| { | |
| "best_metric": 0.003693485399708152, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.042280318511732785, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005637375801564371, | |
| "grad_norm": 2.1648833751678467, | |
| "learning_rate": 5e-06, | |
| "loss": 0.419, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005637375801564371, | |
| "eval_loss": 0.4619485139846802, | |
| "eval_runtime": 483.5609, | |
| "eval_samples_per_second": 6.179, | |
| "eval_steps_per_second": 1.545, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011274751603128743, | |
| "grad_norm": 2.5114240646362305, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4315, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016912127404693116, | |
| "grad_norm": 2.378593683242798, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.4334, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022549503206257485, | |
| "grad_norm": 2.1998493671417236, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4171, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002818687900782186, | |
| "grad_norm": 2.156386613845825, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3483, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0033824254809386232, | |
| "grad_norm": 1.2216063737869263, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2282, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00394616306109506, | |
| "grad_norm": 0.9967670440673828, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.189, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004509900641251497, | |
| "grad_norm": 1.1083791255950928, | |
| "learning_rate": 4e-05, | |
| "loss": 0.1456, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005073638221407935, | |
| "grad_norm": 0.6914762258529663, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.1457, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005637375801564372, | |
| "grad_norm": 0.7410008907318115, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0622, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006201113381720809, | |
| "grad_norm": 1.2113826274871826, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.1035, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0067648509618772465, | |
| "grad_norm": 0.8289437890052795, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0723, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007328588542033683, | |
| "grad_norm": 1.0702934265136719, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.0522, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00789232612219012, | |
| "grad_norm": 0.6274738311767578, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0412, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008456063702346557, | |
| "grad_norm": 0.4598556160926819, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0206, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009019801282502994, | |
| "grad_norm": 0.5833584666252136, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0287, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009583538862659433, | |
| "grad_norm": 0.7033435702323914, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0215, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01014727644281587, | |
| "grad_norm": 0.3314254581928253, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0282, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010711014022972306, | |
| "grad_norm": 0.2847822308540344, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0117, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011274751603128744, | |
| "grad_norm": 0.16592615842819214, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011838489183285181, | |
| "grad_norm": 0.28353503346443176, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 0.0141, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012402226763441618, | |
| "grad_norm": 0.5575234293937683, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 0.0176, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.012965964343598054, | |
| "grad_norm": 0.6154017448425293, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 0.0159, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.013529701923754493, | |
| "grad_norm": 0.1513437181711197, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 0.0053, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01409343950391093, | |
| "grad_norm": 0.24261268973350525, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.0081, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014657177084067366, | |
| "grad_norm": 0.09996633231639862, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 0.0042, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.015220914664223803, | |
| "grad_norm": 0.09420917183160782, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 0.0065, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01578465224438024, | |
| "grad_norm": 0.15072062611579895, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 0.0045, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01634838982453668, | |
| "grad_norm": 0.28533950448036194, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 0.0139, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.016912127404693115, | |
| "grad_norm": 0.30663344264030457, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.0063, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017475864984849553, | |
| "grad_norm": 0.09105496853590012, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0037, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.018039602565005988, | |
| "grad_norm": 0.1351594626903534, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 0.0046, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.018603340145162427, | |
| "grad_norm": 0.10735020041465759, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 0.0031, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.019167077725318865, | |
| "grad_norm": 0.20175467431545258, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 0.0043, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0197308153054753, | |
| "grad_norm": 0.19858188927173615, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.0068, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02029455288563174, | |
| "grad_norm": 0.2514883279800415, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 0.0055, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.020858290465788177, | |
| "grad_norm": 0.18291513621807098, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 0.0026, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.021422028045944612, | |
| "grad_norm": 0.2146664708852768, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 0.0073, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02198576562610105, | |
| "grad_norm": 0.10978978872299194, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 0.0053, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02254950320625749, | |
| "grad_norm": 0.11510439962148666, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0055, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023113240786413924, | |
| "grad_norm": 0.28216826915740967, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 0.0068, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.023676978366570362, | |
| "grad_norm": 0.07864489406347275, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0025, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.024240715946726797, | |
| "grad_norm": 0.16902923583984375, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 0.0059, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.024804453526883236, | |
| "grad_norm": 0.2910400927066803, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 0.0067, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.025368191107039674, | |
| "grad_norm": 0.09773421287536621, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0025, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02593192868719611, | |
| "grad_norm": 0.4094434678554535, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 0.0079, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.026495666267352547, | |
| "grad_norm": 8.514568328857422, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 0.0685, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.027059403847508986, | |
| "grad_norm": 0.21161220967769623, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 0.0037, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02762314142766542, | |
| "grad_norm": 0.07243302464485168, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 0.0016, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02818687900782186, | |
| "grad_norm": 0.09567948430776596, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.005, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02818687900782186, | |
| "eval_loss": 0.003693485399708152, | |
| "eval_runtime": 486.3662, | |
| "eval_samples_per_second": 6.144, | |
| "eval_steps_per_second": 1.536, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028750616587978298, | |
| "grad_norm": 0.1225830614566803, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 0.0021, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.029314354168134733, | |
| "grad_norm": 0.2588897943496704, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 0.0056, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.02987809174829117, | |
| "grad_norm": 0.032464101910591125, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0014, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.030441829328447606, | |
| "grad_norm": 0.06320462375879288, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 0.0015, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.031005566908604044, | |
| "grad_norm": 0.09139032661914825, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0038, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03156930448876048, | |
| "grad_norm": 0.21807141602039337, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 0.0058, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.03213304206891692, | |
| "grad_norm": 0.044844482094049454, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 0.0015, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.03269677964907336, | |
| "grad_norm": 0.411823034286499, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 0.0509, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03326051722922979, | |
| "grad_norm": 0.08910378813743591, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 0.0028, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.03382425480938623, | |
| "grad_norm": 0.02365848794579506, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0012, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03438799238954267, | |
| "grad_norm": 0.07241960614919662, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 0.002, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.03495172996969911, | |
| "grad_norm": 0.12868086993694305, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 0.0068, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.035515467549855545, | |
| "grad_norm": 0.2509536147117615, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 0.0093, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.036079205130011976, | |
| "grad_norm": 0.16926199197769165, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0135, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.036642942710168415, | |
| "grad_norm": 0.06538938730955124, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0022, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03720668029032485, | |
| "grad_norm": 0.03876176103949547, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 0.0015, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.03777041787048129, | |
| "grad_norm": 0.05735520273447037, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 0.0021, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.03833415545063773, | |
| "grad_norm": 0.04489413648843765, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 0.0018, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.03889789303079417, | |
| "grad_norm": 0.05411110073328018, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 0.0019, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0394616306109506, | |
| "grad_norm": 0.13937705755233765, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.0019, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04002536819110704, | |
| "grad_norm": 0.11924191564321518, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 0.0035, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.04058910577126348, | |
| "grad_norm": 0.08436208218336105, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 0.003, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.041152843351419915, | |
| "grad_norm": 0.36739325523376465, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 0.0077, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.041716580931576354, | |
| "grad_norm": 0.10039687901735306, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 0.0047, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.042280318511732785, | |
| "grad_norm": 0.1667713224887848, | |
| "learning_rate": 0.0, | |
| "loss": 0.006, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2703129360125133e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |