| { | |
| "best_metric": 0.9218409657478333, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.624512099921936, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01249024199843872, | |
| "grad_norm": 4.690826892852783, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1234, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01249024199843872, | |
| "eval_loss": 5.620558261871338, | |
| "eval_runtime": 3.8428, | |
| "eval_samples_per_second": 13.011, | |
| "eval_steps_per_second": 3.383, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02498048399687744, | |
| "grad_norm": 5.722167491912842, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7107, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03747072599531616, | |
| "grad_norm": 5.577714443206787, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.8318, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04996096799375488, | |
| "grad_norm": 5.402304172515869, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.4357, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0624512099921936, | |
| "grad_norm": 5.725224494934082, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.9605, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07494145199063232, | |
| "grad_norm": 4.146466255187988, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2876, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08743169398907104, | |
| "grad_norm": 3.2101497650146484, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.1256, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09992193598750976, | |
| "grad_norm": 3.6687138080596924, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.9117, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11241217798594848, | |
| "grad_norm": 3.7865750789642334, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.7385, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1249024199843872, | |
| "grad_norm": 3.5925636291503906, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.5617, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13739266198282593, | |
| "grad_norm": 3.28287410736084, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.5269, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14988290398126464, | |
| "grad_norm": 4.296369552612305, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.5197, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16237314597970337, | |
| "grad_norm": 5.540219783782959, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.7307, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.17486338797814208, | |
| "grad_norm": 5.277021408081055, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.5492, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1873536299765808, | |
| "grad_norm": 2.781581163406372, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.1706, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19984387197501952, | |
| "grad_norm": 2.5811822414398193, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.2165, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.21233411397345825, | |
| "grad_norm": 1.8358145952224731, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.0696, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.22482435597189696, | |
| "grad_norm": 1.5274910926818848, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.9806, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2373145979703357, | |
| "grad_norm": 1.465651035308838, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.134, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2498048399687744, | |
| "grad_norm": 1.4855949878692627, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.9989, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 1.3240143060684204, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.9781, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.27478532396565186, | |
| "grad_norm": 1.5368101596832275, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.9662, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.28727556596409054, | |
| "grad_norm": 1.6269676685333252, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.9193, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2997658079625293, | |
| "grad_norm": 2.395573616027832, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.0187, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.312256049960968, | |
| "grad_norm": 3.4702703952789307, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.0253, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.312256049960968, | |
| "eval_loss": 1.0936610698699951, | |
| "eval_runtime": 3.4692, | |
| "eval_samples_per_second": 14.412, | |
| "eval_steps_per_second": 3.747, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32474629195940674, | |
| "grad_norm": 1.5570573806762695, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.1832, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3372365339578454, | |
| "grad_norm": 1.3983771800994873, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.044, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.34972677595628415, | |
| "grad_norm": 1.282069444656372, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.0703, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3622170179547229, | |
| "grad_norm": 1.3308384418487549, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.0034, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3747072599531616, | |
| "grad_norm": 1.311693787574768, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.9713, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3871975019516003, | |
| "grad_norm": 1.3370124101638794, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.9209, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.39968774395003903, | |
| "grad_norm": 1.313528299331665, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.8721, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.41217798594847777, | |
| "grad_norm": 1.3581171035766602, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.8682, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4246682279469165, | |
| "grad_norm": 1.265177845954895, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.8279, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4371584699453552, | |
| "grad_norm": 1.4047905206680298, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.9059, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4496487119437939, | |
| "grad_norm": 1.6240432262420654, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.9126, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.46213895394223264, | |
| "grad_norm": 1.7853037118911743, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.8382, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4746291959406714, | |
| "grad_norm": 1.212027907371521, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.047, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.48711943793911006, | |
| "grad_norm": 1.175856113433838, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.9885, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4996096799375488, | |
| "grad_norm": 1.1697721481323242, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.9376, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5120999219359875, | |
| "grad_norm": 1.0764572620391846, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.921, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 1.1662276983261108, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.8766, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.537080405932865, | |
| "grad_norm": 1.0305904150009155, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.823, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5495706479313037, | |
| "grad_norm": 1.1411957740783691, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.8284, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5620608899297423, | |
| "grad_norm": 1.1754179000854492, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.8136, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5745511319281811, | |
| "grad_norm": 1.0738892555236816, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.7073, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5870413739266198, | |
| "grad_norm": 1.1244994401931763, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.7384, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5995316159250585, | |
| "grad_norm": 1.3134185075759888, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.8129, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6120218579234973, | |
| "grad_norm": 1.5741225481033325, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.7561, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.624512099921936, | |
| "grad_norm": 1.8192217350006104, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8404, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.624512099921936, | |
| "eval_loss": 0.9218409657478333, | |
| "eval_runtime": 3.4665, | |
| "eval_samples_per_second": 14.424, | |
| "eval_steps_per_second": 3.75, | |
| "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 | |
| } | |