| { | |
| "best_metric": 1.2369416952133179, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.922722029988466, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01845444059976932, | |
| "grad_norm": 13.629104614257812, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4782, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01845444059976932, | |
| "eval_loss": 4.70109224319458, | |
| "eval_runtime": 7.9166, | |
| "eval_samples_per_second": 46.106, | |
| "eval_steps_per_second": 5.811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03690888119953864, | |
| "grad_norm": 11.56096076965332, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0593, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05536332179930796, | |
| "grad_norm": 10.880356788635254, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.8653, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07381776239907728, | |
| "grad_norm": 7.5468339920043945, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.6949, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0922722029988466, | |
| "grad_norm": 4.441961765289307, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.1967, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11072664359861592, | |
| "grad_norm": 2.78538179397583, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7837, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12918108419838523, | |
| "grad_norm": 2.4644691944122314, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.7062, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14763552479815456, | |
| "grad_norm": 2.3316614627838135, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4936, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16608996539792387, | |
| "grad_norm": 1.9944379329681396, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.559, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1845444059976932, | |
| "grad_norm": 1.2435128688812256, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3944, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2029988465974625, | |
| "grad_norm": 2.1226627826690674, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4185, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.22145328719723184, | |
| "grad_norm": 1.763035774230957, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3434, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.23990772779700115, | |
| "grad_norm": 1.7449426651000977, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.6203, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.25836216839677045, | |
| "grad_norm": 1.4836854934692383, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3534, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2768166089965398, | |
| "grad_norm": 1.509963035583496, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.331, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2952710495963091, | |
| "grad_norm": 1.2640007734298706, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.3638, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 1.3952618837356567, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.2752, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.33217993079584773, | |
| "grad_norm": 1.1493841409683228, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3015, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3506343713956171, | |
| "grad_norm": 1.069583535194397, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.284, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3690888119953864, | |
| "grad_norm": 1.182052731513977, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2625, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3875432525951557, | |
| "grad_norm": 0.9903577566146851, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2238, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.405997693194925, | |
| "grad_norm": 0.9605491757392883, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2209, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4244521337946944, | |
| "grad_norm": 1.0718780755996704, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.2431, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4429065743944637, | |
| "grad_norm": 1.2437694072723389, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3402, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.461361014994233, | |
| "grad_norm": 1.4171360731124878, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.269, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.461361014994233, | |
| "eval_loss": 1.2883262634277344, | |
| "eval_runtime": 8.0338, | |
| "eval_samples_per_second": 45.433, | |
| "eval_steps_per_second": 5.726, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4798154555940023, | |
| "grad_norm": 1.2016305923461914, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3585, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4982698961937716, | |
| "grad_norm": 1.0293444395065308, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.2216, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5167243367935409, | |
| "grad_norm": 1.0681506395339966, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.2636, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5351787773933102, | |
| "grad_norm": 0.8969022631645203, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.22, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5536332179930796, | |
| "grad_norm": 1.0133044719696045, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.2688, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5720876585928489, | |
| "grad_norm": 1.0388270616531372, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.232, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5905420991926182, | |
| "grad_norm": 1.102528691291809, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1384, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6089965397923875, | |
| "grad_norm": 1.4005072116851807, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.1417, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": 1.2080509662628174, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.162, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6459054209919262, | |
| "grad_norm": 1.075602650642395, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.2626, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6643598615916955, | |
| "grad_norm": 0.9468011856079102, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.2333, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6828143021914648, | |
| "grad_norm": 0.9746062755584717, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1295, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7012687427912342, | |
| "grad_norm": 1.348818302154541, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3782, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7197231833910035, | |
| "grad_norm": 1.452208399772644, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.2207, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7381776239907728, | |
| "grad_norm": 1.3578698635101318, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.1844, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7566320645905421, | |
| "grad_norm": 1.213419795036316, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.1902, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7750865051903114, | |
| "grad_norm": 0.8172274231910706, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.1263, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7935409457900807, | |
| "grad_norm": 1.0537660121917725, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2337, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.81199538638985, | |
| "grad_norm": 1.0971416234970093, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2341, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8304498269896193, | |
| "grad_norm": 0.8870224356651306, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1304, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8489042675893888, | |
| "grad_norm": 1.0595213174819946, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.1634, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8673587081891581, | |
| "grad_norm": 1.0634539127349854, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.1305, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8858131487889274, | |
| "grad_norm": 1.1929792165756226, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.2521, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9042675893886967, | |
| "grad_norm": 1.0194319486618042, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.2551, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.922722029988466, | |
| "grad_norm": 1.1550265550613403, | |
| "learning_rate": 0.0, | |
| "loss": 1.1364, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.922722029988466, | |
| "eval_loss": 1.2369416952133179, | |
| "eval_runtime": 8.0436, | |
| "eval_samples_per_second": 45.378, | |
| "eval_steps_per_second": 5.719, | |
| "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": 8.391461307836006e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |