| { | |
| "best_metric": 1.266974925994873, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3670566643725625, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00734113328745125, | |
| "grad_norm": 1.0009183883666992, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.7152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00734113328745125, | |
| "eval_loss": 2.739882469177246, | |
| "eval_runtime": 11.5725, | |
| "eval_samples_per_second": 4.321, | |
| "eval_steps_per_second": 4.321, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0146822665749025, | |
| "grad_norm": 1.0102258920669556, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.6972, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02202339986235375, | |
| "grad_norm": 0.9687394499778748, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.7558, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.029364533149805, | |
| "grad_norm": 0.7906656265258789, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.5397, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03670566643725625, | |
| "grad_norm": 0.4140726625919342, | |
| "learning_rate": 0.00015, | |
| "loss": 2.5202, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0440467997247075, | |
| "grad_norm": 0.68717360496521, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.5802, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05138793301215875, | |
| "grad_norm": 0.9959529042243958, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.563, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05872906629961, | |
| "grad_norm": 0.5985053777694702, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.5683, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06607019958706126, | |
| "grad_norm": 0.2967154085636139, | |
| "learning_rate": 0.00027, | |
| "loss": 2.539, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0734113328745125, | |
| "grad_norm": 0.28381672501564026, | |
| "learning_rate": 0.0003, | |
| "loss": 2.5398, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08075246616196376, | |
| "grad_norm": 0.38264232873916626, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 2.5249, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.088093599449415, | |
| "grad_norm": 0.33728712797164917, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 2.4142, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09543473273686626, | |
| "grad_norm": 0.26186007261276245, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 2.3963, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1027758660243175, | |
| "grad_norm": 0.26044395565986633, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 2.4171, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11011699931176876, | |
| "grad_norm": 0.33337321877479553, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 2.3295, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11745813259922, | |
| "grad_norm": 0.2713659703731537, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 2.3165, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12479926588667126, | |
| "grad_norm": 0.24857458472251892, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 2.3045, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1321403991741225, | |
| "grad_norm": 0.2671072781085968, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 2.3119, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13948153246157374, | |
| "grad_norm": 0.2695709466934204, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 2.319, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.146822665749025, | |
| "grad_norm": 0.2995961010456085, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 2.252, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15416379903647626, | |
| "grad_norm": 0.2794254422187805, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 2.2558, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1615049323239275, | |
| "grad_norm": 0.31873247027397156, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 2.2161, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16884606561137874, | |
| "grad_norm": 0.3151024878025055, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 2.2114, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.17618719889883, | |
| "grad_norm": 0.3369925022125244, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 2.1251, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18352833218628126, | |
| "grad_norm": 0.3629818260669708, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 2.2003, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18352833218628126, | |
| "eval_loss": 2.0463967323303223, | |
| "eval_runtime": 11.771, | |
| "eval_samples_per_second": 4.248, | |
| "eval_steps_per_second": 4.248, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1908694654737325, | |
| "grad_norm": 0.4075523316860199, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 2.0395, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.19821059876118377, | |
| "grad_norm": 0.4278491139411926, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 2.0627, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.205551732048635, | |
| "grad_norm": 0.5144158005714417, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 2.1029, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.21289286533608626, | |
| "grad_norm": 0.5315491557121277, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 2.0312, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2202339986235375, | |
| "grad_norm": 0.5522644519805908, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 2.0579, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22757513191098877, | |
| "grad_norm": 0.5328534841537476, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 1.9475, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.23491626519844, | |
| "grad_norm": 0.6033841371536255, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 1.8248, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.24225739848589126, | |
| "grad_norm": 0.7932512760162354, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 1.9608, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2495985317733425, | |
| "grad_norm": 0.6182257533073425, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 1.8797, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.25693966506079374, | |
| "grad_norm": 0.6742249131202698, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 1.8248, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.264280798348245, | |
| "grad_norm": 0.7396733164787292, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 1.8357, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.27162193163569626, | |
| "grad_norm": 0.701486349105835, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 1.7344, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2789630649231475, | |
| "grad_norm": 0.6000120639801025, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 1.7778, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.28630419821059877, | |
| "grad_norm": 0.7575259804725647, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 1.6843, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.29364533149805, | |
| "grad_norm": 0.8110001683235168, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 1.6607, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3009864647855013, | |
| "grad_norm": 0.7647180557250977, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 1.7497, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3083275980729525, | |
| "grad_norm": 0.785166323184967, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 1.515, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.31566873136040374, | |
| "grad_norm": 1.9912952184677124, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 1.553, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.323009864647855, | |
| "grad_norm": 0.9436890482902527, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 1.644, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.33035099793530626, | |
| "grad_norm": 1.1021350622177124, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 1.3351, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3376921312227575, | |
| "grad_norm": 1.1297169923782349, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 1.4851, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.34503326451020877, | |
| "grad_norm": 1.3415935039520264, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 1.4308, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.35237439779766, | |
| "grad_norm": 1.052236557006836, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 1.3211, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3597155310851113, | |
| "grad_norm": 1.047372579574585, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 1.1593, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3670566643725625, | |
| "grad_norm": 1.29693603515625, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 1.2361, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3670566643725625, | |
| "eval_loss": 1.266974925994873, | |
| "eval_runtime": 11.7783, | |
| "eval_samples_per_second": 4.245, | |
| "eval_steps_per_second": 4.245, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 8.76182186309714e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |