| { | |
| "best_metric": 1.3470451831817627, | |
| "best_model_checkpoint": "./output/checkpoint-4200", | |
| "epoch": 0.11244377811094453, | |
| "eval_steps": 150, | |
| "global_step": 4200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002677232812165346, | |
| "grad_norm": 12.16030502319336, | |
| "learning_rate": 4.4e-06, | |
| "loss": 1.5442, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005354465624330692, | |
| "grad_norm": 12.028721809387207, | |
| "learning_rate": 8.8e-06, | |
| "loss": 1.5341, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008031698436496038, | |
| "grad_norm": 9.741438865661621, | |
| "learning_rate": 1.3199999999999999e-05, | |
| "loss": 1.5258, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0010708931248661383, | |
| "grad_norm": 11.791377067565918, | |
| "learning_rate": 1.76e-05, | |
| "loss": 1.4766, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0013386164060826729, | |
| "grad_norm": 10.31489372253418, | |
| "learning_rate": 2.2e-05, | |
| "loss": 1.4898, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0016063396872992076, | |
| "grad_norm": 11.65046501159668, | |
| "learning_rate": 2.6399999999999998e-05, | |
| "loss": 1.4536, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0018740629685157421, | |
| "grad_norm": 11.001107215881348, | |
| "learning_rate": 3.0799999999999996e-05, | |
| "loss": 1.4933, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0021417862497322766, | |
| "grad_norm": 10.670427322387695, | |
| "learning_rate": 3.52e-05, | |
| "loss": 1.4816, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.002409509530948811, | |
| "grad_norm": 11.35387134552002, | |
| "learning_rate": 3.96e-05, | |
| "loss": 1.4636, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0026772328121653457, | |
| "grad_norm": 10.275943756103516, | |
| "learning_rate": 4.4e-05, | |
| "loss": 1.4996, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0029449560933818807, | |
| "grad_norm": 9.64588451385498, | |
| "learning_rate": 4.399954783308405e-05, | |
| "loss": 1.5114, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.003212679374598415, | |
| "grad_norm": 9.566597938537598, | |
| "learning_rate": 4.399819135092302e-05, | |
| "loss": 1.542, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0034804026558149497, | |
| "grad_norm": 10.304100036621094, | |
| "learning_rate": 4.399593060927658e-05, | |
| "loss": 1.4911, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0037481259370314842, | |
| "grad_norm": 8.622906684875488, | |
| "learning_rate": 4.3992765701074955e-05, | |
| "loss": 1.4655, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.004015849218248019, | |
| "grad_norm": 9.855925559997559, | |
| "learning_rate": 4.398869675641513e-05, | |
| "loss": 1.5424, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.004015849218248019, | |
| "eval_loss": 1.5061633586883545, | |
| "eval_runtime": 76.7585, | |
| "eval_samples_per_second": 6.514, | |
| "eval_steps_per_second": 6.514, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.004283572499464553, | |
| "grad_norm": 9.257708549499512, | |
| "learning_rate": 4.398372394255549e-05, | |
| "loss": 1.4863, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.004551295780681088, | |
| "grad_norm": 7.029283046722412, | |
| "learning_rate": 4.397784746390892e-05, | |
| "loss": 1.504, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.004819019061897622, | |
| "grad_norm": 8.059552192687988, | |
| "learning_rate": 4.3971067562034454e-05, | |
| "loss": 1.4734, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.005086742343114157, | |
| "grad_norm": 8.756830215454102, | |
| "learning_rate": 4.39633845156273e-05, | |
| "loss": 1.5308, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.005354465624330691, | |
| "grad_norm": 8.60611629486084, | |
| "learning_rate": 4.39547986405074e-05, | |
| "loss": 1.4985, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.005622188905547227, | |
| "grad_norm": 8.613848686218262, | |
| "learning_rate": 4.3945310289606455e-05, | |
| "loss": 1.493, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.005889912186763761, | |
| "grad_norm": 7.788877010345459, | |
| "learning_rate": 4.39349198529534e-05, | |
| "loss": 1.492, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.006157635467980296, | |
| "grad_norm": 7.323453903198242, | |
| "learning_rate": 4.39236277576584e-05, | |
| "loss": 1.5138, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.00642535874919683, | |
| "grad_norm": 7.350474834442139, | |
| "learning_rate": 4.391143446789526e-05, | |
| "loss": 1.5314, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.006693082030413365, | |
| "grad_norm": 7.383894443511963, | |
| "learning_rate": 4.389834048488236e-05, | |
| "loss": 1.5231, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.006960805311629899, | |
| "grad_norm": 7.436572551727295, | |
| "learning_rate": 4.388434634686206e-05, | |
| "loss": 1.5264, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.007228528592846434, | |
| "grad_norm": 7.9078779220581055, | |
| "learning_rate": 4.386945262907856e-05, | |
| "loss": 1.4744, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.0074962518740629685, | |
| "grad_norm": 7.032011985778809, | |
| "learning_rate": 4.3853659943754275e-05, | |
| "loss": 1.4156, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.007763975155279503, | |
| "grad_norm": 7.743986129760742, | |
| "learning_rate": 4.383696894006463e-05, | |
| "loss": 1.5338, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.008031698436496038, | |
| "grad_norm": 7.996994495391846, | |
| "learning_rate": 4.381938030411141e-05, | |
| "loss": 1.4912, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.008031698436496038, | |
| "eval_loss": 1.5058677196502686, | |
| "eval_runtime": 76.63, | |
| "eval_samples_per_second": 6.525, | |
| "eval_steps_per_second": 6.525, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.008299421717712573, | |
| "grad_norm": 6.838953971862793, | |
| "learning_rate": 4.380089475889457e-05, | |
| "loss": 1.4854, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.008567144998929107, | |
| "grad_norm": 7.260242462158203, | |
| "learning_rate": 4.378151306428244e-05, | |
| "loss": 1.5401, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.008834868280145642, | |
| "grad_norm": 6.737756729125977, | |
| "learning_rate": 4.3761236016980594e-05, | |
| "loss": 1.5013, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.009102591561362176, | |
| "grad_norm": 6.963688373565674, | |
| "learning_rate": 4.3740064450499026e-05, | |
| "loss": 1.4989, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.009370314842578711, | |
| "grad_norm": 7.6938557624816895, | |
| "learning_rate": 4.37179992351179e-05, | |
| "loss": 1.5317, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.009638038123795245, | |
| "grad_norm": 6.700031757354736, | |
| "learning_rate": 4.3695041277851804e-05, | |
| "loss": 1.405, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.00990576140501178, | |
| "grad_norm": 6.925078868865967, | |
| "learning_rate": 4.367119152241245e-05, | |
| "loss": 1.4966, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.010173484686228314, | |
| "grad_norm": 6.87849235534668, | |
| "learning_rate": 4.364645094916985e-05, | |
| "loss": 1.4933, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.01044120796744485, | |
| "grad_norm": 8.074585914611816, | |
| "learning_rate": 4.3620820575112083e-05, | |
| "loss": 1.4782, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.010708931248661383, | |
| "grad_norm": 7.07144832611084, | |
| "learning_rate": 4.359430145380344e-05, | |
| "loss": 1.4871, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.010976654529877918, | |
| "grad_norm": 7.2088117599487305, | |
| "learning_rate": 4.356689467534112e-05, | |
| "loss": 1.4855, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.011244377811094454, | |
| "grad_norm": 7.868666648864746, | |
| "learning_rate": 4.353860136631044e-05, | |
| "loss": 1.5246, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.011512101092310987, | |
| "grad_norm": 7.853616237640381, | |
| "learning_rate": 4.350942268973854e-05, | |
| "loss": 1.5302, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.011779824373527523, | |
| "grad_norm": 7.353667259216309, | |
| "learning_rate": 4.347935984504649e-05, | |
| "loss": 1.4305, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.012047547654744056, | |
| "grad_norm": 6.460302352905273, | |
| "learning_rate": 4.344841406800012e-05, | |
| "loss": 1.4506, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.012047547654744056, | |
| "eval_loss": 1.4909805059432983, | |
| "eval_runtime": 76.606, | |
| "eval_samples_per_second": 6.527, | |
| "eval_steps_per_second": 6.527, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.012315270935960592, | |
| "grad_norm": 7.3225226402282715, | |
| "learning_rate": 4.34165866306591e-05, | |
| "loss": 1.461, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.012582994217177125, | |
| "grad_norm": 6.5725297927856445, | |
| "learning_rate": 4.3383878841324734e-05, | |
| "loss": 1.4007, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.01285071749839366, | |
| "grad_norm": 7.1205315589904785, | |
| "learning_rate": 4.3350292044486125e-05, | |
| "loss": 1.557, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.013118440779610194, | |
| "grad_norm": 6.783862113952637, | |
| "learning_rate": 4.331582762076494e-05, | |
| "loss": 1.5214, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.01338616406082673, | |
| "grad_norm": 6.475296974182129, | |
| "learning_rate": 4.328048698685865e-05, | |
| "loss": 1.4874, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.013653887342043263, | |
| "grad_norm": 7.158287525177002, | |
| "learning_rate": 4.32442715954823e-05, | |
| "loss": 1.4794, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.013921610623259799, | |
| "grad_norm": 5.706000804901123, | |
| "learning_rate": 4.320718293530877e-05, | |
| "loss": 1.4921, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.014189333904476333, | |
| "grad_norm": 7.483499050140381, | |
| "learning_rate": 4.3169222530907634e-05, | |
| "loss": 1.4899, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.014457057185692868, | |
| "grad_norm": 6.9520182609558105, | |
| "learning_rate": 4.313039194268243e-05, | |
| "loss": 1.4908, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.014724780466909402, | |
| "grad_norm": 6.7435784339904785, | |
| "learning_rate": 4.309069276680653e-05, | |
| "loss": 1.45, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.014992503748125937, | |
| "grad_norm": 7.162035942077637, | |
| "learning_rate": 4.305012663515759e-05, | |
| "loss": 1.4702, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.015260227029342472, | |
| "grad_norm": 6.717561721801758, | |
| "learning_rate": 4.300869521525039e-05, | |
| "loss": 1.5131, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.015527950310559006, | |
| "grad_norm": 6.205082893371582, | |
| "learning_rate": 4.296640021016832e-05, | |
| "loss": 1.4342, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.01579567359177554, | |
| "grad_norm": 6.673497676849365, | |
| "learning_rate": 4.292324335849338e-05, | |
| "loss": 1.4917, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.016063396872992075, | |
| "grad_norm": 6.291605472564697, | |
| "learning_rate": 4.287922643423471e-05, | |
| "loss": 1.5018, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.016063396872992075, | |
| "eval_loss": 1.476717472076416, | |
| "eval_runtime": 76.7435, | |
| "eval_samples_per_second": 6.515, | |
| "eval_steps_per_second": 6.515, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.01633112015420861, | |
| "grad_norm": 6.723529815673828, | |
| "learning_rate": 4.283435124675567e-05, | |
| "loss": 1.4652, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.016598843435425146, | |
| "grad_norm": 6.2483062744140625, | |
| "learning_rate": 4.278861964069944e-05, | |
| "loss": 1.5094, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.01686656671664168, | |
| "grad_norm": 6.773886203765869, | |
| "learning_rate": 4.274203349591324e-05, | |
| "loss": 1.4771, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.017134289997858213, | |
| "grad_norm": 7.28003454208374, | |
| "learning_rate": 4.269459472737102e-05, | |
| "loss": 1.436, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.017402013279074747, | |
| "grad_norm": 6.813667297363281, | |
| "learning_rate": 4.264630528509473e-05, | |
| "loss": 1.4094, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.017669736560291284, | |
| "grad_norm": 7.017402172088623, | |
| "learning_rate": 4.259716715407422e-05, | |
| "loss": 1.5255, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.017937459841507818, | |
| "grad_norm": 7.313465595245361, | |
| "learning_rate": 4.254718235418559e-05, | |
| "loss": 1.4647, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.01820518312272435, | |
| "grad_norm": 6.323640823364258, | |
| "learning_rate": 4.249635294010819e-05, | |
| "loss": 1.4799, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.01847290640394089, | |
| "grad_norm": 7.1620588302612305, | |
| "learning_rate": 4.244468100124014e-05, | |
| "loss": 1.4344, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.018740629685157422, | |
| "grad_norm": 6.160943508148193, | |
| "learning_rate": 4.239216866161248e-05, | |
| "loss": 1.516, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.019008352966373956, | |
| "grad_norm": 6.571516036987305, | |
| "learning_rate": 4.233881807980179e-05, | |
| "loss": 1.5133, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.01927607624759049, | |
| "grad_norm": 5.696547031402588, | |
| "learning_rate": 4.228463144884155e-05, | |
| "loss": 1.4318, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.019543799528807027, | |
| "grad_norm": 6.653096675872803, | |
| "learning_rate": 4.2229610996131915e-05, | |
| "loss": 1.461, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.01981152281002356, | |
| "grad_norm": 6.497095584869385, | |
| "learning_rate": 4.217375898334819e-05, | |
| "loss": 1.4359, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.020079246091240094, | |
| "grad_norm": 6.566861629486084, | |
| "learning_rate": 4.211707770634788e-05, | |
| "loss": 1.445, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.020079246091240094, | |
| "eval_loss": 1.4696097373962402, | |
| "eval_runtime": 76.6203, | |
| "eval_samples_per_second": 6.526, | |
| "eval_steps_per_second": 6.526, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.020346969372456628, | |
| "grad_norm": 6.802274703979492, | |
| "learning_rate": 4.205956949507625e-05, | |
| "loss": 1.4485, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.020614692653673165, | |
| "grad_norm": 6.832027912139893, | |
| "learning_rate": 4.200123671347065e-05, | |
| "loss": 1.5034, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.0208824159348897, | |
| "grad_norm": 7.041072368621826, | |
| "learning_rate": 4.1942081759363236e-05, | |
| "loss": 1.5225, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.021150139216106232, | |
| "grad_norm": 6.773481369018555, | |
| "learning_rate": 4.1882107064382496e-05, | |
| "loss": 1.4718, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.021417862497322766, | |
| "grad_norm": 6.902709007263184, | |
| "learning_rate": 4.1821315093853216e-05, | |
| "loss": 1.4562, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.021685585778539303, | |
| "grad_norm": 5.957550048828125, | |
| "learning_rate": 4.1759708346695215e-05, | |
| "loss": 1.4798, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.021953309059755836, | |
| "grad_norm": 6.139000415802002, | |
| "learning_rate": 4.1697289355320565e-05, | |
| "loss": 1.5084, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.02222103234097237, | |
| "grad_norm": 6.227492332458496, | |
| "learning_rate": 4.1634060685529527e-05, | |
| "loss": 1.4597, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.022488755622188907, | |
| "grad_norm": 6.531513214111328, | |
| "learning_rate": 4.157002493640506e-05, | |
| "loss": 1.4326, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.02275647890340544, | |
| "grad_norm": 6.589105606079102, | |
| "learning_rate": 4.1505184740206006e-05, | |
| "loss": 1.431, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.023024202184621975, | |
| "grad_norm": 6.289806842803955, | |
| "learning_rate": 4.143954276225886e-05, | |
| "loss": 1.5167, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.023291925465838508, | |
| "grad_norm": 6.444394111633301, | |
| "learning_rate": 4.1373101700848235e-05, | |
| "loss": 1.4948, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.023559648747055045, | |
| "grad_norm": 6.666561126708984, | |
| "learning_rate": 4.1305864287105946e-05, | |
| "loss": 1.4879, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.02382737202827158, | |
| "grad_norm": 6.169593811035156, | |
| "learning_rate": 4.12378332848987e-05, | |
| "loss": 1.5557, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.024095095309488113, | |
| "grad_norm": 6.8753743171691895, | |
| "learning_rate": 4.116901149071457e-05, | |
| "loss": 1.4446, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.024095095309488113, | |
| "eval_loss": 1.4628037214279175, | |
| "eval_runtime": 76.661, | |
| "eval_samples_per_second": 6.522, | |
| "eval_steps_per_second": 6.522, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.024362818590704646, | |
| "grad_norm": 6.948112964630127, | |
| "learning_rate": 4.1099401733547925e-05, | |
| "loss": 1.4916, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.024630541871921183, | |
| "grad_norm": 6.508751392364502, | |
| "learning_rate": 4.102900687478326e-05, | |
| "loss": 1.4659, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.024898265153137717, | |
| "grad_norm": 6.732906818389893, | |
| "learning_rate": 4.095782980807749e-05, | |
| "loss": 1.4834, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.02516598843435425, | |
| "grad_norm": 6.261349678039551, | |
| "learning_rate": 4.088587345924105e-05, | |
| "loss": 1.4585, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.025433711715570784, | |
| "grad_norm": 5.926994323730469, | |
| "learning_rate": 4.081314078611762e-05, | |
| "loss": 1.4887, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.02570143499678732, | |
| "grad_norm": 6.746396064758301, | |
| "learning_rate": 4.073963477846249e-05, | |
| "loss": 1.4561, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.025969158278003855, | |
| "grad_norm": 6.503916263580322, | |
| "learning_rate": 4.066535845781975e-05, | |
| "loss": 1.5013, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.02623688155922039, | |
| "grad_norm": 6.83921480178833, | |
| "learning_rate": 4.059031487739803e-05, | |
| "loss": 1.517, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.026504604840436926, | |
| "grad_norm": 6.210860252380371, | |
| "learning_rate": 4.051450712194497e-05, | |
| "loss": 1.4849, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.02677232812165346, | |
| "grad_norm": 6.381270885467529, | |
| "learning_rate": 4.043793830762049e-05, | |
| "loss": 1.4685, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.027040051402869993, | |
| "grad_norm": 6.763075351715088, | |
| "learning_rate": 4.036061158186866e-05, | |
| "loss": 1.5412, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.027307774684086527, | |
| "grad_norm": 6.492913722991943, | |
| "learning_rate": 4.028253012328828e-05, | |
| "loss": 1.4398, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.027575497965303064, | |
| "grad_norm": 6.383675575256348, | |
| "learning_rate": 4.0203697141502323e-05, | |
| "loss": 1.4514, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.027843221246519598, | |
| "grad_norm": 6.685030937194824, | |
| "learning_rate": 4.0124115877025874e-05, | |
| "loss": 1.4688, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.02811094452773613, | |
| "grad_norm": 6.681553840637207, | |
| "learning_rate": 4.004378960113303e-05, | |
| "loss": 1.4862, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.02811094452773613, | |
| "eval_loss": 1.4577986001968384, | |
| "eval_runtime": 76.6839, | |
| "eval_samples_per_second": 6.52, | |
| "eval_steps_per_second": 6.52, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.028378667808952665, | |
| "grad_norm": 6.192584037780762, | |
| "learning_rate": 3.996272161572237e-05, | |
| "loss": 1.4383, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.028646391090169202, | |
| "grad_norm": 6.383575439453125, | |
| "learning_rate": 3.988091525318126e-05, | |
| "loss": 1.4015, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.028914114371385736, | |
| "grad_norm": 7.042336940765381, | |
| "learning_rate": 3.979837387624884e-05, | |
| "loss": 1.468, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.02918183765260227, | |
| "grad_norm": 6.60390567779541, | |
| "learning_rate": 3.971510087787784e-05, | |
| "loss": 1.4932, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.029449560933818803, | |
| "grad_norm": 6.5373029708862305, | |
| "learning_rate": 3.9631099681095044e-05, | |
| "loss": 1.4381, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.02971728421503534, | |
| "grad_norm": 7.118472099304199, | |
| "learning_rate": 3.954637373886066e-05, | |
| "loss": 1.4057, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.029985007496251874, | |
| "grad_norm": 7.386786460876465, | |
| "learning_rate": 3.9460926533926315e-05, | |
| "loss": 1.4978, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.030252730777468408, | |
| "grad_norm": 6.418981552124023, | |
| "learning_rate": 3.937476157869193e-05, | |
| "loss": 1.4897, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.030520454058684945, | |
| "grad_norm": 5.941694259643555, | |
| "learning_rate": 3.9287882415061334e-05, | |
| "loss": 1.4381, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.03078817733990148, | |
| "grad_norm": 6.574525833129883, | |
| "learning_rate": 3.9200292614296655e-05, | |
| "loss": 1.4143, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.031055900621118012, | |
| "grad_norm": 6.349545478820801, | |
| "learning_rate": 3.911199577687154e-05, | |
| "loss": 1.3937, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.03132362390233455, | |
| "grad_norm": 6.873767375946045, | |
| "learning_rate": 3.902299553232315e-05, | |
| "loss": 1.4515, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.03159134718355108, | |
| "grad_norm": 6.043056964874268, | |
| "learning_rate": 3.893329553910293e-05, | |
| "loss": 1.5538, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.031859070464767617, | |
| "grad_norm": 6.418127059936523, | |
| "learning_rate": 3.884289948442628e-05, | |
| "loss": 1.4745, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.03212679374598415, | |
| "grad_norm": 6.102353096008301, | |
| "learning_rate": 3.875181108412096e-05, | |
| "loss": 1.4772, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.03212679374598415, | |
| "eval_loss": 1.449093222618103, | |
| "eval_runtime": 76.8079, | |
| "eval_samples_per_second": 6.51, | |
| "eval_steps_per_second": 6.51, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.032394517027200684, | |
| "grad_norm": 6.624678134918213, | |
| "learning_rate": 3.8660034082474316e-05, | |
| "loss": 1.4526, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.03266224030841722, | |
| "grad_norm": 6.601352214813232, | |
| "learning_rate": 3.856757225207944e-05, | |
| "loss": 1.5247, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.03292996358963375, | |
| "grad_norm": 6.580589771270752, | |
| "learning_rate": 3.847442939368002e-05, | |
| "loss": 1.4694, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.03319768687085029, | |
| "grad_norm": 5.504952430725098, | |
| "learning_rate": 3.8380609336014156e-05, | |
| "loss": 1.411, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.033465410152066825, | |
| "grad_norm": 6.643352508544922, | |
| "learning_rate": 3.828611593565694e-05, | |
| "loss": 1.4278, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.03373313343328336, | |
| "grad_norm": 6.425754070281982, | |
| "learning_rate": 3.819095307686197e-05, | |
| "loss": 1.4253, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.03400085671449989, | |
| "grad_norm": 6.0909504890441895, | |
| "learning_rate": 3.809512467140163e-05, | |
| "loss": 1.4681, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.034268579995716426, | |
| "grad_norm": 5.82462215423584, | |
| "learning_rate": 3.799863465840634e-05, | |
| "loss": 1.4275, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.03453630327693296, | |
| "grad_norm": 6.24934720993042, | |
| "learning_rate": 3.790148700420261e-05, | |
| "loss": 1.4313, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.034804026558149494, | |
| "grad_norm": 6.211289882659912, | |
| "learning_rate": 3.7803685702150006e-05, | |
| "loss": 1.4216, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.035071749839366034, | |
| "grad_norm": 5.66799259185791, | |
| "learning_rate": 3.7705234772476984e-05, | |
| "loss": 1.4799, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.03533947312058257, | |
| "grad_norm": 6.351191997528076, | |
| "learning_rate": 3.760613826211567e-05, | |
| "loss": 1.4281, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.0356071964017991, | |
| "grad_norm": 5.707607269287109, | |
| "learning_rate": 3.7506400244535455e-05, | |
| "loss": 1.463, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.035874919683015635, | |
| "grad_norm": 5.780487537384033, | |
| "learning_rate": 3.740602481957561e-05, | |
| "loss": 1.4731, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.03614264296423217, | |
| "grad_norm": 5.354376316070557, | |
| "learning_rate": 3.7305016113276704e-05, | |
| "loss": 1.4492, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.03614264296423217, | |
| "eval_loss": 1.444738745689392, | |
| "eval_runtime": 76.8239, | |
| "eval_samples_per_second": 6.508, | |
| "eval_steps_per_second": 6.508, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.0364103662454487, | |
| "grad_norm": 5.93463134765625, | |
| "learning_rate": 3.7203378277711024e-05, | |
| "loss": 1.4602, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.036678089526665236, | |
| "grad_norm": 5.922112464904785, | |
| "learning_rate": 3.710111549081191e-05, | |
| "loss": 1.4412, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.03694581280788178, | |
| "grad_norm": 6.667977809906006, | |
| "learning_rate": 3.699823195620199e-05, | |
| "loss": 1.4475, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.03721353608909831, | |
| "grad_norm": 6.021790504455566, | |
| "learning_rate": 3.689473190302041e-05, | |
| "loss": 1.4206, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.037481259370314844, | |
| "grad_norm": 6.152276039123535, | |
| "learning_rate": 3.679061958574897e-05, | |
| "loss": 1.4288, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.03774898265153138, | |
| "grad_norm": 5.695444583892822, | |
| "learning_rate": 3.668589928403726e-05, | |
| "loss": 1.4424, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.03801670593274791, | |
| "grad_norm": 6.346884727478027, | |
| "learning_rate": 3.6580575302526706e-05, | |
| "loss": 1.5001, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.038284429213964445, | |
| "grad_norm": 5.674633979797363, | |
| "learning_rate": 3.647465197067368e-05, | |
| "loss": 1.4796, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.03855215249518098, | |
| "grad_norm": 6.168262481689453, | |
| "learning_rate": 3.6368133642571464e-05, | |
| "loss": 1.4428, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.03881987577639751, | |
| "grad_norm": 6.4981369972229, | |
| "learning_rate": 3.6261024696771345e-05, | |
| "loss": 1.4281, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.03908759905761405, | |
| "grad_norm": 5.703588962554932, | |
| "learning_rate": 3.615332953610255e-05, | |
| "loss": 1.3934, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.03935532233883059, | |
| "grad_norm": 5.69433069229126, | |
| "learning_rate": 3.604505258749132e-05, | |
| "loss": 1.4482, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.03962304562004712, | |
| "grad_norm": 5.763268947601318, | |
| "learning_rate": 3.5936198301778945e-05, | |
| "loss": 1.4629, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.039890768901263654, | |
| "grad_norm": 6.472227096557617, | |
| "learning_rate": 3.5826771153538716e-05, | |
| "loss": 1.4301, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.04015849218248019, | |
| "grad_norm": 6.155264854431152, | |
| "learning_rate": 3.571677564089214e-05, | |
| "loss": 1.4703, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04015849218248019, | |
| "eval_loss": 1.4356995820999146, | |
| "eval_runtime": 76.8148, | |
| "eval_samples_per_second": 6.509, | |
| "eval_steps_per_second": 6.509, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04042621546369672, | |
| "grad_norm": 6.241977214813232, | |
| "learning_rate": 3.560621628532389e-05, | |
| "loss": 1.4461, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.040693938744913255, | |
| "grad_norm": 6.195336818695068, | |
| "learning_rate": 3.5495097631496066e-05, | |
| "loss": 1.3735, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.040961662026129796, | |
| "grad_norm": 5.899549961090088, | |
| "learning_rate": 3.5383424247061286e-05, | |
| "loss": 1.4787, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.04122938530734633, | |
| "grad_norm": 6.187289714813232, | |
| "learning_rate": 3.5271200722475e-05, | |
| "loss": 1.4413, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.04149710858856286, | |
| "grad_norm": 5.872448444366455, | |
| "learning_rate": 3.515843167080675e-05, | |
| "loss": 1.4317, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.0417648318697794, | |
| "grad_norm": 6.877863883972168, | |
| "learning_rate": 3.5045121727550566e-05, | |
| "loss": 1.4593, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.04203255515099593, | |
| "grad_norm": 6.644635200500488, | |
| "learning_rate": 3.493127555043441e-05, | |
| "loss": 1.4622, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.042300278432212464, | |
| "grad_norm": 6.314537525177002, | |
| "learning_rate": 3.481689781922871e-05, | |
| "loss": 1.5365, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.042568001713429, | |
| "grad_norm": 6.645462989807129, | |
| "learning_rate": 3.470199323555403e-05, | |
| "loss": 1.4534, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.04283572499464553, | |
| "grad_norm": 6.462603569030762, | |
| "learning_rate": 3.4586566522687734e-05, | |
| "loss": 1.4786, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.04310344827586207, | |
| "grad_norm": 6.516161918640137, | |
| "learning_rate": 3.44706224253699e-05, | |
| "loss": 1.3987, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.043371171557078605, | |
| "grad_norm": 6.5383076667785645, | |
| "learning_rate": 3.435416570960824e-05, | |
| "loss": 1.4993, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.04363889483829514, | |
| "grad_norm": 6.37644100189209, | |
| "learning_rate": 3.4237201162482225e-05, | |
| "loss": 1.4527, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.04390661811951167, | |
| "grad_norm": 6.744267463684082, | |
| "learning_rate": 3.411973359194625e-05, | |
| "loss": 1.4213, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.044174341400728206, | |
| "grad_norm": 6.487947463989258, | |
| "learning_rate": 3.400176782663207e-05, | |
| "loss": 1.4266, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.044174341400728206, | |
| "eval_loss": 1.4300212860107422, | |
| "eval_runtime": 76.7363, | |
| "eval_samples_per_second": 6.516, | |
| "eval_steps_per_second": 6.516, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.04444206468194474, | |
| "grad_norm": 5.463531494140625, | |
| "learning_rate": 3.3883308715650246e-05, | |
| "loss": 1.4868, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.044709787963161274, | |
| "grad_norm": 6.814722537994385, | |
| "learning_rate": 3.3764361128390853e-05, | |
| "loss": 1.441, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.044977511244377814, | |
| "grad_norm": 5.653580665588379, | |
| "learning_rate": 3.3644929954323324e-05, | |
| "loss": 1.4674, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.04524523452559435, | |
| "grad_norm": 5.94467306137085, | |
| "learning_rate": 3.3525020102795434e-05, | |
| "loss": 1.4337, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.04551295780681088, | |
| "grad_norm": 6.066728115081787, | |
| "learning_rate": 3.3404636502831555e-05, | |
| "loss": 1.4701, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.045780681088027415, | |
| "grad_norm": 6.075364112854004, | |
| "learning_rate": 3.328378410292994e-05, | |
| "loss": 1.4264, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.04604840436924395, | |
| "grad_norm": 6.536380290985107, | |
| "learning_rate": 3.3162467870859404e-05, | |
| "loss": 1.4928, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.04631612765046048, | |
| "grad_norm": 6.932302951812744, | |
| "learning_rate": 3.3040692793455106e-05, | |
| "loss": 1.4472, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.046583850931677016, | |
| "grad_norm": 6.54493522644043, | |
| "learning_rate": 3.2918463876413504e-05, | |
| "loss": 1.3929, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.04685157421289355, | |
| "grad_norm": 5.732593059539795, | |
| "learning_rate": 3.279578614408664e-05, | |
| "loss": 1.4182, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.04711929749411009, | |
| "grad_norm": 6.897890090942383, | |
| "learning_rate": 3.2672664639275584e-05, | |
| "loss": 1.466, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.047387020775326624, | |
| "grad_norm": 6.196009159088135, | |
| "learning_rate": 3.254910442302319e-05, | |
| "loss": 1.4552, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.04765474405654316, | |
| "grad_norm": 6.375300407409668, | |
| "learning_rate": 3.242511057440597e-05, | |
| "loss": 1.4139, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.04792246733775969, | |
| "grad_norm": 5.817831993103027, | |
| "learning_rate": 3.2300688190325404e-05, | |
| "loss": 1.4855, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.048190190618976225, | |
| "grad_norm": 5.730225563049316, | |
| "learning_rate": 3.217584238529838e-05, | |
| "loss": 1.3845, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.048190190618976225, | |
| "eval_loss": 1.4201979637145996, | |
| "eval_runtime": 76.7247, | |
| "eval_samples_per_second": 6.517, | |
| "eval_steps_per_second": 6.517, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.04845791390019276, | |
| "grad_norm": 7.2009382247924805, | |
| "learning_rate": 3.205057829124693e-05, | |
| "loss": 1.3661, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.04872563718140929, | |
| "grad_norm": 6.178856372833252, | |
| "learning_rate": 3.192490105728736e-05, | |
| "loss": 1.4082, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.04899336046262583, | |
| "grad_norm": 5.327315330505371, | |
| "learning_rate": 3.17988158495185e-05, | |
| "loss": 1.4033, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.04926108374384237, | |
| "grad_norm": 5.719634532928467, | |
| "learning_rate": 3.1672327850809405e-05, | |
| "loss": 1.4505, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.0495288070250589, | |
| "grad_norm": 6.736356735229492, | |
| "learning_rate": 3.154544226058628e-05, | |
| "loss": 1.4521, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.049796530306275434, | |
| "grad_norm": 5.911272048950195, | |
| "learning_rate": 3.1418164294618766e-05, | |
| "loss": 1.452, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.05006425358749197, | |
| "grad_norm": 6.058777332305908, | |
| "learning_rate": 3.129049918480552e-05, | |
| "loss": 1.4431, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.0503319768687085, | |
| "grad_norm": 5.928140640258789, | |
| "learning_rate": 3.116245217895918e-05, | |
| "loss": 1.4781, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.050599700149925035, | |
| "grad_norm": 5.614587783813477, | |
| "learning_rate": 3.1034028540590635e-05, | |
| "loss": 1.3831, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.05086742343114157, | |
| "grad_norm": 6.133342742919922, | |
| "learning_rate": 3.090523354869266e-05, | |
| "loss": 1.4711, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.05113514671235811, | |
| "grad_norm": 7.014552593231201, | |
| "learning_rate": 3.0776072497522916e-05, | |
| "loss": 1.4404, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.05140286999357464, | |
| "grad_norm": 7.53794002532959, | |
| "learning_rate": 3.064655069638632e-05, | |
| "loss": 1.4262, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.05167059327479118, | |
| "grad_norm": 5.97748327255249, | |
| "learning_rate": 3.0516673469416818e-05, | |
| "loss": 1.3836, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.05193831655600771, | |
| "grad_norm": 5.628602504730225, | |
| "learning_rate": 3.0386446155358518e-05, | |
| "loss": 1.4083, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.052206039837224244, | |
| "grad_norm": 6.5765380859375, | |
| "learning_rate": 3.0255874107346232e-05, | |
| "loss": 1.4374, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.052206039837224244, | |
| "eval_loss": 1.4104682207107544, | |
| "eval_runtime": 76.7665, | |
| "eval_samples_per_second": 6.513, | |
| "eval_steps_per_second": 6.513, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.05247376311844078, | |
| "grad_norm": 6.185977458953857, | |
| "learning_rate": 3.012496269268544e-05, | |
| "loss": 1.4185, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.05274148639965731, | |
| "grad_norm": 6.482154846191406, | |
| "learning_rate": 2.9993717292631652e-05, | |
| "loss": 1.4446, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.05300920968087385, | |
| "grad_norm": 6.260786056518555, | |
| "learning_rate": 2.9862143302169223e-05, | |
| "loss": 1.4123, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.053276932962090386, | |
| "grad_norm": 6.361741542816162, | |
| "learning_rate": 2.9730246129789542e-05, | |
| "loss": 1.4646, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.05354465624330692, | |
| "grad_norm": 6.388660430908203, | |
| "learning_rate": 2.9598031197268768e-05, | |
| "loss": 1.4232, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05381237952452345, | |
| "grad_norm": 6.549992084503174, | |
| "learning_rate": 2.946550393944493e-05, | |
| "loss": 1.398, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.05408010280573999, | |
| "grad_norm": 5.965968132019043, | |
| "learning_rate": 2.933266980399452e-05, | |
| "loss": 1.3618, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.05434782608695652, | |
| "grad_norm": 6.706049919128418, | |
| "learning_rate": 2.9199534251208573e-05, | |
| "loss": 1.4274, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.054615549368173054, | |
| "grad_norm": 5.7372355461120605, | |
| "learning_rate": 2.9066102753768204e-05, | |
| "loss": 1.3954, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.05488327264938959, | |
| "grad_norm": 6.6037468910217285, | |
| "learning_rate": 2.893238079651966e-05, | |
| "loss": 1.3763, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.05515099593060613, | |
| "grad_norm": 6.51908540725708, | |
| "learning_rate": 2.8798373876248843e-05, | |
| "loss": 1.3945, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.05541871921182266, | |
| "grad_norm": 6.044327259063721, | |
| "learning_rate": 2.8664087501455387e-05, | |
| "loss": 1.4487, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.055686442493039195, | |
| "grad_norm": 6.289717674255371, | |
| "learning_rate": 2.852952719212619e-05, | |
| "loss": 1.4311, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.05595416577425573, | |
| "grad_norm": 5.992395401000977, | |
| "learning_rate": 2.8394698479508542e-05, | |
| "loss": 1.3859, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.05622188905547226, | |
| "grad_norm": 6.025457382202148, | |
| "learning_rate": 2.8259606905882712e-05, | |
| "loss": 1.4162, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.05622188905547226, | |
| "eval_loss": 1.4084678888320923, | |
| "eval_runtime": 76.754, | |
| "eval_samples_per_second": 6.514, | |
| "eval_steps_per_second": 6.514, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.056489612336688796, | |
| "grad_norm": 5.75090217590332, | |
| "learning_rate": 2.8124258024334192e-05, | |
| "loss": 1.4478, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.05675733561790533, | |
| "grad_norm": 6.59517240524292, | |
| "learning_rate": 2.7988657398525364e-05, | |
| "loss": 1.4742, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.05702505889912187, | |
| "grad_norm": 5.816342830657959, | |
| "learning_rate": 2.785281060246685e-05, | |
| "loss": 1.4508, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.057292782180338404, | |
| "grad_norm": 5.353818416595459, | |
| "learning_rate": 2.7716723220288365e-05, | |
| "loss": 1.4593, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.05756050546155494, | |
| "grad_norm": 5.926205635070801, | |
| "learning_rate": 2.758040084600916e-05, | |
| "loss": 1.4599, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.05782822874277147, | |
| "grad_norm": 6.504787921905518, | |
| "learning_rate": 2.7443849083308117e-05, | |
| "loss": 1.3973, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.058095952023988005, | |
| "grad_norm": 5.680723190307617, | |
| "learning_rate": 2.7307073545293355e-05, | |
| "loss": 1.4051, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.05836367530520454, | |
| "grad_norm": 7.509329795837402, | |
| "learning_rate": 2.7170079854271533e-05, | |
| "loss": 1.3807, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.05863139858642107, | |
| "grad_norm": 6.508755683898926, | |
| "learning_rate": 2.703287364151672e-05, | |
| "loss": 1.3869, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.058899121867637606, | |
| "grad_norm": 6.544657230377197, | |
| "learning_rate": 2.6895460547038913e-05, | |
| "loss": 1.3409, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.05916684514885415, | |
| "grad_norm": 6.107619762420654, | |
| "learning_rate": 2.6757846219352235e-05, | |
| "loss": 1.389, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.05943456843007068, | |
| "grad_norm": 6.255703449249268, | |
| "learning_rate": 2.6620036315242682e-05, | |
| "loss": 1.4385, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.059702291711287214, | |
| "grad_norm": 5.130046844482422, | |
| "learning_rate": 2.6482036499535665e-05, | |
| "loss": 1.3614, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.05997001499250375, | |
| "grad_norm": 6.854607105255127, | |
| "learning_rate": 2.6343852444863075e-05, | |
| "loss": 1.4465, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.06023773827372028, | |
| "grad_norm": 6.745285511016846, | |
| "learning_rate": 2.6205489831430192e-05, | |
| "loss": 1.4, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.06023773827372028, | |
| "eval_loss": 1.3977503776550293, | |
| "eval_runtime": 76.7205, | |
| "eval_samples_per_second": 6.517, | |
| "eval_steps_per_second": 6.517, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.060505461554936815, | |
| "grad_norm": 5.628711223602295, | |
| "learning_rate": 2.6066954346782113e-05, | |
| "loss": 1.43, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.06077318483615335, | |
| "grad_norm": 6.356362342834473, | |
| "learning_rate": 2.5928251685570005e-05, | |
| "loss": 1.4382, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.06104090811736989, | |
| "grad_norm": 5.99081563949585, | |
| "learning_rate": 2.5789387549317016e-05, | |
| "loss": 1.4363, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.06130863139858642, | |
| "grad_norm": 6.202702522277832, | |
| "learning_rate": 2.5650367646183896e-05, | |
| "loss": 1.3932, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.06157635467980296, | |
| "grad_norm": 6.321465015411377, | |
| "learning_rate": 2.5511197690734344e-05, | |
| "loss": 1.4056, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.06184407796101949, | |
| "grad_norm": 5.804145812988281, | |
| "learning_rate": 2.5371883403700148e-05, | |
| "loss": 1.4132, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.062111801242236024, | |
| "grad_norm": 5.593542098999023, | |
| "learning_rate": 2.5232430511745995e-05, | |
| "loss": 1.4603, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.06237952452345256, | |
| "grad_norm": 6.308177947998047, | |
| "learning_rate": 2.5092844747234063e-05, | |
| "loss": 1.361, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.0626472478046691, | |
| "grad_norm": 5.957157611846924, | |
| "learning_rate": 2.495313184798842e-05, | |
| "loss": 1.435, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.06291497108588563, | |
| "grad_norm": 5.485774517059326, | |
| "learning_rate": 2.4813297557059133e-05, | |
| "loss": 1.413, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.06318269436710217, | |
| "grad_norm": 7.090158939361572, | |
| "learning_rate": 2.467334762248621e-05, | |
| "loss": 1.3819, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.0634504176483187, | |
| "grad_norm": 6.819372653961182, | |
| "learning_rate": 2.4533287797063308e-05, | |
| "loss": 1.4347, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.06371814092953523, | |
| "grad_norm": 5.654256820678711, | |
| "learning_rate": 2.439312383810128e-05, | |
| "loss": 1.3902, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.06398586421075177, | |
| "grad_norm": 6.394632339477539, | |
| "learning_rate": 2.4252861507191487e-05, | |
| "loss": 1.4324, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.0642535874919683, | |
| "grad_norm": 6.346138954162598, | |
| "learning_rate": 2.4112506569969e-05, | |
| "loss": 1.3853, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.0642535874919683, | |
| "eval_loss": 1.389374017715454, | |
| "eval_runtime": 76.6782, | |
| "eval_samples_per_second": 6.521, | |
| "eval_steps_per_second": 6.521, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.06452131077318483, | |
| "grad_norm": 5.798035144805908, | |
| "learning_rate": 2.3972064795875537e-05, | |
| "loss": 1.3668, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.06478903405440137, | |
| "grad_norm": 6.213179588317871, | |
| "learning_rate": 2.3831541957922366e-05, | |
| "loss": 1.3913, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.0650567573356179, | |
| "grad_norm": 6.443445682525635, | |
| "learning_rate": 2.3690943832452967e-05, | |
| "loss": 1.4176, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.06532448061683443, | |
| "grad_norm": 6.543423652648926, | |
| "learning_rate": 2.3550276198905584e-05, | |
| "loss": 1.5036, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.06559220389805097, | |
| "grad_norm": 5.8855977058410645, | |
| "learning_rate": 2.3409544839575687e-05, | |
| "loss": 1.3749, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.0658599271792675, | |
| "grad_norm": 6.113175868988037, | |
| "learning_rate": 2.3268755539378238e-05, | |
| "loss": 1.3555, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.06612765046048405, | |
| "grad_norm": 6.519189357757568, | |
| "learning_rate": 2.3127914085609943e-05, | |
| "loss": 1.3457, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.06639537374170058, | |
| "grad_norm": 6.135042667388916, | |
| "learning_rate": 2.298702626771133e-05, | |
| "loss": 1.4143, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.06666309702291712, | |
| "grad_norm": 6.562228679656982, | |
| "learning_rate": 2.2846097877028762e-05, | |
| "loss": 1.4549, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.06693082030413365, | |
| "grad_norm": 6.2036213874816895, | |
| "learning_rate": 2.270513470657642e-05, | |
| "loss": 1.3422, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06719854358535018, | |
| "grad_norm": 6.321053981781006, | |
| "learning_rate": 2.25641425507981e-05, | |
| "loss": 1.4206, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.06746626686656672, | |
| "grad_norm": 5.922671794891357, | |
| "learning_rate": 2.2423127205329117e-05, | |
| "loss": 1.4368, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.06773399014778325, | |
| "grad_norm": 6.139718532562256, | |
| "learning_rate": 2.2282094466758e-05, | |
| "loss": 1.3574, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.06800171342899979, | |
| "grad_norm": 5.755593776702881, | |
| "learning_rate": 2.2141050132388245e-05, | |
| "loss": 1.4075, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.06826943671021632, | |
| "grad_norm": 5.7373151779174805, | |
| "learning_rate": 2.2e-05, | |
| "loss": 1.3812, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.06826943671021632, | |
| "eval_loss": 1.3869917392730713, | |
| "eval_runtime": 76.6763, | |
| "eval_samples_per_second": 6.521, | |
| "eval_steps_per_second": 6.521, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.06853715999143285, | |
| "grad_norm": 6.435483932495117, | |
| "learning_rate": 2.1858949867611754e-05, | |
| "loss": 1.3586, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.06880488327264939, | |
| "grad_norm": 5.814359188079834, | |
| "learning_rate": 2.1717905533241997e-05, | |
| "loss": 1.3745, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.06907260655386592, | |
| "grad_norm": 6.140771389007568, | |
| "learning_rate": 2.157687279467088e-05, | |
| "loss": 1.3296, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.06934032983508245, | |
| "grad_norm": 5.861440181732178, | |
| "learning_rate": 2.14358574492019e-05, | |
| "loss": 1.3911, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.06960805311629899, | |
| "grad_norm": 6.584283351898193, | |
| "learning_rate": 2.1294865293423586e-05, | |
| "loss": 1.4143, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.06987577639751552, | |
| "grad_norm": 5.859135627746582, | |
| "learning_rate": 2.1153902122971233e-05, | |
| "loss": 1.3923, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.07014349967873207, | |
| "grad_norm": 6.673269748687744, | |
| "learning_rate": 2.101297373228868e-05, | |
| "loss": 1.4072, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.0704112229599486, | |
| "grad_norm": 5.8205180168151855, | |
| "learning_rate": 2.087208591439006e-05, | |
| "loss": 1.3962, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.07067894624116514, | |
| "grad_norm": 5.918448448181152, | |
| "learning_rate": 2.0731244460621764e-05, | |
| "loss": 1.4121, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.07094666952238167, | |
| "grad_norm": 6.024654865264893, | |
| "learning_rate": 2.0590455160424316e-05, | |
| "loss": 1.3958, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.0712143928035982, | |
| "grad_norm": 6.21071195602417, | |
| "learning_rate": 2.044972380109441e-05, | |
| "loss": 1.4155, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.07148211608481474, | |
| "grad_norm": 6.8569207191467285, | |
| "learning_rate": 2.030905616754704e-05, | |
| "loss": 1.3968, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.07174983936603127, | |
| "grad_norm": 6.207950592041016, | |
| "learning_rate": 2.0168458042077636e-05, | |
| "loss": 1.3722, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.0720175626472478, | |
| "grad_norm": 5.884634494781494, | |
| "learning_rate": 2.0027935204124465e-05, | |
| "loss": 1.4165, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.07228528592846434, | |
| "grad_norm": 5.943591117858887, | |
| "learning_rate": 1.9887493430031e-05, | |
| "loss": 1.4054, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.07228528592846434, | |
| "eval_loss": 1.3810029029846191, | |
| "eval_runtime": 76.6801, | |
| "eval_samples_per_second": 6.521, | |
| "eval_steps_per_second": 6.521, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.07255300920968087, | |
| "grad_norm": 6.2774457931518555, | |
| "learning_rate": 1.9747138492808512e-05, | |
| "loss": 1.4184, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.0728207324908974, | |
| "grad_norm": 6.596461772918701, | |
| "learning_rate": 1.960687616189872e-05, | |
| "loss": 1.4314, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.07308845577211394, | |
| "grad_norm": 6.17069149017334, | |
| "learning_rate": 1.9466712202936694e-05, | |
| "loss": 1.4248, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.07335617905333047, | |
| "grad_norm": 6.085130214691162, | |
| "learning_rate": 1.932665237751379e-05, | |
| "loss": 1.3966, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.073623902334547, | |
| "grad_norm": 6.430164813995361, | |
| "learning_rate": 1.9186702442940866e-05, | |
| "loss": 1.3521, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.07389162561576355, | |
| "grad_norm": 5.946996212005615, | |
| "learning_rate": 1.9046868152011587e-05, | |
| "loss": 1.336, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.07415934889698009, | |
| "grad_norm": 6.169567108154297, | |
| "learning_rate": 1.8907155252765942e-05, | |
| "loss": 1.4099, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.07442707217819662, | |
| "grad_norm": 5.974761962890625, | |
| "learning_rate": 1.8767569488254004e-05, | |
| "loss": 1.3588, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.07469479545941315, | |
| "grad_norm": 5.632639408111572, | |
| "learning_rate": 1.8628116596299847e-05, | |
| "loss": 1.3704, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.07496251874062969, | |
| "grad_norm": 5.559203147888184, | |
| "learning_rate": 1.848880230926566e-05, | |
| "loss": 1.3878, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.07523024202184622, | |
| "grad_norm": 6.6522674560546875, | |
| "learning_rate": 1.8349632353816113e-05, | |
| "loss": 1.4324, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.07549796530306276, | |
| "grad_norm": 5.803051471710205, | |
| "learning_rate": 1.8210612450682986e-05, | |
| "loss": 1.4132, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.07576568858427929, | |
| "grad_norm": 5.304571151733398, | |
| "learning_rate": 1.8071748314429994e-05, | |
| "loss": 1.3607, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.07603341186549582, | |
| "grad_norm": 5.904123783111572, | |
| "learning_rate": 1.7933045653217886e-05, | |
| "loss": 1.3963, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.07630113514671236, | |
| "grad_norm": 5.9972686767578125, | |
| "learning_rate": 1.7794510168569814e-05, | |
| "loss": 1.4353, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.07630113514671236, | |
| "eval_loss": 1.3754030466079712, | |
| "eval_runtime": 76.726, | |
| "eval_samples_per_second": 6.517, | |
| "eval_steps_per_second": 6.517, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.07656885842792889, | |
| "grad_norm": 6.276034832000732, | |
| "learning_rate": 1.7656147555136924e-05, | |
| "loss": 1.3894, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.07683658170914542, | |
| "grad_norm": 6.091196060180664, | |
| "learning_rate": 1.7517963500464338e-05, | |
| "loss": 1.3956, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.07710430499036196, | |
| "grad_norm": 6.1393513679504395, | |
| "learning_rate": 1.7379963684757313e-05, | |
| "loss": 1.4192, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.07737202827157849, | |
| "grad_norm": 6.082838535308838, | |
| "learning_rate": 1.7242153780647764e-05, | |
| "loss": 1.3598, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.07763975155279502, | |
| "grad_norm": 7.009051322937012, | |
| "learning_rate": 1.7104539452961086e-05, | |
| "loss": 1.3388, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.07790747483401157, | |
| "grad_norm": 6.073249340057373, | |
| "learning_rate": 1.6967126358483283e-05, | |
| "loss": 1.4014, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.0781751981152281, | |
| "grad_norm": 5.901647567749023, | |
| "learning_rate": 1.6829920145728465e-05, | |
| "loss": 1.3795, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.07844292139644464, | |
| "grad_norm": 5.663522243499756, | |
| "learning_rate": 1.6692926454706644e-05, | |
| "loss": 1.4444, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.07871064467766117, | |
| "grad_norm": 6.163628578186035, | |
| "learning_rate": 1.655615091669189e-05, | |
| "loss": 1.3579, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.07897836795887771, | |
| "grad_norm": 5.641757965087891, | |
| "learning_rate": 1.641959915399084e-05, | |
| "loss": 1.3816, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.07924609124009424, | |
| "grad_norm": 5.533544540405273, | |
| "learning_rate": 1.6283276779711637e-05, | |
| "loss": 1.4021, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.07951381452131077, | |
| "grad_norm": 6.252144813537598, | |
| "learning_rate": 1.614718939753315e-05, | |
| "loss": 1.3424, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.07978153780252731, | |
| "grad_norm": 6.014984607696533, | |
| "learning_rate": 1.6011342601474635e-05, | |
| "loss": 1.3733, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.08004926108374384, | |
| "grad_norm": 6.043126106262207, | |
| "learning_rate": 1.5875741975665813e-05, | |
| "loss": 1.4402, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.08031698436496038, | |
| "grad_norm": 6.2684478759765625, | |
| "learning_rate": 1.5740393094117287e-05, | |
| "loss": 1.3955, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08031698436496038, | |
| "eval_loss": 1.3712314367294312, | |
| "eval_runtime": 77.0642, | |
| "eval_samples_per_second": 6.488, | |
| "eval_steps_per_second": 6.488, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08058470764617691, | |
| "grad_norm": 6.531871795654297, | |
| "learning_rate": 1.560530152049146e-05, | |
| "loss": 1.3728, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.08085243092739344, | |
| "grad_norm": 6.215692043304443, | |
| "learning_rate": 1.5470472807873805e-05, | |
| "loss": 1.322, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.08112015420860998, | |
| "grad_norm": 5.670928001403809, | |
| "learning_rate": 1.5335912498544615e-05, | |
| "loss": 1.3643, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.08138787748982651, | |
| "grad_norm": 5.801737308502197, | |
| "learning_rate": 1.5201626123751158e-05, | |
| "loss": 1.3653, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.08165560077104304, | |
| "grad_norm": 5.651313781738281, | |
| "learning_rate": 1.5067619203480345e-05, | |
| "loss": 1.3818, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.08192332405225959, | |
| "grad_norm": 6.425565242767334, | |
| "learning_rate": 1.4933897246231798e-05, | |
| "loss": 1.3276, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.08219104733347612, | |
| "grad_norm": 6.21942663192749, | |
| "learning_rate": 1.4800465748791428e-05, | |
| "loss": 1.429, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.08245877061469266, | |
| "grad_norm": 6.354944229125977, | |
| "learning_rate": 1.4667330196005485e-05, | |
| "loss": 1.4254, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.08272649389590919, | |
| "grad_norm": 6.185739517211914, | |
| "learning_rate": 1.4534496060555075e-05, | |
| "loss": 1.3998, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.08299421717712573, | |
| "grad_norm": 5.781863212585449, | |
| "learning_rate": 1.4401968802731235e-05, | |
| "loss": 1.3384, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.08326194045834226, | |
| "grad_norm": 6.628792762756348, | |
| "learning_rate": 1.4269753870210459e-05, | |
| "loss": 1.4146, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.0835296637395588, | |
| "grad_norm": 6.093694686889648, | |
| "learning_rate": 1.4137856697830786e-05, | |
| "loss": 1.3662, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.08379738702077533, | |
| "grad_norm": 6.078185558319092, | |
| "learning_rate": 1.4006282707368348e-05, | |
| "loss": 1.3716, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.08406511030199186, | |
| "grad_norm": 6.203483581542969, | |
| "learning_rate": 1.3875037307314563e-05, | |
| "loss": 1.3371, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.0843328335832084, | |
| "grad_norm": 5.880634307861328, | |
| "learning_rate": 1.374412589265377e-05, | |
| "loss": 1.3464, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.0843328335832084, | |
| "eval_loss": 1.3659946918487549, | |
| "eval_runtime": 77.0452, | |
| "eval_samples_per_second": 6.49, | |
| "eval_steps_per_second": 6.49, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.08460055686442493, | |
| "grad_norm": 6.3485426902771, | |
| "learning_rate": 1.3613553844641483e-05, | |
| "loss": 1.3366, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.08486828014564146, | |
| "grad_norm": 6.721098899841309, | |
| "learning_rate": 1.3483326530583184e-05, | |
| "loss": 1.3628, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.085136003426858, | |
| "grad_norm": 5.912144660949707, | |
| "learning_rate": 1.3353449303613682e-05, | |
| "loss": 1.3403, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.08540372670807453, | |
| "grad_norm": 5.860577583312988, | |
| "learning_rate": 1.3223927502477084e-05, | |
| "loss": 1.3453, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.08567144998929106, | |
| "grad_norm": 6.3982977867126465, | |
| "learning_rate": 1.3094766451307336e-05, | |
| "loss": 1.3556, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.08593917327050761, | |
| "grad_norm": 6.073590278625488, | |
| "learning_rate": 1.2965971459409366e-05, | |
| "loss": 1.3984, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.08620689655172414, | |
| "grad_norm": 6.372732162475586, | |
| "learning_rate": 1.2837547821040825e-05, | |
| "loss": 1.4089, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.08647461983294068, | |
| "grad_norm": 6.449525356292725, | |
| "learning_rate": 1.2709500815194487e-05, | |
| "loss": 1.3884, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.08674234311415721, | |
| "grad_norm": 5.904713153839111, | |
| "learning_rate": 1.2581835705381243e-05, | |
| "loss": 1.3976, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.08701006639537374, | |
| "grad_norm": 6.398531913757324, | |
| "learning_rate": 1.2454557739413722e-05, | |
| "loss": 1.3942, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.08727778967659028, | |
| "grad_norm": 6.1607465744018555, | |
| "learning_rate": 1.2327672149190595e-05, | |
| "loss": 1.3698, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.08754551295780681, | |
| "grad_norm": 5.903096675872803, | |
| "learning_rate": 1.2201184150481497e-05, | |
| "loss": 1.4183, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.08781323623902335, | |
| "grad_norm": 6.210367679595947, | |
| "learning_rate": 1.2075098942712635e-05, | |
| "loss": 1.3717, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.08808095952023988, | |
| "grad_norm": 6.082081317901611, | |
| "learning_rate": 1.1949421708753062e-05, | |
| "loss": 1.3694, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.08834868280145641, | |
| "grad_norm": 5.826544284820557, | |
| "learning_rate": 1.1824157614701629e-05, | |
| "loss": 1.4473, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.08834868280145641, | |
| "eval_loss": 1.3619885444641113, | |
| "eval_runtime": 77.1061, | |
| "eval_samples_per_second": 6.485, | |
| "eval_steps_per_second": 6.485, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.08861640608267295, | |
| "grad_norm": 6.470825672149658, | |
| "learning_rate": 1.1699311809674596e-05, | |
| "loss": 1.357, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.08888412936388948, | |
| "grad_norm": 5.989506244659424, | |
| "learning_rate": 1.157488942559403e-05, | |
| "loss": 1.322, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.08915185264510601, | |
| "grad_norm": 6.708034992218018, | |
| "learning_rate": 1.1450895576976816e-05, | |
| "loss": 1.3652, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.08941957592632255, | |
| "grad_norm": 6.264359474182129, | |
| "learning_rate": 1.1327335360724412e-05, | |
| "loss": 1.3661, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.08968729920753908, | |
| "grad_norm": 6.633790969848633, | |
| "learning_rate": 1.1204213855913374e-05, | |
| "loss": 1.3522, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.08995502248875563, | |
| "grad_norm": 5.526124477386475, | |
| "learning_rate": 1.1081536123586505e-05, | |
| "loss": 1.3492, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.09022274576997216, | |
| "grad_norm": 6.267175197601318, | |
| "learning_rate": 1.09593072065449e-05, | |
| "loss": 1.3805, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.0904904690511887, | |
| "grad_norm": 6.826523780822754, | |
| "learning_rate": 1.0837532129140595e-05, | |
| "loss": 1.3379, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.09075819233240523, | |
| "grad_norm": 6.352426052093506, | |
| "learning_rate": 1.0716215897070067e-05, | |
| "loss": 1.378, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.09102591561362176, | |
| "grad_norm": 6.353774547576904, | |
| "learning_rate": 1.0595363497168449e-05, | |
| "loss": 1.4057, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.0912936388948383, | |
| "grad_norm": 6.023704528808594, | |
| "learning_rate": 1.0474979897204557e-05, | |
| "loss": 1.419, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.09156136217605483, | |
| "grad_norm": 6.525381565093994, | |
| "learning_rate": 1.0355070045676677e-05, | |
| "loss": 1.3737, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.09182908545727136, | |
| "grad_norm": 6.321014404296875, | |
| "learning_rate": 1.0235638871609145e-05, | |
| "loss": 1.3252, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.0920968087384879, | |
| "grad_norm": 5.880143165588379, | |
| "learning_rate": 1.011669128434976e-05, | |
| "loss": 1.3581, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.09236453201970443, | |
| "grad_norm": 6.851429462432861, | |
| "learning_rate": 9.99823217336793e-06, | |
| "loss": 1.4074, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.09236453201970443, | |
| "eval_loss": 1.3579777479171753, | |
| "eval_runtime": 76.8014, | |
| "eval_samples_per_second": 6.51, | |
| "eval_steps_per_second": 6.51, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.09263225530092097, | |
| "grad_norm": 6.41058874130249, | |
| "learning_rate": 9.880266408053746e-06, | |
| "loss": 1.433, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.0928999785821375, | |
| "grad_norm": 5.9317474365234375, | |
| "learning_rate": 9.762798837517776e-06, | |
| "loss": 1.3759, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.09316770186335403, | |
| "grad_norm": 5.728269100189209, | |
| "learning_rate": 9.645834290391754e-06, | |
| "loss": 1.4632, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.09343542514457057, | |
| "grad_norm": 5.710354328155518, | |
| "learning_rate": 9.529377574630109e-06, | |
| "loss": 1.422, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.0937031484257871, | |
| "grad_norm": 6.150035381317139, | |
| "learning_rate": 9.413433477312272e-06, | |
| "loss": 1.4113, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.09397087170700365, | |
| "grad_norm": 6.171891689300537, | |
| "learning_rate": 9.298006764445976e-06, | |
| "loss": 1.4115, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.09423859498822018, | |
| "grad_norm": 6.584611415863037, | |
| "learning_rate": 9.183102180771285e-06, | |
| "loss": 1.3631, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.09450631826943671, | |
| "grad_norm": 6.219729423522949, | |
| "learning_rate": 9.068724449565594e-06, | |
| "loss": 1.3497, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.09477404155065325, | |
| "grad_norm": 5.961699485778809, | |
| "learning_rate": 8.954878272449433e-06, | |
| "loss": 1.3476, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.09504176483186978, | |
| "grad_norm": 6.4813385009765625, | |
| "learning_rate": 8.841568329193249e-06, | |
| "loss": 1.3281, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.09530948811308632, | |
| "grad_norm": 5.715578079223633, | |
| "learning_rate": 8.728799277524998e-06, | |
| "loss": 1.3114, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.09557721139430285, | |
| "grad_norm": 5.67549467086792, | |
| "learning_rate": 8.61657575293871e-06, | |
| "loss": 1.3119, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.09584493467551938, | |
| "grad_norm": 6.634474277496338, | |
| "learning_rate": 8.50490236850394e-06, | |
| "loss": 1.3587, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.09611265795673592, | |
| "grad_norm": 5.7471537590026855, | |
| "learning_rate": 8.393783714676107e-06, | |
| "loss": 1.3607, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.09638038123795245, | |
| "grad_norm": 5.866701602935791, | |
| "learning_rate": 8.283224359107863e-06, | |
| "loss": 1.3247, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.09638038123795245, | |
| "eval_loss": 1.3553622961044312, | |
| "eval_runtime": 76.9249, | |
| "eval_samples_per_second": 6.5, | |
| "eval_steps_per_second": 6.5, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.09664810451916898, | |
| "grad_norm": 5.779167652130127, | |
| "learning_rate": 8.17322884646128e-06, | |
| "loss": 1.375, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.09691582780038552, | |
| "grad_norm": 6.503204345703125, | |
| "learning_rate": 8.06380169822107e-06, | |
| "loss": 1.3767, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.09718355108160205, | |
| "grad_norm": 5.67221212387085, | |
| "learning_rate": 7.95494741250868e-06, | |
| "loss": 1.2996, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.09745127436281859, | |
| "grad_norm": 6.475659370422363, | |
| "learning_rate": 7.846670463897457e-06, | |
| "loss": 1.3827, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.09771899764403512, | |
| "grad_norm": 6.146843910217285, | |
| "learning_rate": 7.738975303228659e-06, | |
| "loss": 1.3489, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.09798672092525167, | |
| "grad_norm": 6.763230323791504, | |
| "learning_rate": 7.631866357428526e-06, | |
| "loss": 1.3631, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.0982544442064682, | |
| "grad_norm": 6.853928565979004, | |
| "learning_rate": 7.525348029326323e-06, | |
| "loss": 1.3683, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.09852216748768473, | |
| "grad_norm": 6.183257102966309, | |
| "learning_rate": 7.4194246974732955e-06, | |
| "loss": 1.3744, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.09878989076890127, | |
| "grad_norm": 6.155274391174316, | |
| "learning_rate": 7.314100715962744e-06, | |
| "loss": 1.389, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.0990576140501178, | |
| "grad_norm": 6.754117012023926, | |
| "learning_rate": 7.209380414251028e-06, | |
| "loss": 1.3267, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.09932533733133433, | |
| "grad_norm": 6.333691596984863, | |
| "learning_rate": 7.105268096979596e-06, | |
| "loss": 1.3774, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.09959306061255087, | |
| "grad_norm": 6.452340602874756, | |
| "learning_rate": 7.001768043798013e-06, | |
| "loss": 1.3038, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.0998607838937674, | |
| "grad_norm": 5.832094192504883, | |
| "learning_rate": 6.898884509188095e-06, | |
| "loss": 1.3978, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.10012850717498394, | |
| "grad_norm": 5.7019476890563965, | |
| "learning_rate": 6.796621722288977e-06, | |
| "loss": 1.358, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.10039623045620047, | |
| "grad_norm": 5.743053913116455, | |
| "learning_rate": 6.6949838867233e-06, | |
| "loss": 1.3567, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.10039623045620047, | |
| "eval_loss": 1.3537319898605347, | |
| "eval_runtime": 76.8454, | |
| "eval_samples_per_second": 6.507, | |
| "eval_steps_per_second": 6.507, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.100663953737417, | |
| "grad_norm": 6.490472793579102, | |
| "learning_rate": 6.5939751804243974e-06, | |
| "loss": 1.361, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.10093167701863354, | |
| "grad_norm": 6.32999324798584, | |
| "learning_rate": 6.493599755464546e-06, | |
| "loss": 1.2968, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.10119940029985007, | |
| "grad_norm": 6.559702396392822, | |
| "learning_rate": 6.3938617378843264e-06, | |
| "loss": 1.4176, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.1014671235810666, | |
| "grad_norm": 5.832455158233643, | |
| "learning_rate": 6.294765227523008e-06, | |
| "loss": 1.3828, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.10173484686228314, | |
| "grad_norm": 6.728024005889893, | |
| "learning_rate": 6.196314297849995e-06, | |
| "loss": 1.3902, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.10200257014349969, | |
| "grad_norm": 6.092176914215088, | |
| "learning_rate": 6.098512995797388e-06, | |
| "loss": 1.3587, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.10227029342471622, | |
| "grad_norm": 6.502336025238037, | |
| "learning_rate": 6.0013653415936585e-06, | |
| "loss": 1.3619, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.10253801670593275, | |
| "grad_norm": 6.602701187133789, | |
| "learning_rate": 5.90487532859837e-06, | |
| "loss": 1.3325, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.10280573998714929, | |
| "grad_norm": 6.637482166290283, | |
| "learning_rate": 5.809046923138031e-06, | |
| "loss": 1.3899, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.10307346326836582, | |
| "grad_norm": 5.880363941192627, | |
| "learning_rate": 5.713884064343061e-06, | |
| "loss": 1.3481, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.10334118654958235, | |
| "grad_norm": 7.036133289337158, | |
| "learning_rate": 5.6193906639858486e-06, | |
| "loss": 1.3156, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.10360890983079889, | |
| "grad_norm": 5.999964714050293, | |
| "learning_rate": 5.52557060631998e-06, | |
| "loss": 1.3756, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.10387663311201542, | |
| "grad_norm": 5.966408729553223, | |
| "learning_rate": 5.432427747920561e-06, | |
| "loss": 1.3588, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.10414435639323195, | |
| "grad_norm": 5.987645626068115, | |
| "learning_rate": 5.339965917525687e-06, | |
| "loss": 1.427, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.10441207967444849, | |
| "grad_norm": 5.433709621429443, | |
| "learning_rate": 5.248188915879043e-06, | |
| "loss": 1.3687, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.10441207967444849, | |
| "eval_loss": 1.350784420967102, | |
| "eval_runtime": 76.8402, | |
| "eval_samples_per_second": 6.507, | |
| "eval_steps_per_second": 6.507, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.10467980295566502, | |
| "grad_norm": 6.524111270904541, | |
| "learning_rate": 5.157100515573715e-06, | |
| "loss": 1.3006, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.10494752623688156, | |
| "grad_norm": 5.474837303161621, | |
| "learning_rate": 5.066704460897067e-06, | |
| "loss": 1.3463, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.10521524951809809, | |
| "grad_norm": 5.868412494659424, | |
| "learning_rate": 4.977004467676848e-06, | |
| "loss": 1.2881, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.10548297279931462, | |
| "grad_norm": 5.966287136077881, | |
| "learning_rate": 4.888004223128458e-06, | |
| "loss": 1.3636, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.10575069608053116, | |
| "grad_norm": 5.976463794708252, | |
| "learning_rate": 4.799707385703344e-06, | |
| "loss": 1.3411, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.1060184193617477, | |
| "grad_norm": 5.5595197677612305, | |
| "learning_rate": 4.712117584938669e-06, | |
| "loss": 1.3114, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.10628614264296424, | |
| "grad_norm": 5.7463483810424805, | |
| "learning_rate": 4.625238421308069e-06, | |
| "loss": 1.3472, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.10655386592418077, | |
| "grad_norm": 6.120302200317383, | |
| "learning_rate": 4.5390734660736906e-06, | |
| "loss": 1.4384, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.1068215892053973, | |
| "grad_norm": 6.155236721038818, | |
| "learning_rate": 4.453626261139344e-06, | |
| "loss": 1.3494, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.10708931248661384, | |
| "grad_norm": 6.032073974609375, | |
| "learning_rate": 4.368900318904957e-06, | |
| "loss": 1.3464, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.10735703576783037, | |
| "grad_norm": 6.827203750610352, | |
| "learning_rate": 4.284899122122165e-06, | |
| "loss": 1.3534, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.1076247590490469, | |
| "grad_norm": 5.927024841308594, | |
| "learning_rate": 4.201626123751159e-06, | |
| "loss": 1.333, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.10789248233026344, | |
| "grad_norm": 5.960188865661621, | |
| "learning_rate": 4.1190847468187425e-06, | |
| "loss": 1.3458, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.10816020561147997, | |
| "grad_norm": 6.299499034881592, | |
| "learning_rate": 4.037278384277628e-06, | |
| "loss": 1.3516, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.1084279288926965, | |
| "grad_norm": 6.968238353729248, | |
| "learning_rate": 3.956210398866969e-06, | |
| "loss": 1.369, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.1084279288926965, | |
| "eval_loss": 1.348792552947998, | |
| "eval_runtime": 76.8298, | |
| "eval_samples_per_second": 6.508, | |
| "eval_steps_per_second": 6.508, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.10869565217391304, | |
| "grad_norm": 6.412740707397461, | |
| "learning_rate": 3.875884122974123e-06, | |
| "loss": 1.3756, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.10896337545512957, | |
| "grad_norm": 6.571822643280029, | |
| "learning_rate": 3.7963028584976805e-06, | |
| "loss": 1.3773, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.10923109873634611, | |
| "grad_norm": 6.47897481918335, | |
| "learning_rate": 3.717469876711713e-06, | |
| "loss": 1.3746, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.10949882201756264, | |
| "grad_norm": 6.563449382781982, | |
| "learning_rate": 3.6393884181313417e-06, | |
| "loss": 1.382, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.10976654529877918, | |
| "grad_norm": 6.455676078796387, | |
| "learning_rate": 3.562061692379507e-06, | |
| "loss": 1.3519, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.11003426857999572, | |
| "grad_norm": 5.957856178283691, | |
| "learning_rate": 3.4854928780550306e-06, | |
| "loss": 1.3711, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.11030199186121226, | |
| "grad_norm": 6.082734107971191, | |
| "learning_rate": 3.409685122601979e-06, | |
| "loss": 1.3038, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.11056971514242879, | |
| "grad_norm": 5.809603691101074, | |
| "learning_rate": 3.3346415421802494e-06, | |
| "loss": 1.3587, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.11083743842364532, | |
| "grad_norm": 6.081882476806641, | |
| "learning_rate": 3.26036522153751e-06, | |
| "loss": 1.3672, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.11110516170486186, | |
| "grad_norm": 5.788993835449219, | |
| "learning_rate": 3.186859213882386e-06, | |
| "loss": 1.3615, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.11137288498607839, | |
| "grad_norm": 5.722326755523682, | |
| "learning_rate": 3.114126540758946e-06, | |
| "loss": 1.2914, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.11164060826729492, | |
| "grad_norm": 6.233955383300781, | |
| "learning_rate": 3.042170191922509e-06, | |
| "loss": 1.3286, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.11190833154851146, | |
| "grad_norm": 6.276589393615723, | |
| "learning_rate": 2.9709931252167426e-06, | |
| "loss": 1.3943, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.11217605482972799, | |
| "grad_norm": 6.818645000457764, | |
| "learning_rate": 2.9005982664520734e-06, | |
| "loss": 1.3535, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.11244377811094453, | |
| "grad_norm": 6.53585147857666, | |
| "learning_rate": 2.830988509285433e-06, | |
| "loss": 1.3412, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.11244377811094453, | |
| "eval_loss": 1.3470451831817627, | |
| "eval_runtime": 76.7654, | |
| "eval_samples_per_second": 6.513, | |
| "eval_steps_per_second": 6.513, | |
| "step": 4200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.521351998649088e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |