| { | |
| "best_metric": 1.303703784942627, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.9347826086956523, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03864734299516908, | |
| "grad_norm": 43.994205474853516, | |
| "learning_rate": 5e-05, | |
| "loss": 8.6568, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03864734299516908, | |
| "eval_loss": 9.1878023147583, | |
| "eval_runtime": 2.0977, | |
| "eval_samples_per_second": 23.836, | |
| "eval_steps_per_second": 6.197, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07729468599033816, | |
| "grad_norm": 44.81937789916992, | |
| "learning_rate": 0.0001, | |
| "loss": 8.7587, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11594202898550725, | |
| "grad_norm": 22.639415740966797, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.3945, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15458937198067632, | |
| "grad_norm": 12.981882095336914, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.4909, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1932367149758454, | |
| "grad_norm": 9.375457763671875, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.368, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2318840579710145, | |
| "grad_norm": 6.5740275382995605, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.9888, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.27053140096618356, | |
| "grad_norm": 9.865569114685059, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.9002, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.30917874396135264, | |
| "grad_norm": 4.7327117919921875, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4513, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 3.21882963180542, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.4635, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3864734299516908, | |
| "grad_norm": 4.296223163604736, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.0669, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4251207729468599, | |
| "grad_norm": 3.4720191955566406, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.8726, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.463768115942029, | |
| "grad_norm": 5.160560607910156, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.8661, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5024154589371981, | |
| "grad_norm": 6.284611701965332, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.3536, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5410628019323671, | |
| "grad_norm": 3.090656280517578, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.0601, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5797101449275363, | |
| "grad_norm": 2.348119020462036, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.1875, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6183574879227053, | |
| "grad_norm": 3.1631898880004883, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.8671, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6570048309178744, | |
| "grad_norm": 2.6712419986724854, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.747, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 4.000652313232422, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.6771, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7342995169082126, | |
| "grad_norm": 3.462433338165283, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.9002, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7729468599033816, | |
| "grad_norm": 3.456875801086426, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.1603, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8115942028985508, | |
| "grad_norm": 4.034793853759766, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.113, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8502415458937198, | |
| "grad_norm": 2.055413007736206, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.8101, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 3.6596388816833496, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.529, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.927536231884058, | |
| "grad_norm": 2.597264051437378, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.4767, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "grad_norm": 2.6969473361968994, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.6101, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "eval_loss": 1.6271206140518188, | |
| "eval_runtime": 2.1167, | |
| "eval_samples_per_second": 23.622, | |
| "eval_steps_per_second": 6.142, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0072463768115942, | |
| "grad_norm": 2.4182605743408203, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.0525, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0458937198067633, | |
| "grad_norm": 2.1421666145324707, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.9491, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0845410628019323, | |
| "grad_norm": 1.7140942811965942, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.8787, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1231884057971016, | |
| "grad_norm": 4.363763809204102, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.6661, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1618357487922706, | |
| "grad_norm": 4.567177772521973, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.4169, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2004830917874396, | |
| "grad_norm": 3.036890745162964, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.3714, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2391304347826086, | |
| "grad_norm": 2.796861410140991, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.4206, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2777777777777777, | |
| "grad_norm": 2.9084649085998535, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.0495, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.316425120772947, | |
| "grad_norm": 2.7295870780944824, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.858, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.355072463768116, | |
| "grad_norm": 2.5222678184509277, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.7736, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.393719806763285, | |
| "grad_norm": 2.6319963932037354, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.3707, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.432367149758454, | |
| "grad_norm": 2.874056339263916, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.2943, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.471014492753623, | |
| "grad_norm": 2.2386128902435303, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.4524, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5096618357487923, | |
| "grad_norm": 2.262472152709961, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.739, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5483091787439613, | |
| "grad_norm": 2.2704970836639404, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.7863, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5869565217391304, | |
| "grad_norm": 2.507730007171631, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.7142, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6256038647342996, | |
| "grad_norm": 2.368854284286499, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.384, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6642512077294684, | |
| "grad_norm": 3.2896950244903564, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.0967, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7028985507246377, | |
| "grad_norm": 3.205613851547241, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.1222, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7415458937198067, | |
| "grad_norm": 3.4705772399902344, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.5245, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7801932367149758, | |
| "grad_norm": 2.2479805946350098, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.8427, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.818840579710145, | |
| "grad_norm": 2.6136977672576904, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.6685, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.857487922705314, | |
| "grad_norm": 2.723087787628174, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.2938, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.896135265700483, | |
| "grad_norm": 2.7828848361968994, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.1153, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9347826086956523, | |
| "grad_norm": 2.6135149002075195, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1239, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9347826086956523, | |
| "eval_loss": 1.303703784942627, | |
| "eval_runtime": 2.14, | |
| "eval_samples_per_second": 23.365, | |
| "eval_steps_per_second": 6.075, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |