| { | |
| "best_metric": 6.914133336977102e-07, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1620745542949757, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032414910858995136, | |
| "grad_norm": 163.99354553222656, | |
| "learning_rate": 5e-05, | |
| "loss": 23.2476, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032414910858995136, | |
| "eval_loss": 23.247621536254883, | |
| "eval_runtime": 59.7995, | |
| "eval_samples_per_second": 34.766, | |
| "eval_steps_per_second": 4.348, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006482982171799027, | |
| "grad_norm": 165.3483123779297, | |
| "learning_rate": 0.0001, | |
| "loss": 23.2476, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009724473257698542, | |
| "grad_norm": 88.89081573486328, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 16.1311, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012965964343598054, | |
| "grad_norm": 97.12110137939453, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 12.5386, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01620745542949757, | |
| "grad_norm": 131.9464111328125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 9.6493, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.019448946515397084, | |
| "grad_norm": 162.6240692138672, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.5329, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022690437601296597, | |
| "grad_norm": 87.73365783691406, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.9982, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02593192868719611, | |
| "grad_norm": 18.822898864746094, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.744, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029173419773095625, | |
| "grad_norm": 19.17395782470703, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.7354, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03241491085899514, | |
| "grad_norm": 19.16326141357422, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.6053, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03565640194489465, | |
| "grad_norm": 20.150951385498047, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.3896, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03889789303079417, | |
| "grad_norm": 19.83761215209961, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.0912, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04213938411669368, | |
| "grad_norm": 20.850984573364258, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.7302, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04538087520259319, | |
| "grad_norm": 21.441749572753906, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3511, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04862236628849271, | |
| "grad_norm": 24.02114486694336, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.944, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05186385737439222, | |
| "grad_norm": 24.179325103759766, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.548, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.055105348460291734, | |
| "grad_norm": 16.03411865234375, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2248, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05834683954619125, | |
| "grad_norm": 4.22589111328125, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0301, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06158833063209076, | |
| "grad_norm": 0.563453197479248, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0046, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06482982171799027, | |
| "grad_norm": 0.09107520431280136, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0008, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06807131280388978, | |
| "grad_norm": 0.011570541188120842, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0713128038897893, | |
| "grad_norm": 0.0026428094133734703, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07455429497568881, | |
| "grad_norm": 0.002577363047748804, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07779578606158834, | |
| "grad_norm": 0.0005599510623142123, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08103727714748785, | |
| "grad_norm": 0.00044352569966576993, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08103727714748785, | |
| "eval_loss": 2.4557041342632147e-06, | |
| "eval_runtime": 59.7714, | |
| "eval_samples_per_second": 34.783, | |
| "eval_steps_per_second": 4.35, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08427876823338736, | |
| "grad_norm": 0.00037847296334803104, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08752025931928688, | |
| "grad_norm": 0.0007350973319262266, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09076175040518639, | |
| "grad_norm": 0.00028547627152875066, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0940032414910859, | |
| "grad_norm": 0.001375210820697248, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09724473257698542, | |
| "grad_norm": 0.00023330787371378392, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10048622366288493, | |
| "grad_norm": 0.0001925993274198845, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10372771474878444, | |
| "grad_norm": 0.00047052462468855083, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10696920583468396, | |
| "grad_norm": 0.00018358287343289703, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11021069692058347, | |
| "grad_norm": 0.00017277876031585038, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11345218800648298, | |
| "grad_norm": 0.00012110326497349888, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1166936790923825, | |
| "grad_norm": 0.00024205473891925067, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11993517017828201, | |
| "grad_norm": 0.00011354075832059607, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12317666126418152, | |
| "grad_norm": 0.0005192770040594041, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12641815235008103, | |
| "grad_norm": 0.0003913133987225592, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12965964343598055, | |
| "grad_norm": 0.00033951568184420466, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13290113452188007, | |
| "grad_norm": 0.0006607458344660699, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13614262560777957, | |
| "grad_norm": 0.00010146438580704853, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1393841166936791, | |
| "grad_norm": 0.00011652489774860442, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1426256077795786, | |
| "grad_norm": 0.0008265106589533389, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1458670988654781, | |
| "grad_norm": 0.00017233270045835525, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14910858995137763, | |
| "grad_norm": 0.0009055504924617708, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15235008103727715, | |
| "grad_norm": 0.0006764665013179183, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15559157212317667, | |
| "grad_norm": 0.0003485048655420542, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15883306320907617, | |
| "grad_norm": 9.563385538058355e-05, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1620745542949757, | |
| "grad_norm": 0.0006619396153837442, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1620745542949757, | |
| "eval_loss": 6.914133336977102e-07, | |
| "eval_runtime": 59.8999, | |
| "eval_samples_per_second": 34.708, | |
| "eval_steps_per_second": 4.341, | |
| "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": 1.589463780163584e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |