{ "best_metric": 1.7017016410827637, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.069856793573175, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0013971358714634998, "grad_norm": 0.6773235201835632, "learning_rate": 0.0001, "loss": 1.8541, "step": 1 }, { "epoch": 0.0013971358714634998, "eval_loss": 2.437103509902954, "eval_runtime": 94.4959, "eval_samples_per_second": 3.196, "eval_steps_per_second": 1.598, "step": 1 }, { "epoch": 0.0027942717429269995, "grad_norm": 0.8164823651313782, "learning_rate": 0.0002, "loss": 2.0925, "step": 2 }, { "epoch": 0.0041914076143905, "grad_norm": 0.893460214138031, "learning_rate": 0.00019978589232386035, "loss": 1.9269, "step": 3 }, { "epoch": 0.005588543485853999, "grad_norm": 1.0951659679412842, "learning_rate": 0.00019914448613738106, "loss": 1.9705, "step": 4 }, { "epoch": 0.006985679357317499, "grad_norm": 0.690770149230957, "learning_rate": 0.00019807852804032305, "loss": 2.108, "step": 5 }, { "epoch": 0.008382815228781, "grad_norm": 0.7501918077468872, "learning_rate": 0.00019659258262890683, "loss": 1.6891, "step": 6 }, { "epoch": 0.009779951100244499, "grad_norm": 0.7339282035827637, "learning_rate": 0.0001946930129495106, "loss": 1.7287, "step": 7 }, { "epoch": 0.011177086971707998, "grad_norm": 0.7356044054031372, "learning_rate": 0.0001923879532511287, "loss": 1.704, "step": 8 }, { "epoch": 0.012574222843171499, "grad_norm": 0.7521883249282837, "learning_rate": 0.00018968727415326884, "loss": 1.9468, "step": 9 }, { "epoch": 0.013971358714634998, "grad_norm": 0.628012478351593, "learning_rate": 0.00018660254037844388, "loss": 1.5462, "step": 10 }, { "epoch": 0.015368494586098498, "grad_norm": 0.7118824124336243, "learning_rate": 0.00018314696123025454, "loss": 1.8561, "step": 11 }, { "epoch": 0.016765630457562, "grad_norm": 0.6984536647796631, "learning_rate": 0.00017933533402912354, "loss": 1.8444, "step": 12 }, { "epoch": 0.018162766329025498, "grad_norm": 0.7371782660484314, "learning_rate": 0.00017518398074789775, "loss": 1.8548, "step": 13 }, { "epoch": 0.019559902200488997, "grad_norm": 0.737273633480072, "learning_rate": 0.00017071067811865476, "loss": 1.7329, "step": 14 }, { "epoch": 0.020957038071952497, "grad_norm": 0.7812173962593079, "learning_rate": 0.00016593458151000688, "loss": 1.8888, "step": 15 }, { "epoch": 0.022354173943415996, "grad_norm": 1.094999074935913, "learning_rate": 0.00016087614290087208, "loss": 2.1278, "step": 16 }, { "epoch": 0.023751309814879495, "grad_norm": 0.9387333989143372, "learning_rate": 0.00015555702330196023, "loss": 2.1146, "step": 17 }, { "epoch": 0.025148445686342998, "grad_norm": 0.924557626247406, "learning_rate": 0.00015000000000000001, "loss": 1.9719, "step": 18 }, { "epoch": 0.026545581557806498, "grad_norm": 0.8792619705200195, "learning_rate": 0.00014422886902190014, "loss": 1.9341, "step": 19 }, { "epoch": 0.027942717429269997, "grad_norm": 0.7050760388374329, "learning_rate": 0.000138268343236509, "loss": 1.7321, "step": 20 }, { "epoch": 0.029339853300733496, "grad_norm": 0.9437889456748962, "learning_rate": 0.00013214394653031616, "loss": 1.6508, "step": 21 }, { "epoch": 0.030736989172196996, "grad_norm": 0.6894789338111877, "learning_rate": 0.00012588190451025207, "loss": 1.4325, "step": 22 }, { "epoch": 0.0321341250436605, "grad_norm": 0.8473041653633118, "learning_rate": 0.00011950903220161285, "loss": 1.6303, "step": 23 }, { "epoch": 0.033531260915124, "grad_norm": 1.1612331867218018, "learning_rate": 0.00011305261922200519, "loss": 2.124, "step": 24 }, { "epoch": 0.0349283967865875, "grad_norm": 1.0456833839416504, "learning_rate": 0.00010654031292301432, "loss": 2.0162, "step": 25 }, { "epoch": 0.0349283967865875, "eval_loss": 1.7710518836975098, "eval_runtime": 96.1396, "eval_samples_per_second": 3.141, "eval_steps_per_second": 1.571, "step": 25 }, { "epoch": 0.036325532658050996, "grad_norm": 1.1468117237091064, "learning_rate": 0.0001, "loss": 2.0482, "step": 26 }, { "epoch": 0.037722668529514496, "grad_norm": 0.8366401791572571, "learning_rate": 9.345968707698569e-05, "loss": 1.6346, "step": 27 }, { "epoch": 0.039119804400977995, "grad_norm": 0.7719747424125671, "learning_rate": 8.694738077799488e-05, "loss": 1.5849, "step": 28 }, { "epoch": 0.040516940272441494, "grad_norm": 0.9361782670021057, "learning_rate": 8.049096779838719e-05, "loss": 1.8551, "step": 29 }, { "epoch": 0.041914076143904994, "grad_norm": 1.128204345703125, "learning_rate": 7.411809548974792e-05, "loss": 1.9648, "step": 30 }, { "epoch": 0.04331121201536849, "grad_norm": 1.0024124383926392, "learning_rate": 6.785605346968386e-05, "loss": 1.8017, "step": 31 }, { "epoch": 0.04470834788683199, "grad_norm": 0.9835119843482971, "learning_rate": 6.173165676349103e-05, "loss": 1.7692, "step": 32 }, { "epoch": 0.04610548375829549, "grad_norm": 1.0458788871765137, "learning_rate": 5.577113097809989e-05, "loss": 1.456, "step": 33 }, { "epoch": 0.04750261962975899, "grad_norm": 1.029359221458435, "learning_rate": 5.000000000000002e-05, "loss": 2.1277, "step": 34 }, { "epoch": 0.0488997555012225, "grad_norm": 0.8961425423622131, "learning_rate": 4.444297669803981e-05, "loss": 1.6894, "step": 35 }, { "epoch": 0.050296891372685996, "grad_norm": 0.9357238411903381, "learning_rate": 3.9123857099127936e-05, "loss": 1.6413, "step": 36 }, { "epoch": 0.051694027244149496, "grad_norm": 0.9889127612113953, "learning_rate": 3.406541848999312e-05, "loss": 1.7025, "step": 37 }, { "epoch": 0.053091163115612995, "grad_norm": 0.9021267890930176, "learning_rate": 2.9289321881345254e-05, "loss": 1.3933, "step": 38 }, { "epoch": 0.054488298987076494, "grad_norm": 1.259774088859558, "learning_rate": 2.4816019252102273e-05, "loss": 1.6318, "step": 39 }, { "epoch": 0.055885434858539994, "grad_norm": 0.9996725916862488, "learning_rate": 2.0664665970876496e-05, "loss": 1.6355, "step": 40 }, { "epoch": 0.05728257073000349, "grad_norm": 1.31227707862854, "learning_rate": 1.6853038769745467e-05, "loss": 1.8715, "step": 41 }, { "epoch": 0.05867970660146699, "grad_norm": 1.266066312789917, "learning_rate": 1.339745962155613e-05, "loss": 2.0598, "step": 42 }, { "epoch": 0.06007684247293049, "grad_norm": 1.1719212532043457, "learning_rate": 1.0312725846731175e-05, "loss": 2.1243, "step": 43 }, { "epoch": 0.06147397834439399, "grad_norm": 1.2561590671539307, "learning_rate": 7.612046748871327e-06, "loss": 1.7084, "step": 44 }, { "epoch": 0.06287111421585749, "grad_norm": 1.4959790706634521, "learning_rate": 5.306987050489442e-06, "loss": 1.8423, "step": 45 }, { "epoch": 0.064268250087321, "grad_norm": 1.5612496137619019, "learning_rate": 3.40741737109318e-06, "loss": 1.8425, "step": 46 }, { "epoch": 0.06566538595878449, "grad_norm": 1.473332166671753, "learning_rate": 1.921471959676957e-06, "loss": 1.5454, "step": 47 }, { "epoch": 0.067062521830248, "grad_norm": 1.9833347797393799, "learning_rate": 8.555138626189618e-07, "loss": 2.099, "step": 48 }, { "epoch": 0.06845965770171149, "grad_norm": 1.5466455221176147, "learning_rate": 2.141076761396521e-07, "loss": 1.6702, "step": 49 }, { "epoch": 0.069856793573175, "grad_norm": 1.9173717498779297, "learning_rate": 0.0, "loss": 1.8048, "step": 50 }, { "epoch": 0.069856793573175, "eval_loss": 1.7017016410827637, "eval_runtime": 96.2516, "eval_samples_per_second": 3.138, "eval_steps_per_second": 1.569, "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": 6.99038693326848e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }