| { | |
| "best_metric": 0.0012707465793937445, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09178522257916476, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018357044515832951, | |
| "grad_norm": 0.28899645805358887, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1753, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018357044515832951, | |
| "eval_loss": 0.38865751028060913, | |
| "eval_runtime": 41.8533, | |
| "eval_samples_per_second": 87.687, | |
| "eval_steps_per_second": 10.967, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036714089031665903, | |
| "grad_norm": 0.42189186811447144, | |
| "learning_rate": 0.0001, | |
| "loss": 0.248, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005507113354749885, | |
| "grad_norm": 0.6095991730690002, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.2594, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0073428178063331805, | |
| "grad_norm": 0.7982662916183472, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.2334, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009178522257916476, | |
| "grad_norm": 0.7745523452758789, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1986, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01101422670949977, | |
| "grad_norm": 0.9550557136535645, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.1547, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012849931161083065, | |
| "grad_norm": 1.1150208711624146, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.0993, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014685635612666361, | |
| "grad_norm": 0.5300053358078003, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0317, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.016521340064249657, | |
| "grad_norm": 0.554506242275238, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0284, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018357044515832952, | |
| "grad_norm": 0.22338461875915527, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0165, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020192748967416244, | |
| "grad_norm": 0.22608879208564758, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0133, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02202845341899954, | |
| "grad_norm": 0.19878767430782318, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.011, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.023864157870582835, | |
| "grad_norm": 0.21398384869098663, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0085, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02569986232216613, | |
| "grad_norm": 0.10816192626953125, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0073, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.027535566773749427, | |
| "grad_norm": 0.08344914764165878, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0035, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029371271225332722, | |
| "grad_norm": 0.1762116253376007, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0052, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.031206975676916018, | |
| "grad_norm": 0.11861647665500641, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0046, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03304268012849931, | |
| "grad_norm": 0.07198595255613327, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0042, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.034878384580082605, | |
| "grad_norm": 0.12151943147182465, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0043, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.036714089031665904, | |
| "grad_norm": 0.08527624607086182, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0031, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.038549793483249196, | |
| "grad_norm": 0.11344439536333084, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0052, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04038549793483249, | |
| "grad_norm": 0.025957219302654266, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0011, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04222120238641579, | |
| "grad_norm": 0.10967632383108139, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0023, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04405690683799908, | |
| "grad_norm": 0.027078542858362198, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0015, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04589261128958238, | |
| "grad_norm": 0.16326873004436493, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0056, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04589261128958238, | |
| "eval_loss": 0.0023557350505143404, | |
| "eval_runtime": 41.8035, | |
| "eval_samples_per_second": 87.792, | |
| "eval_steps_per_second": 10.98, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04772831574116567, | |
| "grad_norm": 0.03969290480017662, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0036, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04956402019274897, | |
| "grad_norm": 0.05991506949067116, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.002, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05139972464433226, | |
| "grad_norm": 0.12994393706321716, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0023, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05323542909591556, | |
| "grad_norm": 0.10758275538682938, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.002, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05507113354749885, | |
| "grad_norm": 0.0473983958363533, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0037, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.056906837999082145, | |
| "grad_norm": 0.036021437495946884, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0017, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.058742542450665444, | |
| "grad_norm": 0.07811661064624786, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0019, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.060578246902248736, | |
| "grad_norm": 0.03983394429087639, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.001, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.062413951353832035, | |
| "grad_norm": 0.04007494077086449, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0017, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06424965580541533, | |
| "grad_norm": 0.034313008189201355, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0018, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06608536025699863, | |
| "grad_norm": 0.020503444597125053, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0009, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06792106470858192, | |
| "grad_norm": 0.0259392112493515, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.001, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06975676916016521, | |
| "grad_norm": 0.042154375463724136, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0029, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0715924736117485, | |
| "grad_norm": 0.0755230262875557, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0027, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07342817806333181, | |
| "grad_norm": 0.0874118059873581, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0022, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0752638825149151, | |
| "grad_norm": 0.042569711804389954, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0011, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07709958696649839, | |
| "grad_norm": 0.019847646355628967, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.001, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07893529141808169, | |
| "grad_norm": 0.08393401652574539, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0015, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08077099586966498, | |
| "grad_norm": 0.030877625569701195, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0035, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08260670032124828, | |
| "grad_norm": 0.045764584094285965, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0007, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08444240477283158, | |
| "grad_norm": 0.09352825582027435, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0011, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08627810922441487, | |
| "grad_norm": 0.0760883167386055, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0023, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08811381367599816, | |
| "grad_norm": 0.021919649094343185, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.001, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08994951812758147, | |
| "grad_norm": 0.015877025201916695, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0011, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09178522257916476, | |
| "grad_norm": 0.06634297221899033, | |
| "learning_rate": 0.0, | |
| "loss": 0.0036, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09178522257916476, | |
| "eval_loss": 0.0012707465793937445, | |
| "eval_runtime": 41.8503, | |
| "eval_samples_per_second": 87.694, | |
| "eval_steps_per_second": 10.968, | |
| "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": 1.0598674582837658e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |