| { | |
| "best_metric": 10.649374961853027, | |
| "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": 73.66545867919922, | |
| "learning_rate": 5e-05, | |
| "loss": 176.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018695956999298902, | |
| "eval_loss": 11.092499732971191, | |
| "eval_runtime": 0.5745, | |
| "eval_samples_per_second": 87.033, | |
| "eval_steps_per_second": 22.629, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037391913998597805, | |
| "grad_norm": 73.80960845947266, | |
| "learning_rate": 0.0001, | |
| "loss": 176.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00560878709978967, | |
| "grad_norm": 72.41312408447266, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 175.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007478382799719561, | |
| "grad_norm": 66.03401947021484, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 177.8203, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00934797849964945, | |
| "grad_norm": 71.24486541748047, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 178.0078, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01121757419957934, | |
| "grad_norm": 69.8907699584961, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 178.0391, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013087169899509232, | |
| "grad_norm": 73.62095642089844, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 177.5391, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014956765599439122, | |
| "grad_norm": 69.16584777832031, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 177.125, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01682636129936901, | |
| "grad_norm": 68.54964447021484, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 177.0703, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0186959569992989, | |
| "grad_norm": 69.1641845703125, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 176.7969, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02056555269922879, | |
| "grad_norm": 68.9474105834961, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 176.3359, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02243514839915868, | |
| "grad_norm": 70.42924499511719, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 175.5, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.024304744099088574, | |
| "grad_norm": 42.161109924316406, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 174.6172, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.026174339799018464, | |
| "grad_norm": 67.16651153564453, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 173.9219, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.028043935498948354, | |
| "grad_norm": 66.53196716308594, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 173.5938, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029913531198878244, | |
| "grad_norm": 42.15870666503906, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 173.8281, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.031783126898808134, | |
| "grad_norm": 65.30661010742188, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 174.6016, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03365272259873802, | |
| "grad_norm": 65.66240692138672, | |
| "learning_rate": 7.75e-05, | |
| "loss": 174.0625, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.035522318298667914, | |
| "grad_norm": 64.63104248046875, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 174.0078, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0373919139985978, | |
| "grad_norm": 64.6134262084961, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 173.5859, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.039261509698527694, | |
| "grad_norm": 63.236629486083984, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 173.3672, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04113110539845758, | |
| "grad_norm": 63.01491165161133, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 172.9531, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.043000701098387474, | |
| "grad_norm": 61.668235778808594, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 172.7969, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04487029679831736, | |
| "grad_norm": 61.27495193481445, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 172.6484, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.046739892498247254, | |
| "grad_norm": 58.57524871826172, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 172.1953, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.046739892498247254, | |
| "eval_loss": 10.758125305175781, | |
| "eval_runtime": 0.0853, | |
| "eval_samples_per_second": 586.422, | |
| "eval_steps_per_second": 152.47, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04860948819817715, | |
| "grad_norm": 63.860252380371094, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 172.4219, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.050479083898107034, | |
| "grad_norm": 63.61211013793945, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 172.3281, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05234867959803693, | |
| "grad_norm": 62.87015151977539, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 172.125, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.054218275297966814, | |
| "grad_norm": 54.35555648803711, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 171.8021, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05608787099789671, | |
| "grad_norm": 55.90229415893555, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 171.6797, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.057957466697826594, | |
| "grad_norm": 53.78763961791992, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 171.4062, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05982706239775649, | |
| "grad_norm": 52.55021286010742, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 171.2891, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.061696658097686374, | |
| "grad_norm": 51.70108413696289, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 171.125, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06356625379761627, | |
| "grad_norm": 51.2154655456543, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 171.0859, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06543584949754616, | |
| "grad_norm": 49.51068115234375, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 170.6875, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06730544519747604, | |
| "grad_norm": 48.02348327636719, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 170.6172, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06917504089740593, | |
| "grad_norm": 52.98481750488281, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 170.8828, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07104463659733583, | |
| "grad_norm": 36.483245849609375, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 171.2031, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07291423229726572, | |
| "grad_norm": 55.7339973449707, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 171.7656, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0747838279971956, | |
| "grad_norm": 54.79682540893555, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 171.75, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0766534236971255, | |
| "grad_norm": 35.19290542602539, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 171.0078, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07852301939705539, | |
| "grad_norm": 43.35811233520508, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 170.1641, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08039261509698528, | |
| "grad_norm": 43.71001052856445, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 170.2266, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08226221079691516, | |
| "grad_norm": 45.270477294921875, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 170.3828, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08413180649684505, | |
| "grad_norm": 47.626712799072266, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 170.4922, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08600140219677495, | |
| "grad_norm": 44.49309539794922, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 170.2969, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08787099789670484, | |
| "grad_norm": 43.53394317626953, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 170.1562, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08974059359663472, | |
| "grad_norm": 43.8607177734375, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 170.1562, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09161018929656461, | |
| "grad_norm": 41.6094970703125, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 169.9922, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09347978499649451, | |
| "grad_norm": 43.91381072998047, | |
| "learning_rate": 1e-05, | |
| "loss": 170.2109, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09347978499649451, | |
| "eval_loss": 10.649374961853027, | |
| "eval_runtime": 0.0851, | |
| "eval_samples_per_second": 587.469, | |
| "eval_steps_per_second": 152.742, | |
| "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 | |
| } | |