| { | |
| "best_metric": 7.772435992592364e-07, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.25125628140703515, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005025125628140704, | |
| "grad_norm": 30.701169967651367, | |
| "learning_rate": 5e-05, | |
| "loss": 9.9405, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005025125628140704, | |
| "eval_loss": 10.101932525634766, | |
| "eval_runtime": 2.6623, | |
| "eval_samples_per_second": 18.781, | |
| "eval_steps_per_second": 4.883, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010050251256281407, | |
| "grad_norm": 29.0526065826416, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8776, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01507537688442211, | |
| "grad_norm": 22.58121681213379, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.3181, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020100502512562814, | |
| "grad_norm": 18.6964054107666, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.5278, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02512562814070352, | |
| "grad_norm": 16.57761573791504, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.1788, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03015075376884422, | |
| "grad_norm": 8.9937744140625, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.5682, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.035175879396984924, | |
| "grad_norm": 2.425379753112793, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.076, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04020100502512563, | |
| "grad_norm": 0.4871414005756378, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0062, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04522613065326633, | |
| "grad_norm": 0.013989793136715889, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0003, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05025125628140704, | |
| "grad_norm": 0.004099840763956308, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0001, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05527638190954774, | |
| "grad_norm": 0.0021732994355261326, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06030150753768844, | |
| "grad_norm": 0.0013746238546445966, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06532663316582915, | |
| "grad_norm": 0.001157218823209405, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07035175879396985, | |
| "grad_norm": 0.0011123457225039601, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07537688442211055, | |
| "grad_norm": 0.0009168105898424983, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08040201005025126, | |
| "grad_norm": 0.0009294900228269398, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08542713567839195, | |
| "grad_norm": 0.0008827976998873055, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09045226130653267, | |
| "grad_norm": 0.0010687971953302622, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09547738693467336, | |
| "grad_norm": 0.001405723043717444, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10050251256281408, | |
| "grad_norm": 0.0027099750004708767, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10552763819095477, | |
| "grad_norm": 0.00910093728452921, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11055276381909548, | |
| "grad_norm": 0.006250107195228338, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11557788944723618, | |
| "grad_norm": 0.010045313276350498, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12060301507537688, | |
| "grad_norm": 0.0022839081939309835, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12562814070351758, | |
| "grad_norm": 0.0022522059734910727, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12562814070351758, | |
| "eval_loss": 7.100727088982239e-06, | |
| "eval_runtime": 2.0418, | |
| "eval_samples_per_second": 24.488, | |
| "eval_steps_per_second": 6.367, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1306532663316583, | |
| "grad_norm": 0.0012525977799668908, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.135678391959799, | |
| "grad_norm": 0.0007943892851471901, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1407035175879397, | |
| "grad_norm": 0.003067328594624996, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1457286432160804, | |
| "grad_norm": 0.0008991939830593765, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1507537688442211, | |
| "grad_norm": 0.00046679627848789096, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15577889447236182, | |
| "grad_norm": 0.00047094107139855623, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.16080402010050251, | |
| "grad_norm": 0.00032768698292784393, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1658291457286432, | |
| "grad_norm": 0.0002552347432356328, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1708542713567839, | |
| "grad_norm": 0.0002349390706513077, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.17587939698492464, | |
| "grad_norm": 0.00030390697065740824, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18090452261306533, | |
| "grad_norm": 0.00018882301810663193, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.18592964824120603, | |
| "grad_norm": 0.00014582593576051295, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.19095477386934673, | |
| "grad_norm": 0.00023641975712962449, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.19597989949748743, | |
| "grad_norm": 0.00016852810222189873, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.20100502512562815, | |
| "grad_norm": 0.0002045270084636286, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20603015075376885, | |
| "grad_norm": 0.00016816142306197435, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.21105527638190955, | |
| "grad_norm": 0.0001245664752786979, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.21608040201005024, | |
| "grad_norm": 0.0001389732351526618, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.22110552763819097, | |
| "grad_norm": 0.00014751502021681517, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.22613065326633167, | |
| "grad_norm": 0.0001148287410615012, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23115577889447236, | |
| "grad_norm": 0.00013220967957749963, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.23618090452261306, | |
| "grad_norm": 0.00010563267278485, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.24120603015075376, | |
| "grad_norm": 0.00010591024329187348, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.24623115577889448, | |
| "grad_norm": 0.00011068899766542017, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.25125628140703515, | |
| "grad_norm": 0.0006384285516105592, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.25125628140703515, | |
| "eval_loss": 7.772435992592364e-07, | |
| "eval_runtime": 2.0538, | |
| "eval_samples_per_second": 24.345, | |
| "eval_steps_per_second": 6.33, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |