| { | |
| "best_metric": 1.7241265773773193, | |
| "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": 0.18878626823425293, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7415, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008908685968819599, | |
| "eval_loss": 3.07926607131958, | |
| "eval_runtime": 2.5273, | |
| "eval_samples_per_second": 19.784, | |
| "eval_steps_per_second": 5.144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017817371937639197, | |
| "grad_norm": 0.30595144629478455, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9616, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026726057906458798, | |
| "grad_norm": 0.3551925718784332, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.9984, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.035634743875278395, | |
| "grad_norm": 0.5348491072654724, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.1622, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.044543429844097995, | |
| "grad_norm": 0.9069880843162537, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.1843, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.053452115812917596, | |
| "grad_norm": 0.8640651702880859, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.1915, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.062360801781737196, | |
| "grad_norm": 0.8593299984931946, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.2393, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07126948775055679, | |
| "grad_norm": 0.9860943555831909, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.0448, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0801781737193764, | |
| "grad_norm": 1.5080639123916626, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.0644, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08908685968819599, | |
| "grad_norm": 2.0294370651245117, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.0939, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09799554565701558, | |
| "grad_norm": 3.4236092567443848, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.1193, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10690423162583519, | |
| "grad_norm": 5.392770767211914, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.4573, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11581291759465479, | |
| "grad_norm": 2.2885658740997314, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.8833, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12472160356347439, | |
| "grad_norm": 2.775259494781494, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.8562, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.133630289532294, | |
| "grad_norm": 2.9362523555755615, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.9584, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14253897550111358, | |
| "grad_norm": 2.638282299041748, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.9635, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1514476614699332, | |
| "grad_norm": 0.7820598483085632, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.1001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1603563474387528, | |
| "grad_norm": 0.8463975787162781, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.9806, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16926503340757237, | |
| "grad_norm": 1.3420571088790894, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.0301, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17817371937639198, | |
| "grad_norm": 1.5355807542800903, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.9632, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1870824053452116, | |
| "grad_norm": 1.6824076175689697, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.8468, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19599109131403117, | |
| "grad_norm": 1.8673253059387207, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.7099, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20489977728285078, | |
| "grad_norm": 2.989877462387085, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.8987, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21380846325167038, | |
| "grad_norm": 2.8362205028533936, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.5028, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22271714922049, | |
| "grad_norm": 12.428902626037598, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.6723, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22271714922049, | |
| "eval_loss": 1.8634365797042847, | |
| "eval_runtime": 1.3435, | |
| "eval_samples_per_second": 37.216, | |
| "eval_steps_per_second": 9.676, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23162583518930957, | |
| "grad_norm": 0.4183148443698883, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.6019, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24053452115812918, | |
| "grad_norm": 0.8705766797065735, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.7012, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24944320712694878, | |
| "grad_norm": 0.9665325284004211, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.0064, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2583518930957684, | |
| "grad_norm": 1.193624496459961, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.8895, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.267260579064588, | |
| "grad_norm": 0.8913549780845642, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.9919, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27616926503340755, | |
| "grad_norm": 0.6848633885383606, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.0122, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28507795100222716, | |
| "grad_norm": 0.5318528413772583, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.98, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.29398663697104677, | |
| "grad_norm": 0.4661291241645813, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.7988, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3028953229398664, | |
| "grad_norm": 0.6594870686531067, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.8389, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.311804008908686, | |
| "grad_norm": 0.975502073764801, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.7635, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3207126948775056, | |
| "grad_norm": 1.5235804319381714, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.6875, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.32962138084632514, | |
| "grad_norm": 3.2025015354156494, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.663, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.33853006681514475, | |
| "grad_norm": 0.32783958315849304, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.6698, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.34743875278396436, | |
| "grad_norm": 0.2496582567691803, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.4834, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.35634743875278396, | |
| "grad_norm": 0.3414645195007324, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.7371, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36525612472160357, | |
| "grad_norm": 0.3164196312427521, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.7891, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3741648106904232, | |
| "grad_norm": 0.2685292959213257, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.9454, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3830734966592428, | |
| "grad_norm": 0.2867202162742615, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.8811, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.39198218262806234, | |
| "grad_norm": 0.3341452479362488, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.9291, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.40089086859688194, | |
| "grad_norm": 0.31787121295928955, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.8821, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40979955456570155, | |
| "grad_norm": 0.3769933581352234, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.8162, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.41870824053452116, | |
| "grad_norm": 0.5178400278091431, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.7686, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.42761692650334077, | |
| "grad_norm": 0.7855275273323059, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.8133, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4365256124721604, | |
| "grad_norm": 1.7718549966812134, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.5973, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.44543429844098, | |
| "grad_norm": 4.557711601257324, | |
| "learning_rate": 1e-05, | |
| "loss": 2.0818, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44543429844098, | |
| "eval_loss": 1.7241265773773193, | |
| "eval_runtime": 1.3369, | |
| "eval_samples_per_second": 37.399, | |
| "eval_steps_per_second": 9.724, | |
| "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": 1.0621851957775565e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |