| { | |
| "best_metric": 0.433734267950058, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.010473397570171765, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020946795140343527, | |
| "grad_norm": 0.917009174823761, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6351, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020946795140343527, | |
| "eval_loss": 0.6633584499359131, | |
| "eval_runtime": 873.7203, | |
| "eval_samples_per_second": 9.203, | |
| "eval_steps_per_second": 1.151, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041893590280687055, | |
| "grad_norm": 0.9085473418235779, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6153, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006284038542103058, | |
| "grad_norm": 0.7783277630805969, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6699, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008378718056137411, | |
| "grad_norm": 0.9857844114303589, | |
| "learning_rate": 8e-05, | |
| "loss": 0.5443, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010473397570171764, | |
| "grad_norm": 1.1681126356124878, | |
| "learning_rate": 0.0001, | |
| "loss": 0.62, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012568077084206116, | |
| "grad_norm": 0.7421430945396423, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.5698, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001466275659824047, | |
| "grad_norm": 0.5105298161506653, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.4427, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016757436112274822, | |
| "grad_norm": 0.4216899871826172, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.5019, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018852115626309175, | |
| "grad_norm": 0.5698935985565186, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.7641, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0020946795140343527, | |
| "grad_norm": 0.3788565397262573, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.4966, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002304147465437788, | |
| "grad_norm": 0.3969597816467285, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.508, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0025136154168412233, | |
| "grad_norm": 0.40076708793640137, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.4528, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0027230833682446586, | |
| "grad_norm": 0.40270793437957764, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.4994, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002932551319648094, | |
| "grad_norm": 0.3916158378124237, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.514, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003142019271051529, | |
| "grad_norm": 0.4107060134410858, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.4643, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033514872224549644, | |
| "grad_norm": 0.36159345507621765, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.3534, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0035609551738583997, | |
| "grad_norm": 0.37514373660087585, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.3619, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003770423125261835, | |
| "grad_norm": 0.36177560687065125, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.4452, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003979891076665271, | |
| "grad_norm": 0.3693528175354004, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.4224, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0041893590280687055, | |
| "grad_norm": 0.3881819546222687, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4429, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004398826979472141, | |
| "grad_norm": 0.38602975010871887, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.5013, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004608294930875576, | |
| "grad_norm": 0.3345378041267395, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.3523, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004817762882279012, | |
| "grad_norm": 0.3664139211177826, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.4543, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005027230833682447, | |
| "grad_norm": 0.35118475556373596, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.3659, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005236698785085882, | |
| "grad_norm": 0.3777211010456085, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.4518, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005236698785085882, | |
| "eval_loss": 0.45177578926086426, | |
| "eval_runtime": 878.8268, | |
| "eval_samples_per_second": 9.15, | |
| "eval_steps_per_second": 1.145, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005446166736489317, | |
| "grad_norm": 0.433027982711792, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.432, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005655634687892753, | |
| "grad_norm": 0.6095757484436035, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.4492, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005865102639296188, | |
| "grad_norm": 0.35056862235069275, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.4748, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006074570590699623, | |
| "grad_norm": 0.40742507576942444, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.4191, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006284038542103058, | |
| "grad_norm": 0.3521018624305725, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.4234, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006493506493506494, | |
| "grad_norm": 0.37851810455322266, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.445, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006702974444909929, | |
| "grad_norm": 0.32674071192741394, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.3601, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0069124423963133645, | |
| "grad_norm": 0.32310712337493896, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.3583, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.007121910347716799, | |
| "grad_norm": 0.3961349129676819, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.4433, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007331378299120235, | |
| "grad_norm": 0.33904099464416504, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3749, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00754084625052367, | |
| "grad_norm": 0.3657974898815155, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.4653, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007750314201927106, | |
| "grad_norm": 0.37978294491767883, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.4818, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007959782153330541, | |
| "grad_norm": 0.43654364347457886, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.4463, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.008169250104733976, | |
| "grad_norm": 0.3577118515968323, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.414, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.008378718056137411, | |
| "grad_norm": 0.3934151828289032, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.5138, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008588186007540846, | |
| "grad_norm": 0.3723115026950836, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.4938, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.008797653958944282, | |
| "grad_norm": 0.37193042039871216, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.459, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.009007121910347717, | |
| "grad_norm": 0.43767815828323364, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.606, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009216589861751152, | |
| "grad_norm": 0.4332287013530731, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.5161, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009426057813154587, | |
| "grad_norm": 0.36227110028266907, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.4897, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009635525764558023, | |
| "grad_norm": 0.42358869314193726, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.5444, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.009844993715961458, | |
| "grad_norm": 0.36963951587677, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.4438, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.010054461667364893, | |
| "grad_norm": 0.40725886821746826, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.4948, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.010263929618768328, | |
| "grad_norm": 0.407678484916687, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.4942, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.010473397570171765, | |
| "grad_norm": 0.5885221362113953, | |
| "learning_rate": 0.0, | |
| "loss": 0.597, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010473397570171765, | |
| "eval_loss": 0.433734267950058, | |
| "eval_runtime": 878.5022, | |
| "eval_samples_per_second": 9.153, | |
| "eval_steps_per_second": 1.145, | |
| "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": 5, | |
| "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": 8.39543112597504e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |