| { | |
| "best_metric": 0.160928413271904, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.048667721133957904, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000973354422679158, | |
| "grad_norm": 9.625638008117676, | |
| "learning_rate": 5e-05, | |
| "loss": 5.5684, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000973354422679158, | |
| "eval_loss": 6.539275646209717, | |
| "eval_runtime": 62.869, | |
| "eval_samples_per_second": 110.086, | |
| "eval_steps_per_second": 13.775, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001946708845358316, | |
| "grad_norm": 9.678377151489258, | |
| "learning_rate": 0.0001, | |
| "loss": 5.5684, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0029200632680374742, | |
| "grad_norm": 8.975667953491211, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.4059, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003893417690716632, | |
| "grad_norm": 10.13470458984375, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.861, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00486677211339579, | |
| "grad_norm": 11.194205284118652, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.2056, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0058401265360749485, | |
| "grad_norm": 11.002691268920898, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.4972, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006813480958754107, | |
| "grad_norm": 5.943538188934326, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.9091, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007786835381433264, | |
| "grad_norm": 5.13279914855957, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3804, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008760189804112422, | |
| "grad_norm": 5.182049751281738, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.8848, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00973354422679158, | |
| "grad_norm": 4.752784729003906, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4053, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010706898649470739, | |
| "grad_norm": 6.532019138336182, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.5355, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011680253072149897, | |
| "grad_norm": 6.032060623168945, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2536, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012653607494829055, | |
| "grad_norm": 5.628830909729004, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7092, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.013626961917508213, | |
| "grad_norm": 4.3675689697265625, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4724, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01460031634018737, | |
| "grad_norm": 2.804490089416504, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3723, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015573670762866528, | |
| "grad_norm": 4.587884426116943, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2718, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.016547025185545686, | |
| "grad_norm": 3.3521015644073486, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1409, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.017520379608224845, | |
| "grad_norm": 1.9110612869262695, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0426, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.018493734030904003, | |
| "grad_norm": 0.3547068238258362, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0101, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01946708845358316, | |
| "grad_norm": 0.1654203236103058, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0037, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02044044287626232, | |
| "grad_norm": 0.06659155339002609, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0013, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.021413797298941478, | |
| "grad_norm": 0.028775788843631744, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0006, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.022387151721620636, | |
| "grad_norm": 4.46445894241333, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3989, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.023360506144299794, | |
| "grad_norm": 18.907028198242188, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.7332, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.024333860566978952, | |
| "grad_norm": 14.680952072143555, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.3845, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.024333860566978952, | |
| "eval_loss": 0.23052285611629486, | |
| "eval_runtime": 63.1828, | |
| "eval_samples_per_second": 109.539, | |
| "eval_steps_per_second": 13.706, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02530721498965811, | |
| "grad_norm": 0.10166118294000626, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0027, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02628056941233727, | |
| "grad_norm": 0.193026602268219, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0059, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.027253923835016427, | |
| "grad_norm": 0.27356114983558655, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.009, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.028227278257695585, | |
| "grad_norm": 0.3083343505859375, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0108, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02920063268037474, | |
| "grad_norm": 0.2875608503818512, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0106, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030173987103053898, | |
| "grad_norm": 0.24416722357273102, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0095, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.031147341525733056, | |
| "grad_norm": 0.193377286195755, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0079, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.032120695948412215, | |
| "grad_norm": 0.14682887494564056, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0063, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03309405037109137, | |
| "grad_norm": 0.11604669690132141, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0052, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03406740479377053, | |
| "grad_norm": 0.09484685212373734, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0043, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03504075921644969, | |
| "grad_norm": 5.945147514343262, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.9259, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03601411363912885, | |
| "grad_norm": 5.888754367828369, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9055, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.036987468061808006, | |
| "grad_norm": 1.4646563529968262, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2314, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.037960822484487164, | |
| "grad_norm": 0.12405002862215042, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0059, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03893417690716632, | |
| "grad_norm": 0.14476650953292847, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03990753132984548, | |
| "grad_norm": 0.16240093111991882, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0078, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04088088575252464, | |
| "grad_norm": 0.17413407564163208, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0084, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0418542401752038, | |
| "grad_norm": 0.18335355818271637, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0089, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.042827594597882955, | |
| "grad_norm": 0.18472228944301605, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.009, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04380094902056211, | |
| "grad_norm": 0.1897263079881668, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0092, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04477430344324127, | |
| "grad_norm": 0.1893337368965149, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0091, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04574765786592043, | |
| "grad_norm": 0.18881848454475403, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0091, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04672101228859959, | |
| "grad_norm": 1.1086373329162598, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1602, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.047694366711278746, | |
| "grad_norm": 5.398890972137451, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6574, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.048667721133957904, | |
| "grad_norm": 5.379086017608643, | |
| "learning_rate": 0.0, | |
| "loss": 0.6569, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.048667721133957904, | |
| "eval_loss": 0.160928413271904, | |
| "eval_runtime": 62.7866, | |
| "eval_samples_per_second": 110.231, | |
| "eval_steps_per_second": 13.793, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |