| { | |
| "best_metric": 1.0053794384002686, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.18930430667297682, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003786086133459536, | |
| "grad_norm": 2.95168399810791, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003786086133459536, | |
| "eval_loss": 2.123389959335327, | |
| "eval_runtime": 2.0352, | |
| "eval_samples_per_second": 24.568, | |
| "eval_steps_per_second": 6.388, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007572172266919072, | |
| "grad_norm": 3.173819065093994, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6652, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011358258400378608, | |
| "grad_norm": 2.73962664604187, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.5925, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015144344533838144, | |
| "grad_norm": 1.5520139932632446, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.2602, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01893043066729768, | |
| "grad_norm": 1.4195196628570557, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.2748, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022716516800757217, | |
| "grad_norm": 2.6151468753814697, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.4098, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.026502602934216753, | |
| "grad_norm": 2.7280309200286865, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.2418, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03028868906767629, | |
| "grad_norm": 1.9285898208618164, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.3466, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.034074775201135825, | |
| "grad_norm": 1.6772706508636475, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.2299, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03786086133459536, | |
| "grad_norm": 1.4668546915054321, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.1112, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0416469474680549, | |
| "grad_norm": 1.4179223775863647, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.1843, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04543303360151443, | |
| "grad_norm": 1.7838054895401, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.1332, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04921911973497397, | |
| "grad_norm": 2.4858312606811523, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.2983, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.053005205868433505, | |
| "grad_norm": 2.607907772064209, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.3057, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05679129200189304, | |
| "grad_norm": 2.128920316696167, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.2775, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06057737813535258, | |
| "grad_norm": 1.7699257135391235, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.1653, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06436346426881212, | |
| "grad_norm": 1.3187021017074585, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.1756, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06814955040227165, | |
| "grad_norm": 1.0856595039367676, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2513, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07193563653573119, | |
| "grad_norm": 2.1683356761932373, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.2837, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07572172266919072, | |
| "grad_norm": 2.570289134979248, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.3552, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07950780880265026, | |
| "grad_norm": 2.68222975730896, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.3637, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0832938949361098, | |
| "grad_norm": 2.4270741939544678, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.1851, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08707998106956934, | |
| "grad_norm": 2.465186357498169, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.2125, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09086606720302887, | |
| "grad_norm": 2.1026418209075928, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.0742, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09465215333648841, | |
| "grad_norm": 2.22967791557312, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.0804, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09465215333648841, | |
| "eval_loss": 1.0526127815246582, | |
| "eval_runtime": 2.0278, | |
| "eval_samples_per_second": 24.657, | |
| "eval_steps_per_second": 6.411, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09843823946994794, | |
| "grad_norm": 0.7997608184814453, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.0595, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10222432560340748, | |
| "grad_norm": 0.9007599353790283, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.1109, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10601041173686701, | |
| "grad_norm": 0.9283623099327087, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.1029, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10979649787032655, | |
| "grad_norm": 0.9904077053070068, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.1447, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11358258400378608, | |
| "grad_norm": 0.9736183285713196, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.1642, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11736867013724563, | |
| "grad_norm": 0.8450034856796265, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.2258, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12115475627070516, | |
| "grad_norm": 0.9699908494949341, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.112, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1249408424041647, | |
| "grad_norm": 1.067191243171692, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.0924, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12872692853762424, | |
| "grad_norm": 1.109052062034607, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.1621, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13251301467108376, | |
| "grad_norm": 1.1744805574417114, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.0986, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1362991008045433, | |
| "grad_norm": 1.281468391418457, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.022, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14008518693800284, | |
| "grad_norm": 1.494238257408142, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.0764, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14387127307146239, | |
| "grad_norm": 0.6449403166770935, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.9728, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1476573592049219, | |
| "grad_norm": 0.5640941262245178, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.0272, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15144344533838144, | |
| "grad_norm": 0.5843005776405334, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.0219, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.155229531471841, | |
| "grad_norm": 0.591860294342041, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.0287, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15901561760530053, | |
| "grad_norm": 0.6270464658737183, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.1001, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.16280170373876005, | |
| "grad_norm": 0.6936808824539185, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.1502, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1665877898722196, | |
| "grad_norm": 1.0310381650924683, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.0836, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.17037387600567913, | |
| "grad_norm": 1.016648769378662, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.0123, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.17415996213913867, | |
| "grad_norm": 1.1334302425384521, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.0984, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1779460482725982, | |
| "grad_norm": 1.206661343574524, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.0054, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.18173213440605773, | |
| "grad_norm": 1.2735713720321655, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.9726, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.18551822053951728, | |
| "grad_norm": 1.4444059133529663, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.0457, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.18930430667297682, | |
| "grad_norm": 1.7697523832321167, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0625, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18930430667297682, | |
| "eval_loss": 1.0053794384002686, | |
| "eval_runtime": 2.0429, | |
| "eval_samples_per_second": 24.475, | |
| "eval_steps_per_second": 6.364, | |
| "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": 1.589463780163584e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |