| { | |
| "best_metric": 0.5550857186317444, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01638504864311316, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003277009728622632, | |
| "grad_norm": 31.261045455932617, | |
| "learning_rate": 5e-05, | |
| "loss": 15.7506, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003277009728622632, | |
| "eval_loss": 14.837973594665527, | |
| "eval_runtime": 541.9595, | |
| "eval_samples_per_second": 37.933, | |
| "eval_steps_per_second": 4.742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006554019457245264, | |
| "grad_norm": 29.842008590698242, | |
| "learning_rate": 0.0001, | |
| "loss": 15.5087, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009831029185867896, | |
| "grad_norm": 37.599693298339844, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 14.2453, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013108038914490527, | |
| "grad_norm": 32.512393951416016, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.7125, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001638504864311316, | |
| "grad_norm": 34.252315521240234, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.0529, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001966205837173579, | |
| "grad_norm": 7.67521858215332, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.4588, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022939068100358423, | |
| "grad_norm": 1.5343810319900513, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.0989, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0026216077828981055, | |
| "grad_norm": 0.1755257248878479, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0032, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0029493087557603687, | |
| "grad_norm": 0.29983237385749817, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.007, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003277009728622632, | |
| "grad_norm": 0.009663011878728867, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0001, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003604710701484895, | |
| "grad_norm": 0.0076761022210121155, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0001, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003932411674347158, | |
| "grad_norm": 39.781436920166016, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.8786, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004260112647209421, | |
| "grad_norm": 22.450254440307617, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 5.4304, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004587813620071685, | |
| "grad_norm": 1.042336344718933, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0097, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004915514592933948, | |
| "grad_norm": 0.9374661445617676, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.094, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005243215565796211, | |
| "grad_norm": 0.7043875455856323, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0572, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005570916538658474, | |
| "grad_norm": 0.11888981610536575, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0029, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005898617511520737, | |
| "grad_norm": 0.7907737493515015, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0856, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0062263184843830005, | |
| "grad_norm": 0.004672874230891466, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0001, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.006554019457245264, | |
| "grad_norm": 0.02190549671649933, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0002, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006881720430107527, | |
| "grad_norm": 0.35459205508232117, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0023, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00720942140296979, | |
| "grad_norm": 0.07353981584310532, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0006, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007537122375832053, | |
| "grad_norm": 0.016774479299783707, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0002, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007864823348694316, | |
| "grad_norm": 6.56516170501709, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.2668, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00819252432155658, | |
| "grad_norm": 44.217681884765625, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 7.2224, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00819252432155658, | |
| "eval_loss": 0.6313633918762207, | |
| "eval_runtime": 542.1174, | |
| "eval_samples_per_second": 37.922, | |
| "eval_steps_per_second": 4.741, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008520225294418843, | |
| "grad_norm": 0.5711866617202759, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0027, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.008847926267281106, | |
| "grad_norm": 1.0504467487335205, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.058, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00917562724014337, | |
| "grad_norm": 0.01546482928097248, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0002, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009503328213005632, | |
| "grad_norm": 0.06221342831850052, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0007, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.009831029185867896, | |
| "grad_norm": 0.2583235502243042, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0235, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010158730158730159, | |
| "grad_norm": 0.34219637513160706, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.004, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.010486431131592422, | |
| "grad_norm": 0.08938989788293839, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0011, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.010814132104454685, | |
| "grad_norm": 0.06973156332969666, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0009, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.011141833077316948, | |
| "grad_norm": 0.049496784806251526, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0007, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.011469534050179211, | |
| "grad_norm": 0.059189580380916595, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0008, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.011797235023041475, | |
| "grad_norm": 0.036744456738233566, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0005, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.012124935995903738, | |
| "grad_norm": 15.912163734436035, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 4.041, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.012452636968766001, | |
| "grad_norm": 15.49551010131836, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.3641, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.012780337941628264, | |
| "grad_norm": 3.3970727920532227, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0677, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.013108038914490527, | |
| "grad_norm": 1.7774622440338135, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1034, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01343573988735279, | |
| "grad_norm": 0.6135979294776917, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0112, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.013763440860215054, | |
| "grad_norm": 0.028032571077346802, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0004, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.014091141833077317, | |
| "grad_norm": 0.022963479161262512, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0003, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01441884280593958, | |
| "grad_norm": 0.0068603456020355225, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0001, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.014746543778801843, | |
| "grad_norm": 0.016390018165111542, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0002, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.015074244751664106, | |
| "grad_norm": 0.005271920468658209, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0001, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01540194572452637, | |
| "grad_norm": 0.00490738358348608, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0001, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.015729646697388633, | |
| "grad_norm": 0.005103846546262503, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0001, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.016057347670250896, | |
| "grad_norm": 1.1267679929733276, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2331, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01638504864311316, | |
| "grad_norm": 14.760371208190918, | |
| "learning_rate": 0.0, | |
| "loss": 6.3942, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01638504864311316, | |
| "eval_loss": 0.5550857186317444, | |
| "eval_runtime": 541.4372, | |
| "eval_samples_per_second": 37.969, | |
| "eval_steps_per_second": 4.747, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |