| { | |
| "best_metric": 11.93070125579834, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04424044682851297, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008848089365702593, | |
| "grad_norm": 0.008699431084096432, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9314, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008848089365702593, | |
| "eval_loss": 11.93159008026123, | |
| "eval_runtime": 15.0354, | |
| "eval_samples_per_second": 506.404, | |
| "eval_steps_per_second": 63.317, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017696178731405187, | |
| "grad_norm": 0.010497311130166054, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9329, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002654426809710778, | |
| "grad_norm": 0.012735365889966488, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9317, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0035392357462810374, | |
| "grad_norm": 0.010852599516510963, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9312, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004424044682851297, | |
| "grad_norm": 0.012388749048113823, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9317, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005308853619421556, | |
| "grad_norm": 0.014882532879710197, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.9317, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006193662555991816, | |
| "grad_norm": 0.013572714291512966, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9319, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007078471492562075, | |
| "grad_norm": 0.01670651137828827, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9317, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007963280429132333, | |
| "grad_norm": 0.01918655075132847, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9294, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008848089365702593, | |
| "grad_norm": 0.01989833265542984, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9313, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009732898302272853, | |
| "grad_norm": 0.025229739025235176, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9321, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010617707238843112, | |
| "grad_norm": 0.03575052320957184, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9317, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011502516175413372, | |
| "grad_norm": 0.012016350403428078, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9318, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012387325111983632, | |
| "grad_norm": 0.00892651453614235, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9314, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01327213404855389, | |
| "grad_norm": 0.009865213185548782, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9323, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01415694298512415, | |
| "grad_norm": 0.014640242792665958, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.932, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015041751921694409, | |
| "grad_norm": 0.015863046050071716, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9319, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015926560858264667, | |
| "grad_norm": 0.012915559113025665, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9316, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.016811369794834927, | |
| "grad_norm": 0.01370308082550764, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9328, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.017696178731405186, | |
| "grad_norm": 0.015240599401295185, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9315, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018580987667975446, | |
| "grad_norm": 0.01878294162452221, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9303, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019465796604545706, | |
| "grad_norm": 0.02252139337360859, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.931, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.020350605541115965, | |
| "grad_norm": 0.023968111723661423, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9304, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.021235414477686225, | |
| "grad_norm": 0.02715585008263588, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9302, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022120223414256485, | |
| "grad_norm": 0.058606501668691635, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9267, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022120223414256485, | |
| "eval_loss": 11.93093490600586, | |
| "eval_runtime": 15.1269, | |
| "eval_samples_per_second": 503.343, | |
| "eval_steps_per_second": 62.934, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023005032350826744, | |
| "grad_norm": 0.012165733613073826, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9318, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.023889841287397004, | |
| "grad_norm": 0.014179449528455734, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.9317, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.024774650223967264, | |
| "grad_norm": 0.012790637090802193, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9315, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02565945916053752, | |
| "grad_norm": 0.014043393544852734, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9309, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02654426809710778, | |
| "grad_norm": 0.015668494626879692, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9306, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02742907703367804, | |
| "grad_norm": 0.01923270709812641, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9311, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0283138859702483, | |
| "grad_norm": 0.015900423750281334, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9315, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02919869490681856, | |
| "grad_norm": 0.02023705281317234, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.9309, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.030083503843388818, | |
| "grad_norm": 0.02101036161184311, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.929, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.030968312779959078, | |
| "grad_norm": 0.026951618492603302, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.9296, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.031853121716529334, | |
| "grad_norm": 0.029996080324053764, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.9302, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.032737930653099594, | |
| "grad_norm": 0.03874776139855385, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.9289, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03362273958966985, | |
| "grad_norm": 0.018332069739699364, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9324, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03450754852624011, | |
| "grad_norm": 0.012665345333516598, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.9312, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03539235746281037, | |
| "grad_norm": 0.013432266190648079, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.93, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03627716639938063, | |
| "grad_norm": 0.014370406977832317, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.931, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03716197533595089, | |
| "grad_norm": 0.01412659976631403, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9325, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03804678427252115, | |
| "grad_norm": 0.01652354560792446, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9302, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03893159320909141, | |
| "grad_norm": 0.020123157650232315, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.931, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03981640214566167, | |
| "grad_norm": 0.01787555031478405, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9308, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04070121108223193, | |
| "grad_norm": 0.01903703808784485, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.9314, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04158602001880219, | |
| "grad_norm": 0.022099262103438377, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.9287, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04247082895537245, | |
| "grad_norm": 0.022947920486330986, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.9296, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04335563789194271, | |
| "grad_norm": 0.03329804167151451, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.9314, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04424044682851297, | |
| "grad_norm": 0.06478450447320938, | |
| "learning_rate": 0.0, | |
| "loss": 11.9282, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04424044682851297, | |
| "eval_loss": 11.93070125579834, | |
| "eval_runtime": 15.0267, | |
| "eval_samples_per_second": 506.698, | |
| "eval_steps_per_second": 63.354, | |
| "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": 1042494259200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |