| { | |
| "best_metric": 0.034579914063215256, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2656924609764198, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005313849219528396, | |
| "grad_norm": 23.628463745117188, | |
| "learning_rate": 5e-05, | |
| "loss": 10.8982, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005313849219528396, | |
| "eval_loss": 11.041999816894531, | |
| "eval_runtime": 2.6503, | |
| "eval_samples_per_second": 18.866, | |
| "eval_steps_per_second": 4.905, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010627698439056792, | |
| "grad_norm": 23.705106735229492, | |
| "learning_rate": 0.0001, | |
| "loss": 11.0253, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015941547658585187, | |
| "grad_norm": 27.114561080932617, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 9.6993, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.021255396878113585, | |
| "grad_norm": 25.034391403198242, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.9229, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02656924609764198, | |
| "grad_norm": 6.130597114562988, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.9386, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.031883095317170373, | |
| "grad_norm": 12.182331085205078, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.0357, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03719694453669877, | |
| "grad_norm": 1.75734543800354, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.7076, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04251079375622717, | |
| "grad_norm": 2.458411455154419, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.7182, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04782464297575556, | |
| "grad_norm": 2.2449662685394287, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.7122, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05313849219528396, | |
| "grad_norm": 1.5674667358398438, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.6785, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.058452341414812356, | |
| "grad_norm": 1.9958386421203613, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6132, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06376619063434075, | |
| "grad_norm": 3.479598045349121, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.4993, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06908003985386915, | |
| "grad_norm": 6.28720235824585, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.4418, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07439388907339754, | |
| "grad_norm": 3.4374570846557617, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.3487, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07970773829292593, | |
| "grad_norm": 5.028607368469238, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.3446, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08502158751245434, | |
| "grad_norm": 2.4742584228515625, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.3521, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09033543673198273, | |
| "grad_norm": 4.0169172286987305, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.3533, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09564928595151112, | |
| "grad_norm": 2.451641082763672, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.3394, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10096313517103953, | |
| "grad_norm": 2.82594633102417, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.2622, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10627698439056792, | |
| "grad_norm": 3.50852108001709, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.282, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11159083361009631, | |
| "grad_norm": 3.7088255882263184, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.2771, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11690468282962471, | |
| "grad_norm": 2.132201910018921, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.2332, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1222185320491531, | |
| "grad_norm": 2.604558229446411, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.2375, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1275323812686815, | |
| "grad_norm": 2.225511312484741, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.2396, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1328462304882099, | |
| "grad_norm": 2.3635268211364746, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1778, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1328462304882099, | |
| "eval_loss": 0.09752233326435089, | |
| "eval_runtime": 2.0324, | |
| "eval_samples_per_second": 24.602, | |
| "eval_steps_per_second": 6.397, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1381600797077383, | |
| "grad_norm": 1.9589002132415771, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.1831, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.14347392892726668, | |
| "grad_norm": 2.174701690673828, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.1831, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14878777814679509, | |
| "grad_norm": 2.3990869522094727, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.1238, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1541016273663235, | |
| "grad_norm": 2.058366298675537, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.1291, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.15941547658585187, | |
| "grad_norm": 2.2778303623199463, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.1427, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16472932580538027, | |
| "grad_norm": 2.884948492050171, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0802, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.17004317502490868, | |
| "grad_norm": 2.686048984527588, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.155, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.17535702424443705, | |
| "grad_norm": 2.415022611618042, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.2073, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.18067087346396546, | |
| "grad_norm": 2.207425117492676, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.1384, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.18598472268349386, | |
| "grad_norm": 1.7799278497695923, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.1412, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.19129857190302224, | |
| "grad_norm": 1.3226287364959717, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0728, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.19661242112255065, | |
| "grad_norm": 1.6843650341033936, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.1343, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.20192627034207905, | |
| "grad_norm": 1.350917935371399, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.1155, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.20724011956160743, | |
| "grad_norm": 1.1504665613174438, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0929, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.21255396878113583, | |
| "grad_norm": 1.5761011838912964, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.1395, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21786781800066424, | |
| "grad_norm": 1.5024954080581665, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.107, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.22318166722019261, | |
| "grad_norm": 1.106066346168518, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.1, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.22849551643972102, | |
| "grad_norm": 1.5602272748947144, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0827, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.23380936565924942, | |
| "grad_norm": 1.4273624420166016, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0767, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2391232148787778, | |
| "grad_norm": 1.07826566696167, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0417, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2444370640983062, | |
| "grad_norm": 1.6851541996002197, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0851, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2497509133178346, | |
| "grad_norm": 1.4490783214569092, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0528, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.255064762537363, | |
| "grad_norm": 1.4430365562438965, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.05, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2603786117568914, | |
| "grad_norm": 2.2319040298461914, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0895, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2656924609764198, | |
| "grad_norm": 1.0726263523101807, | |
| "learning_rate": 1e-05, | |
| "loss": 0.024, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2656924609764198, | |
| "eval_loss": 0.034579914063215256, | |
| "eval_runtime": 2.0459, | |
| "eval_samples_per_second": 24.439, | |
| "eval_steps_per_second": 6.354, | |
| "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 | |
| } | |