| { | |
| "best_metric": 0.7238805970149254, | |
| "best_model_checkpoint": "videomae-base-finetuned-good-gesturePhaseV3/checkpoint-690", | |
| "epoch": 9.08695652173913, | |
| "eval_steps": 500, | |
| "global_step": 690, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014492753623188406, | |
| "grad_norm": 8.630314826965332, | |
| "learning_rate": 1.4492753623188408e-06, | |
| "loss": 1.51, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "grad_norm": 7.7164106369018555, | |
| "learning_rate": 2.8985507246376816e-06, | |
| "loss": 1.4827, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.043478260869565216, | |
| "grad_norm": 8.436184883117676, | |
| "learning_rate": 4.347826086956522e-06, | |
| "loss": 1.3066, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.057971014492753624, | |
| "grad_norm": 5.019124507904053, | |
| "learning_rate": 5.797101449275363e-06, | |
| "loss": 1.3189, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07246376811594203, | |
| "grad_norm": 4.321361541748047, | |
| "learning_rate": 7.246376811594203e-06, | |
| "loss": 1.2353, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 5.294806480407715, | |
| "learning_rate": 8.695652173913044e-06, | |
| "loss": 1.0792, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10144927536231885, | |
| "grad_norm": 6.665987491607666, | |
| "learning_rate": 9.98389694041868e-06, | |
| "loss": 1.0859, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.10144927536231885, | |
| "eval_accuracy": 0.5597014925373134, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 1.0, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 0.0, | |
| "eval_loss": 1.2821296453475952, | |
| "eval_runtime": 12.6272, | |
| "eval_samples_per_second": 10.612, | |
| "eval_steps_per_second": 1.346, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0144927536231885, | |
| "grad_norm": 7.540314197540283, | |
| "learning_rate": 9.822866344605476e-06, | |
| "loss": 1.1573, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0289855072463767, | |
| "grad_norm": 6.748633861541748, | |
| "learning_rate": 9.66183574879227e-06, | |
| "loss": 1.1544, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0434782608695652, | |
| "grad_norm": 5.429695129394531, | |
| "learning_rate": 9.500805152979067e-06, | |
| "loss": 1.1273, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0579710144927537, | |
| "grad_norm": 4.697651386260986, | |
| "learning_rate": 9.339774557165862e-06, | |
| "loss": 1.0504, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0724637681159421, | |
| "grad_norm": 5.215806484222412, | |
| "learning_rate": 9.178743961352658e-06, | |
| "loss": 1.3456, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0869565217391304, | |
| "grad_norm": 4.073849201202393, | |
| "learning_rate": 9.017713365539453e-06, | |
| "loss": 1.0036, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.1014492753623188, | |
| "grad_norm": 6.67258882522583, | |
| "learning_rate": 8.85668276972625e-06, | |
| "loss": 1.1816, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.1014492753623188, | |
| "eval_accuracy": 0.5597014925373134, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 1.0, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 0.0, | |
| "eval_loss": 1.2568527460098267, | |
| "eval_runtime": 10.4527, | |
| "eval_samples_per_second": 12.82, | |
| "eval_steps_per_second": 1.626, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0144927536231885, | |
| "grad_norm": 6.217495918273926, | |
| "learning_rate": 8.695652173913044e-06, | |
| "loss": 0.8822, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.028985507246377, | |
| "grad_norm": 7.204903602600098, | |
| "learning_rate": 8.53462157809984e-06, | |
| "loss": 1.3084, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.0434782608695654, | |
| "grad_norm": 6.101042747497559, | |
| "learning_rate": 8.373590982286636e-06, | |
| "loss": 1.2082, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.0579710144927534, | |
| "grad_norm": 7.498929977416992, | |
| "learning_rate": 8.212560386473431e-06, | |
| "loss": 1.0949, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.072463768115942, | |
| "grad_norm": 5.478421688079834, | |
| "learning_rate": 8.051529790660226e-06, | |
| "loss": 1.1815, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.0869565217391304, | |
| "grad_norm": 5.867790222167969, | |
| "learning_rate": 7.890499194847021e-06, | |
| "loss": 1.1617, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.101449275362319, | |
| "grad_norm": 6.117257595062256, | |
| "learning_rate": 7.729468599033817e-06, | |
| "loss": 0.9776, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.101449275362319, | |
| "eval_accuracy": 0.5597014925373134, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 1.0, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 0.0, | |
| "eval_loss": 1.183463454246521, | |
| "eval_runtime": 14.5304, | |
| "eval_samples_per_second": 9.222, | |
| "eval_steps_per_second": 1.17, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0144927536231885, | |
| "grad_norm": 4.579581260681152, | |
| "learning_rate": 7.568438003220613e-06, | |
| "loss": 1.0491, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.028985507246377, | |
| "grad_norm": 7.75211238861084, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 1.1185, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.0434782608695654, | |
| "grad_norm": 5.795550346374512, | |
| "learning_rate": 7.246376811594203e-06, | |
| "loss": 0.8838, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.0579710144927534, | |
| "grad_norm": 19.677343368530273, | |
| "learning_rate": 7.085346215780999e-06, | |
| "loss": 1.1633, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.072463768115942, | |
| "grad_norm": 7.7631025314331055, | |
| "learning_rate": 6.924315619967794e-06, | |
| "loss": 1.1222, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.0869565217391304, | |
| "grad_norm": 10.160636901855469, | |
| "learning_rate": 6.76328502415459e-06, | |
| "loss": 1.1524, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.101449275362319, | |
| "grad_norm": 8.012062072753906, | |
| "learning_rate": 6.602254428341386e-06, | |
| "loss": 0.9867, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.101449275362319, | |
| "eval_accuracy": 0.6119402985074627, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 0.96, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 0.38461538461538464, | |
| "eval_loss": 1.0721046924591064, | |
| "eval_runtime": 10.6287, | |
| "eval_samples_per_second": 12.607, | |
| "eval_steps_per_second": 1.599, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.0144927536231885, | |
| "grad_norm": 7.033966064453125, | |
| "learning_rate": 6.44122383252818e-06, | |
| "loss": 1.1485, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.028985507246377, | |
| "grad_norm": 7.627530097961426, | |
| "learning_rate": 6.280193236714976e-06, | |
| "loss": 0.8141, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.043478260869565, | |
| "grad_norm": 27.910728454589844, | |
| "learning_rate": 6.119162640901772e-06, | |
| "loss": 0.8858, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.057971014492754, | |
| "grad_norm": 10.358675956726074, | |
| "learning_rate": 5.958132045088567e-06, | |
| "loss": 1.0275, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.072463768115942, | |
| "grad_norm": 16.66415023803711, | |
| "learning_rate": 5.797101449275363e-06, | |
| "loss": 1.0072, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.086956521739131, | |
| "grad_norm": 10.6364107131958, | |
| "learning_rate": 5.6360708534621574e-06, | |
| "loss": 0.9873, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.101449275362318, | |
| "grad_norm": 37.127933502197266, | |
| "learning_rate": 5.475040257648953e-06, | |
| "loss": 1.0732, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.101449275362318, | |
| "eval_accuracy": 0.6044776119402985, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 0.7333333333333333, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 1.0, | |
| "eval_loss": 1.10855233669281, | |
| "eval_runtime": 10.2262, | |
| "eval_samples_per_second": 13.104, | |
| "eval_steps_per_second": 1.662, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.0144927536231885, | |
| "grad_norm": 5.9557390213012695, | |
| "learning_rate": 5.314009661835749e-06, | |
| "loss": 1.0058, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.028985507246377, | |
| "grad_norm": 4.721350193023682, | |
| "learning_rate": 5.152979066022544e-06, | |
| "loss": 0.9693, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.043478260869565, | |
| "grad_norm": 10.849539756774902, | |
| "learning_rate": 4.99194847020934e-06, | |
| "loss": 1.0111, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.057971014492754, | |
| "grad_norm": 8.35351276397705, | |
| "learning_rate": 4.830917874396135e-06, | |
| "loss": 0.953, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.072463768115942, | |
| "grad_norm": 9.031652450561523, | |
| "learning_rate": 4.669887278582931e-06, | |
| "loss": 0.957, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.086956521739131, | |
| "grad_norm": 28.449277877807617, | |
| "learning_rate": 4.508856682769726e-06, | |
| "loss": 0.8448, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.101449275362318, | |
| "grad_norm": 8.963016510009766, | |
| "learning_rate": 4.347826086956522e-06, | |
| "loss": 0.9688, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.101449275362318, | |
| "eval_accuracy": 0.6865671641791045, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 0.9333333333333333, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 0.8461538461538461, | |
| "eval_loss": 0.9288297295570374, | |
| "eval_runtime": 10.1881, | |
| "eval_samples_per_second": 13.153, | |
| "eval_steps_per_second": 1.669, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.0144927536231885, | |
| "grad_norm": 6.095980167388916, | |
| "learning_rate": 4.186795491143318e-06, | |
| "loss": 0.7678, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.028985507246377, | |
| "grad_norm": 6.365720272064209, | |
| "learning_rate": 4.025764895330113e-06, | |
| "loss": 0.7864, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.043478260869565, | |
| "grad_norm": 9.036483764648438, | |
| "learning_rate": 3.864734299516908e-06, | |
| "loss": 0.9962, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.057971014492754, | |
| "grad_norm": 7.131446361541748, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.8646, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.072463768115942, | |
| "grad_norm": 20.672754287719727, | |
| "learning_rate": 3.5426731078904997e-06, | |
| "loss": 1.0675, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.086956521739131, | |
| "grad_norm": 7.654391765594482, | |
| "learning_rate": 3.381642512077295e-06, | |
| "loss": 0.8623, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.101449275362318, | |
| "grad_norm": 5.464959144592285, | |
| "learning_rate": 3.22061191626409e-06, | |
| "loss": 0.7733, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.101449275362318, | |
| "eval_accuracy": 0.6567164179104478, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 0.8266666666666667, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 1.0, | |
| "eval_loss": 0.9749326705932617, | |
| "eval_runtime": 10.4474, | |
| "eval_samples_per_second": 12.826, | |
| "eval_steps_per_second": 1.627, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 7.0144927536231885, | |
| "grad_norm": 7.121547698974609, | |
| "learning_rate": 3.059581320450886e-06, | |
| "loss": 0.78, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.028985507246377, | |
| "grad_norm": 6.011748313903809, | |
| "learning_rate": 2.8985507246376816e-06, | |
| "loss": 1.0792, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.043478260869565, | |
| "grad_norm": 7.9175567626953125, | |
| "learning_rate": 2.7375201288244767e-06, | |
| "loss": 0.8386, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.057971014492754, | |
| "grad_norm": 7.427879333496094, | |
| "learning_rate": 2.576489533011272e-06, | |
| "loss": 0.6215, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.072463768115942, | |
| "grad_norm": 4.626201629638672, | |
| "learning_rate": 2.4154589371980677e-06, | |
| "loss": 0.8965, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.086956521739131, | |
| "grad_norm": 14.431778907775879, | |
| "learning_rate": 2.254428341384863e-06, | |
| "loss": 0.9818, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.101449275362318, | |
| "grad_norm": 32.45638656616211, | |
| "learning_rate": 2.093397745571659e-06, | |
| "loss": 0.8798, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.101449275362318, | |
| "eval_accuracy": 0.6865671641791045, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 0.92, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 0.8846153846153846, | |
| "eval_loss": 0.8742198944091797, | |
| "eval_runtime": 10.8069, | |
| "eval_samples_per_second": 12.399, | |
| "eval_steps_per_second": 1.573, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.014492753623188, | |
| "grad_norm": 7.238797664642334, | |
| "learning_rate": 1.932367149758454e-06, | |
| "loss": 0.9141, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.028985507246377, | |
| "grad_norm": 5.496193885803223, | |
| "learning_rate": 1.7713365539452498e-06, | |
| "loss": 0.7796, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.043478260869565, | |
| "grad_norm": 7.790290355682373, | |
| "learning_rate": 1.610305958132045e-06, | |
| "loss": 0.9178, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.057971014492754, | |
| "grad_norm": 10.017251014709473, | |
| "learning_rate": 1.4492753623188408e-06, | |
| "loss": 0.8282, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.072463768115941, | |
| "grad_norm": 11.363780975341797, | |
| "learning_rate": 1.288244766505636e-06, | |
| "loss": 0.8729, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.08695652173913, | |
| "grad_norm": 5.4790778160095215, | |
| "learning_rate": 1.1272141706924316e-06, | |
| "loss": 0.6978, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.101449275362318, | |
| "grad_norm": 9.819117546081543, | |
| "learning_rate": 9.66183574879227e-07, | |
| "loss": 0.7771, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.101449275362318, | |
| "eval_accuracy": 0.7014925373134329, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 0.92, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 0.9615384615384616, | |
| "eval_loss": 0.845240592956543, | |
| "eval_runtime": 10.5946, | |
| "eval_samples_per_second": 12.648, | |
| "eval_steps_per_second": 1.605, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 9.014492753623188, | |
| "grad_norm": 17.136520385742188, | |
| "learning_rate": 8.051529790660226e-07, | |
| "loss": 0.8034, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 9.028985507246377, | |
| "grad_norm": 8.827512741088867, | |
| "learning_rate": 6.44122383252818e-07, | |
| "loss": 0.6385, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 9.043478260869565, | |
| "grad_norm": 9.634197235107422, | |
| "learning_rate": 4.830917874396135e-07, | |
| "loss": 0.8629, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.057971014492754, | |
| "grad_norm": 10.844426155090332, | |
| "learning_rate": 3.22061191626409e-07, | |
| "loss": 0.9232, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.072463768115941, | |
| "grad_norm": 11.182330131530762, | |
| "learning_rate": 1.610305958132045e-07, | |
| "loss": 0.6174, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.08695652173913, | |
| "grad_norm": 9.969412803649902, | |
| "learning_rate": 0.0, | |
| "loss": 1.0448, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.08695652173913, | |
| "eval_accuracy": 0.7238805970149254, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 0.96, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 0.9615384615384616, | |
| "eval_loss": 0.835747241973877, | |
| "eval_runtime": 11.1151, | |
| "eval_samples_per_second": 12.056, | |
| "eval_steps_per_second": 1.529, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.08695652173913, | |
| "step": 690, | |
| "total_flos": 6.856030795503698e+18, | |
| "train_loss": 0.9979172112285227, | |
| "train_runtime": 1188.5395, | |
| "train_samples_per_second": 4.644, | |
| "train_steps_per_second": 0.581 | |
| }, | |
| { | |
| "epoch": 9.08695652173913, | |
| "eval_accuracy": 0.6938775510204082, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 0.8961038961038961, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 0.9428571428571428, | |
| "eval_loss": 0.929679811000824, | |
| "eval_runtime": 14.0873, | |
| "eval_samples_per_second": 10.435, | |
| "eval_steps_per_second": 1.349, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.08695652173913, | |
| "eval_accuracy": 0.6938775510204082, | |
| "eval_accuracy_hold": 0.0, | |
| "eval_accuracy_preparation": 0.8961038961038961, | |
| "eval_accuracy_recovery": 0.0, | |
| "eval_accuracy_stroke": 0.0, | |
| "eval_accuracy_unknown": 0.9428571428571428, | |
| "eval_loss": 0.929679811000824, | |
| "eval_runtime": 15.1756, | |
| "eval_samples_per_second": 9.687, | |
| "eval_steps_per_second": 1.252, | |
| "step": 690 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 690, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.856030795503698e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |