{ "best_metric": 11.920040130615234, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.006184865633794106, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00012369731267588213, "grad_norm": 0.012027100659906864, "learning_rate": 2.9999999999999997e-05, "loss": 11.9301, "step": 1 }, { "epoch": 0.00012369731267588213, "eval_loss": 11.931971549987793, "eval_runtime": 0.2658, "eval_samples_per_second": 188.11, "eval_steps_per_second": 26.335, "step": 1 }, { "epoch": 0.00024739462535176425, "grad_norm": 0.013170535676181316, "learning_rate": 5.9999999999999995e-05, "loss": 11.9357, "step": 2 }, { "epoch": 0.0003710919380276463, "grad_norm": 0.015393908135592937, "learning_rate": 8.999999999999999e-05, "loss": 11.931, "step": 3 }, { "epoch": 0.0004947892507035285, "grad_norm": 0.015217465348541737, "learning_rate": 0.00011999999999999999, "loss": 11.9307, "step": 4 }, { "epoch": 0.0006184865633794106, "grad_norm": 0.015969593077898026, "learning_rate": 0.00015, "loss": 11.9308, "step": 5 }, { "epoch": 0.0007421838760552926, "grad_norm": 0.012820259667932987, "learning_rate": 0.00017999999999999998, "loss": 11.9314, "step": 6 }, { "epoch": 0.0008658811887311748, "grad_norm": 0.013964623212814331, "learning_rate": 0.00020999999999999998, "loss": 11.9306, "step": 7 }, { "epoch": 0.000989578501407057, "grad_norm": 0.019782794639468193, "learning_rate": 0.00023999999999999998, "loss": 11.9299, "step": 8 }, { "epoch": 0.001113275814082939, "grad_norm": 0.0200200155377388, "learning_rate": 0.00027, "loss": 11.9311, "step": 9 }, { "epoch": 0.0012369731267588213, "grad_norm": 0.02155681885778904, "learning_rate": 0.0003, "loss": 11.9329, "step": 10 }, { "epoch": 0.0013606704394347033, "grad_norm": 0.01726888120174408, "learning_rate": 0.0002999794957488703, "loss": 11.9289, "step": 11 }, { "epoch": 0.0014843677521105853, "grad_norm": 0.028205610811710358, "learning_rate": 0.0002999179886011389, "loss": 11.9323, "step": 12 }, { "epoch": 0.0016080650647864675, "grad_norm": 0.018932929262518883, "learning_rate": 0.0002998154953722457, "loss": 11.9303, "step": 13 }, { "epoch": 0.0017317623774623495, "grad_norm": 0.017916956916451454, "learning_rate": 0.00029967204408281613, "loss": 11.929, "step": 14 }, { "epoch": 0.0018554596901382318, "grad_norm": 0.015873437747359276, "learning_rate": 0.00029948767395100045, "loss": 11.9308, "step": 15 }, { "epoch": 0.001979157002814114, "grad_norm": 0.028634965419769287, "learning_rate": 0.0002992624353817517, "loss": 11.9296, "step": 16 }, { "epoch": 0.002102854315489996, "grad_norm": 0.021988065913319588, "learning_rate": 0.0002989963899530457, "loss": 11.9315, "step": 17 }, { "epoch": 0.002226551628165878, "grad_norm": 0.02658429555594921, "learning_rate": 0.00029868961039904624, "loss": 11.9289, "step": 18 }, { "epoch": 0.00235024894084176, "grad_norm": 0.0265872273594141, "learning_rate": 0.00029834218059022024, "loss": 11.9296, "step": 19 }, { "epoch": 0.0024739462535176425, "grad_norm": 0.027340911328792572, "learning_rate": 0.00029795419551040833, "loss": 11.9287, "step": 20 }, { "epoch": 0.0025976435661935245, "grad_norm": 0.031099706888198853, "learning_rate": 0.00029752576123085736, "loss": 11.9258, "step": 21 }, { "epoch": 0.0027213408788694065, "grad_norm": 0.02729742042720318, "learning_rate": 0.0002970569948812214, "loss": 11.9302, "step": 22 }, { "epoch": 0.0028450381915452886, "grad_norm": 0.024717018008232117, "learning_rate": 0.0002965480246175399, "loss": 11.9306, "step": 23 }, { "epoch": 0.0029687355042211706, "grad_norm": 0.04332926496863365, "learning_rate": 0.0002959989895872009, "loss": 11.9283, "step": 24 }, { "epoch": 0.003092432816897053, "grad_norm": 0.03554433956742287, "learning_rate": 0.0002954100398908995, "loss": 11.9265, "step": 25 }, { "epoch": 0.003092432816897053, "eval_loss": 11.9295654296875, "eval_runtime": 0.2693, "eval_samples_per_second": 185.663, "eval_steps_per_second": 25.993, "step": 25 }, { "epoch": 0.003216130129572935, "grad_norm": 0.04288264736533165, "learning_rate": 0.0002947813365416023, "loss": 11.9294, "step": 26 }, { "epoch": 0.003339827442248817, "grad_norm": 0.046658046543598175, "learning_rate": 0.0002941130514205272, "loss": 11.9296, "step": 27 }, { "epoch": 0.003463524754924699, "grad_norm": 0.04863458871841431, "learning_rate": 0.0002934053672301536, "loss": 11.9259, "step": 28 }, { "epoch": 0.0035872220676005815, "grad_norm": 0.0424097515642643, "learning_rate": 0.00029265847744427303, "loss": 11.9289, "step": 29 }, { "epoch": 0.0037109193802764636, "grad_norm": 0.0457475483417511, "learning_rate": 0.00029187258625509513, "loss": 11.9288, "step": 30 }, { "epoch": 0.0038346166929523456, "grad_norm": 0.05019732937216759, "learning_rate": 0.00029104790851742417, "loss": 11.9267, "step": 31 }, { "epoch": 0.003958314005628228, "grad_norm": 0.04077630862593651, "learning_rate": 0.0002901846696899191, "loss": 11.9231, "step": 32 }, { "epoch": 0.00408201131830411, "grad_norm": 0.08654378354549408, "learning_rate": 0.00028928310577345606, "loss": 11.9298, "step": 33 }, { "epoch": 0.004205708630979992, "grad_norm": 0.08918948471546173, "learning_rate": 0.0002883434632466077, "loss": 11.9257, "step": 34 }, { "epoch": 0.0043294059436558745, "grad_norm": 0.06919989734888077, "learning_rate": 0.00028736599899825856, "loss": 11.9268, "step": 35 }, { "epoch": 0.004453103256331756, "grad_norm": 0.06473810225725174, "learning_rate": 0.00028635098025737434, "loss": 11.9275, "step": 36 }, { "epoch": 0.0045768005690076385, "grad_norm": 0.09428096562623978, "learning_rate": 0.00028529868451994384, "loss": 11.9215, "step": 37 }, { "epoch": 0.00470049788168352, "grad_norm": 0.09449499100446701, "learning_rate": 0.0002842093994731145, "loss": 11.9191, "step": 38 }, { "epoch": 0.004824195194359403, "grad_norm": 0.0703858807682991, "learning_rate": 0.00028308342291654174, "loss": 11.9235, "step": 39 }, { "epoch": 0.004947892507035285, "grad_norm": 0.056587882339954376, "learning_rate": 0.00028192106268097334, "loss": 11.9233, "step": 40 }, { "epoch": 0.005071589819711167, "grad_norm": 0.07054153084754944, "learning_rate": 0.00028072263654409154, "loss": 11.9206, "step": 41 }, { "epoch": 0.005195287132387049, "grad_norm": 0.08422651141881943, "learning_rate": 0.0002794884721436361, "loss": 11.9194, "step": 42 }, { "epoch": 0.005318984445062931, "grad_norm": 0.06794271618127823, "learning_rate": 0.00027821890688783083, "loss": 11.9172, "step": 43 }, { "epoch": 0.005442681757738813, "grad_norm": 0.08688784390687943, "learning_rate": 0.0002769142878631403, "loss": 11.9104, "step": 44 }, { "epoch": 0.0055663790704146955, "grad_norm": 0.08762703835964203, "learning_rate": 0.00027557497173937923, "loss": 11.9169, "step": 45 }, { "epoch": 0.005690076383090577, "grad_norm": 0.09055648744106293, "learning_rate": 0.000274201324672203, "loss": 11.9117, "step": 46 }, { "epoch": 0.00581377369576646, "grad_norm": 0.07354215532541275, "learning_rate": 0.00027279372220300385, "loss": 11.916, "step": 47 }, { "epoch": 0.005937471008442341, "grad_norm": 0.08788519352674484, "learning_rate": 0.0002713525491562421, "loss": 11.92, "step": 48 }, { "epoch": 0.006061168321118224, "grad_norm": 0.09053384512662888, "learning_rate": 0.00026987819953423867, "loss": 11.9145, "step": 49 }, { "epoch": 0.006184865633794106, "grad_norm": 0.08623462170362473, "learning_rate": 0.00026837107640945905, "loss": 11.9131, "step": 50 }, { "epoch": 0.006184865633794106, "eval_loss": 11.920040130615234, "eval_runtime": 0.2628, "eval_samples_per_second": 190.255, "eval_steps_per_second": 26.636, "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": 79631155200.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }