| { | |
| "best_metric": 3.6524410247802734, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.20489179152260212, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004097835830452042, | |
| "grad_norm": 8.17273235321045, | |
| "learning_rate": 5e-05, | |
| "loss": 5.8681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004097835830452042, | |
| "eval_loss": 6.038059234619141, | |
| "eval_runtime": 4.7663, | |
| "eval_samples_per_second": 10.49, | |
| "eval_steps_per_second": 2.727, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008195671660904085, | |
| "grad_norm": 8.440423011779785, | |
| "learning_rate": 0.0001, | |
| "loss": 5.9822, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012293507491356128, | |
| "grad_norm": 6.372066497802734, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.4229, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01639134332180817, | |
| "grad_norm": 5.9859232902526855, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.6798, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02048917915226021, | |
| "grad_norm": 6.160243988037109, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.703, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024587014982712256, | |
| "grad_norm": 3.177950620651245, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.5104, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028684850813164298, | |
| "grad_norm": 2.2837774753570557, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.2898, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03278268664361634, | |
| "grad_norm": 1.5388017892837524, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.2678, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03688052247406838, | |
| "grad_norm": 3.053107500076294, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.1682, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04097835830452042, | |
| "grad_norm": 2.493290901184082, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.1832, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04507619413497247, | |
| "grad_norm": 1.949349284172058, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.1423, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04917402996542451, | |
| "grad_norm": 2.94350266456604, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.1833, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.053271865795876554, | |
| "grad_norm": 1.939968466758728, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 4.0466, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.057369701626328595, | |
| "grad_norm": 2.102407932281494, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 4.0055, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06146753745678064, | |
| "grad_norm": 1.9021189212799072, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.9682, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06556537328723268, | |
| "grad_norm": 1.7222744226455688, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.9069, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06966320911768473, | |
| "grad_norm": 1.8017946481704712, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.912, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07376104494813676, | |
| "grad_norm": 1.1817983388900757, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.7766, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07785888077858881, | |
| "grad_norm": 1.441970944404602, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.7548, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08195671660904084, | |
| "grad_norm": 1.084867238998413, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.7368, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08605455243949289, | |
| "grad_norm": 1.1046688556671143, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.8319, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09015238826994494, | |
| "grad_norm": 1.216025710105896, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.701, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09425022410039698, | |
| "grad_norm": 1.1603436470031738, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.7036, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09834805993084902, | |
| "grad_norm": 1.6205642223358154, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.8242, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10244589576130106, | |
| "grad_norm": 1.2837269306182861, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.9515, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10244589576130106, | |
| "eval_loss": 3.763901472091675, | |
| "eval_runtime": 4.8358, | |
| "eval_samples_per_second": 10.34, | |
| "eval_steps_per_second": 2.688, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10654373159175311, | |
| "grad_norm": 1.9079407453536987, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.8517, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11064156742220514, | |
| "grad_norm": 1.4432978630065918, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 3.8022, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11473940325265719, | |
| "grad_norm": 1.3254631757736206, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.7132, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11883723908310924, | |
| "grad_norm": 1.2801110744476318, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.7882, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12293507491356127, | |
| "grad_norm": 0.9412828087806702, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.632, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12703291074401332, | |
| "grad_norm": 1.3773285150527954, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.6076, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13113074657446536, | |
| "grad_norm": 1.1964783668518066, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.638, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1352285824049174, | |
| "grad_norm": 0.9496121406555176, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.7015, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13932641823536945, | |
| "grad_norm": 1.2388590574264526, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 3.6222, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1434242540658215, | |
| "grad_norm": 1.1453251838684082, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.6447, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14752208989627352, | |
| "grad_norm": 1.0861890316009521, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.6983, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15161992572672559, | |
| "grad_norm": 1.466780424118042, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 3.874, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15571776155717762, | |
| "grad_norm": 1.2210124731063843, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.7076, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15981559738762965, | |
| "grad_norm": 1.3490753173828125, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.6633, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1639134332180817, | |
| "grad_norm": 0.9062822461128235, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.7274, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16801126904853375, | |
| "grad_norm": 0.9520427584648132, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.6353, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.17210910487898579, | |
| "grad_norm": 1.2778575420379639, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.6745, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.17620694070943782, | |
| "grad_norm": 1.169716477394104, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.6648, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.18030477653988988, | |
| "grad_norm": 0.8360440731048584, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.6354, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.18440261237034192, | |
| "grad_norm": 0.8596037030220032, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.621, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18850044820079395, | |
| "grad_norm": 0.8236773014068604, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.5638, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.192598284031246, | |
| "grad_norm": 1.0101842880249023, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.6251, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.19669611986169805, | |
| "grad_norm": 1.1143778562545776, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.6001, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.20079395569215008, | |
| "grad_norm": 1.1271101236343384, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 3.6615, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.20489179152260212, | |
| "grad_norm": 1.5570321083068848, | |
| "learning_rate": 1e-05, | |
| "loss": 3.8948, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20489179152260212, | |
| "eval_loss": 3.6524410247802734, | |
| "eval_runtime": 4.841, | |
| "eval_samples_per_second": 10.328, | |
| "eval_steps_per_second": 2.685, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |