| { | |
| "best_metric": 10.665624618530273, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09347978499649451, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018695956999298902, | |
| "grad_norm": 73.23991394042969, | |
| "learning_rate": 5e-05, | |
| "loss": 176.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018695956999298902, | |
| "eval_loss": 11.092499732971191, | |
| "eval_runtime": 0.3895, | |
| "eval_samples_per_second": 128.375, | |
| "eval_steps_per_second": 33.378, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037391913998597805, | |
| "grad_norm": 73.06200408935547, | |
| "learning_rate": 0.0001, | |
| "loss": 176.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00560878709978967, | |
| "grad_norm": 71.66292572021484, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 175.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007478382799719561, | |
| "grad_norm": 58.68143844604492, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 177.8203, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00934797849964945, | |
| "grad_norm": 63.55765151977539, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 178.0078, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01121757419957934, | |
| "grad_norm": 62.28239059448242, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 177.8906, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013087169899509232, | |
| "grad_norm": 64.41303253173828, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 177.2578, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014956765599439122, | |
| "grad_norm": 62.472679138183594, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 177.3281, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01682636129936901, | |
| "grad_norm": 61.45440673828125, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 177.1562, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0186959569992989, | |
| "grad_norm": 61.89149856567383, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 176.5625, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02056555269922879, | |
| "grad_norm": 61.69562911987305, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 176.2969, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02243514839915868, | |
| "grad_norm": 63.3868522644043, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 176.0703, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.024304744099088574, | |
| "grad_norm": 39.87636184692383, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 174.4688, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.026174339799018464, | |
| "grad_norm": 61.98240280151367, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 173.5156, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.028043935498948354, | |
| "grad_norm": 61.44512939453125, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 173.4375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029913531198878244, | |
| "grad_norm": 39.06581497192383, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 173.9974, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.031783126898808134, | |
| "grad_norm": 58.62794494628906, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 174.8438, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03365272259873802, | |
| "grad_norm": 59.17825698852539, | |
| "learning_rate": 7.75e-05, | |
| "loss": 174.2656, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.035522318298667914, | |
| "grad_norm": 57.81831741333008, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 174.2891, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0373919139985978, | |
| "grad_norm": 58.23281478881836, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 173.9062, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.039261509698527694, | |
| "grad_norm": 56.812381744384766, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 173.8594, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04113110539845758, | |
| "grad_norm": 56.91898727416992, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 173.5625, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.043000701098387474, | |
| "grad_norm": 55.818355560302734, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 173.0781, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04487029679831736, | |
| "grad_norm": 56.06446838378906, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 173.1016, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.046739892498247254, | |
| "grad_norm": 53.783058166503906, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 172.7891, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.046739892498247254, | |
| "eval_loss": 10.782500267028809, | |
| "eval_runtime": 0.0931, | |
| "eval_samples_per_second": 536.934, | |
| "eval_steps_per_second": 139.603, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04860948819817715, | |
| "grad_norm": 55.87623596191406, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 172.1094, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.050479083898107034, | |
| "grad_norm": 55.00972366333008, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 172.0312, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05234867959803693, | |
| "grad_norm": 54.83614730834961, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 172.0312, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.054218275297966814, | |
| "grad_norm": 51.00733184814453, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 172.3255, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05608787099789671, | |
| "grad_norm": 51.23164749145508, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 172.2266, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.057957466697826594, | |
| "grad_norm": 50.09794616699219, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 172.0781, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05982706239775649, | |
| "grad_norm": 48.56599807739258, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 171.6719, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.061696658097686374, | |
| "grad_norm": 47.9957389831543, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 171.5469, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06356625379761627, | |
| "grad_norm": 47.916259765625, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 171.5547, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06543584949754616, | |
| "grad_norm": 49.00302505493164, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 171.4844, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06730544519747604, | |
| "grad_norm": 45.9317741394043, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 171.2266, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06917504089740593, | |
| "grad_norm": 49.07448196411133, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 171.5078, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07104463659733583, | |
| "grad_norm": 33.96923065185547, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 171.5234, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07291423229726572, | |
| "grad_norm": 49.62445068359375, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 171.5938, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0747838279971956, | |
| "grad_norm": 49.21584701538086, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 171.5781, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0766534236971255, | |
| "grad_norm": 32.60105514526367, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 171.3047, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07852301939705539, | |
| "grad_norm": 43.163551330566406, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 170.6797, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08039261509698528, | |
| "grad_norm": 43.7245979309082, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 170.7578, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08226221079691516, | |
| "grad_norm": 44.37057876586914, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 170.7578, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08413180649684505, | |
| "grad_norm": 45.123897552490234, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 170.7969, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08600140219677495, | |
| "grad_norm": 43.98640060424805, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 170.6797, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08787099789670484, | |
| "grad_norm": 43.422054290771484, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 170.6328, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08974059359663472, | |
| "grad_norm": 42.80683135986328, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 170.4688, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09161018929656461, | |
| "grad_norm": 42.18162536621094, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 170.4375, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09347978499649451, | |
| "grad_norm": 43.21053695678711, | |
| "learning_rate": 1e-05, | |
| "loss": 170.5703, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09347978499649451, | |
| "eval_loss": 10.665624618530273, | |
| "eval_runtime": 0.1037, | |
| "eval_samples_per_second": 482.071, | |
| "eval_steps_per_second": 125.338, | |
| "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": 4202692608000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |