| { | |
| "best_metric": 0.18403036166096146, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucfcrime-full2/checkpoint-700", | |
| "epoch": 3.25, | |
| "eval_steps": 500, | |
| "global_step": 700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 14.482718467712402, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 2.6878, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 21.39861297607422, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 2.6074, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 17.860671997070312, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 2.7214, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 16.79393768310547, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 2.5776, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 14.525908470153809, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 2.689, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 12.049698829650879, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 2.6499, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 13.192450523376465, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.5365, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 10.041342735290527, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 2.4945, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 10.616167068481445, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 2.7132, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 11.666309356689453, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 2.5329, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 8.298579216003418, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 2.4331, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 9.002656936645508, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 2.3991, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 10.443252563476562, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 2.7184, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 8.290853500366211, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4219, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 8.40210247039795, | |
| "learning_rate": 4.960317460317461e-05, | |
| "loss": 2.3317, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 9.528456687927246, | |
| "learning_rate": 4.9206349206349204e-05, | |
| "loss": 2.7167, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 10.601034164428711, | |
| "learning_rate": 4.880952380952381e-05, | |
| "loss": 2.5201, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 10.306778907775879, | |
| "learning_rate": 4.841269841269841e-05, | |
| "loss": 2.4928, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 10.532262802124023, | |
| "learning_rate": 4.801587301587302e-05, | |
| "loss": 2.4065, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 10.122940063476562, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 2.7106, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 9.78131103515625, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 2.5572, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 10.649138450622559, | |
| "learning_rate": 4.682539682539683e-05, | |
| "loss": 2.5781, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 7.493427753448486, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 2.6114, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 7.953385829925537, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 2.6687, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 8.582961082458496, | |
| "learning_rate": 4.563492063492064e-05, | |
| "loss": 2.6787, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 8.697818756103516, | |
| "learning_rate": 4.523809523809524e-05, | |
| "loss": 2.5829, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 9.811901092529297, | |
| "learning_rate": 4.4841269841269846e-05, | |
| "loss": 2.6221, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 9.103715896606445, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 2.6806, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 8.211301803588867, | |
| "learning_rate": 4.404761904761905e-05, | |
| "loss": 2.6136, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 10.060530662536621, | |
| "learning_rate": 4.3650793650793655e-05, | |
| "loss": 2.6461, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 10.009857177734375, | |
| "learning_rate": 4.3253968253968256e-05, | |
| "loss": 2.571, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 11.69568157196045, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 2.758, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 8.031876564025879, | |
| "learning_rate": 4.2460317460317464e-05, | |
| "loss": 2.4975, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 8.202585220336914, | |
| "learning_rate": 4.2063492063492065e-05, | |
| "loss": 2.719, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 8.405922889709473, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 2.6564, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.17190058044351839, | |
| "eval_loss": 2.5464329719543457, | |
| "eval_runtime": 2790.7409, | |
| "eval_samples_per_second": 4.815, | |
| "eval_steps_per_second": 1.204, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 8.090776443481445, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 2.5153, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 7.668066024780273, | |
| "learning_rate": 4.0873015873015874e-05, | |
| "loss": 2.6691, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 7.451665878295898, | |
| "learning_rate": 4.047619047619048e-05, | |
| "loss": 2.455, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 6.811094284057617, | |
| "learning_rate": 4.007936507936508e-05, | |
| "loss": 2.7581, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 8.437348365783691, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 2.6151, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 9.83616828918457, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 2.7035, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 7.769816875457764, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 2.6254, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 11.614434242248535, | |
| "learning_rate": 3.84920634920635e-05, | |
| "loss": 2.5088, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 7.872964859008789, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 2.4313, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 9.000481605529785, | |
| "learning_rate": 3.76984126984127e-05, | |
| "loss": 2.6319, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 7.4448394775390625, | |
| "learning_rate": 3.730158730158731e-05, | |
| "loss": 2.6064, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 9.439050674438477, | |
| "learning_rate": 3.690476190476191e-05, | |
| "loss": 2.4276, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 7.45771598815918, | |
| "learning_rate": 3.650793650793651e-05, | |
| "loss": 2.6828, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 9.655268669128418, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 2.4295, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 7.304623603820801, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 2.3941, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 8.936468124389648, | |
| "learning_rate": 3.5317460317460324e-05, | |
| "loss": 2.5164, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 6.037725448608398, | |
| "learning_rate": 3.492063492063492e-05, | |
| "loss": 2.3629, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 9.806131362915039, | |
| "learning_rate": 3.4523809523809526e-05, | |
| "loss": 2.1973, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 7.448783874511719, | |
| "learning_rate": 3.412698412698413e-05, | |
| "loss": 2.6785, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 7.902461528778076, | |
| "learning_rate": 3.3730158730158734e-05, | |
| "loss": 2.5689, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 8.133126258850098, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.705, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 7.387323379516602, | |
| "learning_rate": 3.2936507936507936e-05, | |
| "loss": 2.4184, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 7.738976001739502, | |
| "learning_rate": 3.253968253968254e-05, | |
| "loss": 2.5947, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 7.019045352935791, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 2.3066, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 7.5370588302612305, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 2.4445, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 7.962660312652588, | |
| "learning_rate": 3.134920634920635e-05, | |
| "loss": 2.4807, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 8.314027786254883, | |
| "learning_rate": 3.095238095238095e-05, | |
| "loss": 2.5981, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 10.364777565002441, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 2.5207, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 8.472153663635254, | |
| "learning_rate": 3.0158730158730158e-05, | |
| "loss": 2.5291, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 8.788971900939941, | |
| "learning_rate": 2.9761904761904762e-05, | |
| "loss": 2.5238, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 8.0416898727417, | |
| "learning_rate": 2.9365079365079366e-05, | |
| "loss": 2.5041, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 8.097698211669922, | |
| "learning_rate": 2.8968253968253974e-05, | |
| "loss": 2.3977, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 8.505749702453613, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 2.2704, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 7.548125267028809, | |
| "learning_rate": 2.8174603174603175e-05, | |
| "loss": 1.993, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 8.76427936553955, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 2.3285, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.1255395148087513, | |
| "eval_loss": 2.866504192352295, | |
| "eval_runtime": 2724.8913, | |
| "eval_samples_per_second": 4.932, | |
| "eval_steps_per_second": 1.233, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 9.777434349060059, | |
| "learning_rate": 2.7380952380952383e-05, | |
| "loss": 2.3064, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 9.634062767028809, | |
| "learning_rate": 2.6984126984126984e-05, | |
| "loss": 2.6674, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 7.418952941894531, | |
| "learning_rate": 2.6587301587301588e-05, | |
| "loss": 2.3623, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 9.471118927001953, | |
| "learning_rate": 2.6190476190476192e-05, | |
| "loss": 2.5705, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 8.835360527038574, | |
| "learning_rate": 2.5793650793650796e-05, | |
| "loss": 2.6313, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 9.770784378051758, | |
| "learning_rate": 2.5396825396825397e-05, | |
| "loss": 2.3423, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 11.036508560180664, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.4206, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 10.88526725769043, | |
| "learning_rate": 2.4603174603174602e-05, | |
| "loss": 2.3682, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 9.554337501525879, | |
| "learning_rate": 2.4206349206349206e-05, | |
| "loss": 2.3234, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 10.911561012268066, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 2.7633, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 8.518780708312988, | |
| "learning_rate": 2.3412698412698414e-05, | |
| "loss": 2.209, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 10.131900787353516, | |
| "learning_rate": 2.3015873015873015e-05, | |
| "loss": 2.5754, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 7.803353309631348, | |
| "learning_rate": 2.261904761904762e-05, | |
| "loss": 2.2815, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 8.873805046081543, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 2.4105, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "grad_norm": 10.056378364562988, | |
| "learning_rate": 2.1825396825396827e-05, | |
| "loss": 2.4577, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "grad_norm": 9.494528770446777, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 2.5227, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 7.30636739730835, | |
| "learning_rate": 2.1031746031746032e-05, | |
| "loss": 2.1842, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 11.144043922424316, | |
| "learning_rate": 2.0634920634920636e-05, | |
| "loss": 2.3519, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 7.896585941314697, | |
| "learning_rate": 2.023809523809524e-05, | |
| "loss": 2.6106, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 9.881820678710938, | |
| "learning_rate": 1.984126984126984e-05, | |
| "loss": 2.5722, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 7.789708137512207, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 2.385, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 15.662388801574707, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 2.4097, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 11.497434616088867, | |
| "learning_rate": 1.8650793650793654e-05, | |
| "loss": 2.3551, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 8.680765151977539, | |
| "learning_rate": 1.8253968253968254e-05, | |
| "loss": 2.4937, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "grad_norm": 9.611832618713379, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 2.2117, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 8.637816429138184, | |
| "learning_rate": 1.746031746031746e-05, | |
| "loss": 2.2063, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 8.593392372131348, | |
| "learning_rate": 1.7063492063492063e-05, | |
| "loss": 2.5038, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 9.811333656311035, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.1935, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "grad_norm": 9.25893497467041, | |
| "learning_rate": 1.626984126984127e-05, | |
| "loss": 2.7302, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "grad_norm": 8.803714752197266, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 2.3372, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 10.265325546264648, | |
| "learning_rate": 1.5476190476190476e-05, | |
| "loss": 2.3112, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "grad_norm": 8.800261497497559, | |
| "learning_rate": 1.5079365079365079e-05, | |
| "loss": 2.1571, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 9.066210746765137, | |
| "learning_rate": 1.4682539682539683e-05, | |
| "loss": 2.4612, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 11.743760108947754, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 2.3783, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 7.336353302001953, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 2.3545, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.13528798928411967, | |
| "eval_loss": 2.775129556655884, | |
| "eval_runtime": 2705.5287, | |
| "eval_samples_per_second": 4.967, | |
| "eval_steps_per_second": 1.242, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "grad_norm": 11.444567680358887, | |
| "learning_rate": 1.3492063492063492e-05, | |
| "loss": 2.7387, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "grad_norm": 9.247318267822266, | |
| "learning_rate": 1.3095238095238096e-05, | |
| "loss": 2.7047, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "grad_norm": 9.126996040344238, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 2.3381, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "grad_norm": 8.4282865524292, | |
| "learning_rate": 1.2301587301587301e-05, | |
| "loss": 2.292, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "grad_norm": 9.275003433227539, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 2.3291, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "grad_norm": 9.664990425109863, | |
| "learning_rate": 1.1507936507936508e-05, | |
| "loss": 2.3276, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "grad_norm": 9.327167510986328, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 2.1339, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "grad_norm": 8.076509475708008, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 2.1437, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "grad_norm": 10.702942848205566, | |
| "learning_rate": 1.0317460317460318e-05, | |
| "loss": 2.4547, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "grad_norm": 13.38920783996582, | |
| "learning_rate": 9.92063492063492e-06, | |
| "loss": 2.5248, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "grad_norm": 7.934788227081299, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 2.4829, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "grad_norm": 8.314118385314941, | |
| "learning_rate": 9.126984126984127e-06, | |
| "loss": 2.1392, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "grad_norm": 11.382800102233887, | |
| "learning_rate": 8.73015873015873e-06, | |
| "loss": 2.2964, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "grad_norm": 7.882699012756348, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 2.1905, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "grad_norm": 9.530142784118652, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 2.3815, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "grad_norm": 8.318964958190918, | |
| "learning_rate": 7.5396825396825394e-06, | |
| "loss": 2.4007, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "grad_norm": 10.5969820022583, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 2.3558, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "grad_norm": 9.391063690185547, | |
| "learning_rate": 6.746031746031746e-06, | |
| "loss": 2.3825, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "grad_norm": 9.316353797912598, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 2.4972, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "grad_norm": 9.888083457946777, | |
| "learning_rate": 5.9523809523809525e-06, | |
| "loss": 2.2321, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "grad_norm": 8.392168045043945, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 2.196, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "grad_norm": 9.588519096374512, | |
| "learning_rate": 5.158730158730159e-06, | |
| "loss": 2.2595, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "grad_norm": 8.25489616394043, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 2.0537, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "grad_norm": 10.085835456848145, | |
| "learning_rate": 4.365079365079365e-06, | |
| "loss": 2.4893, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "grad_norm": 10.919437408447266, | |
| "learning_rate": 3.968253968253968e-06, | |
| "loss": 2.4032, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "grad_norm": 8.23149299621582, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 2.1834, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "grad_norm": 11.596048355102539, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 2.3302, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 11.665302276611328, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 2.3287, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "grad_norm": 9.233076095581055, | |
| "learning_rate": 2.3809523809523808e-06, | |
| "loss": 2.1008, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "grad_norm": 11.429000854492188, | |
| "learning_rate": 1.984126984126984e-06, | |
| "loss": 2.2577, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "grad_norm": 8.783037185668945, | |
| "learning_rate": 1.5873015873015873e-06, | |
| "loss": 2.0016, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "grad_norm": 8.462553977966309, | |
| "learning_rate": 1.1904761904761904e-06, | |
| "loss": 2.3779, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "grad_norm": 9.461167335510254, | |
| "learning_rate": 7.936507936507937e-07, | |
| "loss": 1.9491, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "grad_norm": 12.051897048950195, | |
| "learning_rate": 3.9682539682539683e-07, | |
| "loss": 2.0514, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "grad_norm": 11.628158569335938, | |
| "learning_rate": 0.0, | |
| "loss": 1.9726, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.18403036166096146, | |
| "eval_loss": 2.5616397857666016, | |
| "eval_runtime": 2737.1764, | |
| "eval_samples_per_second": 4.909, | |
| "eval_steps_per_second": 1.228, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "step": 700, | |
| "total_flos": 3.4893542331777024e+18, | |
| "train_loss": 2.449405036653791, | |
| "train_runtime": 12421.7881, | |
| "train_samples_per_second": 0.225, | |
| "train_steps_per_second": 0.056 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.11733870967741936, | |
| "eval_loss": 2.6881906986236572, | |
| "eval_runtime": 975.7268, | |
| "eval_samples_per_second": 5.083, | |
| "eval_steps_per_second": 1.271, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.11733870967741936, | |
| "eval_loss": 2.6881909370422363, | |
| "eval_runtime": 956.0688, | |
| "eval_samples_per_second": 5.188, | |
| "eval_steps_per_second": 1.297, | |
| "step": 700 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 700, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 3.4893542331777024e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |