| { | |
| "best_metric": 9.99334716796875, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0539419087136928, | |
| "eval_steps": 25, | |
| "global_step": 46, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06639004149377593, | |
| "grad_norm": 2.6923758409220096e+17, | |
| "learning_rate": 5e-05, | |
| "loss": 10.8601, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06639004149377593, | |
| "eval_loss": 10.024558067321777, | |
| "eval_runtime": 2.215, | |
| "eval_samples_per_second": 46.049, | |
| "eval_steps_per_second": 5.869, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13278008298755187, | |
| "grad_norm": 18146476032.0, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4551, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1991701244813278, | |
| "grad_norm": 324049403904.0, | |
| "learning_rate": 9.987260573051269e-05, | |
| "loss": 10.0263, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.26556016597510373, | |
| "grad_norm": 48950799237120.0, | |
| "learning_rate": 9.949107209404665e-05, | |
| "loss": 10.713, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.33195020746887965, | |
| "grad_norm": 13251226107904.0, | |
| "learning_rate": 9.885734329855798e-05, | |
| "loss": 10.821, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3983402489626556, | |
| "grad_norm": 3825862912.0, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 10.5627, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.46473029045643155, | |
| "grad_norm": 923726912.0, | |
| "learning_rate": 9.68474862499881e-05, | |
| "loss": 10.1706, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5311203319502075, | |
| "grad_norm": 796135673298944.0, | |
| "learning_rate": 9.548159976772592e-05, | |
| "loss": 10.4989, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5975103734439834, | |
| "grad_norm": 671497781248.0, | |
| "learning_rate": 9.388394947836279e-05, | |
| "loss": 10.7, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6639004149377593, | |
| "grad_norm": 775149824.0, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 10.1482, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7302904564315352, | |
| "grad_norm": 158336992.0, | |
| "learning_rate": 9.002706204621803e-05, | |
| "loss": 9.7413, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7966804979253111, | |
| "grad_norm": 4.104369360506716e+17, | |
| "learning_rate": 8.778747871771292e-05, | |
| "loss": 10.6833, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8630705394190872, | |
| "grad_norm": 495561113600.0, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.4311, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9294605809128631, | |
| "grad_norm": 357131392.0, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 10.1106, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.995850622406639, | |
| "grad_norm": 334526880.0, | |
| "learning_rate": 7.996388332556735e-05, | |
| "loss": 9.7855, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.062240663900415, | |
| "grad_norm": 104541106208768.0, | |
| "learning_rate": 7.703204087277988e-05, | |
| "loss": 20.1683, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.1286307053941909, | |
| "grad_norm": 6918611456.0, | |
| "learning_rate": 7.396244933600285e-05, | |
| "loss": 10.3514, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1950207468879668, | |
| "grad_norm": 736682816.0, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 9.9971, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.2614107883817427, | |
| "grad_norm": 1.0172717013663744e+16, | |
| "learning_rate": 6.747320897995493e-05, | |
| "loss": 10.124, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.3278008298755186, | |
| "grad_norm": 24326621184.0, | |
| "learning_rate": 6.408662784207149e-05, | |
| "loss": 10.6098, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3941908713692945, | |
| "grad_norm": 1798468992.0, | |
| "learning_rate": 6.062826447764883e-05, | |
| "loss": 10.2548, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.4605809128630705, | |
| "grad_norm": 59435092.0, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 9.6954, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.5269709543568464, | |
| "grad_norm": Infinity, | |
| "learning_rate": 5.3566959159961615e-05, | |
| "loss": 10.1026, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5933609958506225, | |
| "grad_norm": 1125310221254656.0, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3186, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.6597510373443982, | |
| "grad_norm": 100705856.0, | |
| "learning_rate": 4.643304084003839e-05, | |
| "loss": 10.0387, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6597510373443982, | |
| "eval_loss": 9.99334716796875, | |
| "eval_runtime": 2.2129, | |
| "eval_samples_per_second": 46.093, | |
| "eval_steps_per_second": 5.875, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7261410788381744, | |
| "grad_norm": 9312404.0, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 9.8302, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.79253112033195, | |
| "grad_norm": 1229930496000.0, | |
| "learning_rate": 3.937173552235117e-05, | |
| "loss": 10.3458, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.8589211618257262, | |
| "grad_norm": 39236595712.0, | |
| "learning_rate": 3.591337215792852e-05, | |
| "loss": 10.2447, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.9253112033195021, | |
| "grad_norm": 7421381120.0, | |
| "learning_rate": 3.2526791020045086e-05, | |
| "loss": 10.1415, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.991701244813278, | |
| "grad_norm": 57041700.0, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 9.8004, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0580912863070537, | |
| "grad_norm": 3407954575360.0, | |
| "learning_rate": 2.603755066399718e-05, | |
| "loss": 20.4544, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.12448132780083, | |
| "grad_norm": 2498396928.0, | |
| "learning_rate": 2.296795912722014e-05, | |
| "loss": 10.1161, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.190871369294606, | |
| "grad_norm": 738044672.0, | |
| "learning_rate": 2.0036116674432654e-05, | |
| "loss": 10.0431, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.2572614107883817, | |
| "grad_norm": 8632801049968640.0, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 9.9673, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.323651452282158, | |
| "grad_norm": 222836080640.0, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3291, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.3900414937759336, | |
| "grad_norm": 264477792.0, | |
| "learning_rate": 1.2212521282287092e-05, | |
| "loss": 10.2066, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.4564315352697097, | |
| "grad_norm": 187083776.0, | |
| "learning_rate": 9.972937953781986e-06, | |
| "loss": 10.1565, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.5228215767634854, | |
| "grad_norm": 22868152811520.0, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 10.3219, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.5892116182572615, | |
| "grad_norm": 43378626560.0, | |
| "learning_rate": 6.116050521637218e-06, | |
| "loss": 10.4927, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.6556016597510372, | |
| "grad_norm": 13558889472.0, | |
| "learning_rate": 4.5184002322740785e-06, | |
| "loss": 9.9935, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.7219917012448134, | |
| "grad_norm": 194045920.0, | |
| "learning_rate": 3.1525137500119207e-06, | |
| "loss": 9.6793, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.788381742738589, | |
| "grad_norm": 1.1480066189112115e+17, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 10.429, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.854771784232365, | |
| "grad_norm": 744684257280.0, | |
| "learning_rate": 1.1426567014420297e-06, | |
| "loss": 10.2057, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.921161825726141, | |
| "grad_norm": 233727787008.0, | |
| "learning_rate": 5.089279059533658e-07, | |
| "loss": 10.2095, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.987551867219917, | |
| "grad_norm": 51029136.0, | |
| "learning_rate": 1.2739426948732424e-07, | |
| "loss": 9.6324, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.0539419087136928, | |
| "grad_norm": 4598173196615680.0, | |
| "learning_rate": 0.0, | |
| "loss": 20.0993, | |
| "step": 46 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 46, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 2.7365945800812134e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |