| { | |
| "best_metric": 8.977178573608398, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.23564064801178203, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00471281296023564, | |
| "grad_norm": 12.179606437683105, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00471281296023564, | |
| "eval_loss": 11.466094017028809, | |
| "eval_runtime": 0.479, | |
| "eval_samples_per_second": 104.384, | |
| "eval_steps_per_second": 27.14, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00942562592047128, | |
| "grad_norm": 12.07979965209961, | |
| "learning_rate": 0.0001, | |
| "loss": 11.8923, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014138438880706922, | |
| "grad_norm": 12.105081558227539, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.8494, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01885125184094256, | |
| "grad_norm": 10.527697563171387, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.5342, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023564064801178203, | |
| "grad_norm": 9.745538711547852, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.3137, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028276877761413844, | |
| "grad_norm": 9.636290550231934, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.1324, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.032989690721649485, | |
| "grad_norm": 10.097336769104004, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.9673, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03770250368188512, | |
| "grad_norm": 9.702836036682129, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.7491, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04241531664212077, | |
| "grad_norm": 9.295515060424805, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.5877, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.047128129602356406, | |
| "grad_norm": 9.083123207092285, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.4369, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05184094256259205, | |
| "grad_norm": 8.454445838928223, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.2633, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05655375552282769, | |
| "grad_norm": 7.668487548828125, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.0734, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.061266568483063326, | |
| "grad_norm": 6.91172981262207, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.0913, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06597938144329897, | |
| "grad_norm": 6.258518218994141, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.0008, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07069219440353461, | |
| "grad_norm": 5.778624057769775, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 9.8973, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07540500736377025, | |
| "grad_norm": 5.351012706756592, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 9.8215, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0801178203240059, | |
| "grad_norm": 5.0197649002075195, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 9.7604, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08483063328424154, | |
| "grad_norm": 4.372616291046143, | |
| "learning_rate": 7.75e-05, | |
| "loss": 9.6687, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08954344624447717, | |
| "grad_norm": 4.177480697631836, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 9.6424, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09425625920471281, | |
| "grad_norm": 3.839923620223999, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 9.5492, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09896907216494845, | |
| "grad_norm": 3.6521618366241455, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 9.4798, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1036818851251841, | |
| "grad_norm": 3.611121416091919, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 9.4505, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10839469808541974, | |
| "grad_norm": 3.4653425216674805, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 9.3819, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11310751104565538, | |
| "grad_norm": 3.4124841690063477, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 9.35, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11782032400589101, | |
| "grad_norm": 4.023951053619385, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 9.2714, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11782032400589101, | |
| "eval_loss": 9.23811149597168, | |
| "eval_runtime": 0.4908, | |
| "eval_samples_per_second": 101.876, | |
| "eval_steps_per_second": 26.488, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12253313696612665, | |
| "grad_norm": 3.067300319671631, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 9.3613, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1272459499263623, | |
| "grad_norm": 2.990858554840088, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 9.3185, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13195876288659794, | |
| "grad_norm": 2.6319973468780518, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 9.2747, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13667157584683357, | |
| "grad_norm": 2.567063331604004, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 9.2475, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.14138438880706922, | |
| "grad_norm": 2.5072484016418457, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 9.2569, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14609720176730487, | |
| "grad_norm": 2.1724252700805664, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 9.211, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1508100147275405, | |
| "grad_norm": 2.120619297027588, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 9.1952, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.15552282768777614, | |
| "grad_norm": 2.0732386112213135, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 9.1858, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1602356406480118, | |
| "grad_norm": 2.1644465923309326, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 9.1393, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 2.295318365097046, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 9.1125, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16966126656848307, | |
| "grad_norm": 2.5284130573272705, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 9.1036, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1743740795287187, | |
| "grad_norm": 2.977668285369873, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 9.069, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17908689248895435, | |
| "grad_norm": 2.8644096851348877, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 9.1527, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.18379970544919, | |
| "grad_norm": 2.555832862854004, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 9.1339, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18851251840942562, | |
| "grad_norm": 2.2942168712615967, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 9.1262, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19322533136966127, | |
| "grad_norm": 2.1787540912628174, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 9.1232, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1979381443298969, | |
| "grad_norm": 2.0844101905822754, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 9.0999, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.20265095729013255, | |
| "grad_norm": 1.9640425443649292, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 9.1021, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2073637702503682, | |
| "grad_norm": 1.822178840637207, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 9.0733, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.21207658321060383, | |
| "grad_norm": 1.7947851419448853, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 9.0681, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.21678939617083948, | |
| "grad_norm": 1.8649380207061768, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 9.0623, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2215022091310751, | |
| "grad_norm": 2.00160813331604, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 9.0516, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.22621502209131075, | |
| "grad_norm": 2.279819965362549, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 9.0429, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2309278350515464, | |
| "grad_norm": 2.5081207752227783, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 8.9909, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.23564064801178203, | |
| "grad_norm": 4.336541652679443, | |
| "learning_rate": 1e-05, | |
| "loss": 8.9784, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23564064801178203, | |
| "eval_loss": 8.977178573608398, | |
| "eval_runtime": 0.4786, | |
| "eval_samples_per_second": 104.474, | |
| "eval_steps_per_second": 27.163, | |
| "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": 232376319344640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |