| { | |
| "best_metric": 10.347929954528809, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6028636021100227, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012057272042200452, | |
| "grad_norm": 0.29372695088386536, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3802, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012057272042200452, | |
| "eval_loss": 10.380714416503906, | |
| "eval_runtime": 1.6845, | |
| "eval_samples_per_second": 331.845, | |
| "eval_steps_per_second": 41.555, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024114544084400905, | |
| "grad_norm": 0.29436203837394714, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3815, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03617181612660136, | |
| "grad_norm": 0.2924072742462158, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3808, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04822908816880181, | |
| "grad_norm": 0.29187890887260437, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3793, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06028636021100226, | |
| "grad_norm": 0.28935664892196655, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3794, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07234363225320271, | |
| "grad_norm": 0.29046961665153503, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.378, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08440090429540316, | |
| "grad_norm": 0.29813316464424133, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3756, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09645817633760362, | |
| "grad_norm": 0.30296024680137634, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3749, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10851544837980406, | |
| "grad_norm": 0.3060512840747833, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3743, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12057272042200452, | |
| "grad_norm": 0.3108205199241638, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.373, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13262999246420498, | |
| "grad_norm": 0.3159935474395752, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.372, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14468726450640543, | |
| "grad_norm": 0.3171635568141937, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3688, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.15674453654860587, | |
| "grad_norm": 0.3182453513145447, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3699, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.16880180859080632, | |
| "grad_norm": 0.3205792307853699, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3683, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1808590806330068, | |
| "grad_norm": 0.3250167965888977, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3673, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19291635267520724, | |
| "grad_norm": 0.33457398414611816, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.367, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.20497362471740768, | |
| "grad_norm": 0.334460973739624, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3666, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.21703089675960813, | |
| "grad_norm": 0.33570876717567444, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3642, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2290881688018086, | |
| "grad_norm": 0.34196099638938904, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.363, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.24114544084400905, | |
| "grad_norm": 0.3495764136314392, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3616, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2532027128862095, | |
| "grad_norm": 0.35669052600860596, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3619, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.26525998492840996, | |
| "grad_norm": 0.3679502010345459, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3591, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2773172569706104, | |
| "grad_norm": 0.36417484283447266, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3582, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.28937452901281085, | |
| "grad_norm": 0.3735411465167999, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3577, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.30143180105501133, | |
| "grad_norm": 0.37289372086524963, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3567, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.30143180105501133, | |
| "eval_loss": 10.356481552124023, | |
| "eval_runtime": 1.6961, | |
| "eval_samples_per_second": 329.576, | |
| "eval_steps_per_second": 41.271, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31348907309721175, | |
| "grad_norm": 0.37799665331840515, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3576, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3255463451394122, | |
| "grad_norm": 0.3761814832687378, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3566, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.33760361718161264, | |
| "grad_norm": 0.38003864884376526, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3568, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3496608892238131, | |
| "grad_norm": 0.3890228867530823, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3543, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3617181612660136, | |
| "grad_norm": 0.38857603073120117, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3538, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.373775433308214, | |
| "grad_norm": 0.39215660095214844, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3541, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3858327053504145, | |
| "grad_norm": 0.4006653428077698, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3533, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.39788997739261495, | |
| "grad_norm": 0.3988947868347168, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3514, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.40994724943481536, | |
| "grad_norm": 0.4035243093967438, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3511, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.42200452147701584, | |
| "grad_norm": 0.39984676241874695, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3517, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.43406179351921625, | |
| "grad_norm": 0.40296873450279236, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3515, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4461190655614167, | |
| "grad_norm": 0.3979630470275879, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.35, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4581763376036172, | |
| "grad_norm": 0.39856386184692383, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3502, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4702336096458176, | |
| "grad_norm": 0.4138854146003723, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3502, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4822908816880181, | |
| "grad_norm": 0.4107336401939392, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3497, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.49434815373021856, | |
| "grad_norm": 0.4137466549873352, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3504, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.506405425772419, | |
| "grad_norm": 0.4083769619464874, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3496, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5184626978146194, | |
| "grad_norm": 0.4133431911468506, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3482, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5305199698568199, | |
| "grad_norm": 0.41160884499549866, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3485, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5425772418990203, | |
| "grad_norm": 0.4080004096031189, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3491, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5546345139412208, | |
| "grad_norm": 0.4072157144546509, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3493, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5666917859834213, | |
| "grad_norm": 0.41588732600212097, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3482, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5787490580256217, | |
| "grad_norm": 0.40861016511917114, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3485, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5908063300678221, | |
| "grad_norm": 0.4074612259864807, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.347, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6028636021100227, | |
| "grad_norm": 0.4056658446788788, | |
| "learning_rate": 0.0, | |
| "loss": 10.3471, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6028636021100227, | |
| "eval_loss": 10.347929954528809, | |
| "eval_runtime": 1.7039, | |
| "eval_samples_per_second": 328.078, | |
| "eval_steps_per_second": 41.083, | |
| "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": 66784998064128.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |