| { | |
| "best_metric": 3.298891544342041, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.21119324181626187, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004223864836325237, | |
| "grad_norm": 1.4468297958374023, | |
| "learning_rate": 1e-05, | |
| "loss": 2.4216, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004223864836325237, | |
| "eval_loss": 3.413026809692383, | |
| "eval_runtime": 15.4813, | |
| "eval_samples_per_second": 12.919, | |
| "eval_steps_per_second": 3.23, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008447729672650475, | |
| "grad_norm": 1.4951223134994507, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4719, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012671594508975714, | |
| "grad_norm": 1.378113031387329, | |
| "learning_rate": 3e-05, | |
| "loss": 2.4266, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01689545934530095, | |
| "grad_norm": 1.3803629875183105, | |
| "learning_rate": 4e-05, | |
| "loss": 2.4242, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021119324181626188, | |
| "grad_norm": 1.3718631267547607, | |
| "learning_rate": 5e-05, | |
| "loss": 2.429, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.025343189017951427, | |
| "grad_norm": 1.218284010887146, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4887, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.029567053854276663, | |
| "grad_norm": 1.161075234413147, | |
| "learning_rate": 7e-05, | |
| "loss": 2.4304, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0337909186906019, | |
| "grad_norm": 1.3160911798477173, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3349, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03801478352692714, | |
| "grad_norm": 1.6408723592758179, | |
| "learning_rate": 9e-05, | |
| "loss": 2.3673, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.042238648363252376, | |
| "grad_norm": 1.8385587930679321, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2662, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.046462513199577615, | |
| "grad_norm": 1.25449800491333, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 2.223, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.050686378035902854, | |
| "grad_norm": 1.3850810527801514, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.2053, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.054910242872228086, | |
| "grad_norm": 1.521848440170288, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 2.14, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.059134107708553325, | |
| "grad_norm": 0.7431579828262329, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.0468, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06335797254487856, | |
| "grad_norm": 1.3225431442260742, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.0101, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0675818373812038, | |
| "grad_norm": 1.1983656883239746, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.0347, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07180570221752904, | |
| "grad_norm": 0.9302838444709778, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 2.0708, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07602956705385427, | |
| "grad_norm": 1.3141449689865112, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.0202, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08025343189017951, | |
| "grad_norm": 2.162736654281616, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.08, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08447729672650475, | |
| "grad_norm": 1.8238545656204224, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.0146, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08870116156282999, | |
| "grad_norm": 2.3217670917510986, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.029, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09292502639915523, | |
| "grad_norm": 1.7219942808151245, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.0183, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09714889123548047, | |
| "grad_norm": 1.9738433361053467, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.9807, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10137275607180571, | |
| "grad_norm": 1.6816790103912354, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.8833, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10559662090813093, | |
| "grad_norm": 2.078090190887451, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.9582, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10982048574445617, | |
| "grad_norm": 2.3857650756835938, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.8632, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11404435058078141, | |
| "grad_norm": 1.9374221563339233, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 1.9176, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11826821541710665, | |
| "grad_norm": 3.010812282562256, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.9108, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12249208025343189, | |
| "grad_norm": 3.265596628189087, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 1.7971, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12671594508975711, | |
| "grad_norm": 1.8755942583084106, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.823, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13093980992608237, | |
| "grad_norm": 2.2471399307250977, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 1.7691, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1351636747624076, | |
| "grad_norm": 2.2615737915039062, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.9749, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.13938753959873285, | |
| "grad_norm": 2.1230502128601074, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 1.6917, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.14361140443505807, | |
| "grad_norm": 2.2565455436706543, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.737, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14783526927138332, | |
| "grad_norm": 2.0613744258880615, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.7182, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15205913410770855, | |
| "grad_norm": 1.7652757167816162, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.8768, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1562829989440338, | |
| "grad_norm": 1.8088558912277222, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.872, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16050686378035903, | |
| "grad_norm": 1.8547643423080444, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.8, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.16473072861668428, | |
| "grad_norm": 3.2694742679595947, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 2.0919, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1689545934530095, | |
| "grad_norm": 3.890437126159668, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.1158, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17317845828933473, | |
| "grad_norm": 3.148890256881714, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 1.9941, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.17740232312565998, | |
| "grad_norm": 2.840927839279175, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.5792, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1816261879619852, | |
| "grad_norm": 3.339871406555176, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 1.7262, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.18585005279831046, | |
| "grad_norm": 3.198982000350952, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.675, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1900739176346357, | |
| "grad_norm": 3.2554752826690674, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.4044, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19429778247096094, | |
| "grad_norm": 2.540999412536621, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.554, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.19852164730728616, | |
| "grad_norm": 2.6020541191101074, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 1.3886, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.20274551214361142, | |
| "grad_norm": 3.0984528064727783, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.6801, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.20696937697993664, | |
| "grad_norm": 2.8602421283721924, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 1.3767, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.21119324181626187, | |
| "grad_norm": 4.274623870849609, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.359, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21119324181626187, | |
| "eval_loss": 3.298891544342041, | |
| "eval_runtime": 15.8578, | |
| "eval_samples_per_second": 12.612, | |
| "eval_steps_per_second": 3.153, | |
| "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": 5, | |
| "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": 1.6463460040704e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |