| { | |
| "best_metric": 10.373170852661133, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08421052631578947, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "grad_norm": 0.0806819349527359, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3805, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "eval_loss": 10.37641429901123, | |
| "eval_runtime": 2.5054, | |
| "eval_samples_per_second": 99.784, | |
| "eval_steps_per_second": 49.892, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003368421052631579, | |
| "grad_norm": 0.024693956598639488, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3779, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0050526315789473685, | |
| "grad_norm": 0.03821239992976189, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 10.3785, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006736842105263158, | |
| "grad_norm": 0.027714772149920464, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 10.3807, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008421052631578947, | |
| "grad_norm": 0.028413690626621246, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 10.3768, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010105263157894737, | |
| "grad_norm": 0.03714875131845474, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 10.3808, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011789473684210527, | |
| "grad_norm": 0.029419012367725372, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 10.3766, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013473684210526317, | |
| "grad_norm": 0.03351010009646416, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 10.3803, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015157894736842105, | |
| "grad_norm": 0.02861347794532776, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 10.3819, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016842105263157894, | |
| "grad_norm": 0.033412087708711624, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 10.3826, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018526315789473686, | |
| "grad_norm": 0.036408938467502594, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 10.3754, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020210526315789474, | |
| "grad_norm": 0.037720438092947006, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 10.3789, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021894736842105262, | |
| "grad_norm": 0.04012691602110863, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 10.373, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023578947368421053, | |
| "grad_norm": 0.04150703176856041, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.3795, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02526315789473684, | |
| "grad_norm": 0.04563893377780914, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 10.3767, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026947368421052633, | |
| "grad_norm": 0.03193050995469093, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 10.3773, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02863157894736842, | |
| "grad_norm": 0.03927315026521683, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 10.3744, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03031578947368421, | |
| "grad_norm": 0.04184223338961601, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 10.3749, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 0.049206532537937164, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 10.3728, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03368421052631579, | |
| "grad_norm": 0.04716723784804344, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 10.3735, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03536842105263158, | |
| "grad_norm": 0.04559972882270813, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 10.3782, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03705263157894737, | |
| "grad_norm": 0.05300372093915939, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 10.372, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03873684210526316, | |
| "grad_norm": 0.046657513827085495, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 10.3777, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04042105263157895, | |
| "grad_norm": 0.049605146050453186, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 10.3798, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 0.042676687240600586, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 10.3753, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "eval_loss": 10.374467849731445, | |
| "eval_runtime": 2.5035, | |
| "eval_samples_per_second": 99.861, | |
| "eval_steps_per_second": 49.93, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.043789473684210524, | |
| "grad_norm": 0.06261739879846573, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3714, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04547368421052632, | |
| "grad_norm": 0.05161561071872711, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 10.3704, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04715789473684211, | |
| "grad_norm": 0.0623190775513649, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 10.3713, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.048842105263157895, | |
| "grad_norm": 0.04920860007405281, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 10.3743, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05052631578947368, | |
| "grad_norm": 0.0820833221077919, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 10.3766, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05221052631578947, | |
| "grad_norm": 0.0759882777929306, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 10.3706, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.053894736842105266, | |
| "grad_norm": 0.09138514846563339, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 10.3766, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.055578947368421054, | |
| "grad_norm": 0.06546122580766678, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 10.3789, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05726315789473684, | |
| "grad_norm": 0.07500308752059937, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 10.3635, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05894736842105263, | |
| "grad_norm": 0.07415971904993057, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 10.3744, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06063157894736842, | |
| "grad_norm": 0.0628037378191948, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 10.3741, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06231578947368421, | |
| "grad_norm": 0.07070739567279816, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 10.3683, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 0.07649371773004532, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 10.3733, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06568421052631579, | |
| "grad_norm": 0.09366203844547272, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 10.3807, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06736842105263158, | |
| "grad_norm": 0.08414056897163391, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 10.3586, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06905263157894737, | |
| "grad_norm": 0.09400244802236557, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 10.3526, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07073684210526315, | |
| "grad_norm": 0.07930176705121994, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 10.3771, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07242105263157894, | |
| "grad_norm": 0.08477415144443512, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 10.3674, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07410526315789474, | |
| "grad_norm": 0.09532937407493591, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 10.364, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07578947368421053, | |
| "grad_norm": 0.12698949873447418, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 10.3493, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07747368421052632, | |
| "grad_norm": 0.09168936312198639, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 10.3725, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07915789473684211, | |
| "grad_norm": 0.10333892703056335, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 10.3572, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0808421052631579, | |
| "grad_norm": 0.15725451707839966, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 10.3644, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08252631578947368, | |
| "grad_norm": 0.158616304397583, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 10.3458, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 0.16719745099544525, | |
| "learning_rate": 0.0, | |
| "loss": 10.3634, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "eval_loss": 10.373170852661133, | |
| "eval_runtime": 2.7738, | |
| "eval_samples_per_second": 90.128, | |
| "eval_steps_per_second": 45.064, | |
| "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": 5230244659200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |