| { | |
| "best_metric": 0.905018150806427, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7168458781362007, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014336917562724014, | |
| "grad_norm": 0.6041901111602783, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0649, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014336917562724014, | |
| "eval_loss": 1.3422572612762451, | |
| "eval_runtime": 5.603, | |
| "eval_samples_per_second": 83.883, | |
| "eval_steps_per_second": 10.53, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02867383512544803, | |
| "grad_norm": 0.6313121914863586, | |
| "learning_rate": 0.0001, | |
| "loss": 1.095, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.043010752688172046, | |
| "grad_norm": 0.5560466051101685, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.9878, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05734767025089606, | |
| "grad_norm": 0.4491470158100128, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.0302, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07168458781362007, | |
| "grad_norm": 0.39338088035583496, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.942, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08602150537634409, | |
| "grad_norm": 0.4454711079597473, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9521, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1003584229390681, | |
| "grad_norm": 0.4536270499229431, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.9813, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11469534050179211, | |
| "grad_norm": 0.5215060114860535, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0008, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 0.5158147215843201, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.0112, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14336917562724014, | |
| "grad_norm": 0.5433710813522339, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1178, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15770609318996415, | |
| "grad_norm": 0.5769047737121582, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.227, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17204301075268819, | |
| "grad_norm": 0.8490751385688782, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.344, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1863799283154122, | |
| "grad_norm": 0.6094579100608826, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0767, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2007168458781362, | |
| "grad_norm": 0.5022676587104797, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9166, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21505376344086022, | |
| "grad_norm": 0.4170316159725189, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.805, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22939068100358423, | |
| "grad_norm": 0.3328133523464203, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8255, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24372759856630824, | |
| "grad_norm": 0.29863879084587097, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8212, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 0.3009535074234009, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8957, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2724014336917563, | |
| "grad_norm": 0.3121752142906189, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8764, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2867383512544803, | |
| "grad_norm": 0.3003133237361908, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8987, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3010752688172043, | |
| "grad_norm": 0.3068234622478485, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9641, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3154121863799283, | |
| "grad_norm": 0.38228583335876465, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.9765, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.32974910394265233, | |
| "grad_norm": 0.4486004710197449, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.0944, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.34408602150537637, | |
| "grad_norm": 0.4857740104198456, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0844, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.35842293906810035, | |
| "grad_norm": 0.8380986452102661, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1566, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35842293906810035, | |
| "eval_loss": 0.927205502986908, | |
| "eval_runtime": 5.6104, | |
| "eval_samples_per_second": 83.772, | |
| "eval_steps_per_second": 10.516, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3727598566308244, | |
| "grad_norm": 0.306890606880188, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9556, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 0.32755231857299805, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.8453, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4014336917562724, | |
| "grad_norm": 0.327320396900177, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.8859, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4157706093189964, | |
| "grad_norm": 0.26873916387557983, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8621, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 0.2484484165906906, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8585, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.2556518614292145, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8101, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.45878136200716846, | |
| "grad_norm": 0.2587701082229614, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8591, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4731182795698925, | |
| "grad_norm": 0.2929799258708954, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8938, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4874551971326165, | |
| "grad_norm": 0.32331496477127075, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9321, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5017921146953405, | |
| "grad_norm": 0.3812984526157379, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.9969, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 0.48057031631469727, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0929, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5304659498207885, | |
| "grad_norm": 0.5055277943611145, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0387, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5448028673835126, | |
| "grad_norm": 0.2941000759601593, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9023, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5591397849462365, | |
| "grad_norm": 0.22578291594982147, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8705, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5734767025089605, | |
| "grad_norm": 0.2067464292049408, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.82, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5878136200716846, | |
| "grad_norm": 0.2110137641429901, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8518, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6021505376344086, | |
| "grad_norm": 0.21045488119125366, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8105, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6164874551971327, | |
| "grad_norm": 0.2219025194644928, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8502, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6308243727598566, | |
| "grad_norm": 0.24328501522541046, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8586, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 0.23979176580905914, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.8313, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6594982078853047, | |
| "grad_norm": 0.27109646797180176, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.902, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6738351254480287, | |
| "grad_norm": 0.29217034578323364, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.9383, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6881720430107527, | |
| "grad_norm": 0.3429727554321289, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.034, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7025089605734767, | |
| "grad_norm": 0.4209645688533783, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0656, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7168458781362007, | |
| "grad_norm": 0.6673789620399475, | |
| "learning_rate": 0.0, | |
| "loss": 1.2387, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7168458781362007, | |
| "eval_loss": 0.905018150806427, | |
| "eval_runtime": 5.6113, | |
| "eval_samples_per_second": 83.76, | |
| "eval_steps_per_second": 10.515, | |
| "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": 1.067482872849367e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |