| { | |
| "best_metric": 2.0119948387145996, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.15910898965791567, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0031821797931583136, | |
| "grad_norm": 15.198933601379395, | |
| "learning_rate": 5e-05, | |
| "loss": 39.3465, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031821797931583136, | |
| "eval_loss": 3.323753595352173, | |
| "eval_runtime": 2.0706, | |
| "eval_samples_per_second": 24.147, | |
| "eval_steps_per_second": 6.278, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006364359586316627, | |
| "grad_norm": 17.106557846069336, | |
| "learning_rate": 0.0001, | |
| "loss": 41.114, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00954653937947494, | |
| "grad_norm": 16.300945281982422, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 45.0386, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012728719172633254, | |
| "grad_norm": 12.948710441589355, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 46.0242, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015910898965791568, | |
| "grad_norm": 13.421184539794922, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 44.9981, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01909307875894988, | |
| "grad_norm": 13.344169616699219, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 43.8957, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022275258552108195, | |
| "grad_norm": 14.76865005493164, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 44.3444, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02545743834526651, | |
| "grad_norm": 15.796384811401367, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 43.4312, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028639618138424822, | |
| "grad_norm": 15.940340995788574, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 40.8831, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.031821797931583136, | |
| "grad_norm": 14.431788444519043, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 40.777, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.035003977724741446, | |
| "grad_norm": 13.564517974853516, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 38.0055, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03818615751789976, | |
| "grad_norm": 15.250335693359375, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 41.1595, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04136833731105807, | |
| "grad_norm": 13.827449798583984, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 37.8312, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04455051710421639, | |
| "grad_norm": 16.663347244262695, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 33.6901, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0477326968973747, | |
| "grad_norm": 15.85029125213623, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 34.9859, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05091487669053302, | |
| "grad_norm": 13.29968547821045, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 34.034, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05409705648369133, | |
| "grad_norm": 13.060972213745117, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 35.1636, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.057279236276849645, | |
| "grad_norm": 10.443647384643555, | |
| "learning_rate": 7.75e-05, | |
| "loss": 34.8187, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.060461416070007955, | |
| "grad_norm": 8.79858684539795, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 33.5414, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06364359586316627, | |
| "grad_norm": 9.307402610778809, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 33.6995, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06682577565632458, | |
| "grad_norm": 10.254907608032227, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 34.1627, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07000795544948289, | |
| "grad_norm": 11.293334007263184, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 32.8413, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07319013524264122, | |
| "grad_norm": 13.59989070892334, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 33.8421, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07637231503579953, | |
| "grad_norm": 15.483268737792969, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 33.4378, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07955449482895784, | |
| "grad_norm": 23.655391693115234, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 38.3701, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07955449482895784, | |
| "eval_loss": 2.179128646850586, | |
| "eval_runtime": 2.1324, | |
| "eval_samples_per_second": 23.448, | |
| "eval_steps_per_second": 6.096, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08273667462211615, | |
| "grad_norm": 7.140899181365967, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 28.2737, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08591885441527446, | |
| "grad_norm": 6.684019088745117, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 29.4301, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08910103420843278, | |
| "grad_norm": 6.716450214385986, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 30.651, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09228321400159109, | |
| "grad_norm": 6.4075469970703125, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 29.2617, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0954653937947494, | |
| "grad_norm": 6.951930999755859, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 30.6704, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09864757358790771, | |
| "grad_norm": 7.308692455291748, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 30.3067, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10182975338106603, | |
| "grad_norm": 7.781831741333008, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 30.7733, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10501193317422435, | |
| "grad_norm": 8.915492057800293, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 31.8739, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10819411296738266, | |
| "grad_norm": 9.901936531066895, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 32.0253, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11137629276054097, | |
| "grad_norm": 11.143644332885742, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 30.8518, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11455847255369929, | |
| "grad_norm": 13.011932373046875, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 31.0378, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1177406523468576, | |
| "grad_norm": 15.904023170471191, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 32.0556, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12092283214001591, | |
| "grad_norm": 14.756224632263184, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 31.0487, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12410501193317422, | |
| "grad_norm": 7.7856059074401855, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 26.9274, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12728719172633254, | |
| "grad_norm": 7.0406928062438965, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 28.5497, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13046937151949084, | |
| "grad_norm": 7.037178993225098, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 28.4532, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13365155131264916, | |
| "grad_norm": 6.567015171051025, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 29.2796, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1368337311058075, | |
| "grad_norm": 6.716132640838623, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 29.2411, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14001591089896578, | |
| "grad_norm": 7.4442949295043945, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 30.2895, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1431980906921241, | |
| "grad_norm": 7.879354953765869, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 29.7557, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14638027048528243, | |
| "grad_norm": 8.756047248840332, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 30.5347, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14956245027844073, | |
| "grad_norm": 9.600773811340332, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 29.5354, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15274463007159905, | |
| "grad_norm": 11.779766082763672, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 29.4067, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15592680986475735, | |
| "grad_norm": 14.540099143981934, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 31.3298, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15910898965791567, | |
| "grad_norm": 19.141157150268555, | |
| "learning_rate": 1e-05, | |
| "loss": 32.4672, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15910898965791567, | |
| "eval_loss": 2.0119948387145996, | |
| "eval_runtime": 2.1279, | |
| "eval_samples_per_second": 23.497, | |
| "eval_steps_per_second": 6.109, | |
| "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": 2.967137622687744e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |