| { | |
| "best_metric": 0.9614, | |
| "best_model_checkpoint": "clip-vit-base-patch32-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": 1.7241759300231934, | |
| "learning_rate": 4.716981132075472e-06, | |
| "loss": 2.3024, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 3.8202145099639893, | |
| "learning_rate": 9.433962264150944e-06, | |
| "loss": 2.2975, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 8.925788879394531, | |
| "learning_rate": 1.4150943396226415e-05, | |
| "loss": 2.2628, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 16.57902717590332, | |
| "learning_rate": 1.8867924528301888e-05, | |
| "loss": 2.1487, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 22.54959487915039, | |
| "learning_rate": 2.358490566037736e-05, | |
| "loss": 1.9168, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 20.70589256286621, | |
| "learning_rate": 2.830188679245283e-05, | |
| "loss": 1.7142, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 25.339296340942383, | |
| "learning_rate": 3.30188679245283e-05, | |
| "loss": 1.5649, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 30.290817260742188, | |
| "learning_rate": 3.7735849056603776e-05, | |
| "loss": 1.4656, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 36.66164016723633, | |
| "learning_rate": 4.245283018867925e-05, | |
| "loss": 1.2988, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 37.965667724609375, | |
| "learning_rate": 4.716981132075472e-05, | |
| "loss": 1.3997, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 22.961999893188477, | |
| "learning_rate": 4.978880675818374e-05, | |
| "loss": 1.1785, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 17.519174575805664, | |
| "learning_rate": 4.9260823653643085e-05, | |
| "loss": 1.1307, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 22.371517181396484, | |
| "learning_rate": 4.8732840549102435e-05, | |
| "loss": 1.1619, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 26.505937576293945, | |
| "learning_rate": 4.820485744456177e-05, | |
| "loss": 1.0016, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 26.786195755004883, | |
| "learning_rate": 4.767687434002112e-05, | |
| "loss": 0.9419, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 27.246932983398438, | |
| "learning_rate": 4.7148891235480466e-05, | |
| "loss": 0.9388, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 26.55625343322754, | |
| "learning_rate": 4.662090813093981e-05, | |
| "loss": 0.9833, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 31.99274253845215, | |
| "learning_rate": 4.609292502639916e-05, | |
| "loss": 0.9239, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 29.839174270629883, | |
| "learning_rate": 4.55649419218585e-05, | |
| "loss": 0.8898, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 30.187131881713867, | |
| "learning_rate": 4.503695881731785e-05, | |
| "loss": 0.8662, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 26.78498649597168, | |
| "learning_rate": 4.45089757127772e-05, | |
| "loss": 0.8236, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 21.103544235229492, | |
| "learning_rate": 4.398099260823654e-05, | |
| "loss": 0.8185, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 19.34087371826172, | |
| "learning_rate": 4.3453009503695884e-05, | |
| "loss": 0.8716, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 14.883440017700195, | |
| "learning_rate": 4.292502639915523e-05, | |
| "loss": 0.8187, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 16.855531692504883, | |
| "learning_rate": 4.239704329461457e-05, | |
| "loss": 0.7924, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 14.5891695022583, | |
| "learning_rate": 4.186906019007392e-05, | |
| "loss": 0.7738, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 17.91446876525879, | |
| "learning_rate": 4.1341077085533265e-05, | |
| "loss": 0.7254, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 16.657079696655273, | |
| "learning_rate": 4.081309398099261e-05, | |
| "loss": 0.7443, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 28.285350799560547, | |
| "learning_rate": 4.028511087645195e-05, | |
| "loss": 0.7667, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 15.021693229675293, | |
| "learning_rate": 3.97571277719113e-05, | |
| "loss": 0.7379, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 24.571500778198242, | |
| "learning_rate": 3.9229144667370646e-05, | |
| "loss": 0.7032, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 18.02920150756836, | |
| "learning_rate": 3.870116156282999e-05, | |
| "loss": 0.7563, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 24.86216926574707, | |
| "learning_rate": 3.817317845828934e-05, | |
| "loss": 0.7057, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 21.064966201782227, | |
| "learning_rate": 3.764519535374868e-05, | |
| "loss": 0.704, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 17.003034591674805, | |
| "learning_rate": 3.711721224920803e-05, | |
| "loss": 0.6844, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8944, | |
| "eval_loss": 0.32426366209983826, | |
| "eval_runtime": 45.5941, | |
| "eval_samples_per_second": 109.663, | |
| "eval_steps_per_second": 3.443, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 16.356178283691406, | |
| "learning_rate": 3.658922914466738e-05, | |
| "loss": 0.6784, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 17.41063690185547, | |
| "learning_rate": 3.6061246040126714e-05, | |
| "loss": 0.6746, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 22.446226119995117, | |
| "learning_rate": 3.5533262935586064e-05, | |
| "loss": 0.7191, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 14.2515230178833, | |
| "learning_rate": 3.500527983104541e-05, | |
| "loss": 0.6181, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 21.2375545501709, | |
| "learning_rate": 3.447729672650475e-05, | |
| "loss": 0.6146, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 30.0297794342041, | |
| "learning_rate": 3.3949313621964095e-05, | |
| "loss": 0.5986, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 18.535289764404297, | |
| "learning_rate": 3.3421330517423445e-05, | |
| "loss": 0.584, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 20.00425910949707, | |
| "learning_rate": 3.289334741288279e-05, | |
| "loss": 0.6802, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 16.380542755126953, | |
| "learning_rate": 3.236536430834213e-05, | |
| "loss": 0.6259, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 14.940071105957031, | |
| "learning_rate": 3.183738120380148e-05, | |
| "loss": 0.6096, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 15.746271133422852, | |
| "learning_rate": 3.130939809926082e-05, | |
| "loss": 0.6153, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 23.13232421875, | |
| "learning_rate": 3.078141499472017e-05, | |
| "loss": 0.6158, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 16.764955520629883, | |
| "learning_rate": 3.0253431890179517e-05, | |
| "loss": 0.5553, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 14.932197570800781, | |
| "learning_rate": 2.972544878563886e-05, | |
| "loss": 0.5601, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 13.885882377624512, | |
| "learning_rate": 2.9197465681098207e-05, | |
| "loss": 0.5535, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 17.77952003479004, | |
| "learning_rate": 2.8669482576557548e-05, | |
| "loss": 0.6082, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 15.429793357849121, | |
| "learning_rate": 2.8141499472016898e-05, | |
| "loss": 0.5267, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 16.568571090698242, | |
| "learning_rate": 2.7613516367476245e-05, | |
| "loss": 0.5515, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 17.248546600341797, | |
| "learning_rate": 2.7085533262935585e-05, | |
| "loss": 0.5345, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 12.159417152404785, | |
| "learning_rate": 2.6557550158394935e-05, | |
| "loss": 0.4961, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 14.413479804992676, | |
| "learning_rate": 2.6029567053854276e-05, | |
| "loss": 0.5178, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 14.496917724609375, | |
| "learning_rate": 2.5501583949313622e-05, | |
| "loss": 0.5092, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 14.64006519317627, | |
| "learning_rate": 2.497360084477297e-05, | |
| "loss": 0.5421, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 16.412023544311523, | |
| "learning_rate": 2.4445617740232313e-05, | |
| "loss": 0.5297, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 13.8049898147583, | |
| "learning_rate": 2.391763463569166e-05, | |
| "loss": 0.5268, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 18.511188507080078, | |
| "learning_rate": 2.3389651531151003e-05, | |
| "loss": 0.5105, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 14.077324867248535, | |
| "learning_rate": 2.286166842661035e-05, | |
| "loss": 0.4611, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 13.796318054199219, | |
| "learning_rate": 2.2333685322069694e-05, | |
| "loss": 0.5079, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 12.892987251281738, | |
| "learning_rate": 2.180570221752904e-05, | |
| "loss": 0.5148, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 16.096128463745117, | |
| "learning_rate": 2.1277719112988384e-05, | |
| "loss": 0.5426, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 13.577393531799316, | |
| "learning_rate": 2.074973600844773e-05, | |
| "loss": 0.5145, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 12.556589126586914, | |
| "learning_rate": 2.0221752903907075e-05, | |
| "loss": 0.472, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 21.511499404907227, | |
| "learning_rate": 1.9693769799366422e-05, | |
| "loss": 0.5104, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 19.831825256347656, | |
| "learning_rate": 1.9165786694825765e-05, | |
| "loss": 0.4633, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 17.47673797607422, | |
| "learning_rate": 1.863780359028511e-05, | |
| "loss": 0.4737, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9384, | |
| "eval_loss": 0.17878523468971252, | |
| "eval_runtime": 44.7121, | |
| "eval_samples_per_second": 111.827, | |
| "eval_steps_per_second": 3.511, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 13.325546264648438, | |
| "learning_rate": 1.810982048574446e-05, | |
| "loss": 0.4421, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 12.169154167175293, | |
| "learning_rate": 1.7581837381203803e-05, | |
| "loss": 0.4291, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 15.889957427978516, | |
| "learning_rate": 1.7053854276663146e-05, | |
| "loss": 0.4336, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 16.29996681213379, | |
| "learning_rate": 1.6525871172122493e-05, | |
| "loss": 0.4241, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 14.88168716430664, | |
| "learning_rate": 1.5997888067581837e-05, | |
| "loss": 0.3791, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 16.35209083557129, | |
| "learning_rate": 1.5469904963041184e-05, | |
| "loss": 0.4707, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 14.11000919342041, | |
| "learning_rate": 1.4941921858500529e-05, | |
| "loss": 0.405, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 12.48878288269043, | |
| "learning_rate": 1.4413938753959874e-05, | |
| "loss": 0.4214, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 13.443764686584473, | |
| "learning_rate": 1.388595564941922e-05, | |
| "loss": 0.3816, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "grad_norm": 11.2753267288208, | |
| "learning_rate": 1.3357972544878563e-05, | |
| "loss": 0.4273, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 9.510777473449707, | |
| "learning_rate": 1.2829989440337912e-05, | |
| "loss": 0.4543, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "grad_norm": 15.178093910217285, | |
| "learning_rate": 1.2302006335797255e-05, | |
| "loss": 0.4011, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 12.959372520446777, | |
| "learning_rate": 1.17740232312566e-05, | |
| "loss": 0.3952, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "grad_norm": 13.760416030883789, | |
| "learning_rate": 1.1246040126715946e-05, | |
| "loss": 0.4096, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "grad_norm": 14.852051734924316, | |
| "learning_rate": 1.0718057022175291e-05, | |
| "loss": 0.4518, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 15.75942325592041, | |
| "learning_rate": 1.0190073917634636e-05, | |
| "loss": 0.4095, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "grad_norm": 12.429645538330078, | |
| "learning_rate": 9.662090813093982e-06, | |
| "loss": 0.3606, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 14.525588035583496, | |
| "learning_rate": 9.134107708553327e-06, | |
| "loss": 0.386, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "grad_norm": 8.88588809967041, | |
| "learning_rate": 8.606124604012672e-06, | |
| "loss": 0.3748, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 13.352007865905762, | |
| "learning_rate": 8.078141499472017e-06, | |
| "loss": 0.364, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "grad_norm": 13.020881652832031, | |
| "learning_rate": 7.5501583949313625e-06, | |
| "loss": 0.371, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "grad_norm": 10.579428672790527, | |
| "learning_rate": 7.022175290390708e-06, | |
| "loss": 0.3952, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 14.498714447021484, | |
| "learning_rate": 6.494192185850054e-06, | |
| "loss": 0.3954, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 11.845131874084473, | |
| "learning_rate": 5.966209081309398e-06, | |
| "loss": 0.3882, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 9.537396430969238, | |
| "learning_rate": 5.438225976768744e-06, | |
| "loss": 0.3686, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "grad_norm": 11.347996711730957, | |
| "learning_rate": 4.910242872228089e-06, | |
| "loss": 0.362, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 13.484134674072266, | |
| "learning_rate": 4.382259767687434e-06, | |
| "loss": 0.3536, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 12.782801628112793, | |
| "learning_rate": 3.854276663146779e-06, | |
| "loss": 0.3648, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "grad_norm": 11.670198440551758, | |
| "learning_rate": 3.326293558606125e-06, | |
| "loss": 0.3361, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 14.617063522338867, | |
| "learning_rate": 2.79831045406547e-06, | |
| "loss": 0.3345, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "grad_norm": 10.081778526306152, | |
| "learning_rate": 2.2703273495248154e-06, | |
| "loss": 0.3359, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 13.262909889221191, | |
| "learning_rate": 1.7423442449841606e-06, | |
| "loss": 0.3221, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "grad_norm": 13.598889350891113, | |
| "learning_rate": 1.2143611404435059e-06, | |
| "loss": 0.3582, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 11.878829002380371, | |
| "learning_rate": 6.863780359028511e-07, | |
| "loss": 0.3085, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "grad_norm": 13.71689224243164, | |
| "learning_rate": 1.5839493136219642e-07, | |
| "loss": 0.3252, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.9614, | |
| "eval_loss": 0.12246201187372208, | |
| "eval_runtime": 45.5034, | |
| "eval_samples_per_second": 109.882, | |
| "eval_steps_per_second": 3.45, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 1053, | |
| "total_flos": 1.0638717415807058e+19, | |
| "train_loss": 0.6938335181754313, | |
| "train_runtime": 1591.9984, | |
| "train_samples_per_second": 84.799, | |
| "train_steps_per_second": 0.661 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1053, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.0638717415807058e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |