| { | |
| "best_metric": 10.90896224975586, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.2734499205087442, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.025437201907790145, | |
| "grad_norm": 17.424699783325195, | |
| "learning_rate": 5e-05, | |
| "loss": 177.3172, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025437201907790145, | |
| "eval_loss": 11.081862449645996, | |
| "eval_runtime": 0.7927, | |
| "eval_samples_per_second": 334.307, | |
| "eval_steps_per_second": 42.892, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05087440381558029, | |
| "grad_norm": 18.484657287597656, | |
| "learning_rate": 0.0001, | |
| "loss": 177.3859, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07631160572337042, | |
| "grad_norm": 19.929227828979492, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 177.2063, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10174880763116058, | |
| "grad_norm": 18.820032119750977, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 177.2563, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1271860095389507, | |
| "grad_norm": 18.274093627929688, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 176.9297, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15262321144674085, | |
| "grad_norm": 19.563762664794922, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 176.8359, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.178060413354531, | |
| "grad_norm": 17.0075626373291, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 176.6438, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.20349761526232116, | |
| "grad_norm": 17.95867347717285, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 176.5922, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2289348171701113, | |
| "grad_norm": 17.614946365356445, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 176.4031, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2543720190779014, | |
| "grad_norm": 17.622127532958984, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 176.3594, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.27980922098569155, | |
| "grad_norm": 16.21497344970703, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 176.3015, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3052464228934817, | |
| "grad_norm": 16.24370765686035, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 176.1437, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.33068362480127184, | |
| "grad_norm": 15.409339904785156, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 176.05, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.356120826709062, | |
| "grad_norm": 15.61033821105957, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 175.9594, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3815580286168522, | |
| "grad_norm": 15.05919075012207, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 175.7938, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4069952305246423, | |
| "grad_norm": 15.350239753723145, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 175.6891, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 13.883095741271973, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 175.6719, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4578696343402226, | |
| "grad_norm": 14.999556541442871, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 175.5359, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.48330683624801274, | |
| "grad_norm": 13.84604549407959, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 175.5188, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5087440381558028, | |
| "grad_norm": 13.595047950744629, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 175.3969, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.534181240063593, | |
| "grad_norm": 14.166274070739746, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 175.1922, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5596184419713831, | |
| "grad_norm": 13.406230926513672, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 175.2406, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5850556438791733, | |
| "grad_norm": 14.314190864562988, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 175.0266, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6104928457869634, | |
| "grad_norm": 12.607808113098145, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 175.2156, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6359300476947536, | |
| "grad_norm": 13.26458740234375, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 174.8984, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6359300476947536, | |
| "eval_loss": 10.940447807312012, | |
| "eval_runtime": 0.7733, | |
| "eval_samples_per_second": 342.688, | |
| "eval_steps_per_second": 43.968, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6613672496025437, | |
| "grad_norm": 13.278068542480469, | |
| "learning_rate": 5e-05, | |
| "loss": 175.0375, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6868044515103339, | |
| "grad_norm": 12.864252090454102, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 174.925, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.712241653418124, | |
| "grad_norm": 13.144230842590332, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 174.7344, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7376788553259142, | |
| "grad_norm": 13.34295654296875, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 174.6859, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7631160572337043, | |
| "grad_norm": 12.916960716247559, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 174.8438, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7885532591414944, | |
| "grad_norm": 13.577077865600586, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 174.6344, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8139904610492846, | |
| "grad_norm": 12.431527137756348, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 174.5969, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8394276629570747, | |
| "grad_norm": 12.354952812194824, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 174.7516, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 12.568489074707031, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 174.8016, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.890302066772655, | |
| "grad_norm": 12.316400527954102, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 174.7937, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9157392686804452, | |
| "grad_norm": 13.003135681152344, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 174.4141, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 13.115909576416016, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 174.275, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9666136724960255, | |
| "grad_norm": 12.456389427185059, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 174.6125, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9920508744038156, | |
| "grad_norm": 12.58653736114502, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 174.5969, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.0190779014308426, | |
| "grad_norm": 12.444266319274902, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 174.6016, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0445151033386328, | |
| "grad_norm": 12.287275314331055, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 174.7563, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0699523052464228, | |
| "grad_norm": 12.920654296875, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 174.4234, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.095389507154213, | |
| "grad_norm": 12.601585388183594, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 174.4937, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1208267090620032, | |
| "grad_norm": 12.357393264770508, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 174.6625, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.1462639109697934, | |
| "grad_norm": 12.532998085021973, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 174.5516, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1717011128775834, | |
| "grad_norm": 12.560898780822754, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 174.425, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1971383147853736, | |
| "grad_norm": 12.610762596130371, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 174.3813, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.2225755166931638, | |
| "grad_norm": 12.676226615905762, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 174.6047, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.248012718600954, | |
| "grad_norm": 13.310853958129883, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 174.2234, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.2734499205087442, | |
| "grad_norm": 12.485175132751465, | |
| "learning_rate": 0.0, | |
| "loss": 174.6688, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2734499205087442, | |
| "eval_loss": 10.90896224975586, | |
| "eval_runtime": 0.7939, | |
| "eval_samples_per_second": 333.783, | |
| "eval_steps_per_second": 42.825, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 4202692608000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |