| { | |
| "best_metric": 0.13963158428668976, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1266624445851805, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00253324889170361, | |
| "grad_norm": 3.6676442623138428, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0591, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00253324889170361, | |
| "eval_loss": 3.577761650085449, | |
| "eval_runtime": 44.9583, | |
| "eval_samples_per_second": 3.715, | |
| "eval_steps_per_second": 1.868, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00506649778340722, | |
| "grad_norm": 3.199979305267334, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7215, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007599746675110829, | |
| "grad_norm": 3.33293080329895, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9505, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01013299556681444, | |
| "grad_norm": 4.012212753295898, | |
| "learning_rate": 0.00016, | |
| "loss": 2.8184, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01266624445851805, | |
| "grad_norm": 4.058014869689941, | |
| "learning_rate": 0.0002, | |
| "loss": 1.986, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015199493350221659, | |
| "grad_norm": 3.3792548179626465, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 1.3189, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01773274224192527, | |
| "grad_norm": 3.53857159614563, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 0.7923, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02026599113362888, | |
| "grad_norm": 5.587308406829834, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 0.7796, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022799240025332488, | |
| "grad_norm": 3.04203724861145, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 0.1713, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0253324889170361, | |
| "grad_norm": 3.9056479930877686, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.223, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02786573780873971, | |
| "grad_norm": 3.32242488861084, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 0.256, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.030398986700443317, | |
| "grad_norm": 0.5264054536819458, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 0.0183, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.032932235592146926, | |
| "grad_norm": 2.039252281188965, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 0.2864, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03546548448385054, | |
| "grad_norm": 1.891056776046753, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 0.0422, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03799873337555415, | |
| "grad_norm": 2.2989518642425537, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.5805, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04053198226725776, | |
| "grad_norm": 2.4155068397521973, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 0.2322, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04306523115896137, | |
| "grad_norm": 2.4074628353118896, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 0.4752, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.045598480050664976, | |
| "grad_norm": 0.9219037294387817, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 0.2356, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.048131728942368585, | |
| "grad_norm": 1.37091064453125, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.2088, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0506649778340722, | |
| "grad_norm": 0.2628805935382843, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.0109, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05319822672577581, | |
| "grad_norm": 2.158172845840454, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 0.2097, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05573147561747942, | |
| "grad_norm": 1.4831571578979492, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.1739, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.058264724509183026, | |
| "grad_norm": 1.6883933544158936, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 0.2868, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.060797973400886635, | |
| "grad_norm": 1.1558237075805664, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.1405, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06333122229259025, | |
| "grad_norm": 1.421405553817749, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.162, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06586447118429385, | |
| "grad_norm": 3.7727131843566895, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 0.291, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06839772007599747, | |
| "grad_norm": 1.3770571947097778, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 0.12, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07093096896770108, | |
| "grad_norm": 6.9208149909973145, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 0.7353, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07346421785940468, | |
| "grad_norm": 2.6051218509674072, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 0.2355, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0759974667511083, | |
| "grad_norm": 3.3124608993530273, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.7072, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0785307156428119, | |
| "grad_norm": 2.073368787765503, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 0.1301, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08106396453451552, | |
| "grad_norm": 0.6973274350166321, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 0.0637, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08359721342621912, | |
| "grad_norm": 1.706817865371704, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.125, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08613046231792273, | |
| "grad_norm": 1.9682927131652832, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 0.3533, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08866371120962635, | |
| "grad_norm": 2.4648215770721436, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.6709, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09119696010132995, | |
| "grad_norm": 2.308652877807617, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 0.1397, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09373020899303357, | |
| "grad_norm": 3.2563140392303467, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 0.3003, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09626345788473717, | |
| "grad_norm": 3.14212965965271, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 0.2907, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09879670677644078, | |
| "grad_norm": 1.726691484451294, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 0.0962, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1013299556681444, | |
| "grad_norm": 4.3779449462890625, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.3433, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.103863204559848, | |
| "grad_norm": 3.401987314224243, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 0.2321, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10639645345155162, | |
| "grad_norm": 1.7866804599761963, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 0.0461, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10892970234325522, | |
| "grad_norm": 2.7210962772369385, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.2669, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11146295123495883, | |
| "grad_norm": 0.31108513474464417, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 0.0179, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11399620012666245, | |
| "grad_norm": 1.0655226707458496, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.1818, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11652944901836605, | |
| "grad_norm": 2.1581103801727295, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 0.4705, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11906269791006967, | |
| "grad_norm": 0.13762931525707245, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 0.0066, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12159594680177327, | |
| "grad_norm": 0.04102027043700218, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 0.0021, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12412919569347688, | |
| "grad_norm": 0.09145709127187729, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 0.0054, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1266624445851805, | |
| "grad_norm": 0.6207671165466309, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.009, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1266624445851805, | |
| "eval_loss": 0.13963158428668976, | |
| "eval_runtime": 45.5826, | |
| "eval_samples_per_second": 3.664, | |
| "eval_steps_per_second": 1.843, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.6109411688448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |