| { | |
| "best_metric": 1.4320266246795654, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.44543429844098, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008908685968819599, | |
| "grad_norm": 0.11033952981233597, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4532, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008908685968819599, | |
| "eval_loss": 2.072521686553955, | |
| "eval_runtime": 4.4272, | |
| "eval_samples_per_second": 11.294, | |
| "eval_steps_per_second": 2.936, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017817371937639197, | |
| "grad_norm": 0.17115096747875214, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5536, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026726057906458798, | |
| "grad_norm": 0.1790250539779663, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.6081, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.035634743875278395, | |
| "grad_norm": 0.18719469010829926, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.7893, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.044543429844097995, | |
| "grad_norm": 0.2129625529050827, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.7922, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.053452115812917596, | |
| "grad_norm": 0.22301524877548218, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.7971, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.062360801781737196, | |
| "grad_norm": 0.25857338309288025, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.8543, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07126948775055679, | |
| "grad_norm": 0.32929691672325134, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.5799, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0801781737193764, | |
| "grad_norm": 0.3331943452358246, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.4807, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08908685968819599, | |
| "grad_norm": 0.374052494764328, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.473, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09799554565701558, | |
| "grad_norm": 0.7826215028762817, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.4114, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10690423162583519, | |
| "grad_norm": 1.5824209451675415, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.5343, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11581291759465479, | |
| "grad_norm": 0.28257080912590027, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.5744, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12472160356347439, | |
| "grad_norm": 0.35731062293052673, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.5104, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.133630289532294, | |
| "grad_norm": 0.3936142027378082, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.6377, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14253897550111358, | |
| "grad_norm": 0.39975523948669434, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.64, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1514476614699332, | |
| "grad_norm": 0.32727664709091187, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.7832, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1603563474387528, | |
| "grad_norm": 0.27095872163772583, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.7017, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16926503340757237, | |
| "grad_norm": 0.2469450682401657, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.7756, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17817371937639198, | |
| "grad_norm": 0.21339151263237, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.679, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1870824053452116, | |
| "grad_norm": 0.24853827059268951, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.5501, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19599109131403117, | |
| "grad_norm": 0.29591605067253113, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.3952, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20489977728285078, | |
| "grad_norm": 0.501408040523529, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.5036, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21380846325167038, | |
| "grad_norm": 0.9292784929275513, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.0597, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22271714922049, | |
| "grad_norm": 2.544874668121338, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.6981, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22271714922049, | |
| "eval_loss": 1.4878519773483276, | |
| "eval_runtime": 4.4683, | |
| "eval_samples_per_second": 11.19, | |
| "eval_steps_per_second": 2.909, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23162583518930957, | |
| "grad_norm": 0.106295645236969, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.4001, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24053452115812918, | |
| "grad_norm": 0.1709941029548645, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.4012, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24944320712694878, | |
| "grad_norm": 0.16162072122097015, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.7046, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2583518930957684, | |
| "grad_norm": 0.19702105224132538, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.5872, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.267260579064588, | |
| "grad_norm": 0.16122843325138092, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.7371, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27616926503340755, | |
| "grad_norm": 0.16591770946979523, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.7689, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28507795100222716, | |
| "grad_norm": 0.18897826969623566, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.7202, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.29398663697104677, | |
| "grad_norm": 0.19742853939533234, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.5054, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3028953229398664, | |
| "grad_norm": 0.23214320838451385, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.5492, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.311804008908686, | |
| "grad_norm": 0.3052574396133423, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.4624, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3207126948775056, | |
| "grad_norm": 0.4707745909690857, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.3587, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.32962138084632514, | |
| "grad_norm": 0.7316482663154602, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.1474, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.33853006681514475, | |
| "grad_norm": 0.15378858149051666, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.3779, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.34743875278396436, | |
| "grad_norm": 0.11696304380893707, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.3097, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.35634743875278396, | |
| "grad_norm": 0.1411445140838623, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.4874, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36525612472160357, | |
| "grad_norm": 0.16639839112758636, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.5469, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3741648106904232, | |
| "grad_norm": 0.1573583036661148, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.7053, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3830734966592428, | |
| "grad_norm": 0.16417503356933594, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.6204, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.39198218262806234, | |
| "grad_norm": 0.18815577030181885, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.7019, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.40089086859688194, | |
| "grad_norm": 0.19217829406261444, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.6421, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40979955456570155, | |
| "grad_norm": 0.20727165043354034, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.5612, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.41870824053452116, | |
| "grad_norm": 0.25485751032829285, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.4737, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.42761692650334077, | |
| "grad_norm": 0.33714011311531067, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.5148, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4365256124721604, | |
| "grad_norm": 0.4841104745864868, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.2554, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.44543429844098, | |
| "grad_norm": 1.1299854516983032, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4161, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44543429844098, | |
| "eval_loss": 1.4320266246795654, | |
| "eval_runtime": 4.4777, | |
| "eval_samples_per_second": 11.166, | |
| "eval_steps_per_second": 2.903, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.6372392263417856e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |