|
{ |
|
"best_metric": 0.6213592233009708, |
|
"best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-conflab-traj-direction-rh-v2/checkpoint-1053", |
|
"epoch": 8.103513770180436, |
|
"eval_steps": 500, |
|
"global_step": 1053, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00949667616334283, |
|
"grad_norm": 8.752718925476074, |
|
"learning_rate": 4.716981132075472e-06, |
|
"loss": 2.1131, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.01899335232668566, |
|
"grad_norm": 7.10194206237793, |
|
"learning_rate": 9.433962264150944e-06, |
|
"loss": 2.031, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.02849002849002849, |
|
"grad_norm": 8.048168182373047, |
|
"learning_rate": 1.4150943396226415e-05, |
|
"loss": 2.0382, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.03798670465337132, |
|
"grad_norm": 8.191485404968262, |
|
"learning_rate": 1.8867924528301888e-05, |
|
"loss": 1.9895, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.04748338081671415, |
|
"grad_norm": 7.475042819976807, |
|
"learning_rate": 2.358490566037736e-05, |
|
"loss": 1.9052, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.05698005698005698, |
|
"grad_norm": 12.284913063049316, |
|
"learning_rate": 2.830188679245283e-05, |
|
"loss": 1.9474, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.06647673314339982, |
|
"grad_norm": 6.110039234161377, |
|
"learning_rate": 3.30188679245283e-05, |
|
"loss": 1.8688, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.07597340930674264, |
|
"grad_norm": 9.754578590393066, |
|
"learning_rate": 3.7735849056603776e-05, |
|
"loss": 1.9115, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.08547008547008547, |
|
"grad_norm": 7.101430892944336, |
|
"learning_rate": 4.245283018867925e-05, |
|
"loss": 1.9359, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.0949667616334283, |
|
"grad_norm": 5.658616065979004, |
|
"learning_rate": 4.716981132075472e-05, |
|
"loss": 1.9613, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.10446343779677113, |
|
"grad_norm": 4.824208736419678, |
|
"learning_rate": 4.978880675818374e-05, |
|
"loss": 1.9728, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.1120607787274454, |
|
"eval_accuracy": 0.2912621359223301, |
|
"eval_loss": 1.8081567287445068, |
|
"eval_runtime": 37.3417, |
|
"eval_samples_per_second": 5.517, |
|
"eval_steps_per_second": 0.696, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 1.0018993352326686, |
|
"grad_norm": 5.8929443359375, |
|
"learning_rate": 4.9260823653643085e-05, |
|
"loss": 1.8685, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.0113960113960114, |
|
"grad_norm": 5.137537956237793, |
|
"learning_rate": 4.8732840549102435e-05, |
|
"loss": 1.8045, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.0208926875593543, |
|
"grad_norm": 8.457473754882812, |
|
"learning_rate": 4.820485744456177e-05, |
|
"loss": 1.7704, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.030389363722697, |
|
"grad_norm": 6.545841693878174, |
|
"learning_rate": 4.767687434002112e-05, |
|
"loss": 1.7769, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.03988603988604, |
|
"grad_norm": 11.467026710510254, |
|
"learning_rate": 4.7148891235480466e-05, |
|
"loss": 1.664, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.0493827160493827, |
|
"grad_norm": 7.759367942810059, |
|
"learning_rate": 4.662090813093981e-05, |
|
"loss": 1.6638, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.0588793922127255, |
|
"grad_norm": 4.53931188583374, |
|
"learning_rate": 4.609292502639916e-05, |
|
"loss": 1.6305, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.0683760683760684, |
|
"grad_norm": 11.055715560913086, |
|
"learning_rate": 4.55649419218585e-05, |
|
"loss": 1.6884, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.0778727445394112, |
|
"grad_norm": 7.864542007446289, |
|
"learning_rate": 4.503695881731785e-05, |
|
"loss": 1.5855, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.087369420702754, |
|
"grad_norm": 10.435840606689453, |
|
"learning_rate": 4.45089757127772e-05, |
|
"loss": 1.4554, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.0968660968660968, |
|
"grad_norm": 9.551925659179688, |
|
"learning_rate": 4.398099260823654e-05, |
|
"loss": 1.6277, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.1063627730294396, |
|
"grad_norm": 8.910355567932129, |
|
"learning_rate": 4.3453009503695884e-05, |
|
"loss": 1.5903, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.1120607787274455, |
|
"eval_accuracy": 0.3786407766990291, |
|
"eval_loss": 1.803798794746399, |
|
"eval_runtime": 30.5748, |
|
"eval_samples_per_second": 6.738, |
|
"eval_steps_per_second": 0.85, |
|
"step": 236 |
|
}, |
|
{ |
|
"epoch": 2.003798670465337, |
|
"grad_norm": 5.9250712394714355, |
|
"learning_rate": 4.292502639915523e-05, |
|
"loss": 1.7366, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 2.01329534662868, |
|
"grad_norm": 7.3831400871276855, |
|
"learning_rate": 4.239704329461457e-05, |
|
"loss": 1.4794, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.022792022792023, |
|
"grad_norm": 4.820956230163574, |
|
"learning_rate": 4.186906019007392e-05, |
|
"loss": 1.2516, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 2.0322886989553655, |
|
"grad_norm": 10.172005653381348, |
|
"learning_rate": 4.1341077085533265e-05, |
|
"loss": 1.3548, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.0417853751187085, |
|
"grad_norm": 14.752180099487305, |
|
"learning_rate": 4.081309398099261e-05, |
|
"loss": 1.2371, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 2.051282051282051, |
|
"grad_norm": 12.396346092224121, |
|
"learning_rate": 4.028511087645195e-05, |
|
"loss": 1.4009, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.060778727445394, |
|
"grad_norm": 11.691078186035156, |
|
"learning_rate": 3.97571277719113e-05, |
|
"loss": 1.2658, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.0702754036087367, |
|
"grad_norm": 7.867719650268555, |
|
"learning_rate": 3.9229144667370646e-05, |
|
"loss": 1.3029, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 2.07977207977208, |
|
"grad_norm": 11.82673454284668, |
|
"learning_rate": 3.870116156282999e-05, |
|
"loss": 1.1971, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 2.0892687559354224, |
|
"grad_norm": 12.339221954345703, |
|
"learning_rate": 3.817317845828934e-05, |
|
"loss": 1.3162, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 2.0987654320987654, |
|
"grad_norm": 14.504555702209473, |
|
"learning_rate": 3.764519535374868e-05, |
|
"loss": 1.4248, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 2.1082621082621085, |
|
"grad_norm": 12.908592224121094, |
|
"learning_rate": 3.711721224920803e-05, |
|
"loss": 1.2371, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.1120607787274452, |
|
"eval_accuracy": 0.4563106796116505, |
|
"eval_loss": 1.466732382774353, |
|
"eval_runtime": 28.3624, |
|
"eval_samples_per_second": 7.263, |
|
"eval_steps_per_second": 0.917, |
|
"step": 354 |
|
}, |
|
{ |
|
"epoch": 3.005698005698006, |
|
"grad_norm": 10.089714050292969, |
|
"learning_rate": 3.658922914466738e-05, |
|
"loss": 0.9885, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 3.0151946818613484, |
|
"grad_norm": 6.925798416137695, |
|
"learning_rate": 3.6061246040126714e-05, |
|
"loss": 0.8912, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 3.0246913580246915, |
|
"grad_norm": 7.01603889465332, |
|
"learning_rate": 3.5533262935586064e-05, |
|
"loss": 0.78, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 3.034188034188034, |
|
"grad_norm": 7.25798225402832, |
|
"learning_rate": 3.500527983104541e-05, |
|
"loss": 0.6707, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 3.043684710351377, |
|
"grad_norm": 11.455845832824707, |
|
"learning_rate": 3.447729672650475e-05, |
|
"loss": 0.8491, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 3.0531813865147197, |
|
"grad_norm": 13.49953556060791, |
|
"learning_rate": 3.3949313621964095e-05, |
|
"loss": 0.7744, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 3.0626780626780628, |
|
"grad_norm": 19.157188415527344, |
|
"learning_rate": 3.3421330517423445e-05, |
|
"loss": 0.83, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 3.0721747388414054, |
|
"grad_norm": 15.591106414794922, |
|
"learning_rate": 3.289334741288279e-05, |
|
"loss": 0.8751, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 3.0816714150047484, |
|
"grad_norm": 15.52799129486084, |
|
"learning_rate": 3.236536430834213e-05, |
|
"loss": 0.868, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 3.091168091168091, |
|
"grad_norm": 15.363070487976074, |
|
"learning_rate": 3.183738120380148e-05, |
|
"loss": 0.7792, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 3.100664767331434, |
|
"grad_norm": 9.656035423278809, |
|
"learning_rate": 3.130939809926082e-05, |
|
"loss": 0.6143, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 3.1101614434947766, |
|
"grad_norm": 11.785117149353027, |
|
"learning_rate": 3.078141499472017e-05, |
|
"loss": 0.9635, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 3.1120607787274452, |
|
"eval_accuracy": 0.5631067961165048, |
|
"eval_loss": 1.418686032295227, |
|
"eval_runtime": 23.7661, |
|
"eval_samples_per_second": 8.668, |
|
"eval_steps_per_second": 1.094, |
|
"step": 472 |
|
}, |
|
{ |
|
"epoch": 4.007597340930674, |
|
"grad_norm": 5.675172805786133, |
|
"learning_rate": 3.0253431890179517e-05, |
|
"loss": 0.5573, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 4.017094017094017, |
|
"grad_norm": 5.014197826385498, |
|
"learning_rate": 2.972544878563886e-05, |
|
"loss": 0.4382, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 4.02659069325736, |
|
"grad_norm": 8.953272819519043, |
|
"learning_rate": 2.9197465681098207e-05, |
|
"loss": 0.639, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 4.036087369420703, |
|
"grad_norm": 10.838029861450195, |
|
"learning_rate": 2.8669482576557548e-05, |
|
"loss": 0.493, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 4.045584045584046, |
|
"grad_norm": 8.463229179382324, |
|
"learning_rate": 2.8141499472016898e-05, |
|
"loss": 0.4703, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 4.055080721747388, |
|
"grad_norm": 8.104616165161133, |
|
"learning_rate": 2.7613516367476245e-05, |
|
"loss": 0.3912, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 4.064577397910731, |
|
"grad_norm": 13.097394943237305, |
|
"learning_rate": 2.7085533262935585e-05, |
|
"loss": 0.4528, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 4.074074074074074, |
|
"grad_norm": 11.679549217224121, |
|
"learning_rate": 2.6557550158394935e-05, |
|
"loss": 0.5598, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 4.083570750237417, |
|
"grad_norm": 17.88136100769043, |
|
"learning_rate": 2.6029567053854276e-05, |
|
"loss": 0.4933, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 4.09306742640076, |
|
"grad_norm": 4.025656700134277, |
|
"learning_rate": 2.5501583949313622e-05, |
|
"loss": 0.4895, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 4.102564102564102, |
|
"grad_norm": 18.150617599487305, |
|
"learning_rate": 2.497360084477297e-05, |
|
"loss": 0.5344, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 4.112060778727446, |
|
"grad_norm": 10.502995491027832, |
|
"learning_rate": 2.4445617740232313e-05, |
|
"loss": 0.3984, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 4.112060778727446, |
|
"eval_accuracy": 0.5631067961165048, |
|
"eval_loss": 1.398964285850525, |
|
"eval_runtime": 20.6856, |
|
"eval_samples_per_second": 9.959, |
|
"eval_steps_per_second": 1.257, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 5.009496676163343, |
|
"grad_norm": 7.37868070602417, |
|
"learning_rate": 2.391763463569166e-05, |
|
"loss": 0.3346, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 5.018993352326686, |
|
"grad_norm": 5.786819934844971, |
|
"learning_rate": 2.3389651531151003e-05, |
|
"loss": 0.2937, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 5.028490028490029, |
|
"grad_norm": 8.739676475524902, |
|
"learning_rate": 2.286166842661035e-05, |
|
"loss": 0.2478, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 5.037986704653371, |
|
"grad_norm": 3.41898512840271, |
|
"learning_rate": 2.2333685322069694e-05, |
|
"loss": 0.2988, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 5.047483380816714, |
|
"grad_norm": 13.979087829589844, |
|
"learning_rate": 2.180570221752904e-05, |
|
"loss": 0.2672, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 5.056980056980057, |
|
"grad_norm": 9.218252182006836, |
|
"learning_rate": 2.1277719112988384e-05, |
|
"loss": 0.2932, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 5.0664767331434, |
|
"grad_norm": 8.248359680175781, |
|
"learning_rate": 2.074973600844773e-05, |
|
"loss": 0.2845, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 5.075973409306743, |
|
"grad_norm": 12.172591209411621, |
|
"learning_rate": 2.0221752903907075e-05, |
|
"loss": 0.2125, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 5.085470085470085, |
|
"grad_norm": 4.901180267333984, |
|
"learning_rate": 1.9693769799366422e-05, |
|
"loss": 0.2387, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 5.094966761633429, |
|
"grad_norm": 3.2035112380981445, |
|
"learning_rate": 1.9165786694825765e-05, |
|
"loss": 0.1137, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 5.104463437796771, |
|
"grad_norm": 1.4330121278762817, |
|
"learning_rate": 1.863780359028511e-05, |
|
"loss": 0.1962, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 5.112060778727446, |
|
"eval_accuracy": 0.5825242718446602, |
|
"eval_loss": 1.4243208169937134, |
|
"eval_runtime": 20.9667, |
|
"eval_samples_per_second": 9.825, |
|
"eval_steps_per_second": 1.24, |
|
"step": 708 |
|
}, |
|
{ |
|
"epoch": 6.001899335232668, |
|
"grad_norm": 17.324275970458984, |
|
"learning_rate": 1.810982048574446e-05, |
|
"loss": 0.2794, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 6.011396011396012, |
|
"grad_norm": 13.693547248840332, |
|
"learning_rate": 1.7581837381203803e-05, |
|
"loss": 0.2361, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 6.020892687559354, |
|
"grad_norm": 1.044037938117981, |
|
"learning_rate": 1.7053854276663146e-05, |
|
"loss": 0.0796, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 6.030389363722697, |
|
"grad_norm": 1.7120157480239868, |
|
"learning_rate": 1.6525871172122493e-05, |
|
"loss": 0.1323, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 6.0398860398860394, |
|
"grad_norm": 16.39497184753418, |
|
"learning_rate": 1.5997888067581837e-05, |
|
"loss": 0.1033, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 6.049382716049383, |
|
"grad_norm": 0.9011927247047424, |
|
"learning_rate": 1.5469904963041184e-05, |
|
"loss": 0.082, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 6.0588793922127255, |
|
"grad_norm": 19.976755142211914, |
|
"learning_rate": 1.4941921858500529e-05, |
|
"loss": 0.1568, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 6.068376068376068, |
|
"grad_norm": 1.4492021799087524, |
|
"learning_rate": 1.4413938753959874e-05, |
|
"loss": 0.1059, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 6.077872744539412, |
|
"grad_norm": 10.073105812072754, |
|
"learning_rate": 1.388595564941922e-05, |
|
"loss": 0.0908, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 6.087369420702754, |
|
"grad_norm": 12.8700532913208, |
|
"learning_rate": 1.3357972544878563e-05, |
|
"loss": 0.1215, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 6.096866096866097, |
|
"grad_norm": 0.7424122095108032, |
|
"learning_rate": 1.2829989440337912e-05, |
|
"loss": 0.1036, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 6.106362773029439, |
|
"grad_norm": 4.486748218536377, |
|
"learning_rate": 1.2302006335797255e-05, |
|
"loss": 0.1952, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 6.112060778727446, |
|
"eval_accuracy": 0.6019417475728155, |
|
"eval_loss": 1.557113528251648, |
|
"eval_runtime": 56.6502, |
|
"eval_samples_per_second": 3.636, |
|
"eval_steps_per_second": 0.459, |
|
"step": 826 |
|
}, |
|
{ |
|
"epoch": 7.003798670465337, |
|
"grad_norm": 18.093158721923828, |
|
"learning_rate": 1.17740232312566e-05, |
|
"loss": 0.1356, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 7.01329534662868, |
|
"grad_norm": 0.3082960247993469, |
|
"learning_rate": 1.1246040126715946e-05, |
|
"loss": 0.0692, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 7.022792022792022, |
|
"grad_norm": 0.9313774108886719, |
|
"learning_rate": 1.0718057022175291e-05, |
|
"loss": 0.0197, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 7.032288698955366, |
|
"grad_norm": 0.9466642141342163, |
|
"learning_rate": 1.0190073917634636e-05, |
|
"loss": 0.0202, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 7.0417853751187085, |
|
"grad_norm": 7.768035888671875, |
|
"learning_rate": 9.662090813093982e-06, |
|
"loss": 0.0544, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 7.051282051282051, |
|
"grad_norm": 0.7909216284751892, |
|
"learning_rate": 9.134107708553327e-06, |
|
"loss": 0.0614, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 7.060778727445394, |
|
"grad_norm": 0.6131118535995483, |
|
"learning_rate": 8.606124604012672e-06, |
|
"loss": 0.0458, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 7.070275403608737, |
|
"grad_norm": 0.46935775876045227, |
|
"learning_rate": 8.078141499472017e-06, |
|
"loss": 0.0309, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 7.07977207977208, |
|
"grad_norm": 4.931636333465576, |
|
"learning_rate": 7.5501583949313625e-06, |
|
"loss": 0.0386, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 7.089268755935422, |
|
"grad_norm": 0.7869710326194763, |
|
"learning_rate": 7.022175290390708e-06, |
|
"loss": 0.0599, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 7.098765432098766, |
|
"grad_norm": 18.208322525024414, |
|
"learning_rate": 6.494192185850054e-06, |
|
"loss": 0.1256, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 7.1082621082621085, |
|
"grad_norm": 6.396451473236084, |
|
"learning_rate": 5.966209081309398e-06, |
|
"loss": 0.0319, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 7.112060778727446, |
|
"eval_accuracy": 0.587378640776699, |
|
"eval_loss": 1.5844324827194214, |
|
"eval_runtime": 38.1637, |
|
"eval_samples_per_second": 5.398, |
|
"eval_steps_per_second": 0.681, |
|
"step": 944 |
|
}, |
|
{ |
|
"epoch": 8.005698005698006, |
|
"grad_norm": 0.25447767972946167, |
|
"learning_rate": 5.438225976768744e-06, |
|
"loss": 0.0605, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 8.015194681861349, |
|
"grad_norm": 3.442044973373413, |
|
"learning_rate": 4.910242872228089e-06, |
|
"loss": 0.0193, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 8.024691358024691, |
|
"grad_norm": 0.15950489044189453, |
|
"learning_rate": 4.382259767687434e-06, |
|
"loss": 0.0443, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 8.034188034188034, |
|
"grad_norm": 0.21153709292411804, |
|
"learning_rate": 3.854276663146779e-06, |
|
"loss": 0.0152, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 8.043684710351377, |
|
"grad_norm": 0.30688220262527466, |
|
"learning_rate": 3.326293558606125e-06, |
|
"loss": 0.0275, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 8.05318138651472, |
|
"grad_norm": 0.7708584070205688, |
|
"learning_rate": 2.79831045406547e-06, |
|
"loss": 0.0195, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 8.062678062678062, |
|
"grad_norm": 1.1436554193496704, |
|
"learning_rate": 2.2703273495248154e-06, |
|
"loss": 0.0098, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 8.072174738841406, |
|
"grad_norm": 1.9318220615386963, |
|
"learning_rate": 1.7423442449841606e-06, |
|
"loss": 0.0597, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 8.081671415004749, |
|
"grad_norm": 3.5386385917663574, |
|
"learning_rate": 1.2143611404435059e-06, |
|
"loss": 0.0213, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 8.091168091168091, |
|
"grad_norm": 0.16293883323669434, |
|
"learning_rate": 6.863780359028511e-07, |
|
"loss": 0.0118, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 8.100664767331434, |
|
"grad_norm": 2.2753586769104004, |
|
"learning_rate": 1.5839493136219642e-07, |
|
"loss": 0.0203, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 8.103513770180436, |
|
"eval_accuracy": 0.6213592233009708, |
|
"eval_loss": 1.579399824142456, |
|
"eval_runtime": 23.3894, |
|
"eval_samples_per_second": 8.807, |
|
"eval_steps_per_second": 1.112, |
|
"step": 1053 |
|
}, |
|
{ |
|
"epoch": 8.103513770180436, |
|
"step": 1053, |
|
"total_flos": 1.0477471675667448e+19, |
|
"train_loss": 0.7528787313023864, |
|
"train_runtime": 2130.6056, |
|
"train_samples_per_second": 3.954, |
|
"train_steps_per_second": 0.494 |
|
}, |
|
{ |
|
"epoch": 8.103513770180436, |
|
"eval_accuracy": 0.551219512195122, |
|
"eval_loss": 1.7062230110168457, |
|
"eval_runtime": 32.2785, |
|
"eval_samples_per_second": 6.351, |
|
"eval_steps_per_second": 0.805, |
|
"step": 1053 |
|
}, |
|
{ |
|
"epoch": 8.103513770180436, |
|
"eval_accuracy": 0.551219512195122, |
|
"eval_loss": 1.7062228918075562, |
|
"eval_runtime": 25.2134, |
|
"eval_samples_per_second": 8.131, |
|
"eval_steps_per_second": 1.031, |
|
"step": 1053 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 1053, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 9223372036854775807, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 3, |
|
"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": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.0477471675667448e+19, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|