| { | |
| "best_metric": 0.03815676271915436, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.014104372355430184, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028208744710860365, | |
| "grad_norm": 6.236761093139648, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9039, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028208744710860365, | |
| "eval_loss": 4.070339202880859, | |
| "eval_runtime": 637.254, | |
| "eval_samples_per_second": 37.476, | |
| "eval_steps_per_second": 4.686, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005641748942172073, | |
| "grad_norm": 6.449122428894043, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7988, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000846262341325811, | |
| "grad_norm": 6.0404133796691895, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.6179, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011283497884344146, | |
| "grad_norm": 6.546438694000244, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.3526, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014104372355430183, | |
| "grad_norm": 15.546788215637207, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.7515, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001692524682651622, | |
| "grad_norm": 7.398496627807617, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.603, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019746121297602257, | |
| "grad_norm": 4.642514228820801, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.2168, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002256699576868829, | |
| "grad_norm": 2.4016270637512207, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8918, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002538787023977433, | |
| "grad_norm": 2.460822820663452, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6891, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028208744710860366, | |
| "grad_norm": 2.040602684020996, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.6123, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0031029619181946405, | |
| "grad_norm": 2.504974365234375, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.4788, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003385049365303244, | |
| "grad_norm": 2.2518203258514404, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4071, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0036671368124118475, | |
| "grad_norm": 1.7780072689056396, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.2691, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0039492242595204514, | |
| "grad_norm": 1.5694814920425415, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2313, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004231311706629055, | |
| "grad_norm": 1.693428635597229, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1835, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004513399153737658, | |
| "grad_norm": 1.7875328063964844, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2302, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004795486600846262, | |
| "grad_norm": 1.6762068271636963, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1631, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005077574047954866, | |
| "grad_norm": 1.9579442739486694, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1048, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005359661495063469, | |
| "grad_norm": 1.3954004049301147, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1057, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005641748942172073, | |
| "grad_norm": 1.2719477415084839, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1004, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005923836389280677, | |
| "grad_norm": 1.2574114799499512, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1052, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006205923836389281, | |
| "grad_norm": 0.9059264659881592, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0508, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006488011283497884, | |
| "grad_norm": 1.8527705669403076, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0806, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006770098730606488, | |
| "grad_norm": 1.9850269556045532, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1193, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007052186177715092, | |
| "grad_norm": 1.0578618049621582, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0669, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007052186177715092, | |
| "eval_loss": 0.06095504388213158, | |
| "eval_runtime": 636.7709, | |
| "eval_samples_per_second": 37.505, | |
| "eval_steps_per_second": 4.689, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007334273624823695, | |
| "grad_norm": 1.1075620651245117, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0845, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007616361071932299, | |
| "grad_norm": 0.8992208242416382, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0661, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007898448519040903, | |
| "grad_norm": 0.9340633153915405, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0432, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008180535966149507, | |
| "grad_norm": 1.0387746095657349, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0787, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.00846262341325811, | |
| "grad_norm": 0.9487574100494385, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0525, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008744710860366713, | |
| "grad_norm": 1.0404561758041382, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.05, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009026798307475317, | |
| "grad_norm": 0.8051718473434448, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0493, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00930888575458392, | |
| "grad_norm": 0.47407007217407227, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0185, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009590973201692525, | |
| "grad_norm": 1.1965396404266357, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0496, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009873060648801129, | |
| "grad_norm": 0.8554047346115112, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0348, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010155148095909733, | |
| "grad_norm": 0.5990251302719116, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.022, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010437235543018336, | |
| "grad_norm": 0.4175862967967987, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0243, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010719322990126939, | |
| "grad_norm": 0.7823725342750549, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0384, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.011001410437235543, | |
| "grad_norm": 0.5732550024986267, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0436, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011283497884344146, | |
| "grad_norm": 0.7381021976470947, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0311, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01156558533145275, | |
| "grad_norm": 0.7738580107688904, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0475, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011847672778561354, | |
| "grad_norm": 0.739055335521698, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0292, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.012129760225669958, | |
| "grad_norm": 1.1671977043151855, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0565, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012411847672778562, | |
| "grad_norm": 0.6021670699119568, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0347, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012693935119887164, | |
| "grad_norm": 0.6920357346534729, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0291, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012976022566995768, | |
| "grad_norm": 0.42046383023262024, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0132, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013258110014104372, | |
| "grad_norm": 0.5549576878547668, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.028, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013540197461212976, | |
| "grad_norm": 0.5346555709838867, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0223, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01382228490832158, | |
| "grad_norm": 5.4132866859436035, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0755, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.014104372355430184, | |
| "grad_norm": 1.7002118825912476, | |
| "learning_rate": 0.0, | |
| "loss": 0.0479, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014104372355430184, | |
| "eval_loss": 0.03815676271915436, | |
| "eval_runtime": 637.1574, | |
| "eval_samples_per_second": 37.482, | |
| "eval_steps_per_second": 4.686, | |
| "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": 5.977408742935757e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |