| { | |
| "best_metric": 0.8908902406692505, | |
| "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily_scale4_frozenVision/lora/sft/checkpoint-300", | |
| "epoch": 0.20602626834921453, | |
| "eval_steps": 50, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025753283543651817, | |
| "grad_norm": 21.336819681898895, | |
| "learning_rate": 2.9411764705882355e-06, | |
| "loss": 3.0444, | |
| "num_input_tokens_seen": 58496, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0051506567087303634, | |
| "grad_norm": 20.576623155848594, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 2.9824, | |
| "num_input_tokens_seen": 116960, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007725985063095545, | |
| "grad_norm": 22.989873871108518, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 2.8371, | |
| "num_input_tokens_seen": 175448, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010301313417460727, | |
| "grad_norm": 19.533434089690918, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 2.5198, | |
| "num_input_tokens_seen": 233944, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012876641771825908, | |
| "grad_norm": 12.509494197145006, | |
| "learning_rate": 1.4705882352941177e-05, | |
| "loss": 1.772, | |
| "num_input_tokens_seen": 292416, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01545197012619109, | |
| "grad_norm": 3.6901887027066667, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 1.2263, | |
| "num_input_tokens_seen": 350904, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018027298480556272, | |
| "grad_norm": 2.3996076770849744, | |
| "learning_rate": 2.058823529411765e-05, | |
| "loss": 1.0102, | |
| "num_input_tokens_seen": 409384, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.020602626834921454, | |
| "grad_norm": 0.9253415848864577, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 0.9378, | |
| "num_input_tokens_seen": 467864, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023177955189286635, | |
| "grad_norm": 1.1966244115097795, | |
| "learning_rate": 2.647058823529412e-05, | |
| "loss": 0.9265, | |
| "num_input_tokens_seen": 526384, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.025753283543651816, | |
| "grad_norm": 1.853648349752417, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 0.9157, | |
| "num_input_tokens_seen": 584856, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.025753283543651816, | |
| "eval_loss": 0.9191630482673645, | |
| "eval_runtime": 36.6123, | |
| "eval_samples_per_second": 1.639, | |
| "eval_steps_per_second": 0.41, | |
| "num_input_tokens_seen": 584856, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028328611898016998, | |
| "grad_norm": 0.8294990584587586, | |
| "learning_rate": 3.235294117647059e-05, | |
| "loss": 0.9009, | |
| "num_input_tokens_seen": 643344, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03090394025238218, | |
| "grad_norm": 0.8278765532866457, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 0.9063, | |
| "num_input_tokens_seen": 701808, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03347926860674736, | |
| "grad_norm": 0.7285901101792476, | |
| "learning_rate": 3.8235294117647055e-05, | |
| "loss": 0.9031, | |
| "num_input_tokens_seen": 760304, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.036054596961112545, | |
| "grad_norm": 0.5341783688819233, | |
| "learning_rate": 4.11764705882353e-05, | |
| "loss": 0.8991, | |
| "num_input_tokens_seen": 818760, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03862992531547772, | |
| "grad_norm": 0.46059313680988906, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 0.9055, | |
| "num_input_tokens_seen": 877256, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04120525366984291, | |
| "grad_norm": 0.8194379237293679, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 0.9092, | |
| "num_input_tokens_seen": 935752, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.043780582024208085, | |
| "grad_norm": 0.6745093544830881, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9069, | |
| "num_input_tokens_seen": 994216, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.04635591037857327, | |
| "grad_norm": 0.2894672897884604, | |
| "learning_rate": 5.294117647058824e-05, | |
| "loss": 0.8924, | |
| "num_input_tokens_seen": 1052704, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04893123873293845, | |
| "grad_norm": 0.5108489024576455, | |
| "learning_rate": 5.588235294117647e-05, | |
| "loss": 0.9059, | |
| "num_input_tokens_seen": 1111176, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.05150656708730363, | |
| "grad_norm": 0.40317180386305224, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.901, | |
| "num_input_tokens_seen": 1169664, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05150656708730363, | |
| "eval_loss": 0.9077914953231812, | |
| "eval_runtime": 16.8879, | |
| "eval_samples_per_second": 3.553, | |
| "eval_steps_per_second": 0.888, | |
| "num_input_tokens_seen": 1169664, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05408189544166881, | |
| "grad_norm": 0.412918917979438, | |
| "learning_rate": 6.176470588235295e-05, | |
| "loss": 0.9159, | |
| "num_input_tokens_seen": 1228112, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.056657223796033995, | |
| "grad_norm": 0.34797408069968117, | |
| "learning_rate": 6.470588235294118e-05, | |
| "loss": 0.91, | |
| "num_input_tokens_seen": 1286608, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05923255215039917, | |
| "grad_norm": 0.27558494796967653, | |
| "learning_rate": 6.764705882352942e-05, | |
| "loss": 0.9047, | |
| "num_input_tokens_seen": 1345072, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.06180788050476436, | |
| "grad_norm": 0.5422134023513459, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.9022, | |
| "num_input_tokens_seen": 1403544, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06438320885912954, | |
| "grad_norm": 0.4452796218739235, | |
| "learning_rate": 7.352941176470589e-05, | |
| "loss": 0.9081, | |
| "num_input_tokens_seen": 1462024, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06695853721349472, | |
| "grad_norm": 0.5632558160730559, | |
| "learning_rate": 7.647058823529411e-05, | |
| "loss": 0.8939, | |
| "num_input_tokens_seen": 1520528, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0695338655678599, | |
| "grad_norm": 0.3383115884436812, | |
| "learning_rate": 7.941176470588235e-05, | |
| "loss": 0.9029, | |
| "num_input_tokens_seen": 1579024, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.07210919392222509, | |
| "grad_norm": 0.3506611095466577, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 0.9014, | |
| "num_input_tokens_seen": 1637504, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07468452227659027, | |
| "grad_norm": 0.6328034405712752, | |
| "learning_rate": 8.529411764705883e-05, | |
| "loss": 0.9053, | |
| "num_input_tokens_seen": 1696024, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.07725985063095545, | |
| "grad_norm": 0.3511657661506363, | |
| "learning_rate": 8.823529411764706e-05, | |
| "loss": 0.9032, | |
| "num_input_tokens_seen": 1754512, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07725985063095545, | |
| "eval_loss": 0.8962129950523376, | |
| "eval_runtime": 17.0673, | |
| "eval_samples_per_second": 3.515, | |
| "eval_steps_per_second": 0.879, | |
| "num_input_tokens_seen": 1754512, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07983517898532062, | |
| "grad_norm": 0.4047681172482029, | |
| "learning_rate": 9.11764705882353e-05, | |
| "loss": 0.8985, | |
| "num_input_tokens_seen": 1812976, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.08241050733968582, | |
| "grad_norm": 0.37729033726569733, | |
| "learning_rate": 9.411764705882353e-05, | |
| "loss": 0.8949, | |
| "num_input_tokens_seen": 1871464, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.08498583569405099, | |
| "grad_norm": 0.4655744785034158, | |
| "learning_rate": 9.705882352941177e-05, | |
| "loss": 0.9069, | |
| "num_input_tokens_seen": 1929928, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.08756116404841617, | |
| "grad_norm": 0.30643056878817176, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9049, | |
| "num_input_tokens_seen": 1988432, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09013649240278135, | |
| "grad_norm": 0.39944696269496754, | |
| "learning_rate": 9.999940874631277e-05, | |
| "loss": 0.9026, | |
| "num_input_tokens_seen": 2046920, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.09271182075714654, | |
| "grad_norm": 0.31301259106593154, | |
| "learning_rate": 9.999763499923432e-05, | |
| "loss": 0.8984, | |
| "num_input_tokens_seen": 2105392, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.09528714911151172, | |
| "grad_norm": 0.4309753054454554, | |
| "learning_rate": 9.999467880071402e-05, | |
| "loss": 0.9057, | |
| "num_input_tokens_seen": 2163872, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.0978624774658769, | |
| "grad_norm": 0.262930252305763, | |
| "learning_rate": 9.999054022066641e-05, | |
| "loss": 0.9078, | |
| "num_input_tokens_seen": 2222352, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.10043780582024209, | |
| "grad_norm": 0.22073598270887426, | |
| "learning_rate": 9.998521935696953e-05, | |
| "loss": 0.9028, | |
| "num_input_tokens_seen": 2280800, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.10301313417460727, | |
| "grad_norm": 0.23764668792524696, | |
| "learning_rate": 9.997871633546257e-05, | |
| "loss": 0.9053, | |
| "num_input_tokens_seen": 2339304, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.10301313417460727, | |
| "eval_loss": 0.8982028961181641, | |
| "eval_runtime": 16.9118, | |
| "eval_samples_per_second": 3.548, | |
| "eval_steps_per_second": 0.887, | |
| "num_input_tokens_seen": 2339304, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.10558846252897244, | |
| "grad_norm": 0.6222576114383499, | |
| "learning_rate": 9.997103130994296e-05, | |
| "loss": 0.9003, | |
| "num_input_tokens_seen": 2397808, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.10816379088333762, | |
| "grad_norm": 0.2983149992592585, | |
| "learning_rate": 9.996216446216267e-05, | |
| "loss": 0.8969, | |
| "num_input_tokens_seen": 2456288, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.11073911923770281, | |
| "grad_norm": 0.3505370510576513, | |
| "learning_rate": 9.995211600182397e-05, | |
| "loss": 0.9114, | |
| "num_input_tokens_seen": 2514784, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.11331444759206799, | |
| "grad_norm": 0.3683806652106065, | |
| "learning_rate": 9.994088616657444e-05, | |
| "loss": 0.899, | |
| "num_input_tokens_seen": 2573240, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.11588977594643317, | |
| "grad_norm": 0.21111769827155855, | |
| "learning_rate": 9.992847522200133e-05, | |
| "loss": 0.898, | |
| "num_input_tokens_seen": 2631672, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.11846510430079835, | |
| "grad_norm": 0.3426987181783304, | |
| "learning_rate": 9.99148834616253e-05, | |
| "loss": 0.9006, | |
| "num_input_tokens_seen": 2690112, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.12104043265516354, | |
| "grad_norm": 0.236983209071443, | |
| "learning_rate": 9.990011120689351e-05, | |
| "loss": 0.8973, | |
| "num_input_tokens_seen": 2748608, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.12361576100952872, | |
| "grad_norm": 0.4575208248826409, | |
| "learning_rate": 9.988415880717194e-05, | |
| "loss": 0.8885, | |
| "num_input_tokens_seen": 2807080, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1261910893638939, | |
| "grad_norm": 0.5470317919414993, | |
| "learning_rate": 9.986702663973722e-05, | |
| "loss": 0.9066, | |
| "num_input_tokens_seen": 2865520, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.12876641771825909, | |
| "grad_norm": 0.4992479706331095, | |
| "learning_rate": 9.98487151097676e-05, | |
| "loss": 0.9098, | |
| "num_input_tokens_seen": 2924016, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.12876641771825909, | |
| "eval_loss": 0.8956434726715088, | |
| "eval_runtime": 17.4804, | |
| "eval_samples_per_second": 3.432, | |
| "eval_steps_per_second": 0.858, | |
| "num_input_tokens_seen": 2924016, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.13134174607262425, | |
| "grad_norm": 0.3762164361984238, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.8987, | |
| "num_input_tokens_seen": 2982520, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.13391707442698944, | |
| "grad_norm": 0.6447043002410199, | |
| "learning_rate": 9.980855572238714e-05, | |
| "loss": 0.9036, | |
| "num_input_tokens_seen": 3041008, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.13649240278135463, | |
| "grad_norm": 0.5308092769971742, | |
| "learning_rate": 9.978670881475172e-05, | |
| "loss": 0.8961, | |
| "num_input_tokens_seen": 3099464, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.1390677311357198, | |
| "grad_norm": 0.508333330469703, | |
| "learning_rate": 9.976368444410985e-05, | |
| "loss": 0.9012, | |
| "num_input_tokens_seen": 3157944, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.141643059490085, | |
| "grad_norm": 0.6801788563719119, | |
| "learning_rate": 9.973948315499126e-05, | |
| "loss": 0.8985, | |
| "num_input_tokens_seen": 3216448, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.14421838784445018, | |
| "grad_norm": 0.6933074703933572, | |
| "learning_rate": 9.971410551976002e-05, | |
| "loss": 0.9114, | |
| "num_input_tokens_seen": 3274928, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.14679371619881534, | |
| "grad_norm": 0.21208820897494882, | |
| "learning_rate": 9.968755213860094e-05, | |
| "loss": 0.8886, | |
| "num_input_tokens_seen": 3333408, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.14936904455318054, | |
| "grad_norm": 0.5791422669000065, | |
| "learning_rate": 9.96598236395054e-05, | |
| "loss": 0.8929, | |
| "num_input_tokens_seen": 3391896, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.1519443729075457, | |
| "grad_norm": 0.3460368893191152, | |
| "learning_rate": 9.96309206782565e-05, | |
| "loss": 0.9091, | |
| "num_input_tokens_seen": 3450392, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.1545197012619109, | |
| "grad_norm": 0.22425222135997747, | |
| "learning_rate": 9.960084393841355e-05, | |
| "loss": 0.8893, | |
| "num_input_tokens_seen": 3508888, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1545197012619109, | |
| "eval_loss": 0.8908902406692505, | |
| "eval_runtime": 16.9521, | |
| "eval_samples_per_second": 3.539, | |
| "eval_steps_per_second": 0.885, | |
| "num_input_tokens_seen": 3508888, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15709502961627608, | |
| "grad_norm": 0.23111596622064604, | |
| "learning_rate": 9.956959413129585e-05, | |
| "loss": 0.9056, | |
| "num_input_tokens_seen": 3567368, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.15967035797064125, | |
| "grad_norm": 0.3918406894807393, | |
| "learning_rate": 9.953717199596598e-05, | |
| "loss": 0.8982, | |
| "num_input_tokens_seen": 3625848, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.16224568632500644, | |
| "grad_norm": 0.22081666860189372, | |
| "learning_rate": 9.95035782992122e-05, | |
| "loss": 0.8968, | |
| "num_input_tokens_seen": 3684336, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.16482101467937163, | |
| "grad_norm": 0.18024383676398176, | |
| "learning_rate": 9.94688138355304e-05, | |
| "loss": 0.8975, | |
| "num_input_tokens_seen": 3742800, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.1673963430337368, | |
| "grad_norm": 0.3866897344302321, | |
| "learning_rate": 9.943287942710527e-05, | |
| "loss": 0.9061, | |
| "num_input_tokens_seen": 3801280, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.16997167138810199, | |
| "grad_norm": 0.4804151381712559, | |
| "learning_rate": 9.939577592379088e-05, | |
| "loss": 0.8948, | |
| "num_input_tokens_seen": 3859792, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.17254699974246718, | |
| "grad_norm": 0.35878231707669056, | |
| "learning_rate": 9.935750420309055e-05, | |
| "loss": 0.9063, | |
| "num_input_tokens_seen": 3918272, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.17512232809683234, | |
| "grad_norm": 0.8713957774909928, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.8952, | |
| "num_input_tokens_seen": 3976760, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.17769765645119753, | |
| "grad_norm": 0.6671526212854116, | |
| "learning_rate": 9.927745975766654e-05, | |
| "loss": 0.9136, | |
| "num_input_tokens_seen": 4035240, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.1802729848055627, | |
| "grad_norm": 0.28702679234521244, | |
| "learning_rate": 9.923568892600578e-05, | |
| "loss": 0.9075, | |
| "num_input_tokens_seen": 4093688, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1802729848055627, | |
| "eval_loss": 0.89204341173172, | |
| "eval_runtime": 16.5819, | |
| "eval_samples_per_second": 3.618, | |
| "eval_steps_per_second": 0.905, | |
| "num_input_tokens_seen": 4093688, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1828483131599279, | |
| "grad_norm": 0.32233149132200706, | |
| "learning_rate": 9.91927536630402e-05, | |
| "loss": 0.8812, | |
| "num_input_tokens_seen": 4152160, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.18542364151429308, | |
| "grad_norm": 0.5071871697326992, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.9109, | |
| "num_input_tokens_seen": 4210648, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.18799896986865824, | |
| "grad_norm": 0.4532792519849944, | |
| "learning_rate": 9.91033939324107e-05, | |
| "loss": 0.9176, | |
| "num_input_tokens_seen": 4269136, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.19057429822302344, | |
| "grad_norm": 0.5409761562534501, | |
| "learning_rate": 9.905697157811761e-05, | |
| "loss": 0.9077, | |
| "num_input_tokens_seen": 4327664, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.19314962657738863, | |
| "grad_norm": 0.3432361562809093, | |
| "learning_rate": 9.900938901921131e-05, | |
| "loss": 0.893, | |
| "num_input_tokens_seen": 4386120, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.1957249549317538, | |
| "grad_norm": 0.4756530294720616, | |
| "learning_rate": 9.896064738102635e-05, | |
| "loss": 0.9094, | |
| "num_input_tokens_seen": 4444560, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.19830028328611898, | |
| "grad_norm": 0.424836974193983, | |
| "learning_rate": 9.891074781630966e-05, | |
| "loss": 0.9091, | |
| "num_input_tokens_seen": 4503016, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.20087561164048418, | |
| "grad_norm": 0.31316926977469683, | |
| "learning_rate": 9.885969150519331e-05, | |
| "loss": 0.9033, | |
| "num_input_tokens_seen": 4561496, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.20345093999484934, | |
| "grad_norm": 0.6108378682480797, | |
| "learning_rate": 9.88074796551666e-05, | |
| "loss": 0.8851, | |
| "num_input_tokens_seen": 4619944, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.20602626834921453, | |
| "grad_norm": 0.38294566619219206, | |
| "learning_rate": 9.875411350104744e-05, | |
| "loss": 0.9004, | |
| "num_input_tokens_seen": 4678384, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.20602626834921453, | |
| "eval_loss": 0.9086406826972961, | |
| "eval_runtime": 16.7827, | |
| "eval_samples_per_second": 3.575, | |
| "eval_steps_per_second": 0.894, | |
| "num_input_tokens_seen": 4678384, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 3400, | |
| "num_input_tokens_seen": 4678384, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 262667545346048.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |