| { | |
| "best_metric": 0.4647972583770752, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11417154274297131, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022834308548594262, | |
| "grad_norm": 0.22352558374404907, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3501, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022834308548594262, | |
| "eval_loss": 0.6596930623054504, | |
| "eval_runtime": 199.7271, | |
| "eval_samples_per_second": 14.775, | |
| "eval_steps_per_second": 1.848, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0045668617097188524, | |
| "grad_norm": 0.22944499552249908, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3151, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006850292564578279, | |
| "grad_norm": 0.25442609190940857, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.4302, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009133723419437705, | |
| "grad_norm": 0.23109865188598633, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.3642, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01141715427429713, | |
| "grad_norm": 0.2240833193063736, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.384, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013700585129156558, | |
| "grad_norm": 0.3342019319534302, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.4452, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015984015984015984, | |
| "grad_norm": 0.24696463346481323, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.4171, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01826744683887541, | |
| "grad_norm": 0.19478027522563934, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5231, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020550877693734836, | |
| "grad_norm": 0.24609534442424774, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.596, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02283430854859426, | |
| "grad_norm": 0.28049376606941223, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7177, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02511773940345369, | |
| "grad_norm": 0.29955780506134033, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7868, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027401170258313116, | |
| "grad_norm": 0.36411595344543457, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.9749, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029684601113172542, | |
| "grad_norm": 0.18460534512996674, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.4207, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03196803196803197, | |
| "grad_norm": 0.17489702999591827, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2473, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0342514628228914, | |
| "grad_norm": 0.21636372804641724, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3951, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03653489367775082, | |
| "grad_norm": 0.17221340537071228, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3723, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03881832453261025, | |
| "grad_norm": 0.19175592064857483, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4137, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04110175538746967, | |
| "grad_norm": 0.14810311794281006, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4384, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0433851862423291, | |
| "grad_norm": 0.15883894264698029, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4779, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04566861709718852, | |
| "grad_norm": 0.16838154196739197, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5587, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04795204795204795, | |
| "grad_norm": 0.19557560980319977, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5752, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05023547880690738, | |
| "grad_norm": 0.21928991377353668, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6232, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.052518909661766804, | |
| "grad_norm": 0.2531813383102417, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6836, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05480234051662623, | |
| "grad_norm": 0.3150889277458191, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8324, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.057085771371485655, | |
| "grad_norm": 0.46165594458580017, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0094, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.057085771371485655, | |
| "eval_loss": 0.4723083972930908, | |
| "eval_runtime": 199.7961, | |
| "eval_samples_per_second": 14.77, | |
| "eval_steps_per_second": 1.847, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.059369202226345084, | |
| "grad_norm": 0.11321822553873062, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2331, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06165263308120451, | |
| "grad_norm": 0.12643055617809296, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2789, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06393606393606394, | |
| "grad_norm": 0.12930473685264587, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2976, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06621949479092336, | |
| "grad_norm": 0.16039571166038513, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4174, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0685029256457828, | |
| "grad_norm": 0.16308578848838806, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4616, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07078635650064222, | |
| "grad_norm": 0.1640356034040451, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.459, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07306978735550164, | |
| "grad_norm": 0.18700158596038818, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5077, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07535321821036106, | |
| "grad_norm": 0.17209619283676147, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3712, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0776366490652205, | |
| "grad_norm": 0.21681387722492218, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6435, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07992007992007992, | |
| "grad_norm": 0.23583181202411652, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5585, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08220351077493934, | |
| "grad_norm": 0.2708075940608978, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7303, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08448694162979878, | |
| "grad_norm": 0.3559795916080475, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9089, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0867703724846582, | |
| "grad_norm": 0.13110557198524475, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3621, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08905380333951762, | |
| "grad_norm": 0.10051524639129639, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.281, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09133723419437705, | |
| "grad_norm": 0.1045868918299675, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3734, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09362066504923648, | |
| "grad_norm": 0.11752200871706009, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3841, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0959040959040959, | |
| "grad_norm": 0.1255699247121811, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4339, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09818752675895533, | |
| "grad_norm": 0.12778422236442566, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4218, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10047095761381476, | |
| "grad_norm": 0.1273931860923767, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3851, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10275438846867418, | |
| "grad_norm": 0.15921363234519958, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5618, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10503781932353361, | |
| "grad_norm": 0.1663666069507599, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5424, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10732125017839303, | |
| "grad_norm": 0.18781325221061707, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6158, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10960468103325247, | |
| "grad_norm": 0.23529550433158875, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7798, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11188811188811189, | |
| "grad_norm": 0.3098900020122528, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.8341, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11417154274297131, | |
| "grad_norm": 0.43187907338142395, | |
| "learning_rate": 0.0, | |
| "loss": 0.9767, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11417154274297131, | |
| "eval_loss": 0.4647972583770752, | |
| "eval_runtime": 199.7736, | |
| "eval_samples_per_second": 14.772, | |
| "eval_steps_per_second": 1.847, | |
| "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 | |
| } | |