| { | |
| "best_metric": 0.18903478980064392, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5639760310186817, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011279520620373634, | |
| "grad_norm": 36.880802154541016, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2688, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011279520620373634, | |
| "eval_loss": 11.644784927368164, | |
| "eval_runtime": 5.145, | |
| "eval_samples_per_second": 9.718, | |
| "eval_steps_per_second": 2.527, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022559041240747268, | |
| "grad_norm": 52.238494873046875, | |
| "learning_rate": 0.0001, | |
| "loss": 7.0015, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0338385618611209, | |
| "grad_norm": 34.7283821105957, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.1285, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.045118082481494536, | |
| "grad_norm": 9.916765213012695, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.1123, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05639760310186817, | |
| "grad_norm": 6.687779903411865, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.7972, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0676771237222418, | |
| "grad_norm": 12.266751289367676, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.7382, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07895664434261544, | |
| "grad_norm": 4.8768720626831055, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.2173, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09023616496298907, | |
| "grad_norm": 1.1768091917037964, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0488, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10151568558336271, | |
| "grad_norm": 0.318095862865448, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.0097, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11279520620373634, | |
| "grad_norm": 0.058398641645908356, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.001, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12407472682410997, | |
| "grad_norm": 0.06085561588406563, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0008, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1353542474444836, | |
| "grad_norm": 2.22983455657959, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0118, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14663376806485726, | |
| "grad_norm": 3.997262477874756, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.8721, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15791328868523088, | |
| "grad_norm": 1.2388508319854736, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0029, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1691928093056045, | |
| "grad_norm": 0.19173941016197205, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.002, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18047232992597814, | |
| "grad_norm": 0.12461928278207779, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0012, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19175185054635177, | |
| "grad_norm": 0.020498143509030342, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0002, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20303137116672543, | |
| "grad_norm": 0.05477139726281166, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0005, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21431089178709906, | |
| "grad_norm": 0.0029262660536915064, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22559041240747268, | |
| "grad_norm": 0.08859766274690628, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0006, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2368699330278463, | |
| "grad_norm": 0.008368107490241528, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24814945364821994, | |
| "grad_norm": 0.03288047015666962, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0002, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.25942897426859357, | |
| "grad_norm": 0.035197172313928604, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0002, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2707084948889672, | |
| "grad_norm": 0.06742740422487259, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0003, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.28198801550934083, | |
| "grad_norm": 0.000817757158074528, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28198801550934083, | |
| "eval_loss": 0.22943511605262756, | |
| "eval_runtime": 5.1472, | |
| "eval_samples_per_second": 9.714, | |
| "eval_steps_per_second": 2.526, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2932675361297145, | |
| "grad_norm": 2.8830854892730713, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.5776, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.30454705675008814, | |
| "grad_norm": 0.001804250292479992, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.31582657737046177, | |
| "grad_norm": 0.018968435004353523, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0001, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3271060979908354, | |
| "grad_norm": 0.08772213757038116, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0002, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.338385618611209, | |
| "grad_norm": 0.06046594679355621, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0005, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34966513923158266, | |
| "grad_norm": 0.09872586280107498, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0001, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3609446598519563, | |
| "grad_norm": 0.0029770503751933575, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3722241804723299, | |
| "grad_norm": 0.3427497148513794, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0011, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38350370109270354, | |
| "grad_norm": 0.006538857705891132, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0001, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39478322171307717, | |
| "grad_norm": 0.0016080508939921856, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.40606274233345085, | |
| "grad_norm": 0.00036259597982279956, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4173422629538245, | |
| "grad_norm": 0.00044910263386555016, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4286217835741981, | |
| "grad_norm": 3.9493634700775146, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.4749, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.43990130419457174, | |
| "grad_norm": 0.0019561927765607834, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.45118082481494537, | |
| "grad_norm": 0.003831230802461505, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.462460345435319, | |
| "grad_norm": 0.0014211925445124507, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4737398660556926, | |
| "grad_norm": 0.0003359741240274161, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48501938667606626, | |
| "grad_norm": 0.00035142392152920365, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4962989072964399, | |
| "grad_norm": 0.0010094629833474755, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5075784279168135, | |
| "grad_norm": 0.029661918058991432, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0003, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5188579485371871, | |
| "grad_norm": 0.00044001490459777415, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5301374691575608, | |
| "grad_norm": 0.005407867021858692, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5414169897779344, | |
| "grad_norm": 0.0023250116501003504, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.552696510398308, | |
| "grad_norm": 0.0011205272749066353, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5639760310186817, | |
| "grad_norm": 0.0002717706374824047, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5639760310186817, | |
| "eval_loss": 0.18903478980064392, | |
| "eval_runtime": 5.157, | |
| "eval_samples_per_second": 9.696, | |
| "eval_steps_per_second": 2.521, | |
| "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": 6.019371851170447e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |