| { | |
| "best_metric": 11.756505966186523, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2518891687657431, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005037783375314861, | |
| "grad_norm": 0.11665327101945877, | |
| "learning_rate": 4e-05, | |
| "loss": 11.7818, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005037783375314861, | |
| "eval_loss": 11.777442932128906, | |
| "eval_runtime": 1.3844, | |
| "eval_samples_per_second": 60.678, | |
| "eval_steps_per_second": 30.339, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010075566750629723, | |
| "grad_norm": 0.09411647170782089, | |
| "learning_rate": 8e-05, | |
| "loss": 11.7749, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015113350125944584, | |
| "grad_norm": 0.11491205543279648, | |
| "learning_rate": 0.00012, | |
| "loss": 11.7791, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020151133501259445, | |
| "grad_norm": 0.10814717411994934, | |
| "learning_rate": 0.00016, | |
| "loss": 11.7724, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02518891687657431, | |
| "grad_norm": 0.09395021945238113, | |
| "learning_rate": 0.0002, | |
| "loss": 11.7741, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.030226700251889168, | |
| "grad_norm": 0.08854291588068008, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 11.7739, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03526448362720403, | |
| "grad_norm": 0.09998143464326859, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 11.7719, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04030226700251889, | |
| "grad_norm": 0.1092071384191513, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 11.7766, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04534005037783375, | |
| "grad_norm": 0.13437338173389435, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 11.7695, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05037783375314862, | |
| "grad_norm": 0.10191803425550461, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 11.7726, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.055415617128463476, | |
| "grad_norm": 0.13112697005271912, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 11.7715, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.060453400503778336, | |
| "grad_norm": 0.1708078533411026, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 11.765, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0654911838790932, | |
| "grad_norm": 0.14378079771995544, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 11.7693, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07052896725440806, | |
| "grad_norm": 0.11845815926790237, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 11.754, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07556675062972293, | |
| "grad_norm": 0.13851119577884674, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 11.7614, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08060453400503778, | |
| "grad_norm": 0.14140120148658752, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 11.7656, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08564231738035265, | |
| "grad_norm": 0.21620717644691467, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 11.7735, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0906801007556675, | |
| "grad_norm": 0.2548966407775879, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 11.775, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09571788413098237, | |
| "grad_norm": 0.2564621865749359, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 11.7763, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10075566750629723, | |
| "grad_norm": 0.24637818336486816, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 11.7768, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10579345088161209, | |
| "grad_norm": 0.20252592861652374, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 11.7709, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11083123425692695, | |
| "grad_norm": 0.1991090625524521, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 11.77, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11586901763224182, | |
| "grad_norm": 0.19447946548461914, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 11.7763, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12090680100755667, | |
| "grad_norm": 0.31570008397102356, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 11.7832, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12594458438287154, | |
| "grad_norm": 0.26807549595832825, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 11.781, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1309823677581864, | |
| "grad_norm": 0.20723332464694977, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 11.7613, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13602015113350127, | |
| "grad_norm": 0.16287362575531006, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 11.7537, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14105793450881612, | |
| "grad_norm": 0.19770941138267517, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 11.7782, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14609571788413098, | |
| "grad_norm": 0.20761863887310028, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 11.758, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.15113350125944586, | |
| "grad_norm": 0.25872254371643066, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 11.7536, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1561712846347607, | |
| "grad_norm": 0.3000946342945099, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 11.7583, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.16120906801007556, | |
| "grad_norm": 0.2385156750679016, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 11.7501, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.16624685138539042, | |
| "grad_norm": 0.2373785525560379, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 11.7478, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1712846347607053, | |
| "grad_norm": 0.5123424530029297, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 11.788, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.17632241813602015, | |
| "grad_norm": 0.4221782386302948, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 11.7738, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.181360201511335, | |
| "grad_norm": 0.3816068768501282, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 11.771, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.18639798488664988, | |
| "grad_norm": 0.34051746129989624, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 11.7577, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.19143576826196473, | |
| "grad_norm": 0.2573257386684418, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 11.7447, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1964735516372796, | |
| "grad_norm": 0.5065600275993347, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 11.7931, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.20151133501259447, | |
| "grad_norm": 0.48842620849609375, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 11.7782, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20654911838790932, | |
| "grad_norm": 0.5999230742454529, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 11.7796, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.21158690176322417, | |
| "grad_norm": 0.5456677079200745, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 11.7846, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.21662468513853905, | |
| "grad_norm": 0.544049859046936, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 11.7765, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2216624685138539, | |
| "grad_norm": 0.4290430545806885, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 11.7786, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.22670025188916876, | |
| "grad_norm": 0.624894380569458, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 11.7792, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23173803526448364, | |
| "grad_norm": 0.6616364121437073, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 11.7779, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2367758186397985, | |
| "grad_norm": 0.6500002145767212, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 11.7756, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.24181360201511334, | |
| "grad_norm": 0.7946918606758118, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 11.7614, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.24685138539042822, | |
| "grad_norm": 0.7269666790962219, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 11.7358, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2518891687657431, | |
| "grad_norm": 0.14651153981685638, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 11.7679, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2518891687657431, | |
| "eval_loss": 11.756505966186523, | |
| "eval_runtime": 1.3815, | |
| "eval_samples_per_second": 60.803, | |
| "eval_steps_per_second": 30.401, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 20370004377600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |