| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.16454134101192924, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003290826820238585, | |
| "grad_norm": 1.0346159934997559, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8771, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003290826820238585, | |
| "eval_loss": NaN, | |
| "eval_runtime": 69.8818, | |
| "eval_samples_per_second": 29.292, | |
| "eval_steps_per_second": 3.663, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00658165364047717, | |
| "grad_norm": 1.0091608762741089, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8875, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009872480460715755, | |
| "grad_norm": 0.9086618423461914, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.883, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01316330728095434, | |
| "grad_norm": 0.6887710690498352, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7599, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016454134101192924, | |
| "grad_norm": 1.2729499340057373, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.793, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01974496092143151, | |
| "grad_norm": 0.9051786065101624, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7709, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023035787741670095, | |
| "grad_norm": 0.5344353318214417, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.7071, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02632661456190868, | |
| "grad_norm": 0.4626157879829407, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6658, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029617441382147263, | |
| "grad_norm": 0.4907883107662201, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6414, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03290826820238585, | |
| "grad_norm": 0.5179497003555298, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.6759, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03619909502262444, | |
| "grad_norm": 0.51333087682724, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.687, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03948992184286302, | |
| "grad_norm": 0.5249148607254028, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.6956, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 0.5152816772460938, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5483, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04607157548334019, | |
| "grad_norm": 0.5774461627006531, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5946, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04936240230357877, | |
| "grad_norm": 0.5459073781967163, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5203, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05265322912381736, | |
| "grad_norm": 0.41019120812416077, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.5404, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.055944055944055944, | |
| "grad_norm": 0.3290754556655884, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.5368, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.059234882764294526, | |
| "grad_norm": 0.32175275683403015, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5479, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06252570958453312, | |
| "grad_norm": 0.33732640743255615, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.5241, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0658165364047717, | |
| "grad_norm": 0.3740571141242981, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5439, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06910736322501028, | |
| "grad_norm": 0.3677571415901184, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4904, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07239819004524888, | |
| "grad_norm": 0.39620983600616455, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5138, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07568901686548746, | |
| "grad_norm": 0.38531434535980225, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5189, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07897984368572604, | |
| "grad_norm": 0.43503570556640625, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5547, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08227067050596462, | |
| "grad_norm": 0.5323113203048706, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.5302, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08227067050596462, | |
| "eval_loss": NaN, | |
| "eval_runtime": 69.7289, | |
| "eval_samples_per_second": 29.357, | |
| "eval_steps_per_second": 3.671, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "grad_norm": 0.3497832715511322, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4674, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0888523241464418, | |
| "grad_norm": 0.3645464777946472, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4983, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09214315096668038, | |
| "grad_norm": 0.38531163334846497, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.4955, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09543397778691896, | |
| "grad_norm": 0.38884270191192627, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4825, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09872480460715755, | |
| "grad_norm": 0.3684292435646057, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.4773, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10201563142739613, | |
| "grad_norm": 0.3575262725353241, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.4762, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10530645824763472, | |
| "grad_norm": 0.381324827671051, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4799, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1085972850678733, | |
| "grad_norm": 0.33787867426872253, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.48, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11188811188811189, | |
| "grad_norm": 0.3649922013282776, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.4888, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11517893870835047, | |
| "grad_norm": 0.3968355357646942, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4914, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11846976552858905, | |
| "grad_norm": 0.40086013078689575, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4862, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12176059234882765, | |
| "grad_norm": 0.4988168179988861, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.5299, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12505141916906623, | |
| "grad_norm": 0.3682207465171814, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4489, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": 0.29406920075416565, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.4104, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1316330728095434, | |
| "grad_norm": 0.2865390479564667, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.4344, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.134923899629782, | |
| "grad_norm": 0.25812751054763794, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.4365, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13821472645002056, | |
| "grad_norm": 0.2659599483013153, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.4671, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14150555327025915, | |
| "grad_norm": 0.2916855812072754, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.4769, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14479638009049775, | |
| "grad_norm": 0.28812867403030396, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.417, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14808720691073632, | |
| "grad_norm": 0.2936413288116455, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.4749, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15137803373097491, | |
| "grad_norm": 0.3101555407047272, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.4661, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15466886055121348, | |
| "grad_norm": 0.32980605959892273, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.501, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15795968737145208, | |
| "grad_norm": 0.3773946464061737, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.4537, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16125051419169067, | |
| "grad_norm": 0.4222414791584015, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.4935, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16454134101192924, | |
| "grad_norm": 0.6277649402618408, | |
| "learning_rate": 0.0, | |
| "loss": 1.5493, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16454134101192924, | |
| "eval_loss": NaN, | |
| "eval_runtime": 69.9625, | |
| "eval_samples_per_second": 29.259, | |
| "eval_steps_per_second": 3.659, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.26462276232151e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |