| { | |
| "best_metric": 0.25502192974090576, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5445881552076243, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010891763104152484, | |
| "grad_norm": 8.492592811584473, | |
| "learning_rate": 5e-05, | |
| "loss": 11.243, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010891763104152484, | |
| "eval_loss": 11.950016975402832, | |
| "eval_runtime": 11.137, | |
| "eval_samples_per_second": 55.58, | |
| "eval_steps_per_second": 7.004, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021783526208304968, | |
| "grad_norm": 8.458826065063477, | |
| "learning_rate": 0.0001, | |
| "loss": 12.0045, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03267528931245745, | |
| "grad_norm": 7.634145736694336, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.2415, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.043567052416609936, | |
| "grad_norm": 7.782668590545654, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.4128, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05445881552076242, | |
| "grad_norm": 7.3410258293151855, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 9.4192, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0653505786249149, | |
| "grad_norm": 7.889185905456543, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 7.7838, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0762423417290674, | |
| "grad_norm": 8.49261474609375, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.6898, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08713410483321987, | |
| "grad_norm": 10.78543758392334, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.4752, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09802586793737236, | |
| "grad_norm": 10.449393272399902, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.2353, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10891763104152484, | |
| "grad_norm": 7.051181793212891, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.0683, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11980939414567733, | |
| "grad_norm": 5.701692581176758, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.3351, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1307011572498298, | |
| "grad_norm": 5.048213005065918, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.8347, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1415929203539823, | |
| "grad_norm": 4.25048303604126, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3458, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1524846834581348, | |
| "grad_norm": 3.201993227005005, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9775, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16337644656228728, | |
| "grad_norm": 4.068605899810791, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.849, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17426820966643974, | |
| "grad_norm": 2.541156053543091, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7482, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18515997277059223, | |
| "grad_norm": 1.8843153715133667, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7112, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19605173587474473, | |
| "grad_norm": 1.8535648584365845, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6856, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20694349897889722, | |
| "grad_norm": 2.564185619354248, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6998, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21783526208304968, | |
| "grad_norm": 1.898092269897461, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6603, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22872702518720217, | |
| "grad_norm": 1.9189125299453735, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6357, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23961878829135466, | |
| "grad_norm": 1.8812559843063354, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6076, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.25051055139550715, | |
| "grad_norm": 1.204092264175415, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6028, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2614023144996596, | |
| "grad_norm": 1.467858076095581, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5894, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.27229407760381213, | |
| "grad_norm": 2.3753695487976074, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6095, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27229407760381213, | |
| "eval_loss": 0.5813907384872437, | |
| "eval_runtime": 11.1311, | |
| "eval_samples_per_second": 55.61, | |
| "eval_steps_per_second": 7.007, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2831858407079646, | |
| "grad_norm": 2.464270830154419, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5738, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.29407760381211706, | |
| "grad_norm": 2.69157338142395, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5481, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3049693669162696, | |
| "grad_norm": 1.5113294124603271, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5112, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31586113002042204, | |
| "grad_norm": 1.6194149255752563, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4175, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32675289312457456, | |
| "grad_norm": 2.4440693855285645, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.417, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.337644656228727, | |
| "grad_norm": 2.4268813133239746, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3865, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3485364193328795, | |
| "grad_norm": 2.906593084335327, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4172, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.359428182437032, | |
| "grad_norm": 1.8728927373886108, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.2971, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.37031994554118447, | |
| "grad_norm": 3.3725411891937256, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3505, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.381211708645337, | |
| "grad_norm": 2.383547067642212, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3038, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.39210347174948945, | |
| "grad_norm": 2.2084460258483887, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3124, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4029952348536419, | |
| "grad_norm": 2.340491771697998, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.2721, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.41388699795779443, | |
| "grad_norm": 2.8425796031951904, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3493, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4247787610619469, | |
| "grad_norm": 1.770458698272705, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2772, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.43567052416609936, | |
| "grad_norm": 2.0324440002441406, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3137, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4465622872702519, | |
| "grad_norm": 1.6991618871688843, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2973, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.45745405037440434, | |
| "grad_norm": 1.9309918880462646, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3162, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.46834581347855686, | |
| "grad_norm": 1.798869252204895, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2602, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4792375765827093, | |
| "grad_norm": 1.7334697246551514, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2819, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4901293396868618, | |
| "grad_norm": 2.004193067550659, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.3022, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5010211027910143, | |
| "grad_norm": 1.3644194602966309, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2163, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5119128658951668, | |
| "grad_norm": 1.6829291582107544, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3081, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5228046289993192, | |
| "grad_norm": 1.201421856880188, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2756, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5336963921034718, | |
| "grad_norm": 1.3379050493240356, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2207, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5445881552076243, | |
| "grad_norm": 1.5710933208465576, | |
| "learning_rate": 0.0, | |
| "loss": 0.2275, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5445881552076243, | |
| "eval_loss": 0.25502192974090576, | |
| "eval_runtime": 11.1383, | |
| "eval_samples_per_second": 55.574, | |
| "eval_steps_per_second": 7.003, | |
| "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": 2.254995537788928e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |