| { | |
| "best_metric": 6.92307186126709, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.010162214346506104, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020324428693012207, | |
| "grad_norm": 0.08410007506608963, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9386, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020324428693012207, | |
| "eval_loss": 6.941287040710449, | |
| "eval_runtime": 0.1174, | |
| "eval_samples_per_second": 425.819, | |
| "eval_steps_per_second": 110.713, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00040648857386024414, | |
| "grad_norm": 0.08960605412721634, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9386, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006097328607903663, | |
| "grad_norm": 0.08601795881986618, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.9382, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008129771477204883, | |
| "grad_norm": 0.09231054782867432, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9385, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010162214346506103, | |
| "grad_norm": 0.09385655075311661, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.9373, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012194657215807325, | |
| "grad_norm": 0.10033882409334183, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 6.9395, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014227100085108546, | |
| "grad_norm": 0.10151656717061996, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.9374, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016259542954409766, | |
| "grad_norm": 0.10626529902219772, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.9356, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018291985823710986, | |
| "grad_norm": 0.1114870011806488, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.9349, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0020324428693012206, | |
| "grad_norm": 0.12120575457811356, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 6.9321, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022356871562313426, | |
| "grad_norm": 0.12660174071788788, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 6.9331, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002438931443161465, | |
| "grad_norm": 0.14304086565971375, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 6.9333, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002642175730091587, | |
| "grad_norm": 0.10343854874372482, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 6.9351, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002845420017021709, | |
| "grad_norm": 0.08956442028284073, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 6.9348, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003048664303951831, | |
| "grad_norm": 0.09538648277521133, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 6.9332, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003251908590881953, | |
| "grad_norm": 0.09813094139099121, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 6.9334, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003455152877812075, | |
| "grad_norm": 0.09969386458396912, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 6.9312, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003658397164742197, | |
| "grad_norm": 0.10542583465576172, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.9304, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003861641451672319, | |
| "grad_norm": 0.11531369388103485, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 6.9319, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004064885738602441, | |
| "grad_norm": 0.11504054814577103, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.9309, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004268130025532563, | |
| "grad_norm": 0.12010727822780609, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 6.9303, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004471374312462685, | |
| "grad_norm": 0.12595853209495544, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 6.9275, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004674618599392807, | |
| "grad_norm": 0.1284550428390503, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 6.9256, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00487786288632293, | |
| "grad_norm": 0.14215584099292755, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 6.9281, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005081107173253052, | |
| "grad_norm": 0.16178622841835022, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 6.9265, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005081107173253052, | |
| "eval_loss": 6.92898416519165, | |
| "eval_runtime": 0.1272, | |
| "eval_samples_per_second": 392.966, | |
| "eval_steps_per_second": 102.171, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005284351460183174, | |
| "grad_norm": 0.09798461943864822, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 6.9302, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005487595747113296, | |
| "grad_norm": 0.09589119255542755, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 6.9309, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005690840034043418, | |
| "grad_norm": 0.10878289490938187, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 6.9289, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00589408432097354, | |
| "grad_norm": 0.10759259760379791, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 6.9276, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006097328607903662, | |
| "grad_norm": 0.10860608518123627, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 6.9266, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006300572894833784, | |
| "grad_norm": 0.12264492362737656, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 6.9263, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006503817181763906, | |
| "grad_norm": 0.12330181896686554, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 6.9263, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006707061468694028, | |
| "grad_norm": 0.12452418357133865, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 6.9239, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00691030575562415, | |
| "grad_norm": 0.131307452917099, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 6.9239, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007113550042554272, | |
| "grad_norm": 0.1308247298002243, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 6.9252, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007316794329484394, | |
| "grad_norm": 0.14916321635246277, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 6.924, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007520038616414516, | |
| "grad_norm": 0.15847186744213104, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 6.9211, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007723282903344638, | |
| "grad_norm": 0.1158829927444458, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 6.925, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00792652719027476, | |
| "grad_norm": 0.10773951560258865, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 6.9268, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.008129771477204882, | |
| "grad_norm": 0.11924441158771515, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 6.9269, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008333015764135004, | |
| "grad_norm": 0.12030573934316635, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 6.9251, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.008536260051065126, | |
| "grad_norm": 0.12425759434700012, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 6.9232, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008739504337995248, | |
| "grad_norm": 0.12707437574863434, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 6.9242, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.00894274862492537, | |
| "grad_norm": 0.13171014189720154, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 6.9229, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009145992911855493, | |
| "grad_norm": 0.12991087138652802, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 6.921, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009349237198785615, | |
| "grad_norm": 0.13416709005832672, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 6.9232, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.009552481485715738, | |
| "grad_norm": 0.13503502309322357, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 6.9227, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.00975572577264586, | |
| "grad_norm": 0.14602893590927124, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 6.9204, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.009958970059575982, | |
| "grad_norm": 0.14785030484199524, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 6.9203, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.010162214346506104, | |
| "grad_norm": 0.17115415632724762, | |
| "learning_rate": 1e-05, | |
| "loss": 6.9184, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010162214346506104, | |
| "eval_loss": 6.92307186126709, | |
| "eval_runtime": 0.1177, | |
| "eval_samples_per_second": 424.749, | |
| "eval_steps_per_second": 110.435, | |
| "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": 5705957376000.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |