| { | |
| "best_metric": 0.02783067524433136, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.11286681715575621, | |
| "eval_steps": 50, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007524454477050414, | |
| "grad_norm": 0.2406926155090332, | |
| "learning_rate": 1.004e-05, | |
| "loss": 0.4829, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007524454477050414, | |
| "eval_loss": 0.448444128036499, | |
| "eval_runtime": 25.7969, | |
| "eval_samples_per_second": 21.708, | |
| "eval_steps_per_second": 5.427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015048908954100827, | |
| "grad_norm": 0.2582743167877197, | |
| "learning_rate": 2.008e-05, | |
| "loss": 0.0809, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002257336343115124, | |
| "grad_norm": 0.4347482919692993, | |
| "learning_rate": 3.012e-05, | |
| "loss": 0.1315, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0030097817908201654, | |
| "grad_norm": 0.39034780859947205, | |
| "learning_rate": 4.016e-05, | |
| "loss": 0.1019, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003762227238525207, | |
| "grad_norm": 0.5869060754776001, | |
| "learning_rate": 5.02e-05, | |
| "loss": 0.1216, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004514672686230248, | |
| "grad_norm": 0.4321593940258026, | |
| "learning_rate": 6.024e-05, | |
| "loss": 0.1246, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005267118133935289, | |
| "grad_norm": 0.4198409914970398, | |
| "learning_rate": 7.028e-05, | |
| "loss": 0.1255, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006019563581640331, | |
| "grad_norm": 0.4511987864971161, | |
| "learning_rate": 8.032e-05, | |
| "loss": 0.0875, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006772009029345372, | |
| "grad_norm": 0.30963364243507385, | |
| "learning_rate": 9.036000000000001e-05, | |
| "loss": 0.0681, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007524454477050414, | |
| "grad_norm": 0.5047326683998108, | |
| "learning_rate": 0.0001004, | |
| "loss": 0.0941, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008276899924755455, | |
| "grad_norm": 0.3052256107330322, | |
| "learning_rate": 9.987157894736842e-05, | |
| "loss": 0.0641, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009029345372460496, | |
| "grad_norm": 0.29083898663520813, | |
| "learning_rate": 9.934315789473684e-05, | |
| "loss": 0.0529, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009781790820165538, | |
| "grad_norm": 0.46031373739242554, | |
| "learning_rate": 9.881473684210525e-05, | |
| "loss": 0.0923, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010534236267870579, | |
| "grad_norm": 0.3271160125732422, | |
| "learning_rate": 9.828631578947369e-05, | |
| "loss": 0.0459, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011286681715575621, | |
| "grad_norm": 0.43920812010765076, | |
| "learning_rate": 9.77578947368421e-05, | |
| "loss": 0.059, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012039127163280662, | |
| "grad_norm": 0.502988874912262, | |
| "learning_rate": 9.722947368421052e-05, | |
| "loss": 0.056, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012791572610985704, | |
| "grad_norm": 1.8321483135223389, | |
| "learning_rate": 9.670105263157895e-05, | |
| "loss": 0.0628, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013544018058690745, | |
| "grad_norm": 0.35579952597618103, | |
| "learning_rate": 9.617263157894737e-05, | |
| "loss": 0.0259, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014296463506395787, | |
| "grad_norm": 0.6292356252670288, | |
| "learning_rate": 9.564421052631579e-05, | |
| "loss": 0.0443, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015048908954100828, | |
| "grad_norm": 0.4263708293437958, | |
| "learning_rate": 9.511578947368421e-05, | |
| "loss": 0.0445, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01580135440180587, | |
| "grad_norm": 0.5908687114715576, | |
| "learning_rate": 9.458736842105264e-05, | |
| "loss": 0.0441, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01655379984951091, | |
| "grad_norm": 0.7689208984375, | |
| "learning_rate": 9.405894736842106e-05, | |
| "loss": 0.0351, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01730624529721595, | |
| "grad_norm": 0.87498939037323, | |
| "learning_rate": 9.353052631578947e-05, | |
| "loss": 0.0163, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01805869074492099, | |
| "grad_norm": 0.2699977457523346, | |
| "learning_rate": 9.300210526315789e-05, | |
| "loss": 0.0118, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.018811136192626036, | |
| "grad_norm": 0.30637574195861816, | |
| "learning_rate": 9.247368421052631e-05, | |
| "loss": 0.0065, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.019563581640331076, | |
| "grad_norm": 0.6475765109062195, | |
| "learning_rate": 9.194526315789473e-05, | |
| "loss": 0.012, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.020316027088036117, | |
| "grad_norm": 0.7173324227333069, | |
| "learning_rate": 9.141684210526316e-05, | |
| "loss": 0.0178, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.021068472535741158, | |
| "grad_norm": 0.3768528699874878, | |
| "learning_rate": 9.088842105263158e-05, | |
| "loss": 0.0228, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0218209179834462, | |
| "grad_norm": 0.34722164273262024, | |
| "learning_rate": 9.036000000000001e-05, | |
| "loss": 0.0099, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.022573363431151242, | |
| "grad_norm": 0.07302386313676834, | |
| "learning_rate": 8.983157894736843e-05, | |
| "loss": 0.0015, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023325808878856283, | |
| "grad_norm": 1.0248472690582275, | |
| "learning_rate": 8.930315789473684e-05, | |
| "loss": 0.021, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.024078254326561323, | |
| "grad_norm": 0.1479930877685547, | |
| "learning_rate": 8.877473684210526e-05, | |
| "loss": 0.003, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.024830699774266364, | |
| "grad_norm": 1.3804433345794678, | |
| "learning_rate": 8.824631578947368e-05, | |
| "loss": 0.016, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.025583145221971408, | |
| "grad_norm": 1.6197274923324585, | |
| "learning_rate": 8.771789473684211e-05, | |
| "loss": 0.0367, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02633559066967645, | |
| "grad_norm": 0.6973819732666016, | |
| "learning_rate": 8.718947368421053e-05, | |
| "loss": 0.0141, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02708803611738149, | |
| "grad_norm": 0.8518109321594238, | |
| "learning_rate": 8.666105263157895e-05, | |
| "loss": 0.0319, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02784048156508653, | |
| "grad_norm": 0.9821231961250305, | |
| "learning_rate": 8.613263157894737e-05, | |
| "loss": 0.0333, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.028592927012791574, | |
| "grad_norm": 0.1206764355301857, | |
| "learning_rate": 8.560421052631578e-05, | |
| "loss": 0.0038, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.029345372460496615, | |
| "grad_norm": 1.610734462738037, | |
| "learning_rate": 8.50757894736842e-05, | |
| "loss": 0.0207, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.030097817908201655, | |
| "grad_norm": 0.8153631687164307, | |
| "learning_rate": 8.454736842105263e-05, | |
| "loss": 0.0363, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.030850263355906696, | |
| "grad_norm": 2.7571136951446533, | |
| "learning_rate": 8.401894736842106e-05, | |
| "loss": 0.0164, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03160270880361174, | |
| "grad_norm": 0.11961274594068527, | |
| "learning_rate": 8.349052631578948e-05, | |
| "loss": 0.0035, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03235515425131678, | |
| "grad_norm": 0.6352341771125793, | |
| "learning_rate": 8.29621052631579e-05, | |
| "loss": 0.0049, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03310759969902182, | |
| "grad_norm": 0.2854023873806, | |
| "learning_rate": 8.243368421052632e-05, | |
| "loss": 0.0134, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.033860045146726865, | |
| "grad_norm": 0.2841341197490692, | |
| "learning_rate": 8.190526315789474e-05, | |
| "loss": 0.0068, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0346124905944319, | |
| "grad_norm": 0.21941381692886353, | |
| "learning_rate": 8.137684210526315e-05, | |
| "loss": 0.0031, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.035364936042136946, | |
| "grad_norm": 1.6787192821502686, | |
| "learning_rate": 8.084842105263157e-05, | |
| "loss": 0.0155, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03611738148984198, | |
| "grad_norm": 2.5062623023986816, | |
| "learning_rate": 8.032e-05, | |
| "loss": 0.0486, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03686982693754703, | |
| "grad_norm": 3.1842916011810303, | |
| "learning_rate": 7.979157894736842e-05, | |
| "loss": 0.0298, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03762227238525207, | |
| "grad_norm": 1.3214054107666016, | |
| "learning_rate": 7.926315789473684e-05, | |
| "loss": 0.0393, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03762227238525207, | |
| "eval_loss": 0.04788399860262871, | |
| "eval_runtime": 22.4157, | |
| "eval_samples_per_second": 24.983, | |
| "eval_steps_per_second": 6.246, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03837471783295711, | |
| "grad_norm": 0.3795923590660095, | |
| "learning_rate": 7.873473684210526e-05, | |
| "loss": 0.0368, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.03912716328066215, | |
| "grad_norm": 0.7790267467498779, | |
| "learning_rate": 7.820631578947369e-05, | |
| "loss": 0.1122, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0398796087283672, | |
| "grad_norm": 0.4049144983291626, | |
| "learning_rate": 7.76778947368421e-05, | |
| "loss": 0.0085, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.040632054176072234, | |
| "grad_norm": 0.07192933559417725, | |
| "learning_rate": 7.714947368421052e-05, | |
| "loss": 0.0009, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04138449962377728, | |
| "grad_norm": 0.09724583476781845, | |
| "learning_rate": 7.662105263157896e-05, | |
| "loss": 0.0029, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.042136945071482315, | |
| "grad_norm": 0.17651653289794922, | |
| "learning_rate": 7.609263157894737e-05, | |
| "loss": 0.0082, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.04288939051918736, | |
| "grad_norm": 0.28293490409851074, | |
| "learning_rate": 7.556421052631579e-05, | |
| "loss": 0.003, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0436418359668924, | |
| "grad_norm": 1.0796512365341187, | |
| "learning_rate": 7.503578947368421e-05, | |
| "loss": 0.0071, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.04439428141459744, | |
| "grad_norm": 0.5031782388687134, | |
| "learning_rate": 7.450736842105263e-05, | |
| "loss": 0.016, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.045146726862302484, | |
| "grad_norm": 0.2986276149749756, | |
| "learning_rate": 7.397894736842105e-05, | |
| "loss": 0.0068, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04589917231000752, | |
| "grad_norm": 1.870119571685791, | |
| "learning_rate": 7.345052631578948e-05, | |
| "loss": 0.0103, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.046651617757712566, | |
| "grad_norm": 0.13697421550750732, | |
| "learning_rate": 7.29221052631579e-05, | |
| "loss": 0.0025, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.04740406320541761, | |
| "grad_norm": 0.03275276720523834, | |
| "learning_rate": 7.239368421052631e-05, | |
| "loss": 0.0011, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.04815650865312265, | |
| "grad_norm": 0.06320174783468246, | |
| "learning_rate": 7.186526315789474e-05, | |
| "loss": 0.0031, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.04890895410082769, | |
| "grad_norm": 0.03870139271020889, | |
| "learning_rate": 7.133684210526316e-05, | |
| "loss": 0.0012, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.04966139954853273, | |
| "grad_norm": 0.03169720619916916, | |
| "learning_rate": 7.080842105263158e-05, | |
| "loss": 0.0012, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05041384499623777, | |
| "grad_norm": 0.8996763825416565, | |
| "learning_rate": 7.028e-05, | |
| "loss": 0.0197, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.051166290443942816, | |
| "grad_norm": 0.05753805488348007, | |
| "learning_rate": 6.975157894736843e-05, | |
| "loss": 0.0011, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.05191873589164785, | |
| "grad_norm": 0.16330073773860931, | |
| "learning_rate": 6.922315789473685e-05, | |
| "loss": 0.0029, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0526711813393529, | |
| "grad_norm": 0.1298224925994873, | |
| "learning_rate": 6.869473684210527e-05, | |
| "loss": 0.0022, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05342362678705794, | |
| "grad_norm": 0.04153815284371376, | |
| "learning_rate": 6.816631578947368e-05, | |
| "loss": 0.0014, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.05417607223476298, | |
| "grad_norm": 0.06644019484519958, | |
| "learning_rate": 6.76378947368421e-05, | |
| "loss": 0.0019, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.05492851768246802, | |
| "grad_norm": 0.12409530580043793, | |
| "learning_rate": 6.710947368421052e-05, | |
| "loss": 0.0017, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.05568096313017306, | |
| "grad_norm": 0.06674883514642715, | |
| "learning_rate": 6.658105263157894e-05, | |
| "loss": 0.0016, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.056433408577878104, | |
| "grad_norm": 0.09339006245136261, | |
| "learning_rate": 6.605263157894737e-05, | |
| "loss": 0.0011, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.05718585402558315, | |
| "grad_norm": 0.04911891743540764, | |
| "learning_rate": 6.55242105263158e-05, | |
| "loss": 0.0015, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.057938299473288185, | |
| "grad_norm": 0.3085123598575592, | |
| "learning_rate": 6.499578947368422e-05, | |
| "loss": 0.0096, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.05869074492099323, | |
| "grad_norm": 0.11163350194692612, | |
| "learning_rate": 6.446736842105264e-05, | |
| "loss": 0.0013, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.059443190368698266, | |
| "grad_norm": 0.06438886374235153, | |
| "learning_rate": 6.393894736842105e-05, | |
| "loss": 0.0011, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.06019563581640331, | |
| "grad_norm": 0.04296841472387314, | |
| "learning_rate": 6.341052631578947e-05, | |
| "loss": 0.0009, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.060948081264108354, | |
| "grad_norm": 0.03423371911048889, | |
| "learning_rate": 6.288210526315789e-05, | |
| "loss": 0.001, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.06170052671181339, | |
| "grad_norm": 0.09237401187419891, | |
| "learning_rate": 6.235368421052632e-05, | |
| "loss": 0.001, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.062452972159518436, | |
| "grad_norm": 0.01862478442490101, | |
| "learning_rate": 6.182526315789474e-05, | |
| "loss": 0.0006, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.06320541760722348, | |
| "grad_norm": 0.06537121534347534, | |
| "learning_rate": 6.129684210526316e-05, | |
| "loss": 0.0016, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.06395786305492852, | |
| "grad_norm": 0.6745563745498657, | |
| "learning_rate": 6.076842105263158e-05, | |
| "loss": 0.0117, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.06471030850263355, | |
| "grad_norm": 0.16666635870933533, | |
| "learning_rate": 6.024e-05, | |
| "loss": 0.0062, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.0654627539503386, | |
| "grad_norm": 0.017271826043725014, | |
| "learning_rate": 5.971157894736842e-05, | |
| "loss": 0.0005, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.06621519939804364, | |
| "grad_norm": 0.390020489692688, | |
| "learning_rate": 5.9183157894736835e-05, | |
| "loss": 0.0117, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.06696764484574869, | |
| "grad_norm": 0.9855097532272339, | |
| "learning_rate": 5.8654736842105267e-05, | |
| "loss": 0.0413, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.06772009029345373, | |
| "grad_norm": 0.08488702028989792, | |
| "learning_rate": 5.8126315789473684e-05, | |
| "loss": 0.002, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06847253574115876, | |
| "grad_norm": 0.019529394805431366, | |
| "learning_rate": 5.759789473684211e-05, | |
| "loss": 0.0005, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0692249811888638, | |
| "grad_norm": 2.2314491271972656, | |
| "learning_rate": 5.706947368421053e-05, | |
| "loss": 0.0078, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.06997742663656885, | |
| "grad_norm": 0.01869085058569908, | |
| "learning_rate": 5.6541052631578945e-05, | |
| "loss": 0.0006, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.07072987208427389, | |
| "grad_norm": 0.9058141112327576, | |
| "learning_rate": 5.601263157894736e-05, | |
| "loss": 0.0469, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.07148231753197894, | |
| "grad_norm": 0.47502413392066956, | |
| "learning_rate": 5.5484210526315794e-05, | |
| "loss": 0.0102, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.07223476297968397, | |
| "grad_norm": 3.3080074787139893, | |
| "learning_rate": 5.495578947368421e-05, | |
| "loss": 0.0324, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.07298720842738901, | |
| "grad_norm": 2.7681944370269775, | |
| "learning_rate": 5.442736842105264e-05, | |
| "loss": 0.027, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.07373965387509406, | |
| "grad_norm": 0.02752815932035446, | |
| "learning_rate": 5.3898947368421055e-05, | |
| "loss": 0.001, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0744920993227991, | |
| "grad_norm": 0.4413633346557617, | |
| "learning_rate": 5.337052631578947e-05, | |
| "loss": 0.0032, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.07524454477050414, | |
| "grad_norm": 6.715440273284912, | |
| "learning_rate": 5.284210526315789e-05, | |
| "loss": 0.0134, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07524454477050414, | |
| "eval_loss": 0.04449079558253288, | |
| "eval_runtime": 22.4889, | |
| "eval_samples_per_second": 24.901, | |
| "eval_steps_per_second": 6.225, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07599699021820917, | |
| "grad_norm": 3.5583584308624268, | |
| "learning_rate": 5.231368421052631e-05, | |
| "loss": 1.4636, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.07674943566591422, | |
| "grad_norm": 0.1338910460472107, | |
| "learning_rate": 5.178526315789474e-05, | |
| "loss": 0.0514, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.07750188111361926, | |
| "grad_norm": 0.21548093855381012, | |
| "learning_rate": 5.1256842105263165e-05, | |
| "loss": 0.0055, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.0782543265613243, | |
| "grad_norm": 0.2258404642343521, | |
| "learning_rate": 5.072842105263158e-05, | |
| "loss": 0.0067, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.07900677200902935, | |
| "grad_norm": 0.3479577898979187, | |
| "learning_rate": 5.02e-05, | |
| "loss": 0.0025, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.0797592174567344, | |
| "grad_norm": 0.13383802771568298, | |
| "learning_rate": 4.967157894736842e-05, | |
| "loss": 0.0074, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.08051166290443942, | |
| "grad_norm": 0.11670215427875519, | |
| "learning_rate": 4.914315789473684e-05, | |
| "loss": 0.0026, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.08126410835214447, | |
| "grad_norm": 0.32123813033103943, | |
| "learning_rate": 4.861473684210526e-05, | |
| "loss": 0.0095, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.08201655379984951, | |
| "grad_norm": 0.05738672614097595, | |
| "learning_rate": 4.8086315789473686e-05, | |
| "loss": 0.001, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.08276899924755456, | |
| "grad_norm": 0.05406120792031288, | |
| "learning_rate": 4.7557894736842104e-05, | |
| "loss": 0.0016, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0835214446952596, | |
| "grad_norm": 0.02784488908946514, | |
| "learning_rate": 4.702947368421053e-05, | |
| "loss": 0.0016, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.08427389014296463, | |
| "grad_norm": 0.03466448560357094, | |
| "learning_rate": 4.6501052631578946e-05, | |
| "loss": 0.0017, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.08502633559066967, | |
| "grad_norm": 0.03824542835354805, | |
| "learning_rate": 4.5972631578947364e-05, | |
| "loss": 0.0021, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.08577878103837472, | |
| "grad_norm": 0.15851886570453644, | |
| "learning_rate": 4.544421052631579e-05, | |
| "loss": 0.0043, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.08653122648607976, | |
| "grad_norm": 0.025240371003746986, | |
| "learning_rate": 4.4915789473684213e-05, | |
| "loss": 0.0009, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.0872836719337848, | |
| "grad_norm": 0.019472820684313774, | |
| "learning_rate": 4.438736842105263e-05, | |
| "loss": 0.0009, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.08803611738148984, | |
| "grad_norm": 0.48911502957344055, | |
| "learning_rate": 4.3858947368421056e-05, | |
| "loss": 0.0037, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.08878856282919488, | |
| "grad_norm": 0.1643715500831604, | |
| "learning_rate": 4.3330526315789474e-05, | |
| "loss": 0.0056, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.08954100827689992, | |
| "grad_norm": 0.19596649706363678, | |
| "learning_rate": 4.280210526315789e-05, | |
| "loss": 0.0065, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.09029345372460497, | |
| "grad_norm": 1.3377373218536377, | |
| "learning_rate": 4.2273684210526317e-05, | |
| "loss": 0.0621, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09104589917231001, | |
| "grad_norm": 0.505384087562561, | |
| "learning_rate": 4.174526315789474e-05, | |
| "loss": 0.0104, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.09179834462001504, | |
| "grad_norm": 0.0544271357357502, | |
| "learning_rate": 4.121684210526316e-05, | |
| "loss": 0.0023, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.09255079006772009, | |
| "grad_norm": 0.16811607778072357, | |
| "learning_rate": 4.068842105263158e-05, | |
| "loss": 0.0163, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.09330323551542513, | |
| "grad_norm": 0.019329270347952843, | |
| "learning_rate": 4.016e-05, | |
| "loss": 0.0008, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.09405568096313018, | |
| "grad_norm": 0.05329417437314987, | |
| "learning_rate": 3.963157894736842e-05, | |
| "loss": 0.0027, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.09480812641083522, | |
| "grad_norm": 0.08204272389411926, | |
| "learning_rate": 3.9103157894736844e-05, | |
| "loss": 0.0029, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.09556057185854025, | |
| "grad_norm": 0.06737394630908966, | |
| "learning_rate": 3.857473684210526e-05, | |
| "loss": 0.0014, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.0963130173062453, | |
| "grad_norm": 0.20691591501235962, | |
| "learning_rate": 3.804631578947369e-05, | |
| "loss": 0.0039, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.09706546275395034, | |
| "grad_norm": 0.010593212209641933, | |
| "learning_rate": 3.7517894736842105e-05, | |
| "loss": 0.0007, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.09781790820165538, | |
| "grad_norm": 0.025148313492536545, | |
| "learning_rate": 3.698947368421052e-05, | |
| "loss": 0.0014, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09857035364936043, | |
| "grad_norm": 0.1723494529724121, | |
| "learning_rate": 3.646105263157895e-05, | |
| "loss": 0.0043, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.09932279909706546, | |
| "grad_norm": 0.01964077726006508, | |
| "learning_rate": 3.593263157894737e-05, | |
| "loss": 0.001, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.1000752445447705, | |
| "grad_norm": 0.2998151481151581, | |
| "learning_rate": 3.540421052631579e-05, | |
| "loss": 0.0105, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.10082768999247554, | |
| "grad_norm": 0.1715938299894333, | |
| "learning_rate": 3.4875789473684215e-05, | |
| "loss": 0.0035, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.10158013544018059, | |
| "grad_norm": 0.028639964759349823, | |
| "learning_rate": 3.434736842105263e-05, | |
| "loss": 0.0015, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.10233258088788563, | |
| "grad_norm": 0.13613921403884888, | |
| "learning_rate": 3.381894736842105e-05, | |
| "loss": 0.0029, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.10308502633559068, | |
| "grad_norm": 0.03546198457479477, | |
| "learning_rate": 3.329052631578947e-05, | |
| "loss": 0.0016, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.1038374717832957, | |
| "grad_norm": 0.4500066936016083, | |
| "learning_rate": 3.27621052631579e-05, | |
| "loss": 0.0062, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.10458991723100075, | |
| "grad_norm": 0.13641779124736786, | |
| "learning_rate": 3.223368421052632e-05, | |
| "loss": 0.0022, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.1053423626787058, | |
| "grad_norm": 0.24456901848316193, | |
| "learning_rate": 3.1705263157894736e-05, | |
| "loss": 0.0047, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.10609480812641084, | |
| "grad_norm": 0.6857782006263733, | |
| "learning_rate": 3.117684210526316e-05, | |
| "loss": 0.0237, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.10684725357411588, | |
| "grad_norm": 0.017228834331035614, | |
| "learning_rate": 3.064842105263158e-05, | |
| "loss": 0.001, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.10759969902182091, | |
| "grad_norm": 0.8723503351211548, | |
| "learning_rate": 3.012e-05, | |
| "loss": 0.0409, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.10835214446952596, | |
| "grad_norm": 0.1626891791820526, | |
| "learning_rate": 2.9591578947368418e-05, | |
| "loss": 0.0035, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.109104589917231, | |
| "grad_norm": 0.020657368004322052, | |
| "learning_rate": 2.9063157894736842e-05, | |
| "loss": 0.0009, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.10985703536493605, | |
| "grad_norm": 0.12785644829273224, | |
| "learning_rate": 2.8534736842105264e-05, | |
| "loss": 0.0024, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.11060948081264109, | |
| "grad_norm": 0.13075271248817444, | |
| "learning_rate": 2.800631578947368e-05, | |
| "loss": 0.0028, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.11136192626034612, | |
| "grad_norm": 0.02945193648338318, | |
| "learning_rate": 2.7477894736842106e-05, | |
| "loss": 0.0015, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.11211437170805116, | |
| "grad_norm": 0.6050726175308228, | |
| "learning_rate": 2.6949473684210527e-05, | |
| "loss": 0.0216, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.11286681715575621, | |
| "grad_norm": 2.671539068222046, | |
| "learning_rate": 2.6421052631578945e-05, | |
| "loss": 0.0604, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11286681715575621, | |
| "eval_loss": 0.02783067524433136, | |
| "eval_runtime": 22.4241, | |
| "eval_samples_per_second": 24.973, | |
| "eval_steps_per_second": 6.243, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 1.03394618376192e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |