_samples_per_second": 174.665, | |
| "eval_steps_per_second": 10.917, | |
| "step": 861246 | |
| }, | |
| { | |
| "epoch": 98.79, | |
| "learning_rate": 3.0241128755855137e-05, | |
| "loss": 0.8712, | |
| "step": 864747 | |
| }, | |
| { | |
| "epoch": 98.79, | |
| "eval_loss": 0.8745043873786926, | |
| "eval_runtime": 178.0858, | |
| "eval_samples_per_second": 174.747, | |
| "eval_steps_per_second": 10.922, | |
| "step": 864747 | |
| }, | |
| { | |
| "epoch": 99.19, | |
| "learning_rate": 3.01611333257169e-05, | |
| "loss": 0.8691, | |
| "step": 868248 | |
| }, | |
| { | |
| "epoch": 99.19, | |
| "eval_loss": 0.8719183802604675, | |
| "eval_runtime": 177.9082, | |
| "eval_samples_per_second": 174.922, | |
| "eval_steps_per_second": 10.933, | |
| "step": 868248 | |
| }, | |
| { | |
| "epoch": 99.59, | |
| "learning_rate": 3.008113789557866e-05, | |
| "loss": 0.8693, | |
| "step": 871749 | |
| }, | |
| { | |
| "epoch": 99.59, | |
| "eval_loss": 0.8701997399330139, | |
| "eval_runtime": 177.8864, | |
| "eval_samples_per_second": 174.943, | |
| "eval_steps_per_second": 10.934, | |
| "step": 871749 | |
| }, | |
| { | |
| "epoch": 99.99, | |
| "learning_rate": 3.0001142465440425e-05, | |
| "loss": 0.8692, | |
| "step": 875250 | |
| }, | |
| { | |
| "epoch": 99.99, | |
| "eval_loss": 0.8659647107124329, | |
| "eval_runtime": 177.9913, | |
| "eval_samples_per_second": 174.84, | |
| "eval_steps_per_second": 10.927, | |
| "step": 875250 | |
| }, | |
| { | |
| "epoch": 100.39, | |
| "learning_rate": 2.9921147035302184e-05, | |
| "loss": 0.8646, | |
| "step": 878751 | |
| }, | |
| { | |
| "epoch": 100.39, | |
| "eval_loss": 0.86882084608078, | |
| "eval_runtime": 177.9376, | |
| "eval_samples_per_second": 174.893, | |
| "eval_steps_per_second": 10.931, | |
| "step": 878751 | |
| }, | |
| { | |
| "epoch": 100.79, | |
| "learning_rate": 2.9841151605163947e-05, | |
| "loss": 0.8698, | |
| "step": 882252 | |
| }, | |
| { | |
| "epoch": 100.79, | |
| "eval_loss": 0.8718056082725525, | |
| "eval_runtime": 178.2288, | |
| "eval_samples_per_second": 174.607, | |
| "eval_steps_per_second": 10.913, | |
| "step": 882252 | |
| }, | |
| { | |
| "epoch": 101.19, | |
| "learning_rate": 2.9761156175025706e-05, | |
| "loss": 0.8675, | |
| "step": 885753 | |
| }, | |
| { | |
| "epoch": 101.19, | |
| "eval_loss": 0.8696756362915039, | |
| "eval_runtime": 178.0145, | |
| "eval_samples_per_second": 174.817, | |
| "eval_steps_per_second": 10.926, | |
| "step": 885753 | |
| }, | |
| { | |
| "epoch": 101.59, | |
| "learning_rate": 2.968116074488747e-05, | |
| "loss": 0.8668, | |
| "step": 889254 | |
| }, | |
| { | |
| "epoch": 101.59, | |
| "eval_loss": 0.8669666051864624, | |
| "eval_runtime": 177.9105, | |
| "eval_samples_per_second": 174.919, | |
| "eval_steps_per_second": 10.932, | |
| "step": 889254 | |
| }, | |
| { | |
| "epoch": 101.99, | |
| "learning_rate": 2.960116531474923e-05, | |
| "loss": 0.8676, | |
| "step": 892755 | |
| }, | |
| { | |
| "epoch": 101.99, | |
| "eval_loss": 0.8685517311096191, | |
| "eval_runtime": 178.0845, | |
| "eval_samples_per_second": 174.749, | |
| "eval_steps_per_second": 10.922, | |
| "step": 892755 | |
| }, | |
| { | |
| "epoch": 102.39, | |
| "learning_rate": 2.9521169884610994e-05, | |
| "loss": 0.8645, | |
| "step": 896256 | |
| }, | |
| { | |
| "epoch": 102.39, | |
| "eval_loss": 0.8676366209983826, | |
| "eval_runtime": 177.8814, | |
| "eval_samples_per_second": 174.948, | |
| "eval_steps_per_second": 10.934, | |
| "step": 896256 | |
| }, | |
| { | |
| "epoch": 102.79, | |
| "learning_rate": 2.9441174454472754e-05, | |
| "loss": 0.8652, | |
| "step": 899757 | |
| }, | |
| { | |
| "epoch": 102.79, | |
| "eval_loss": 0.8648022413253784, | |
| "eval_runtime": 177.9084, | |
| "eval_samples_per_second": 174.921, | |
| "eval_steps_per_second": 10.933, | |
| "step": 899757 | |
| }, | |
| { | |
| "epoch": 103.19, | |
| "learning_rate": 2.9361179024334517e-05, | |
| "loss": 0.8646, | |
| "step": 903258 | |
| }, | |
| { | |
| "epoch": 103.19, | |
| "eval_loss": 0.8692647814750671, | |
| "eval_runtime": 177.9213, | |
| "eval_samples_per_second": 174.909, | |
| "eval_steps_per_second": 10.932, | |
| "step": 903258 | |
| }, | |
| { | |
| "epoch": 103.59, | |
| "learning_rate": 2.9281183594196276e-05, | |
| "loss": 0.8634, | |
| "step": 906759 | |
| }, | |
| { | |
| "epoch": 103.59, | |
| "eval_loss": 0.8666937351226807, | |
| "eval_runtime": 178.0016, | |
| "eval_samples_per_second": 174.83, | |
| "eval_steps_per_second": 10.927, | |
| "step": 906759 | |
| }, | |
| { | |
| "epoch": 103.99, | |
| "learning_rate": 2.9201188164058042e-05, | |
| "loss": 0.8678, | |
| "step": 910260 | |
| }, | |
| { | |
| "epoch": 103.99, | |
| "eval_loss": 0.8698520660400391, | |
| "eval_runtime": 178.1156, | |
| "eval_samples_per_second": 174.718, | |
| "eval_steps_per_second": 10.92, | |
| "step": 910260 | |
| }, | |
| { | |
| "epoch": 104.39, | |
| "learning_rate": 2.91211927339198e-05, | |
| "loss": 0.8616, | |
| "step": 913761 | |
| }, | |
| { | |
| "epoch": 104.39, | |
| "eval_loss": 0.864092230796814, | |
| "eval_runtime": 177.9776, | |
| "eval_samples_per_second": 174.853, | |
| "eval_steps_per_second": 10.928, | |
| "step": 913761 | |
| }, | |
| { | |
| "epoch": 104.79, | |
| "learning_rate": 2.9041197303781564e-05, | |
| "loss": 0.8631, | |
| "step": 917262 | |
| }, | |
| { | |
| "epoch": 104.79, | |
| "eval_loss": 0.8643292188644409, | |
| "eval_runtime": 178.3388, | |
| "eval_samples_per_second": 174.499, | |
| "eval_steps_per_second": 10.906, | |
| "step": 917262 | |
| }, | |
| { | |
| "epoch": 105.19, | |
| "learning_rate": 2.8961201873643323e-05, | |
| "loss": 0.8643, | |
| "step": 920763 | |
| }, | |
| { | |
| "epoch": 105.19, | |
| "eval_loss": 0.867784857749939, | |
| "eval_runtime": 178.0618, | |
| "eval_samples_per_second": 174.771, | |
| "eval_steps_per_second": 10.923, | |
| "step": 920763 | |
| }, | |
| { | |
| "epoch": 105.59, | |
| "learning_rate": 2.8881206443505086e-05, | |
| "loss": 0.8616, | |
| "step": 924264 | |
| }, | |
| { | |
| "epoch": 105.59, | |
| "eval_loss": 0.8667683601379395, | |
| "eval_runtime": 177.9577, | |
| "eval_samples_per_second": 174.873, | |
| "eval_steps_per_second": 10.93, | |
| "step": 924264 | |
| }, | |
| { | |
| "epoch": 105.99, | |
| "learning_rate": 2.8801211013366845e-05, | |
| "loss": 0.8644, | |
| "step": 927765 | |
| }, | |
| { | |
| "epoch": 105.99, | |
| "eval_loss": 0.8647730946540833, | |
| "eval_runtime": 178.1529, | |
| "eval_samples_per_second": 174.681, | |
| "eval_steps_per_second": 10.918, | |
| "step": 927765 | |
| }, | |
| { | |
| "epoch": 106.39, | |
| "learning_rate": 2.872121558322861e-05, | |
| "loss": 0.859, | |
| "step": 931266 | |
| }, | |
| { | |
| "epoch": 106.39, | |
| "eval_loss": 0.8621995449066162, | |
| "eval_runtime": 178.0998, | |
| "eval_samples_per_second": 174.733, | |
| "eval_steps_per_second": 10.921, | |
| "step": 931266 | |
| }, | |
| { | |
| "epoch": 106.79, | |
| "learning_rate": 2.864122015309037e-05, | |
| "loss": 0.8611, | |
| "step": 934767 | |
| }, | |
| { | |
| "epoch": 106.79, | |
| "eval_loss": 0.8664916753768921, | |
| "eval_runtime": 178.2296, | |
| "eval_samples_per_second": 174.606, | |
| "eval_steps_per_second": 10.913, | |
| "step": 934767 | |
| }, | |
| { | |
| "epoch": 107.19, | |
| "learning_rate": 2.8561224722952134e-05, | |
| "loss": 0.8608, | |
| "step": 938268 | |
| }, | |
| { | |
| "epoch": 107.19, | |
| "eval_loss": 0.8675068020820618, | |
| "eval_runtime": 178.0022, | |
| "eval_samples_per_second": 174.829, | |
| "eval_steps_per_second": 10.927, | |
| "step": 938268 | |
| }, | |
| { | |
| "epoch": 107.59, | |
| "learning_rate": 2.8481229292813893e-05, | |
| "loss": 0.8596, | |
| "step": 941769 | |
| }, | |
| { | |
| "epoch": 107.59, | |
| "eval_loss": 0.8647910356521606, | |
| "eval_runtime": 177.9926, | |
| "eval_samples_per_second": 174.839, | |
| "eval_steps_per_second": 10.927, | |
| "step": 941769 | |
| }, | |
| { | |
| "epoch": 107.99, | |
| "learning_rate": 2.840123386267566e-05, | |
| "loss": 0.863, | |
| "step": 945270 | |
| }, | |
| { | |
| "epoch": 107.99, | |
| "eval_loss": 0.8669795393943787, | |
| "eval_runtime": 177.9511, | |
| "eval_samples_per_second": 174.879, | |
| "eval_steps_per_second": 10.93, | |
| "step": 945270 | |
| }, | |
| { | |
| "epoch": 108.39, | |
| "learning_rate": 2.832123843253742e-05, | |
| "loss": 0.8589, | |
| "step": 948771 | |
| }, | |
| { | |
| "epoch": 108.39, | |
| "eval_loss": 0.8626872301101685, | |
| "eval_runtime": 178.2769, | |
| "eval_samples_per_second": 174.56, | |
| "eval_steps_per_second": 10.91, | |
| "step": 948771 | |
| }, | |
| { | |
| "epoch": 108.79, | |
| "learning_rate": 2.824124300239918e-05, | |
| "loss": 0.8605, | |
| "step": 952272 | |
| }, | |
| { | |
| "epoch": 108.79, | |
| "eval_loss": 0.8620831370353699, | |
| "eval_runtime": 177.8108, | |
| "eval_samples_per_second": 175.018, | |
| "eval_steps_per_second": 10.939, | |
| "step": 952272 | |
| }, | |
| { | |
| "epoch": 109.19, | |
| "learning_rate": 2.816124757226094e-05, | |
| "loss": 0.8578, | |
| "step": 955773 | |
| }, | |
| { | |
| "epoch": 109.19, | |
| "eval_loss": 0.8637415170669556, | |
| "eval_runtime": 177.6547, | |
| "eval_samples_per_second": 175.171, | |
| "eval_steps_per_second": 10.948, | |
| "step": 955773 | |
| }, | |
| { | |
| "epoch": 109.59, | |
| "learning_rate": 2.8081252142122706e-05, | |
| "loss": 0.8594, | |
| "step": 959274 | |
| }, | |
| { | |
| "epoch": 109.59, | |
| "eval_loss": 0.8635110855102539, | |
| "eval_runtime": 177.7697, | |
| "eval_samples_per_second": 175.058, | |
| "eval_steps_per_second": 10.941, | |
| "step": 959274 | |
| }, | |
| { | |
| "epoch": 109.99, | |
| "learning_rate": 2.8001256711984462e-05, | |
| "loss": 0.8619, | |
| "step": 962775 | |
| }, | |
| { | |
| "epoch": 109.99, | |
| "eval_loss": 0.8643426299095154, | |
| "eval_runtime": 177.7171, | |
| "eval_samples_per_second": 175.11, | |
| "eval_steps_per_second": 10.944, | |
| "step": 962775 | |
| } | |
| ], | |
| "max_steps": 2188250, | |
| "num_train_epochs": 250, | |
| "total_flos": 8.10959302547497e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |