| { | |
| "best_metric": 0.07640355080366135, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.15939430165371588, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0031878860330743176, | |
| "grad_norm": 21.039119720458984, | |
| "learning_rate": 5e-05, | |
| "loss": 12.8383, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031878860330743176, | |
| "eval_loss": 13.454628944396973, | |
| "eval_runtime": 143.3396, | |
| "eval_samples_per_second": 14.748, | |
| "eval_steps_per_second": 1.849, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006375772066148635, | |
| "grad_norm": 21.684816360473633, | |
| "learning_rate": 0.0001, | |
| "loss": 12.8279, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009563658099222952, | |
| "grad_norm": 23.908435821533203, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.4862, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01275154413229727, | |
| "grad_norm": 34.252071380615234, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.7458, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01593943016537159, | |
| "grad_norm": 13.637765884399414, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.7309, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.019127316198445904, | |
| "grad_norm": 0.7787806987762451, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.017, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022315202231520222, | |
| "grad_norm": 0.2431143969297409, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.0029, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02550308826459454, | |
| "grad_norm": 0.021578334271907806, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0004, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02869097429766886, | |
| "grad_norm": 2.1936194896698, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0859, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03187886033074318, | |
| "grad_norm": 4.893922328948975, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.3001, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03506674636381749, | |
| "grad_norm": 3.905122995376587, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.317, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03825463239689181, | |
| "grad_norm": 3.8358139991760254, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6007, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04144251842996613, | |
| "grad_norm": 1.3878974914550781, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3397, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.044630404463040445, | |
| "grad_norm": 1.4316143989562988, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.019, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04781829049611477, | |
| "grad_norm": 0.023320436477661133, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0002, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05100617652918908, | |
| "grad_norm": 0.0005990703357383609, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0541940625622634, | |
| "grad_norm": 0.00043424381874501705, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05738194859533772, | |
| "grad_norm": 0.0003476722922641784, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.060569834628412034, | |
| "grad_norm": 0.00039929794729687274, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06375772066148636, | |
| "grad_norm": 0.08998116850852966, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0097, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06694560669456066, | |
| "grad_norm": 0.09896165132522583, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0072, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07013349272763499, | |
| "grad_norm": 0.4899124801158905, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0759, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07332137876070931, | |
| "grad_norm": 1.5196644067764282, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2731, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07650926479378362, | |
| "grad_norm": 1.9914950132369995, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4005, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07969715082685794, | |
| "grad_norm": 1.3223192691802979, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5097, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07969715082685794, | |
| "eval_loss": 0.07755980640649796, | |
| "eval_runtime": 143.3592, | |
| "eval_samples_per_second": 14.746, | |
| "eval_steps_per_second": 1.849, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08288503685993226, | |
| "grad_norm": 0.0372718870639801, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0005, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08607292289300658, | |
| "grad_norm": 0.0864085778594017, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0087, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08926080892608089, | |
| "grad_norm": 0.07040909677743912, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.001, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09244869495915521, | |
| "grad_norm": 0.08171924203634262, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0013, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09563658099222953, | |
| "grad_norm": 0.04170752316713333, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0006, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09882446702530384, | |
| "grad_norm": 0.04046756774187088, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0006, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10201235305837816, | |
| "grad_norm": 0.10425488650798798, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0097, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10520023909145249, | |
| "grad_norm": 0.13888247311115265, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0111, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1083881251245268, | |
| "grad_norm": 0.42929139733314514, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0647, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11157601115760112, | |
| "grad_norm": 0.5731561779975891, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0943, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11476389719067544, | |
| "grad_norm": 0.602446973323822, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2037, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11795178322374975, | |
| "grad_norm": 1.7377841472625732, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5449, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12113966925682407, | |
| "grad_norm": 1.0830893516540527, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3696, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12432755528989839, | |
| "grad_norm": 0.007708725985139608, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0001, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1275154413229727, | |
| "grad_norm": 0.008319525048136711, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13070332735604703, | |
| "grad_norm": 0.006531168706715107, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0001, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13389121338912133, | |
| "grad_norm": 0.005489464849233627, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0001, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13707909942219565, | |
| "grad_norm": 0.005156314000487328, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0001, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14026698545526997, | |
| "grad_norm": 0.005498033948242664, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0001, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1434548714883443, | |
| "grad_norm": 0.005461568012833595, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0001, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14664275752141862, | |
| "grad_norm": 0.0800841674208641, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0069, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14983064355449294, | |
| "grad_norm": 0.22930651903152466, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0571, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15301852958756723, | |
| "grad_norm": 0.622684121131897, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.201, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15620641562064155, | |
| "grad_norm": 0.3593548834323883, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2477, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15939430165371588, | |
| "grad_norm": 0.9446438550949097, | |
| "learning_rate": 0.0, | |
| "loss": 0.593, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15939430165371588, | |
| "eval_loss": 0.07640355080366135, | |
| "eval_runtime": 143.3385, | |
| "eval_samples_per_second": 14.748, | |
| "eval_steps_per_second": 1.849, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |