| { | |
| "best_metric": 1.1698991060256958, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6872852233676976, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013745704467353952, | |
| "grad_norm": 8.785038948059082, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7568, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013745704467353952, | |
| "eval_loss": 1.69869065284729, | |
| "eval_runtime": 10.6566, | |
| "eval_samples_per_second": 45.981, | |
| "eval_steps_per_second": 5.818, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027491408934707903, | |
| "grad_norm": 8.94119644165039, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5639, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": 9.636877059936523, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.6319, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.054982817869415807, | |
| "grad_norm": 8.029925346374512, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.4327, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06872852233676977, | |
| "grad_norm": 7.860167503356934, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.4608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 5.4412407875061035, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3567, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09621993127147767, | |
| "grad_norm": 5.89894962310791, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3971, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10996563573883161, | |
| "grad_norm": 5.186604022979736, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4175, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "grad_norm": 5.103099822998047, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.3878, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13745704467353953, | |
| "grad_norm": 5.33500337600708, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.369, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15120274914089346, | |
| "grad_norm": 6.5175461769104, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.421, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 6.966541767120361, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3992, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17869415807560138, | |
| "grad_norm": 8.68342399597168, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5289, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19243986254295534, | |
| "grad_norm": 9.655024528503418, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3686, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20618556701030927, | |
| "grad_norm": 6.294942378997803, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.1776, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21993127147766323, | |
| "grad_norm": 4.730772018432617, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.1616, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23367697594501718, | |
| "grad_norm": 4.466562271118164, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1928, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24742268041237114, | |
| "grad_norm": 4.346698760986328, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1748, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2611683848797251, | |
| "grad_norm": 3.3439648151397705, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1408, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.27491408934707906, | |
| "grad_norm": 3.6823015213012695, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2258, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28865979381443296, | |
| "grad_norm": 3.547337055206299, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2464, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3024054982817869, | |
| "grad_norm": 4.661966323852539, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2667, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3161512027491409, | |
| "grad_norm": 3.798068046569824, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.2766, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32989690721649484, | |
| "grad_norm": 5.671876907348633, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3518, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3436426116838488, | |
| "grad_norm": 8.123512268066406, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.3007, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3436426116838488, | |
| "eval_loss": 1.2220337390899658, | |
| "eval_runtime": 10.6468, | |
| "eval_samples_per_second": 46.023, | |
| "eval_steps_per_second": 5.823, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35738831615120276, | |
| "grad_norm": 5.381728649139404, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3701, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3711340206185567, | |
| "grad_norm": 6.220064640045166, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.2507, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3848797250859107, | |
| "grad_norm": 4.7269744873046875, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.179, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.39862542955326463, | |
| "grad_norm": 4.9649858474731445, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.1498, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 3.2343597412109375, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1384, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4261168384879725, | |
| "grad_norm": 3.9605014324188232, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1833, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.43986254295532645, | |
| "grad_norm": 3.200035810470581, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.169, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4536082474226804, | |
| "grad_norm": 2.95031476020813, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0898, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.46735395189003437, | |
| "grad_norm": 3.0987446308135986, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1105, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.48109965635738833, | |
| "grad_norm": 3.7635719776153564, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.2252, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4948453608247423, | |
| "grad_norm": 4.340725421905518, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1103, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5085910652920962, | |
| "grad_norm": 5.118636131286621, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1931, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5223367697594502, | |
| "grad_norm": 5.125694274902344, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4035, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5360824742268041, | |
| "grad_norm": 3.891624927520752, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.2566, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5498281786941581, | |
| "grad_norm": 3.4594714641571045, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.2246, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.563573883161512, | |
| "grad_norm": 2.602104425430298, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.0392, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5773195876288659, | |
| "grad_norm": 2.893939733505249, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9737, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5910652920962199, | |
| "grad_norm": 3.1298158168792725, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.1841, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6048109965635738, | |
| "grad_norm": 2.5724339485168457, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1307, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6185567010309279, | |
| "grad_norm": 2.649641990661621, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1849, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6323024054982818, | |
| "grad_norm": 3.0026814937591553, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.185, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6460481099656358, | |
| "grad_norm": 3.2685275077819824, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.164, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6597938144329897, | |
| "grad_norm": 4.725792407989502, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.2381, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6735395189003437, | |
| "grad_norm": 4.6360273361206055, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1273, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6872852233676976, | |
| "grad_norm": 8.433632850646973, | |
| "learning_rate": 0.0, | |
| "loss": 1.2185, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6872852233676976, | |
| "eval_loss": 1.1698991060256958, | |
| "eval_runtime": 10.6554, | |
| "eval_samples_per_second": 45.986, | |
| "eval_steps_per_second": 5.819, | |
| "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": 2.975488880578396e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |