| { | |
| "best_metric": 12.451294898986816, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.38860103626943004, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0051813471502590676, | |
| "grad_norm": 0.009733538143336773, | |
| "learning_rate": 4e-05, | |
| "loss": 12.4632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0051813471502590676, | |
| "eval_loss": 12.459209442138672, | |
| "eval_runtime": 2.7206, | |
| "eval_samples_per_second": 30.141, | |
| "eval_steps_per_second": 15.07, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010362694300518135, | |
| "grad_norm": 0.00900011882185936, | |
| "learning_rate": 8e-05, | |
| "loss": 12.4665, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015544041450777202, | |
| "grad_norm": 0.010131618939340115, | |
| "learning_rate": 0.00012, | |
| "loss": 12.4591, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02072538860103627, | |
| "grad_norm": 0.014053963124752045, | |
| "learning_rate": 0.00016, | |
| "loss": 12.4641, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025906735751295335, | |
| "grad_norm": 0.013694445602595806, | |
| "learning_rate": 0.0002, | |
| "loss": 12.4626, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.031088082901554404, | |
| "grad_norm": 0.012138248421251774, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 12.4688, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03626943005181347, | |
| "grad_norm": 0.011199451982975006, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 12.452, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04145077720207254, | |
| "grad_norm": 0.01216774433851242, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 12.4551, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.046632124352331605, | |
| "grad_norm": 0.010164499282836914, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 12.4611, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05181347150259067, | |
| "grad_norm": 0.011890110559761524, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 12.4661, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05699481865284974, | |
| "grad_norm": 0.011710001155734062, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 12.4662, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06217616580310881, | |
| "grad_norm": 0.011335656978189945, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 12.4509, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06735751295336788, | |
| "grad_norm": 0.011207724921405315, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 12.461, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07253886010362694, | |
| "grad_norm": 0.012399866245687008, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 12.4604, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07772020725388601, | |
| "grad_norm": 0.012533013708889484, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 12.4634, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08290155440414508, | |
| "grad_norm": 0.012151951901614666, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 12.4559, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08808290155440414, | |
| "grad_norm": 0.013444810174405575, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 12.4702, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09326424870466321, | |
| "grad_norm": 0.015751156955957413, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 12.4622, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09844559585492228, | |
| "grad_norm": 0.016734309494495392, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 12.4618, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10362694300518134, | |
| "grad_norm": 0.01627177745103836, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 12.4723, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10880829015544041, | |
| "grad_norm": 0.01785571686923504, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 12.4617, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11398963730569948, | |
| "grad_norm": 0.01880309171974659, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 12.4674, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11917098445595854, | |
| "grad_norm": 0.01608671247959137, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 12.461, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12435233160621761, | |
| "grad_norm": 0.020015588030219078, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 12.4573, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12953367875647667, | |
| "grad_norm": 0.018211856484413147, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 12.4653, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12953367875647667, | |
| "eval_loss": 12.45799446105957, | |
| "eval_runtime": 2.7173, | |
| "eval_samples_per_second": 30.177, | |
| "eval_steps_per_second": 15.089, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13471502590673576, | |
| "grad_norm": 0.021804824471473694, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 12.4638, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13989637305699482, | |
| "grad_norm": 0.021040290594100952, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 12.4644, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14507772020725387, | |
| "grad_norm": 0.025091087445616722, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 12.4708, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.15025906735751296, | |
| "grad_norm": 0.024071145802736282, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 12.4589, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.15544041450777202, | |
| "grad_norm": 0.028311707079410553, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 12.4677, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16062176165803108, | |
| "grad_norm": 0.026514964178204536, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 12.4489, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.16580310880829016, | |
| "grad_norm": 0.03242511302232742, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 12.4624, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.17098445595854922, | |
| "grad_norm": 0.03276370093226433, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 12.461, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.17616580310880828, | |
| "grad_norm": 0.031001713126897812, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 12.4701, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.18134715025906736, | |
| "grad_norm": 0.03384930640459061, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 12.461, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.18652849740932642, | |
| "grad_norm": 0.039669886231422424, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 12.4614, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.19170984455958548, | |
| "grad_norm": 0.03610478714108467, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 12.4614, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.19689119170984457, | |
| "grad_norm": 0.04812079295516014, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 12.453, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.20207253886010362, | |
| "grad_norm": 0.04061286896467209, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 12.4646, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.20725388601036268, | |
| "grad_norm": 0.048531003296375275, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 12.4561, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21243523316062177, | |
| "grad_norm": 0.05337219685316086, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 12.4593, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.21761658031088082, | |
| "grad_norm": 0.04679669812321663, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 12.4629, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.22279792746113988, | |
| "grad_norm": 0.05289416015148163, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 12.4662, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.22797927461139897, | |
| "grad_norm": 0.06214183568954468, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 12.4517, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.23316062176165803, | |
| "grad_norm": 0.06562865525484085, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 12.4603, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.23834196891191708, | |
| "grad_norm": 0.06988850980997086, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 12.4598, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.24352331606217617, | |
| "grad_norm": 0.06310445815324783, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 12.4625, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.24870466321243523, | |
| "grad_norm": 0.07609426230192184, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 12.4652, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2538860103626943, | |
| "grad_norm": 0.05050159618258476, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 12.4593, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.25906735751295334, | |
| "grad_norm": 0.05446188151836395, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 12.4652, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.25906735751295334, | |
| "eval_loss": 12.454829216003418, | |
| "eval_runtime": 2.7166, | |
| "eval_samples_per_second": 30.184, | |
| "eval_steps_per_second": 15.092, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.26424870466321243, | |
| "grad_norm": 0.05474114790558815, | |
| "learning_rate": 0.00010495837546732224, | |
| "loss": 12.4555, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2694300518134715, | |
| "grad_norm": 0.06194544583559036, | |
| "learning_rate": 0.00010165339447663587, | |
| "loss": 12.4549, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.27461139896373055, | |
| "grad_norm": 0.07049047946929932, | |
| "learning_rate": 9.834660552336415e-05, | |
| "loss": 12.4587, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.27979274611398963, | |
| "grad_norm": 0.06702786684036255, | |
| "learning_rate": 9.504162453267777e-05, | |
| "loss": 12.4568, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2849740932642487, | |
| "grad_norm": 0.06343399733304977, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 12.4554, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.29015544041450775, | |
| "grad_norm": 0.06678463518619537, | |
| "learning_rate": 8.845153630304139e-05, | |
| "loss": 12.4561, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.29533678756476683, | |
| "grad_norm": 0.07747721672058105, | |
| "learning_rate": 8.517363522881579e-05, | |
| "loss": 12.4523, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3005181347150259, | |
| "grad_norm": 0.07417742162942886, | |
| "learning_rate": 8.191194656678904e-05, | |
| "loss": 12.4628, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.30569948186528495, | |
| "grad_norm": 0.07810303568840027, | |
| "learning_rate": 7.867003692562534e-05, | |
| "loss": 12.4572, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.31088082901554404, | |
| "grad_norm": 0.08061844110488892, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 12.4548, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3160621761658031, | |
| "grad_norm": 0.0870494544506073, | |
| "learning_rate": 7.225970912381556e-05, | |
| "loss": 12.4503, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.32124352331606215, | |
| "grad_norm": 0.08460117876529694, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 12.4587, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.32642487046632124, | |
| "grad_norm": 0.08417250216007233, | |
| "learning_rate": 6.59706825558357e-05, | |
| "loss": 12.4613, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3316062176165803, | |
| "grad_norm": 0.09139107912778854, | |
| "learning_rate": 6.28802751081779e-05, | |
| "loss": 12.453, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.33678756476683935, | |
| "grad_norm": 0.0929340347647667, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 12.4633, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.34196891191709844, | |
| "grad_norm": 0.09280311316251755, | |
| "learning_rate": 5.6824564766150726e-05, | |
| "loss": 12.4553, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3471502590673575, | |
| "grad_norm": 0.08577651530504227, | |
| "learning_rate": 5.386588370213124e-05, | |
| "loss": 12.4622, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.35233160621761656, | |
| "grad_norm": 0.10077881813049316, | |
| "learning_rate": 5.095764961694922e-05, | |
| "loss": 12.4606, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.35751295336787564, | |
| "grad_norm": 0.09882701188325882, | |
| "learning_rate": 4.810304262187852e-05, | |
| "loss": 12.4532, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3626943005181347, | |
| "grad_norm": 0.10326765477657318, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 12.4606, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.36787564766839376, | |
| "grad_norm": 0.101172536611557, | |
| "learning_rate": 4.256713373170564e-05, | |
| "loss": 12.4627, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.37305699481865284, | |
| "grad_norm": 0.09795894473791122, | |
| "learning_rate": 3.9891885271697496e-05, | |
| "loss": 12.4615, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.37823834196891193, | |
| "grad_norm": 0.10780131071805954, | |
| "learning_rate": 3.7282364152646297e-05, | |
| "loss": 12.4575, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.38341968911917096, | |
| "grad_norm": 0.11272040009498596, | |
| "learning_rate": 3.4741423847583134e-05, | |
| "loss": 12.4538, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.38860103626943004, | |
| "grad_norm": 0.10471823811531067, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 12.4525, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.38860103626943004, | |
| "eval_loss": 12.451294898986816, | |
| "eval_runtime": 2.7116, | |
| "eval_samples_per_second": 30.241, | |
| "eval_steps_per_second": 15.12, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 92484403200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |