| { | |
| "best_metric": 0.31632593274116516, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.09746588693957114, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003898635477582846, | |
| "grad_norm": 0.30886903405189514, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4841, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003898635477582846, | |
| "eval_loss": 0.5646668076515198, | |
| "eval_runtime": 23.1259, | |
| "eval_samples_per_second": 4.67, | |
| "eval_steps_per_second": 2.335, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007797270955165692, | |
| "grad_norm": 0.2530393898487091, | |
| "learning_rate": 4e-05, | |
| "loss": 0.517, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011695906432748537, | |
| "grad_norm": 0.2777021527290344, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5642, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015594541910331383, | |
| "grad_norm": 0.2688068449497223, | |
| "learning_rate": 8e-05, | |
| "loss": 0.4727, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01949317738791423, | |
| "grad_norm": 0.31678125262260437, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5679, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01949317738791423, | |
| "eval_loss": 0.5465080738067627, | |
| "eval_runtime": 21.7035, | |
| "eval_samples_per_second": 4.976, | |
| "eval_steps_per_second": 2.488, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 0.3961825668811798, | |
| "learning_rate": 0.00012, | |
| "loss": 0.5048, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02729044834307992, | |
| "grad_norm": 0.4862196445465088, | |
| "learning_rate": 0.00014, | |
| "loss": 0.4916, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.031189083820662766, | |
| "grad_norm": 0.35146328806877136, | |
| "learning_rate": 0.00016, | |
| "loss": 0.4825, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 0.40440186858177185, | |
| "learning_rate": 0.00018, | |
| "loss": 0.4927, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "grad_norm": 0.4066947102546692, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4768, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "eval_loss": 0.4105689525604248, | |
| "eval_runtime": 21.8054, | |
| "eval_samples_per_second": 4.953, | |
| "eval_steps_per_second": 2.476, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.042884990253411304, | |
| "grad_norm": 0.4722544550895691, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.4067, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 0.2893505096435547, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.3599, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.050682261208576995, | |
| "grad_norm": 0.29872167110443115, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.3891, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05458089668615984, | |
| "grad_norm": 0.3668901324272156, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.3932, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "grad_norm": 0.38297227025032043, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.3373, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "eval_loss": 0.3280330300331116, | |
| "eval_runtime": 21.8227, | |
| "eval_samples_per_second": 4.949, | |
| "eval_steps_per_second": 2.474, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06237816764132553, | |
| "grad_norm": 0.41975319385528564, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.3135, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06627680311890838, | |
| "grad_norm": 0.33132046461105347, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.3787, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 0.384635329246521, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.4993, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.316310316324234, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.3265, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07797270955165692, | |
| "grad_norm": 0.4260328710079193, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.3335, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07797270955165692, | |
| "eval_loss": 0.3193468749523163, | |
| "eval_runtime": 21.9533, | |
| "eval_samples_per_second": 4.92, | |
| "eval_steps_per_second": 2.46, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08187134502923976, | |
| "grad_norm": 0.37978965044021606, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.3882, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08576998050682261, | |
| "grad_norm": 0.3311784565448761, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.3009, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08966861598440545, | |
| "grad_norm": 0.3548380136489868, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.2982, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": 0.34436410665512085, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.3098, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09746588693957114, | |
| "grad_norm": 0.384309321641922, | |
| "learning_rate": 0.0, | |
| "loss": 0.366, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09746588693957114, | |
| "eval_loss": 0.31632593274116516, | |
| "eval_runtime": 21.7761, | |
| "eval_samples_per_second": 4.96, | |
| "eval_steps_per_second": 2.48, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 9419457413775360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |