| { | |
| "best_metric": 11.016731262207031, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.10351966873706005, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002070393374741201, | |
| "grad_norm": 6.086023807525635, | |
| "learning_rate": 5e-05, | |
| "loss": 177.6369, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002070393374741201, | |
| "eval_loss": 11.103808403015137, | |
| "eval_runtime": 0.5591, | |
| "eval_samples_per_second": 89.431, | |
| "eval_steps_per_second": 23.252, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004140786749482402, | |
| "grad_norm": 4.320464134216309, | |
| "learning_rate": 0.0001, | |
| "loss": 177.827, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006211180124223602, | |
| "grad_norm": 3.7203009128570557, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 177.7243, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008281573498964804, | |
| "grad_norm": 3.6285226345062256, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 177.6228, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010351966873706004, | |
| "grad_norm": 3.561692237854004, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 177.7155, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012422360248447204, | |
| "grad_norm": 3.790656089782715, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 177.6258, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014492753623188406, | |
| "grad_norm": 3.853480339050293, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 177.5562, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016563146997929608, | |
| "grad_norm": 4.005135536193848, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 177.6082, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018633540372670808, | |
| "grad_norm": 4.643294334411621, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 177.568, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020703933747412008, | |
| "grad_norm": 5.119444370269775, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 177.4234, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022774327122153208, | |
| "grad_norm": 5.751838207244873, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 177.2939, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.024844720496894408, | |
| "grad_norm": 7.102801322937012, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 177.3568, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.026915113871635612, | |
| "grad_norm": 8.331995964050293, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 176.9811, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "grad_norm": 5.497199535369873, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 177.014, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.031055900621118012, | |
| "grad_norm": 4.23492956161499, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 177.209, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.033126293995859216, | |
| "grad_norm": 4.067819595336914, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 177.2137, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.035196687370600416, | |
| "grad_norm": 3.9193811416625977, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 177.1131, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.037267080745341616, | |
| "grad_norm": 3.8284318447113037, | |
| "learning_rate": 7.75e-05, | |
| "loss": 177.1983, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.039337474120082816, | |
| "grad_norm": 4.166711807250977, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 177.0419, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.041407867494824016, | |
| "grad_norm": 4.264215469360352, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 177.0668, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.043478260869565216, | |
| "grad_norm": 4.3174943923950195, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 177.1095, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.045548654244306416, | |
| "grad_norm": 5.148275375366211, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 177.0244, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 5.267536640167236, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 176.8738, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.049689440993788817, | |
| "grad_norm": 6.1932902336120605, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 176.6368, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.051759834368530024, | |
| "grad_norm": 8.919533729553223, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 176.5659, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.051759834368530024, | |
| "eval_loss": 11.04233169555664, | |
| "eval_runtime": 0.0849, | |
| "eval_samples_per_second": 588.797, | |
| "eval_steps_per_second": 153.087, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.053830227743271224, | |
| "grad_norm": 6.590371608734131, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 176.4769, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.055900621118012424, | |
| "grad_norm": 4.6611480712890625, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 176.7507, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.057971014492753624, | |
| "grad_norm": 4.020076274871826, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 176.7667, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.060041407867494824, | |
| "grad_norm": 4.015106678009033, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 176.8385, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.062111801242236024, | |
| "grad_norm": 3.977048873901367, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 176.9064, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06418219461697723, | |
| "grad_norm": 3.951341152191162, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 176.7282, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06625258799171843, | |
| "grad_norm": 4.043701648712158, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 176.7812, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06832298136645963, | |
| "grad_norm": 4.244744300842285, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 176.6306, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07039337474120083, | |
| "grad_norm": 4.570371627807617, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 176.5429, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07246376811594203, | |
| "grad_norm": 4.860273361206055, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 176.557, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07453416149068323, | |
| "grad_norm": 5.925064563751221, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 176.2983, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07660455486542443, | |
| "grad_norm": 6.933615207672119, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 176.0812, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07867494824016563, | |
| "grad_norm": 7.716263294219971, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 175.6745, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08074534161490683, | |
| "grad_norm": 6.395534992218018, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 176.2174, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08281573498964803, | |
| "grad_norm": 4.4871673583984375, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 176.5033, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08488612836438923, | |
| "grad_norm": 4.042433738708496, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 176.6441, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 4.071824073791504, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 176.6377, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08902691511387163, | |
| "grad_norm": 4.026284217834473, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 176.613, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09109730848861283, | |
| "grad_norm": 4.184352874755859, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 176.524, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09316770186335403, | |
| "grad_norm": 4.085234642028809, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 176.5405, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 4.481105804443359, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 176.4587, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09730848861283643, | |
| "grad_norm": 4.551030158996582, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 176.3409, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09937888198757763, | |
| "grad_norm": 5.4851813316345215, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 176.1347, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10144927536231885, | |
| "grad_norm": 5.989502906799316, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 176.0228, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10351966873706005, | |
| "grad_norm": 9.128138542175293, | |
| "learning_rate": 1e-05, | |
| "loss": 175.3216, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10351966873706005, | |
| "eval_loss": 11.016731262207031, | |
| "eval_runtime": 0.0781, | |
| "eval_samples_per_second": 640.344, | |
| "eval_steps_per_second": 166.489, | |
| "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": 38111123865600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |