| { | |
| "best_metric": 1.5799205303192139, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3252032520325203, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0065040650406504065, | |
| "grad_norm": 0.452924519777298, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6465, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0065040650406504065, | |
| "eval_loss": 1.9445749521255493, | |
| "eval_runtime": 38.5546, | |
| "eval_samples_per_second": 26.871, | |
| "eval_steps_per_second": 3.372, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013008130081300813, | |
| "grad_norm": 0.4472135603427887, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6244, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01951219512195122, | |
| "grad_norm": 0.4465356767177582, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.7331, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.026016260162601626, | |
| "grad_norm": 0.3531281054019928, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.562, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.032520325203252036, | |
| "grad_norm": 0.3484897017478943, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.5634, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03902439024390244, | |
| "grad_norm": 0.37977728247642517, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.5041, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04552845528455285, | |
| "grad_norm": 0.3207574784755707, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.5048, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05203252032520325, | |
| "grad_norm": 0.28961050510406494, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4995, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05853658536585366, | |
| "grad_norm": 0.29030150175094604, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.5662, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06504065040650407, | |
| "grad_norm": 0.32431498169898987, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5892, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07154471544715447, | |
| "grad_norm": 0.48661676049232483, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.4132, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07804878048780488, | |
| "grad_norm": 1.1666473150253296, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.302, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08455284552845528, | |
| "grad_norm": 0.5734682679176331, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5264, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0910569105691057, | |
| "grad_norm": 0.4539637267589569, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4126, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.3586958944797516, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.4338, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1040650406504065, | |
| "grad_norm": 0.32105886936187744, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.4378, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11056910569105691, | |
| "grad_norm": 0.26258349418640137, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3505, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11707317073170732, | |
| "grad_norm": 0.23742343485355377, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3453, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12357723577235773, | |
| "grad_norm": 0.24130068719387054, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.3356, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13008130081300814, | |
| "grad_norm": 0.23312045633792877, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3239, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13658536585365855, | |
| "grad_norm": 0.22841376066207886, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3797, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14308943089430895, | |
| "grad_norm": 0.26299354434013367, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.4505, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14959349593495935, | |
| "grad_norm": 0.3494158387184143, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5376, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15609756097560976, | |
| "grad_norm": 0.6514765024185181, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.0249, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16260162601626016, | |
| "grad_norm": 1.2873810529708862, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.2734, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16260162601626016, | |
| "eval_loss": 1.6350988149642944, | |
| "eval_runtime": 38.3759, | |
| "eval_samples_per_second": 26.996, | |
| "eval_steps_per_second": 3.388, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16910569105691056, | |
| "grad_norm": 0.28785306215286255, | |
| "learning_rate": 5e-05, | |
| "loss": 1.37, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.17560975609756097, | |
| "grad_norm": 0.26578181982040405, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.3331, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1821138211382114, | |
| "grad_norm": 0.26452162861824036, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3761, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1886178861788618, | |
| "grad_norm": 0.20922784507274628, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.3182, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.18566425144672394, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.2673, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2016260162601626, | |
| "grad_norm": 0.18694765865802765, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.2826, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.208130081300813, | |
| "grad_norm": 0.181863933801651, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2765, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2146341463414634, | |
| "grad_norm": 0.1935238540172577, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.295, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.22113821138211381, | |
| "grad_norm": 0.21044613420963287, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3621, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22764227642276422, | |
| "grad_norm": 0.2689436972141266, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4391, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23414634146341465, | |
| "grad_norm": 0.376651793718338, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.8876, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24065040650406505, | |
| "grad_norm": 1.4348276853561401, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.0286, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.24715447154471545, | |
| "grad_norm": 0.2289065718650818, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3651, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.25365853658536586, | |
| "grad_norm": 0.19455616176128387, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.2948, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2601626016260163, | |
| "grad_norm": 0.2245715707540512, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.3066, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.20435915887355804, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.3163, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2731707317073171, | |
| "grad_norm": 0.17328569293022156, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.2732, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.27967479674796747, | |
| "grad_norm": 0.1736893206834793, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2619, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2861788617886179, | |
| "grad_norm": 0.1751582771539688, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2683, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 0.17826324701309204, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.2849, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2991869918699187, | |
| "grad_norm": 0.18487432599067688, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.3155, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3056910569105691, | |
| "grad_norm": 0.22769266366958618, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3759, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3121951219512195, | |
| "grad_norm": 0.2902439534664154, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.5236, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.31869918699186994, | |
| "grad_norm": 1.0033760070800781, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.0646, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3252032520325203, | |
| "grad_norm": 1.7348500490188599, | |
| "learning_rate": 0.0, | |
| "loss": 2.9307, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3252032520325203, | |
| "eval_loss": 1.5799205303192139, | |
| "eval_runtime": 38.3497, | |
| "eval_samples_per_second": 27.015, | |
| "eval_steps_per_second": 3.39, | |
| "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": 1.3307911230560666e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |