| { | |
| "best_metric": 0.2656872272491455, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.024906600249066, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00049813200498132, | |
| "grad_norm": 5.953134059906006, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 4.8123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00049813200498132, | |
| "eval_loss": 5.567110538482666, | |
| "eval_runtime": 4.675, | |
| "eval_samples_per_second": 10.695, | |
| "eval_steps_per_second": 1.497, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00099626400996264, | |
| "grad_norm": 6.526628494262695, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 4.6673, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014943960149439602, | |
| "grad_norm": 6.885717391967773, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 4.9635, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00199252801992528, | |
| "grad_norm": 6.974002361297607, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 4.7067, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024906600249066002, | |
| "grad_norm": 6.78061580657959, | |
| "learning_rate": 0.00015, | |
| "loss": 3.2747, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029887920298879204, | |
| "grad_norm": 6.11532735824585, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.2891, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034869240348692405, | |
| "grad_norm": 7.936379909515381, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.9396, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00398505603985056, | |
| "grad_norm": 4.918308258056641, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.0278, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00448318804483188, | |
| "grad_norm": 2.4183318614959717, | |
| "learning_rate": 0.00027, | |
| "loss": 0.6151, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0049813200498132005, | |
| "grad_norm": 3.024343252182007, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5268, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005479452054794521, | |
| "grad_norm": 5.444397926330566, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.6453, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005977584059775841, | |
| "grad_norm": 1.5527619123458862, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.4021, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006475716064757161, | |
| "grad_norm": 2.6941704750061035, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.5887, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006973848069738481, | |
| "grad_norm": 2.389618158340454, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.5361, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007471980074719801, | |
| "grad_norm": 3.0418622493743896, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.6187, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00797011207970112, | |
| "grad_norm": 2.0878942012786865, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.5258, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008468244084682441, | |
| "grad_norm": 1.712019681930542, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.5596, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00896637608966376, | |
| "grad_norm": 1.5270085334777832, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.5545, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009464508094645082, | |
| "grad_norm": 1.2116973400115967, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.5171, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009962640099626401, | |
| "grad_norm": 1.9724152088165283, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.5578, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01046077210460772, | |
| "grad_norm": 1.3572190999984741, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.4079, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010958904109589041, | |
| "grad_norm": 1.0932906866073608, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.3469, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01145703611457036, | |
| "grad_norm": 2.3079965114593506, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.4726, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011955168119551681, | |
| "grad_norm": 1.4202669858932495, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.432, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012453300124533, | |
| "grad_norm": 1.4758336544036865, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.4866, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012453300124533, | |
| "eval_loss": 0.4223214089870453, | |
| "eval_runtime": 4.2101, | |
| "eval_samples_per_second": 11.876, | |
| "eval_steps_per_second": 1.663, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012951432129514322, | |
| "grad_norm": 1.7702012062072754, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.404, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013449564134495641, | |
| "grad_norm": 1.6178979873657227, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.4401, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013947696139476962, | |
| "grad_norm": 1.7393587827682495, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.3987, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014445828144458281, | |
| "grad_norm": 1.4745129346847534, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.3417, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014943960149439602, | |
| "grad_norm": 2.148548126220703, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.389, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015442092154420922, | |
| "grad_norm": 1.60543692111969, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.3174, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01594022415940224, | |
| "grad_norm": 1.9873653650283813, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.3543, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01643835616438356, | |
| "grad_norm": 2.2028841972351074, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.3658, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016936488169364883, | |
| "grad_norm": 2.061235189437866, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.3557, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017434620174346202, | |
| "grad_norm": 1.9047632217407227, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.3839, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01793275217932752, | |
| "grad_norm": 1.9746155738830566, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.337, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01843088418430884, | |
| "grad_norm": 1.2726603746414185, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.2521, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.018929016189290163, | |
| "grad_norm": 1.6630284786224365, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.3524, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019427148194271483, | |
| "grad_norm": 2.152161121368408, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.3155, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019925280199252802, | |
| "grad_norm": 1.6489615440368652, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.2775, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02042341220423412, | |
| "grad_norm": 1.6735095977783203, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.2775, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02092154420921544, | |
| "grad_norm": 1.5859333276748657, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.3597, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.021419676214196763, | |
| "grad_norm": 1.8575478792190552, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.3549, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.021917808219178082, | |
| "grad_norm": 1.4628279209136963, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.2813, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0224159402241594, | |
| "grad_norm": 1.3827449083328247, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.2231, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02291407222914072, | |
| "grad_norm": 1.371862769126892, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.2659, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.023412204234122044, | |
| "grad_norm": 1.628051519393921, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.3401, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.023910336239103363, | |
| "grad_norm": 1.2595473527908325, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.2926, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.024408468244084682, | |
| "grad_norm": 1.9967325925827026, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.3504, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.024906600249066, | |
| "grad_norm": 1.8664722442626953, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.278, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024906600249066, | |
| "eval_loss": 0.2656872272491455, | |
| "eval_runtime": 4.2304, | |
| "eval_samples_per_second": 11.819, | |
| "eval_steps_per_second": 1.655, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.88255238782976e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |