| { | |
| "best_metric": 11.928899765014648, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.028310566919102553, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005662113383820511, | |
| "grad_norm": 0.014313064515590668, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005662113383820511, | |
| "eval_loss": 11.930351257324219, | |
| "eval_runtime": 0.1793, | |
| "eval_samples_per_second": 278.83, | |
| "eval_steps_per_second": 72.496, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011324226767641021, | |
| "grad_norm": 0.013985024765133858, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9302, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016986340151461533, | |
| "grad_norm": 0.01707862690091133, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9294, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022648453535282042, | |
| "grad_norm": 0.016713785007596016, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9304, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028310566919102554, | |
| "grad_norm": 0.017722394317388535, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9312, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0033972680302923066, | |
| "grad_norm": 0.017210278660058975, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9308, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003963479368674357, | |
| "grad_norm": 0.019824953749775887, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.929, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0045296907070564085, | |
| "grad_norm": 0.01971767097711563, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9303, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00509590204543846, | |
| "grad_norm": 0.019251316785812378, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9315, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005662113383820511, | |
| "grad_norm": 0.01913530007004738, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006228324722202562, | |
| "grad_norm": 0.025022396817803383, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9297, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006794536060584613, | |
| "grad_norm": 0.02492283657193184, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9327, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007360747398966664, | |
| "grad_norm": 0.016085179522633553, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9288, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007926958737348715, | |
| "grad_norm": 0.012558051384985447, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.93, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008493170075730767, | |
| "grad_norm": 0.013234994374215603, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9295, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009059381414112817, | |
| "grad_norm": 0.01846655271947384, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.93, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009625592752494869, | |
| "grad_norm": 0.017039023339748383, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9297, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01019180409087692, | |
| "grad_norm": 0.01856965199112892, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9287, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010758015429258971, | |
| "grad_norm": 0.022288938984274864, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.93, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011324226767641022, | |
| "grad_norm": 0.017395729199051857, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9321, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011890438106023074, | |
| "grad_norm": 0.017993543297052383, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9297, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012456649444405124, | |
| "grad_norm": 0.022735625505447388, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9294, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.013022860782787176, | |
| "grad_norm": 0.023601284250617027, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9292, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.013589072121169226, | |
| "grad_norm": 0.02474777214229107, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9324, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014155283459551277, | |
| "grad_norm": 0.030384186655282974, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9304, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014155283459551277, | |
| "eval_loss": 11.929415702819824, | |
| "eval_runtime": 0.1799, | |
| "eval_samples_per_second": 277.931, | |
| "eval_steps_per_second": 72.262, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014721494797933329, | |
| "grad_norm": 0.012115604244172573, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9298, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.015287706136315379, | |
| "grad_norm": 0.015809347853064537, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.9293, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01585391747469743, | |
| "grad_norm": 0.01634780876338482, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9297, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01642012881307948, | |
| "grad_norm": 0.020341364666819572, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.9294, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.016986340151461533, | |
| "grad_norm": 0.01740851253271103, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9284, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017552551489843585, | |
| "grad_norm": 0.019351454451680183, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9297, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.018118762828225634, | |
| "grad_norm": 0.021286247298121452, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9289, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.018684974166607686, | |
| "grad_norm": 0.023984717205166817, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9305, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.019251185504989738, | |
| "grad_norm": 0.02307896316051483, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.9313, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01981739684337179, | |
| "grad_norm": 0.026456082239747047, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.9288, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02038360818175384, | |
| "grad_norm": 0.0284335445612669, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9304, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02094981952013589, | |
| "grad_norm": 0.02930847555398941, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.929, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.021516030858517943, | |
| "grad_norm": 0.018983187153935432, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.93, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02208224219689999, | |
| "grad_norm": 0.019949011504650116, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.9298, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.022648453535282043, | |
| "grad_norm": 0.016765393316745758, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.9298, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023214664873664095, | |
| "grad_norm": 0.015138785354793072, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9289, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.023780876212046147, | |
| "grad_norm": 0.01913069188594818, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9286, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.024347087550428196, | |
| "grad_norm": 0.022110899910330772, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.9294, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.024913298888810248, | |
| "grad_norm": 0.022065572440624237, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.9296, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0254795102271923, | |
| "grad_norm": 0.02415025234222412, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.9284, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026045721565574352, | |
| "grad_norm": 0.02194690704345703, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.9289, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0266119329039564, | |
| "grad_norm": 0.030053917318582535, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.9295, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.027178144242338453, | |
| "grad_norm": 0.02687782235443592, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9293, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.027744355580720505, | |
| "grad_norm": 0.028278199955821037, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.9279, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.028310566919102553, | |
| "grad_norm": 0.03565681725740433, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9283, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028310566919102553, | |
| "eval_loss": 11.928899765014648, | |
| "eval_runtime": 0.1799, | |
| "eval_samples_per_second": 277.982, | |
| "eval_steps_per_second": 72.275, | |
| "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": 1042494259200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |