| { | |
| "best_metric": 0.9858, | |
| "best_model_checkpoint": "vit-small-patch16-224-finetuned-eurosat/checkpoint-1053", | |
| "epoch": 2.9936034115138592, | |
| "eval_steps": 500, | |
| "global_step": 1053, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 10.28113842010498, | |
| "learning_rate": 4.716981132075472e-06, | |
| "loss": 2.4319, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 8.099526405334473, | |
| "learning_rate": 9.433962264150944e-06, | |
| "loss": 2.2018, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 7.611712455749512, | |
| "learning_rate": 1.4150943396226415e-05, | |
| "loss": 1.8435, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 6.348332405090332, | |
| "learning_rate": 1.8867924528301888e-05, | |
| "loss": 1.3723, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 6.2716383934021, | |
| "learning_rate": 2.358490566037736e-05, | |
| "loss": 0.94, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 5.221578598022461, | |
| "learning_rate": 2.830188679245283e-05, | |
| "loss": 0.6525, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 6.387922286987305, | |
| "learning_rate": 3.30188679245283e-05, | |
| "loss": 0.4783, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 7.3089280128479, | |
| "learning_rate": 3.7735849056603776e-05, | |
| "loss": 0.4596, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 7.125087738037109, | |
| "learning_rate": 4.245283018867925e-05, | |
| "loss": 0.4017, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 6.698434352874756, | |
| "learning_rate": 4.716981132075472e-05, | |
| "loss": 0.4367, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 5.051684379577637, | |
| "learning_rate": 4.978880675818374e-05, | |
| "loss": 0.4136, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 5.622159481048584, | |
| "learning_rate": 4.9260823653643085e-05, | |
| "loss": 0.3495, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 4.886028289794922, | |
| "learning_rate": 4.8732840549102435e-05, | |
| "loss": 0.3584, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 5.2919464111328125, | |
| "learning_rate": 4.820485744456177e-05, | |
| "loss": 0.3697, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 4.783895015716553, | |
| "learning_rate": 4.767687434002112e-05, | |
| "loss": 0.3255, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 5.268603801727295, | |
| "learning_rate": 4.7148891235480466e-05, | |
| "loss": 0.2753, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 4.839652061462402, | |
| "learning_rate": 4.662090813093981e-05, | |
| "loss": 0.3665, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 6.260977268218994, | |
| "learning_rate": 4.609292502639916e-05, | |
| "loss": 0.3538, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 6.801572322845459, | |
| "learning_rate": 4.55649419218585e-05, | |
| "loss": 0.3209, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 4.416426181793213, | |
| "learning_rate": 4.503695881731785e-05, | |
| "loss": 0.3639, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 4.522943496704102, | |
| "learning_rate": 4.45089757127772e-05, | |
| "loss": 0.3549, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 4.867265701293945, | |
| "learning_rate": 4.398099260823654e-05, | |
| "loss": 0.3162, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 3.9709298610687256, | |
| "learning_rate": 4.3453009503695884e-05, | |
| "loss": 0.3262, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 6.413914203643799, | |
| "learning_rate": 4.292502639915523e-05, | |
| "loss": 0.3138, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 5.912984371185303, | |
| "learning_rate": 4.239704329461457e-05, | |
| "loss": 0.3392, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 6.368038654327393, | |
| "learning_rate": 4.186906019007392e-05, | |
| "loss": 0.3455, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 5.320718765258789, | |
| "learning_rate": 4.1341077085533265e-05, | |
| "loss": 0.366, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 7.292255401611328, | |
| "learning_rate": 4.081309398099261e-05, | |
| "loss": 0.2717, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 5.049527645111084, | |
| "learning_rate": 4.028511087645195e-05, | |
| "loss": 0.2975, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 6.135931968688965, | |
| "learning_rate": 3.97571277719113e-05, | |
| "loss": 0.3062, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 4.831919193267822, | |
| "learning_rate": 3.9229144667370646e-05, | |
| "loss": 0.2905, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 5.4459004402160645, | |
| "learning_rate": 3.870116156282999e-05, | |
| "loss": 0.2793, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 4.388113021850586, | |
| "learning_rate": 3.817317845828934e-05, | |
| "loss": 0.2693, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 6.186318397521973, | |
| "learning_rate": 3.764519535374868e-05, | |
| "loss": 0.2748, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 5.3381571769714355, | |
| "learning_rate": 3.711721224920803e-05, | |
| "loss": 0.2917, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.978, | |
| "eval_loss": 0.06850162893533707, | |
| "eval_runtime": 25.1899, | |
| "eval_samples_per_second": 198.492, | |
| "eval_steps_per_second": 6.233, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 5.977785110473633, | |
| "learning_rate": 3.658922914466738e-05, | |
| "loss": 0.2555, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 5.4659833908081055, | |
| "learning_rate": 3.6061246040126714e-05, | |
| "loss": 0.2848, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 4.9763102531433105, | |
| "learning_rate": 3.5533262935586064e-05, | |
| "loss": 0.2683, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 4.409792423248291, | |
| "learning_rate": 3.500527983104541e-05, | |
| "loss": 0.251, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 4.857778549194336, | |
| "learning_rate": 3.447729672650475e-05, | |
| "loss": 0.2863, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 4.256765365600586, | |
| "learning_rate": 3.3949313621964095e-05, | |
| "loss": 0.2713, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 5.335643291473389, | |
| "learning_rate": 3.3421330517423445e-05, | |
| "loss": 0.2399, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 5.516129970550537, | |
| "learning_rate": 3.289334741288279e-05, | |
| "loss": 0.2996, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 4.931915760040283, | |
| "learning_rate": 3.236536430834213e-05, | |
| "loss": 0.2589, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 5.359438419342041, | |
| "learning_rate": 3.183738120380148e-05, | |
| "loss": 0.2484, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 6.711644172668457, | |
| "learning_rate": 3.130939809926082e-05, | |
| "loss": 0.2653, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 5.4322123527526855, | |
| "learning_rate": 3.078141499472017e-05, | |
| "loss": 0.2792, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 4.9093217849731445, | |
| "learning_rate": 3.0253431890179517e-05, | |
| "loss": 0.2582, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 4.9250407218933105, | |
| "learning_rate": 2.972544878563886e-05, | |
| "loss": 0.2654, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 2.4999403953552246, | |
| "learning_rate": 2.9197465681098207e-05, | |
| "loss": 0.215, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 4.765162944793701, | |
| "learning_rate": 2.8669482576557548e-05, | |
| "loss": 0.2582, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 6.872219085693359, | |
| "learning_rate": 2.8141499472016898e-05, | |
| "loss": 0.2744, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 6.02485990524292, | |
| "learning_rate": 2.7613516367476245e-05, | |
| "loss": 0.2729, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 4.077101230621338, | |
| "learning_rate": 2.7085533262935585e-05, | |
| "loss": 0.2844, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 4.896088600158691, | |
| "learning_rate": 2.6557550158394935e-05, | |
| "loss": 0.2644, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 3.769162893295288, | |
| "learning_rate": 2.6029567053854276e-05, | |
| "loss": 0.2404, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 6.33480978012085, | |
| "learning_rate": 2.5501583949313622e-05, | |
| "loss": 0.2395, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 3.935082197189331, | |
| "learning_rate": 2.497360084477297e-05, | |
| "loss": 0.262, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 4.223917007446289, | |
| "learning_rate": 2.4445617740232313e-05, | |
| "loss": 0.2497, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 6.122809886932373, | |
| "learning_rate": 2.391763463569166e-05, | |
| "loss": 0.2601, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 4.6242218017578125, | |
| "learning_rate": 2.3389651531151003e-05, | |
| "loss": 0.2498, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 3.434412717819214, | |
| "learning_rate": 2.286166842661035e-05, | |
| "loss": 0.2504, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 4.349066734313965, | |
| "learning_rate": 2.2333685322069694e-05, | |
| "loss": 0.2176, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 5.38076114654541, | |
| "learning_rate": 2.180570221752904e-05, | |
| "loss": 0.2372, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 4.073547840118408, | |
| "learning_rate": 2.1277719112988384e-05, | |
| "loss": 0.2349, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 5.9817304611206055, | |
| "learning_rate": 2.074973600844773e-05, | |
| "loss": 0.2477, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 4.140634536743164, | |
| "learning_rate": 2.0221752903907075e-05, | |
| "loss": 0.2351, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 4.554591178894043, | |
| "learning_rate": 1.9693769799366422e-05, | |
| "loss": 0.2299, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 4.5683770179748535, | |
| "learning_rate": 1.9165786694825765e-05, | |
| "loss": 0.2564, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 4.515622615814209, | |
| "learning_rate": 1.863780359028511e-05, | |
| "loss": 0.2336, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9846, | |
| "eval_loss": 0.049049846827983856, | |
| "eval_runtime": 25.411, | |
| "eval_samples_per_second": 196.765, | |
| "eval_steps_per_second": 6.178, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 5.377518177032471, | |
| "learning_rate": 1.810982048574446e-05, | |
| "loss": 0.2321, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 4.5595879554748535, | |
| "learning_rate": 1.7581837381203803e-05, | |
| "loss": 0.23, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 4.823131561279297, | |
| "learning_rate": 1.7053854276663146e-05, | |
| "loss": 0.2022, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 4.324634552001953, | |
| "learning_rate": 1.6525871172122493e-05, | |
| "loss": 0.2141, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 3.307523727416992, | |
| "learning_rate": 1.5997888067581837e-05, | |
| "loss": 0.2063, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 3.5987954139709473, | |
| "learning_rate": 1.5469904963041184e-05, | |
| "loss": 0.1993, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 5.780092716217041, | |
| "learning_rate": 1.4941921858500529e-05, | |
| "loss": 0.1778, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 4.3173394203186035, | |
| "learning_rate": 1.4413938753959874e-05, | |
| "loss": 0.2026, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 2.905527114868164, | |
| "learning_rate": 1.388595564941922e-05, | |
| "loss": 0.1962, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "grad_norm": 4.181800842285156, | |
| "learning_rate": 1.3357972544878563e-05, | |
| "loss": 0.2342, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 4.401543140411377, | |
| "learning_rate": 1.2829989440337912e-05, | |
| "loss": 0.208, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "grad_norm": 3.915311813354492, | |
| "learning_rate": 1.2302006335797255e-05, | |
| "loss": 0.2125, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 4.805098533630371, | |
| "learning_rate": 1.17740232312566e-05, | |
| "loss": 0.2336, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "grad_norm": 3.744398355484009, | |
| "learning_rate": 1.1246040126715946e-05, | |
| "loss": 0.2234, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "grad_norm": 2.4920966625213623, | |
| "learning_rate": 1.0718057022175291e-05, | |
| "loss": 0.2075, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 3.641676902770996, | |
| "learning_rate": 1.0190073917634636e-05, | |
| "loss": 0.213, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "grad_norm": 5.000159740447998, | |
| "learning_rate": 9.662090813093982e-06, | |
| "loss": 0.1963, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 4.8027119636535645, | |
| "learning_rate": 9.134107708553327e-06, | |
| "loss": 0.2021, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "grad_norm": 3.8849587440490723, | |
| "learning_rate": 8.606124604012672e-06, | |
| "loss": 0.2295, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 4.998702049255371, | |
| "learning_rate": 8.078141499472017e-06, | |
| "loss": 0.2199, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "grad_norm": 3.681274175643921, | |
| "learning_rate": 7.5501583949313625e-06, | |
| "loss": 0.2181, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "grad_norm": 3.923170804977417, | |
| "learning_rate": 7.022175290390708e-06, | |
| "loss": 0.2138, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 4.893486976623535, | |
| "learning_rate": 6.494192185850054e-06, | |
| "loss": 0.2181, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 3.597585916519165, | |
| "learning_rate": 5.966209081309398e-06, | |
| "loss": 0.229, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 4.191518783569336, | |
| "learning_rate": 5.438225976768744e-06, | |
| "loss": 0.2209, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "grad_norm": 4.912830352783203, | |
| "learning_rate": 4.910242872228089e-06, | |
| "loss": 0.1633, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 4.285012722015381, | |
| "learning_rate": 4.382259767687434e-06, | |
| "loss": 0.2035, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 5.451338768005371, | |
| "learning_rate": 3.854276663146779e-06, | |
| "loss": 0.187, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "grad_norm": 3.7574963569641113, | |
| "learning_rate": 3.326293558606125e-06, | |
| "loss": 0.2181, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 4.432431221008301, | |
| "learning_rate": 2.79831045406547e-06, | |
| "loss": 0.2048, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "grad_norm": 6.7038726806640625, | |
| "learning_rate": 2.2703273495248154e-06, | |
| "loss": 0.2121, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 5.3371500968933105, | |
| "learning_rate": 1.7423442449841606e-06, | |
| "loss": 0.2299, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "grad_norm": 5.540638446807861, | |
| "learning_rate": 1.2143611404435059e-06, | |
| "loss": 0.2052, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 6.598842620849609, | |
| "learning_rate": 6.863780359028511e-07, | |
| "loss": 0.2063, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "grad_norm": 4.390342712402344, | |
| "learning_rate": 1.5839493136219642e-07, | |
| "loss": 0.1666, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.9858, | |
| "eval_loss": 0.041506800800561905, | |
| "eval_runtime": 25.8539, | |
| "eval_samples_per_second": 193.394, | |
| "eval_steps_per_second": 6.073, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 1053, | |
| "total_flos": 2.636946768879747e+18, | |
| "train_loss": 0.33888192813054563, | |
| "train_runtime": 1629.4605, | |
| "train_samples_per_second": 82.85, | |
| "train_steps_per_second": 0.646 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1053, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.636946768879747e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |