| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7565011820330969, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015130023640661938, | |
| "grad_norm": 0.007734136655926704, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9302, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015130023640661938, | |
| "eval_loss": 11.932888984680176, | |
| "eval_runtime": 0.2037, | |
| "eval_samples_per_second": 245.425, | |
| "eval_steps_per_second": 63.811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.030260047281323876, | |
| "grad_norm": 0.007177683059126139, | |
| "learning_rate": 0.0001, | |
| "loss": 11.931, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04539007092198582, | |
| "grad_norm": 0.007821178995072842, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9312, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06052009456264775, | |
| "grad_norm": 0.009464521892368793, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9313, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07565011820330969, | |
| "grad_norm": 0.0079513443633914, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9312, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09078014184397164, | |
| "grad_norm": 0.00863523781299591, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.931, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10591016548463357, | |
| "grad_norm": 0.008535042405128479, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9313, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1210401891252955, | |
| "grad_norm": 0.007440511137247086, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.931, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13617021276595745, | |
| "grad_norm": 0.006813289597630501, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.932, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15130023640661938, | |
| "grad_norm": 0.008292514830827713, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9311, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16643026004728131, | |
| "grad_norm": 0.00823824480175972, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9319, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18156028368794327, | |
| "grad_norm": 0.009189211763441563, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9317, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1966903073286052, | |
| "grad_norm": 0.007587582804262638, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9307, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.21182033096926714, | |
| "grad_norm": 0.010311111807823181, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9301, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.22695035460992907, | |
| "grad_norm": 0.009515615180134773, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9314, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.242080378250591, | |
| "grad_norm": 0.011019989848136902, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.931, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.25721040189125294, | |
| "grad_norm": 0.008023861795663834, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9312, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2723404255319149, | |
| "grad_norm": 0.010304928757250309, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9316, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.28747044917257686, | |
| "grad_norm": 0.01065912190824747, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.931, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.30260047281323876, | |
| "grad_norm": 0.009081180207431316, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9301, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3177304964539007, | |
| "grad_norm": 0.011267852038145065, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9316, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.33286052009456263, | |
| "grad_norm": 0.010181689634919167, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9315, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3479905437352246, | |
| "grad_norm": 0.01211818028241396, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9308, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.36312056737588655, | |
| "grad_norm": 0.013043578714132309, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9316, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.37825059101654845, | |
| "grad_norm": 0.01362883672118187, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.932, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.37825059101654845, | |
| "eval_loss": 11.932381629943848, | |
| "eval_runtime": 0.202, | |
| "eval_samples_per_second": 247.551, | |
| "eval_steps_per_second": 64.363, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3933806146572104, | |
| "grad_norm": 0.011090955697000027, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9304, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4085106382978723, | |
| "grad_norm": 0.011664253659546375, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.9306, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4236406619385343, | |
| "grad_norm": 0.014071961864829063, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9306, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.43877068557919624, | |
| "grad_norm": 0.013513321988284588, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.9313, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.45390070921985815, | |
| "grad_norm": 0.01655971258878708, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9318, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4690307328605201, | |
| "grad_norm": 0.014017711393535137, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9305, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.484160756501182, | |
| "grad_norm": 0.011544297449290752, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9314, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.49929078014184397, | |
| "grad_norm": 0.012642547488212585, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9314, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5144208037825059, | |
| "grad_norm": 0.01794467680156231, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.9302, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5295508274231678, | |
| "grad_norm": 0.013963800854980946, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.9299, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5446808510638298, | |
| "grad_norm": 0.021733710542321205, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9303, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5598108747044918, | |
| "grad_norm": 0.02163160964846611, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.9305, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5749408983451537, | |
| "grad_norm": 0.014926633797585964, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.9306, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5900709219858156, | |
| "grad_norm": 0.015309125185012817, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.9299, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6052009456264775, | |
| "grad_norm": 0.01804831251502037, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.9294, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6203309692671395, | |
| "grad_norm": 0.017892878502607346, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9306, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6354609929078014, | |
| "grad_norm": 0.016832858324050903, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9301, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6505910165484634, | |
| "grad_norm": 0.020296163856983185, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.9303, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6657210401891253, | |
| "grad_norm": 0.018417399376630783, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.9303, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 0.018799107521772385, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.9308, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6959810874704492, | |
| "grad_norm": 0.01869620941579342, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.9309, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.0199186522513628, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.9309, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7262411347517731, | |
| "grad_norm": 0.01802201010286808, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9306, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.741371158392435, | |
| "grad_norm": 0.015932127833366394, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.9317, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7565011820330969, | |
| "grad_norm": 0.021696912124753, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9307, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7565011820330969, | |
| "eval_loss": 11.932082176208496, | |
| "eval_runtime": 0.2066, | |
| "eval_samples_per_second": 242.043, | |
| "eval_steps_per_second": 62.931, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1064973041664.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |