| { | |
| "best_metric": 1.2211970090866089, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07923145488759037, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015846290977518075, | |
| "grad_norm": 3.19248104095459, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6582, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015846290977518075, | |
| "eval_loss": 2.480543613433838, | |
| "eval_runtime": 86.9858, | |
| "eval_samples_per_second": 48.882, | |
| "eval_steps_per_second": 6.116, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003169258195503615, | |
| "grad_norm": 3.7163660526275635, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8843, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004753887293255423, | |
| "grad_norm": 3.3315393924713135, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.8817, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00633851639100723, | |
| "grad_norm": 1.9999974966049194, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.5509, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007923145488759038, | |
| "grad_norm": 1.619550347328186, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.4816, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009507774586510845, | |
| "grad_norm": 1.4740045070648193, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.5248, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011092403684262652, | |
| "grad_norm": 1.5236130952835083, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.5319, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01267703278201446, | |
| "grad_norm": 1.3448103666305542, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4529, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014261661879766267, | |
| "grad_norm": 1.2267500162124634, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.437, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015846290977518076, | |
| "grad_norm": 1.337751030921936, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3067, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017430920075269883, | |
| "grad_norm": 1.5498002767562866, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.5566, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01901554917302169, | |
| "grad_norm": 1.593153476715088, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4297, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020600178270773498, | |
| "grad_norm": 1.0519171953201294, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.209, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.022184807368525305, | |
| "grad_norm": 0.9687233567237854, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1539, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.023769436466277112, | |
| "grad_norm": 0.971585214138031, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2927, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02535406556402892, | |
| "grad_norm": 0.9708733558654785, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.3581, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.026938694661780727, | |
| "grad_norm": 0.9558900594711304, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3051, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028523323759532534, | |
| "grad_norm": 0.9811197519302368, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4076, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03010795285728434, | |
| "grad_norm": 1.0043089389801025, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.2776, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03169258195503615, | |
| "grad_norm": 1.0165150165557861, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3444, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.033277211052787956, | |
| "grad_norm": 1.0422500371932983, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4593, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.034861840150539766, | |
| "grad_norm": 1.104314923286438, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3518, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03644646924829157, | |
| "grad_norm": 1.1625736951828003, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.3296, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03803109834604338, | |
| "grad_norm": 1.3231720924377441, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3023, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.039615727443795185, | |
| "grad_norm": 1.5862479209899902, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.3948, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.039615727443795185, | |
| "eval_loss": 1.244596004486084, | |
| "eval_runtime": 86.2833, | |
| "eval_samples_per_second": 49.28, | |
| "eval_steps_per_second": 6.166, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.041200356541546995, | |
| "grad_norm": 0.69757080078125, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1166, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0427849856392988, | |
| "grad_norm": 0.7477506399154663, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.1383, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04436961473705061, | |
| "grad_norm": 0.8282836675643921, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3684, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.045954243834802413, | |
| "grad_norm": 0.7872549891471863, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.2038, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.047538872932554224, | |
| "grad_norm": 0.848495602607727, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.2335, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.049123502030306035, | |
| "grad_norm": 0.8855195045471191, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.2782, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05070813112805784, | |
| "grad_norm": 0.9403620362281799, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3107, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05229276022580965, | |
| "grad_norm": 0.9452459812164307, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2787, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05387738932356145, | |
| "grad_norm": 1.062166452407837, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3067, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.055462018421313264, | |
| "grad_norm": 1.1450388431549072, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.3326, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05704664751906507, | |
| "grad_norm": 1.1706715822219849, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.3093, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05863127661681688, | |
| "grad_norm": 1.3499324321746826, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.4092, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06021590571456868, | |
| "grad_norm": 0.7645833492279053, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1249, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06180053481232049, | |
| "grad_norm": 0.7073479294776917, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.2296, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0633851639100723, | |
| "grad_norm": 0.7113702893257141, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.1356, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0649697930078241, | |
| "grad_norm": 0.7894446849822998, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.2843, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06655442210557591, | |
| "grad_norm": 0.767471432685852, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.1519, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06813905120332772, | |
| "grad_norm": 0.9337680339813232, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.3667, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06972368030107953, | |
| "grad_norm": 0.8977687358856201, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2943, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07130830939883133, | |
| "grad_norm": 0.8998286128044128, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.171, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07289293849658314, | |
| "grad_norm": 0.9295518398284912, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.1533, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07447756759433495, | |
| "grad_norm": 1.0339083671569824, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3036, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07606219669208676, | |
| "grad_norm": 1.183160424232483, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.3415, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.07764682578983857, | |
| "grad_norm": 1.2279109954833984, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.2925, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07923145488759037, | |
| "grad_norm": 1.5355768203735352, | |
| "learning_rate": 0.0, | |
| "loss": 1.2531, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07923145488759037, | |
| "eval_loss": 1.2211970090866089, | |
| "eval_runtime": 86.1186, | |
| "eval_samples_per_second": 49.374, | |
| "eval_steps_per_second": 6.178, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |