| { | |
| "best_metric": 1.1020798683166504, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", | |
| "epoch": 0.06390593047034765, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001278118609406953, | |
| "eval_loss": 1.55583918094635, | |
| "eval_runtime": 164.9281, | |
| "eval_samples_per_second": 9.992, | |
| "eval_steps_per_second": 2.498, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001278118609406953, | |
| "grad_norm": 0.8316797614097595, | |
| "learning_rate": 4.12e-05, | |
| "loss": 2.8146, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002556237218813906, | |
| "grad_norm": 1.5763788223266602, | |
| "learning_rate": 8.24e-05, | |
| "loss": 2.7539, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003834355828220859, | |
| "grad_norm": 1.363692283630371, | |
| "learning_rate": 0.0001236, | |
| "loss": 2.5238, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005112474437627812, | |
| "grad_norm": 1.2749073505401611, | |
| "learning_rate": 0.0001648, | |
| "loss": 2.4211, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006390593047034765, | |
| "grad_norm": 1.517897129058838, | |
| "learning_rate": 0.000206, | |
| "loss": 2.464, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006390593047034765, | |
| "eval_loss": 1.184857964515686, | |
| "eval_runtime": 164.9457, | |
| "eval_samples_per_second": 9.991, | |
| "eval_steps_per_second": 2.498, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007668711656441718, | |
| "grad_norm": 1.6017893552780151, | |
| "learning_rate": 0.0002057490971767619, | |
| "loss": 2.5335, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00894683026584867, | |
| "grad_norm": 1.576207160949707, | |
| "learning_rate": 0.00020499761108038175, | |
| "loss": 2.3625, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.010224948875255624, | |
| "grad_norm": 1.646509051322937, | |
| "learning_rate": 0.00020374920287558198, | |
| "loss": 2.2446, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.011503067484662576, | |
| "grad_norm": 1.8106887340545654, | |
| "learning_rate": 0.00020200995468164684, | |
| "loss": 2.0361, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01278118609406953, | |
| "grad_norm": 5.966978073120117, | |
| "learning_rate": 0.00019978833994094855, | |
| "loss": 1.7612, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01278118609406953, | |
| "eval_loss": 1.323485255241394, | |
| "eval_runtime": 164.4974, | |
| "eval_samples_per_second": 10.018, | |
| "eval_steps_per_second": 2.505, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.014059304703476482, | |
| "grad_norm": 0.9883098006248474, | |
| "learning_rate": 0.00019709518213718787, | |
| "loss": 2.5625, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.015337423312883436, | |
| "grad_norm": 0.9952566027641296, | |
| "learning_rate": 0.00019394360206446948, | |
| "loss": 2.5723, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.016615541922290387, | |
| "grad_norm": 1.1392284631729126, | |
| "learning_rate": 0.00019034895390411186, | |
| "loss": 2.487, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01789366053169734, | |
| "grad_norm": 1.1261663436889648, | |
| "learning_rate": 0.0001863287504206196, | |
| "loss": 2.4156, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.019171779141104295, | |
| "grad_norm": 1.3464722633361816, | |
| "learning_rate": 0.00018190257764125471, | |
| "loss": 2.4932, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.019171779141104295, | |
| "eval_loss": 1.177261471748352, | |
| "eval_runtime": 164.3678, | |
| "eval_samples_per_second": 10.026, | |
| "eval_steps_per_second": 2.507, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02044989775051125, | |
| "grad_norm": 1.7977056503295898, | |
| "learning_rate": 0.00017709199943488106, | |
| "loss": 2.3259, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0217280163599182, | |
| "grad_norm": 1.4776368141174316, | |
| "learning_rate": 0.00017192045245496238, | |
| "loss": 2.3461, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.023006134969325152, | |
| "grad_norm": 1.747175931930542, | |
| "learning_rate": 0.00016641313195854277, | |
| "loss": 2.3122, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.024284253578732106, | |
| "grad_norm": 1.9792368412017822, | |
| "learning_rate": 0.0001605968690574869, | |
| "loss": 2.0044, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.02556237218813906, | |
| "grad_norm": 1.2479664087295532, | |
| "learning_rate": 0.0001545, | |
| "loss": 1.6114, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02556237218813906, | |
| "eval_loss": 1.4369239807128906, | |
| "eval_runtime": 164.2247, | |
| "eval_samples_per_second": 10.035, | |
| "eval_steps_per_second": 2.509, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.026840490797546013, | |
| "grad_norm": 0.9227780103683472, | |
| "learning_rate": 0.00014815222811927496, | |
| "loss": 2.6329, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.028118609406952964, | |
| "grad_norm": 1.103001356124878, | |
| "learning_rate": 0.00014158447912183896, | |
| "loss": 2.5218, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.029396728016359917, | |
| "grad_norm": 1.1868301630020142, | |
| "learning_rate": 0.00013482875042061958, | |
| "loss": 2.3236, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.03067484662576687, | |
| "grad_norm": 1.4458407163619995, | |
| "learning_rate": 0.00012791795524676576, | |
| "loss": 2.4963, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.031952965235173825, | |
| "grad_norm": 1.193825602531433, | |
| "learning_rate": 0.00012088576229969385, | |
| "loss": 2.2952, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.031952965235173825, | |
| "eval_loss": 1.1527986526489258, | |
| "eval_runtime": 164.1739, | |
| "eval_samples_per_second": 10.038, | |
| "eval_steps_per_second": 2.51, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.033231083844580775, | |
| "grad_norm": 1.4545817375183105, | |
| "learning_rate": 0.0001137664317165683, | |
| "loss": 2.2958, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.03450920245398773, | |
| "grad_norm": 1.3638569116592407, | |
| "learning_rate": 0.00010659464816035761, | |
| "loss": 2.2994, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.03578732106339468, | |
| "grad_norm": 1.6373779773712158, | |
| "learning_rate": 9.940535183964242e-05, | |
| "loss": 2.0054, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.03706543967280164, | |
| "grad_norm": 1.795109510421753, | |
| "learning_rate": 9.22335682834317e-05, | |
| "loss": 1.9559, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.03834355828220859, | |
| "grad_norm": 3.544909954071045, | |
| "learning_rate": 8.511423770030617e-05, | |
| "loss": 1.7323, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03834355828220859, | |
| "eval_loss": 1.2193244695663452, | |
| "eval_runtime": 164.1641, | |
| "eval_samples_per_second": 10.039, | |
| "eval_steps_per_second": 2.51, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03962167689161554, | |
| "grad_norm": 0.8290108442306519, | |
| "learning_rate": 7.808204475323423e-05, | |
| "loss": 2.3842, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.0408997955010225, | |
| "grad_norm": 0.8988869786262512, | |
| "learning_rate": 7.117124957938042e-05, | |
| "loss": 2.4288, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.04217791411042945, | |
| "grad_norm": 1.1712989807128906, | |
| "learning_rate": 6.441552087816105e-05, | |
| "loss": 2.3214, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.0434560327198364, | |
| "grad_norm": 1.1696773767471313, | |
| "learning_rate": 5.784777188072502e-05, | |
| "loss": 2.4251, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.044734151329243355, | |
| "grad_norm": 1.3218914270401, | |
| "learning_rate": 5.150000000000002e-05, | |
| "loss": 2.2685, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.044734151329243355, | |
| "eval_loss": 1.1176284551620483, | |
| "eval_runtime": 164.1946, | |
| "eval_samples_per_second": 10.037, | |
| "eval_steps_per_second": 2.509, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.046012269938650305, | |
| "grad_norm": 1.2911388874053955, | |
| "learning_rate": 4.540313094251309e-05, | |
| "loss": 2.3459, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.04729038854805726, | |
| "grad_norm": 1.5387221574783325, | |
| "learning_rate": 3.958686804145719e-05, | |
| "loss": 2.2075, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.04856850715746421, | |
| "grad_norm": 1.4516918659210205, | |
| "learning_rate": 3.4079547545037634e-05, | |
| "loss": 2.157, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.04984662576687116, | |
| "grad_norm": 1.8935630321502686, | |
| "learning_rate": 2.8908000565118947e-05, | |
| "loss": 1.9017, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.05112474437627812, | |
| "grad_norm": 4.446241855621338, | |
| "learning_rate": 2.4097422358745275e-05, | |
| "loss": 1.6619, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05112474437627812, | |
| "eval_loss": 1.13141667842865, | |
| "eval_runtime": 164.2729, | |
| "eval_samples_per_second": 10.032, | |
| "eval_steps_per_second": 2.508, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05240286298568507, | |
| "grad_norm": 1.162409782409668, | |
| "learning_rate": 1.9671249579380422e-05, | |
| "loss": 2.313, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.05368098159509203, | |
| "grad_norm": 1.0322766304016113, | |
| "learning_rate": 1.5651046095888127e-05, | |
| "loss": 2.564, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.05495910020449898, | |
| "grad_norm": 0.9610581994056702, | |
| "learning_rate": 1.205639793553052e-05, | |
| "loss": 2.3624, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.05623721881390593, | |
| "grad_norm": 1.0807439088821411, | |
| "learning_rate": 8.904817862812098e-06, | |
| "loss": 2.409, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.057515337423312884, | |
| "grad_norm": 1.0476551055908203, | |
| "learning_rate": 6.211660059051443e-06, | |
| "loss": 2.236, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.057515337423312884, | |
| "eval_loss": 1.1031837463378906, | |
| "eval_runtime": 164.1828, | |
| "eval_samples_per_second": 10.038, | |
| "eval_steps_per_second": 2.509, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.058793456032719835, | |
| "grad_norm": 1.250786542892456, | |
| "learning_rate": 3.990045318353154e-06, | |
| "loss": 2.3246, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.06007157464212679, | |
| "grad_norm": 1.4708008766174316, | |
| "learning_rate": 2.250797124418014e-06, | |
| "loss": 2.15, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.06134969325153374, | |
| "grad_norm": 1.5800373554229736, | |
| "learning_rate": 1.0023889196182526e-06, | |
| "loss": 2.0596, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.0626278118609407, | |
| "grad_norm": 1.864892601966858, | |
| "learning_rate": 2.5090282323810766e-07, | |
| "loss": 1.793, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.06390593047034765, | |
| "grad_norm": 3.8768982887268066, | |
| "learning_rate": 0.0, | |
| "loss": 1.6742, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06390593047034765, | |
| "eval_loss": 1.1020798683166504, | |
| "eval_runtime": 164.1474, | |
| "eval_samples_per_second": 10.04, | |
| "eval_steps_per_second": 2.51, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 8.074298032914432e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |