| { | |
| "best_metric": 1.4106714725494385, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3568242640499554, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007136485280999108, | |
| "grad_norm": 0.6175674796104431, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8728, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007136485280999108, | |
| "eval_loss": 2.002394437789917, | |
| "eval_runtime": 30.7215, | |
| "eval_samples_per_second": 30.728, | |
| "eval_steps_per_second": 3.841, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014272970561998216, | |
| "grad_norm": 0.5661294460296631, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9178, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.021409455842997322, | |
| "grad_norm": 0.5823862552642822, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.844, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.028545941123996433, | |
| "grad_norm": 0.5266484618186951, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7699, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03568242640499554, | |
| "grad_norm": 0.6617392897605896, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.6637, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.042818911685994644, | |
| "grad_norm": 0.5150014162063599, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.6131, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.049955396966993755, | |
| "grad_norm": 0.48592281341552734, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.6481, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.057091882247992866, | |
| "grad_norm": 0.6050815582275391, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6882, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06422836752899197, | |
| "grad_norm": 0.6173608303070068, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.666, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07136485280999108, | |
| "grad_norm": 0.6555174589157104, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.6982, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07850133809099019, | |
| "grad_norm": 0.7624517679214478, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.7869, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08563782337198929, | |
| "grad_norm": 0.9466533064842224, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.8974, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0927743086529884, | |
| "grad_norm": 0.6618228554725647, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.7405, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09991079393398751, | |
| "grad_norm": 0.4013254642486572, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6472, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10704727921498662, | |
| "grad_norm": 0.41740894317626953, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.6267, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11418376449598573, | |
| "grad_norm": 0.4490373730659485, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.587, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12132024977698483, | |
| "grad_norm": 0.45013779401779175, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.5025, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12845673505798394, | |
| "grad_norm": 0.40676969289779663, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4488, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 0.3980136811733246, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.3683, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14272970561998216, | |
| "grad_norm": 0.36879634857177734, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3982, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14986619090098127, | |
| "grad_norm": 0.37536928057670593, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4288, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15700267618198038, | |
| "grad_norm": 0.4245150685310364, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5434, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1641391614629795, | |
| "grad_norm": 0.494149774312973, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5239, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.17127564674397858, | |
| "grad_norm": 0.5720580816268921, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.6833, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1784121320249777, | |
| "grad_norm": 0.9948855042457581, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.8018, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1784121320249777, | |
| "eval_loss": 1.4687479734420776, | |
| "eval_runtime": 30.7545, | |
| "eval_samples_per_second": 30.695, | |
| "eval_steps_per_second": 3.837, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1855486173059768, | |
| "grad_norm": 0.3600711226463318, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5342, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1926851025869759, | |
| "grad_norm": 0.3504575490951538, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5703, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19982158786797502, | |
| "grad_norm": 0.3406086266040802, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.4813, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.20695807314897413, | |
| "grad_norm": 0.32979071140289307, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4443, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.21409455842997324, | |
| "grad_norm": 0.32950469851493835, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.3329, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22123104371097235, | |
| "grad_norm": 0.293745219707489, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.3487, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.22836752899197146, | |
| "grad_norm": 0.2850325107574463, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2256, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.23550401427297057, | |
| "grad_norm": 0.3074958920478821, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.3394, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.24264049955396966, | |
| "grad_norm": 0.3559531569480896, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.4278, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.24977698483496877, | |
| "grad_norm": 0.3970128297805786, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4543, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2569134701159679, | |
| "grad_norm": 0.4422309994697571, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4932, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.264049955396967, | |
| "grad_norm": 0.5918712019920349, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.6008, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 0.37357911467552185, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5213, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2783229259589652, | |
| "grad_norm": 0.25279656052589417, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5196, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2854594112399643, | |
| "grad_norm": 0.2838667333126068, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5639, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2925958965209634, | |
| "grad_norm": 0.3013131022453308, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.4475, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.29973238180196254, | |
| "grad_norm": 0.25624337792396545, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3707, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3068688670829616, | |
| "grad_norm": 0.27869874238967896, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2227, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.31400535236396077, | |
| "grad_norm": 0.2727345824241638, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2668, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.32114183764495985, | |
| "grad_norm": 0.2815842628479004, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.2812, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.328278322925959, | |
| "grad_norm": 0.3167998790740967, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2754, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.33541480820695807, | |
| "grad_norm": 0.3581273853778839, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.426, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.34255129348795715, | |
| "grad_norm": 0.3858048617839813, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.4207, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3496877787689563, | |
| "grad_norm": 0.470745325088501, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.5814, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3568242640499554, | |
| "grad_norm": 0.8137080073356628, | |
| "learning_rate": 0.0, | |
| "loss": 1.751, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3568242640499554, | |
| "eval_loss": 1.4106714725494385, | |
| "eval_runtime": 30.5549, | |
| "eval_samples_per_second": 30.895, | |
| "eval_steps_per_second": 3.862, | |
| "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": 5.498086011835515e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |