| { | |
| "best_metric": 1.1896018981933594, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", | |
| "epoch": 0.026203390718759007, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.240678143751801e-05, | |
| "eval_loss": 2.1741511821746826, | |
| "eval_runtime": 489.2013, | |
| "eval_samples_per_second": 16.425, | |
| "eval_steps_per_second": 4.107, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005240678143751802, | |
| "grad_norm": 2.150914192199707, | |
| "learning_rate": 4.08e-05, | |
| "loss": 1.3698, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010481356287503603, | |
| "grad_norm": 1.843773365020752, | |
| "learning_rate": 8.16e-05, | |
| "loss": 1.33, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015722034431255405, | |
| "grad_norm": 2.1218819618225098, | |
| "learning_rate": 0.0001224, | |
| "loss": 1.2321, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0020962712575007206, | |
| "grad_norm": 2.44899320602417, | |
| "learning_rate": 0.0001632, | |
| "loss": 1.2333, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002620339071875901, | |
| "grad_norm": 13.852787017822266, | |
| "learning_rate": 0.000204, | |
| "loss": 2.0712, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002620339071875901, | |
| "eval_loss": 1.7819404602050781, | |
| "eval_runtime": 489.242, | |
| "eval_samples_per_second": 16.423, | |
| "eval_steps_per_second": 4.106, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003144406886251081, | |
| "grad_norm": 1.8030827045440674, | |
| "learning_rate": 0.00020375153312650207, | |
| "loss": 1.3647, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.003668474700626261, | |
| "grad_norm": 1.8373987674713135, | |
| "learning_rate": 0.00020300734301164017, | |
| "loss": 1.1339, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.004192542515001441, | |
| "grad_norm": 1.8776074647903442, | |
| "learning_rate": 0.00020177105527484818, | |
| "loss": 1.1834, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.004716610329376621, | |
| "grad_norm": 2.3595855236053467, | |
| "learning_rate": 0.00020004869298570854, | |
| "loss": 1.2042, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.005240678143751802, | |
| "grad_norm": 11.033510208129883, | |
| "learning_rate": 0.00019784864732016265, | |
| "loss": 1.8743, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.005240678143751802, | |
| "eval_loss": 1.7514146566390991, | |
| "eval_runtime": 489.1456, | |
| "eval_samples_per_second": 16.427, | |
| "eval_steps_per_second": 4.107, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.005764745958126981, | |
| "grad_norm": 1.6452189683914185, | |
| "learning_rate": 0.00019518163667954527, | |
| "loss": 1.2991, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.006288813772502162, | |
| "grad_norm": 1.5686390399932861, | |
| "learning_rate": 0.00019206065447161056, | |
| "loss": 1.162, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.006812881586877342, | |
| "grad_norm": 1.821743369102478, | |
| "learning_rate": 0.00018850090580795544, | |
| "loss": 1.1572, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.007336949401252522, | |
| "grad_norm": 4.036351680755615, | |
| "learning_rate": 0.00018451973342624464, | |
| "loss": 1.2418, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.007861017215627703, | |
| "grad_norm": 12.068865776062012, | |
| "learning_rate": 0.00018013653319813575, | |
| "loss": 1.8739, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.007861017215627703, | |
| "eval_loss": 1.8119529485702515, | |
| "eval_runtime": 489.208, | |
| "eval_samples_per_second": 16.425, | |
| "eval_steps_per_second": 4.107, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.008385085030002883, | |
| "grad_norm": 1.7102468013763428, | |
| "learning_rate": 0.0001753726596345424, | |
| "loss": 1.3199, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.008909152844378062, | |
| "grad_norm": 1.9763778448104858, | |
| "learning_rate": 0.00017025132184860355, | |
| "loss": 1.2008, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.009433220658753242, | |
| "grad_norm": 1.650948405265808, | |
| "learning_rate": 0.00016479747048321714, | |
| "loss": 1.1192, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.009957288473128423, | |
| "grad_norm": 2.9453556537628174, | |
| "learning_rate": 0.00015903767615401616, | |
| "loss": 1.2746, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.010481356287503603, | |
| "grad_norm": 14.243999481201172, | |
| "learning_rate": 0.000153, | |
| "loss": 2.1821, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.010481356287503603, | |
| "eval_loss": 1.688521385192871, | |
| "eval_runtime": 488.6728, | |
| "eval_samples_per_second": 16.442, | |
| "eval_steps_per_second": 4.111, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.011005424101878783, | |
| "grad_norm": 1.8800654411315918, | |
| "learning_rate": 0.0001467138569724859, | |
| "loss": 1.328, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.011529491916253963, | |
| "grad_norm": 1.8253871202468872, | |
| "learning_rate": 0.00014020987252842305, | |
| "loss": 1.1803, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.012053559730629144, | |
| "grad_norm": 2.225597858428955, | |
| "learning_rate": 0.00013351973342624464, | |
| "loss": 1.1601, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.012577627545004324, | |
| "grad_norm": 2.5397775173187256, | |
| "learning_rate": 0.00012667603335116609, | |
| "loss": 1.227, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.013101695359379504, | |
| "grad_norm": 11.309868812561035, | |
| "learning_rate": 0.00011971211412202691, | |
| "loss": 1.7126, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.013101695359379504, | |
| "eval_loss": 1.499428391456604, | |
| "eval_runtime": 488.4857, | |
| "eval_samples_per_second": 16.449, | |
| "eval_steps_per_second": 4.113, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.013625763173754683, | |
| "grad_norm": 1.6462516784667969, | |
| "learning_rate": 0.00011266190325330066, | |
| "loss": 1.1976, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.014149830988129865, | |
| "grad_norm": 1.5284520387649536, | |
| "learning_rate": 0.00010555974866365511, | |
| "loss": 1.0957, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.014673898802505045, | |
| "grad_norm": 1.8043922185897827, | |
| "learning_rate": 9.844025133634492e-05, | |
| "loss": 1.0894, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.015197966616880224, | |
| "grad_norm": 2.4363131523132324, | |
| "learning_rate": 9.133809674669937e-05, | |
| "loss": 1.1335, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.015722034431255406, | |
| "grad_norm": 8.980298042297363, | |
| "learning_rate": 8.428788587797311e-05, | |
| "loss": 1.8793, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.015722034431255406, | |
| "eval_loss": 1.4283676147460938, | |
| "eval_runtime": 489.4252, | |
| "eval_samples_per_second": 16.417, | |
| "eval_steps_per_second": 4.105, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.016246102245630584, | |
| "grad_norm": 1.416838526725769, | |
| "learning_rate": 7.73239666488339e-05, | |
| "loss": 1.1683, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.016770170060005765, | |
| "grad_norm": 1.574950933456421, | |
| "learning_rate": 7.048026657375537e-05, | |
| "loss": 1.0502, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.017294237874380947, | |
| "grad_norm": 1.8394525051116943, | |
| "learning_rate": 6.379012747157697e-05, | |
| "loss": 1.0767, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.017818305688756125, | |
| "grad_norm": 2.86199688911438, | |
| "learning_rate": 5.7286143027514095e-05, | |
| "loss": 1.1481, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.018342373503131306, | |
| "grad_norm": 12.534944534301758, | |
| "learning_rate": 5.100000000000002e-05, | |
| "loss": 1.8794, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.018342373503131306, | |
| "eval_loss": 1.309641718864441, | |
| "eval_runtime": 490.402, | |
| "eval_samples_per_second": 16.385, | |
| "eval_steps_per_second": 4.097, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.018866441317506484, | |
| "grad_norm": 1.5316487550735474, | |
| "learning_rate": 4.496232384598384e-05, | |
| "loss": 1.1357, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.019390509131881666, | |
| "grad_norm": 1.5178347826004028, | |
| "learning_rate": 3.9202529516782854e-05, | |
| "loss": 1.0699, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.019914576946256847, | |
| "grad_norm": 2.074788808822632, | |
| "learning_rate": 3.374867815139649e-05, | |
| "loss": 1.0479, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.020438644760632025, | |
| "grad_norm": 2.566411256790161, | |
| "learning_rate": 2.8627340365457602e-05, | |
| "loss": 1.1419, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.020962712575007206, | |
| "grad_norm": 7.236230850219727, | |
| "learning_rate": 2.3863466801864254e-05, | |
| "loss": 1.6114, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.020962712575007206, | |
| "eval_loss": 1.215065360069275, | |
| "eval_runtime": 490.1796, | |
| "eval_samples_per_second": 16.392, | |
| "eval_steps_per_second": 4.098, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.021486780389382384, | |
| "grad_norm": 1.1142139434814453, | |
| "learning_rate": 1.9480266573755372e-05, | |
| "loss": 1.0362, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.022010848203757566, | |
| "grad_norm": 1.5296214818954468, | |
| "learning_rate": 1.5499094192044554e-05, | |
| "loss": 1.038, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.022534916018132747, | |
| "grad_norm": 1.5614051818847656, | |
| "learning_rate": 1.1939345528389446e-05, | |
| "loss": 1.0573, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.023058983832507925, | |
| "grad_norm": 2.5465171337127686, | |
| "learning_rate": 8.818363320454701e-06, | |
| "loss": 1.082, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.023583051646883107, | |
| "grad_norm": 12.415629386901855, | |
| "learning_rate": 6.1513526798373514e-06, | |
| "loss": 1.8403, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.023583051646883107, | |
| "eval_loss": 1.1930021047592163, | |
| "eval_runtime": 489.2822, | |
| "eval_samples_per_second": 16.422, | |
| "eval_steps_per_second": 4.106, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.02410711946125829, | |
| "grad_norm": 1.3619661331176758, | |
| "learning_rate": 3.9513070142914725e-06, | |
| "loss": 1.077, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.024631187275633466, | |
| "grad_norm": 1.5200282335281372, | |
| "learning_rate": 2.2289447251518195e-06, | |
| "loss": 1.0089, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.025155255090008648, | |
| "grad_norm": 1.4571294784545898, | |
| "learning_rate": 9.92656988359823e-07, | |
| "loss": 1.0334, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.025679322904383826, | |
| "grad_norm": 2.3840417861938477, | |
| "learning_rate": 2.4846687349793185e-07, | |
| "loss": 1.0615, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.026203390718759007, | |
| "grad_norm": 9.744729995727539, | |
| "learning_rate": 0.0, | |
| "loss": 1.8475, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.026203390718759007, | |
| "eval_loss": 1.1896018981933594, | |
| "eval_runtime": 488.1331, | |
| "eval_samples_per_second": 16.461, | |
| "eval_steps_per_second": 4.116, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 9.4282098671616e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |