| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9993284083277367, | |
| "global_step": 744, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.865591397849462e-05, | |
| "loss": 1.8106, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.19744795560836792, | |
| "eval_loss": 1.7615934610366821, | |
| "eval_runtime": 134.0063, | |
| "eval_samples_per_second": 11.111, | |
| "eval_steps_per_second": 2.783, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.731182795698925e-05, | |
| "loss": 1.7268, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.2525184750556946, | |
| "eval_loss": 1.7187447547912598, | |
| "eval_runtime": 145.4077, | |
| "eval_samples_per_second": 10.24, | |
| "eval_steps_per_second": 2.565, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.596774193548387e-05, | |
| "loss": 1.7269, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.309603750705719, | |
| "eval_loss": 1.6442092657089233, | |
| "eval_runtime": 144.9066, | |
| "eval_samples_per_second": 10.276, | |
| "eval_steps_per_second": 2.574, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.46236559139785e-05, | |
| "loss": 1.7086, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.33378106355667114, | |
| "eval_loss": 1.583362340927124, | |
| "eval_runtime": 135.7155, | |
| "eval_samples_per_second": 10.971, | |
| "eval_steps_per_second": 2.748, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.327956989247312e-05, | |
| "loss": 1.6983, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.35997313261032104, | |
| "eval_loss": 1.6194798946380615, | |
| "eval_runtime": 135.5719, | |
| "eval_samples_per_second": 10.983, | |
| "eval_steps_per_second": 2.751, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.193548387096774e-05, | |
| "loss": 1.5845, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.34184014797210693, | |
| "eval_loss": 1.575337290763855, | |
| "eval_runtime": 135.8178, | |
| "eval_samples_per_second": 10.963, | |
| "eval_steps_per_second": 2.746, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.059139784946237e-05, | |
| "loss": 1.5744, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_accuracy": 0.3707185983657837, | |
| "eval_loss": 1.5669182538986206, | |
| "eval_runtime": 135.433, | |
| "eval_samples_per_second": 10.994, | |
| "eval_steps_per_second": 2.754, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.924731182795699e-05, | |
| "loss": 1.5915, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.3754197359085083, | |
| "eval_loss": 1.5411657094955444, | |
| "eval_runtime": 135.3362, | |
| "eval_samples_per_second": 11.002, | |
| "eval_steps_per_second": 2.756, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.790322580645162e-05, | |
| "loss": 1.5105, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.2612491548061371, | |
| "eval_loss": 2.0037343502044678, | |
| "eval_runtime": 135.2385, | |
| "eval_samples_per_second": 11.01, | |
| "eval_steps_per_second": 2.758, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.655913978494624e-05, | |
| "loss": 1.4689, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.3626595139503479, | |
| "eval_loss": 1.5439659357070923, | |
| "eval_runtime": 135.2487, | |
| "eval_samples_per_second": 11.009, | |
| "eval_steps_per_second": 2.758, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.521505376344086e-05, | |
| "loss": 1.527, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.38616520166397095, | |
| "eval_loss": 1.540026068687439, | |
| "eval_runtime": 135.6976, | |
| "eval_samples_per_second": 10.973, | |
| "eval_steps_per_second": 2.749, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.387096774193549e-05, | |
| "loss": 1.6481, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.32975152134895325, | |
| "eval_loss": 1.6678365468978882, | |
| "eval_runtime": 135.8659, | |
| "eval_samples_per_second": 10.959, | |
| "eval_steps_per_second": 2.745, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.252688172043011e-05, | |
| "loss": 1.7504, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.29952988028526306, | |
| "eval_loss": 1.6077724695205688, | |
| "eval_runtime": 135.8936, | |
| "eval_samples_per_second": 10.957, | |
| "eval_steps_per_second": 2.745, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.118279569892473e-05, | |
| "loss": 1.3748, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.32505038380622864, | |
| "eval_loss": 1.5750231742858887, | |
| "eval_runtime": 135.7593, | |
| "eval_samples_per_second": 10.968, | |
| "eval_steps_per_second": 2.748, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 7.983870967741936e-05, | |
| "loss": 1.6417, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.25990596413612366, | |
| "eval_loss": 1.7033889293670654, | |
| "eval_runtime": 140.3888, | |
| "eval_samples_per_second": 10.606, | |
| "eval_steps_per_second": 2.657, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.849462365591398e-05, | |
| "loss": 1.6146, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.35191404819488525, | |
| "eval_loss": 1.6161645650863647, | |
| "eval_runtime": 136.7498, | |
| "eval_samples_per_second": 10.889, | |
| "eval_steps_per_second": 2.728, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.715053763440861e-05, | |
| "loss": 1.4896, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.37407657504081726, | |
| "eval_loss": 1.5245014429092407, | |
| "eval_runtime": 137.1791, | |
| "eval_samples_per_second": 10.854, | |
| "eval_steps_per_second": 2.719, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.580645161290323e-05, | |
| "loss": 1.4278, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.24244458973407745, | |
| "eval_loss": 1.7536966800689697, | |
| "eval_runtime": 137.1089, | |
| "eval_samples_per_second": 10.86, | |
| "eval_steps_per_second": 2.72, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.446236559139786e-05, | |
| "loss": 1.4475, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.3881799876689911, | |
| "eval_loss": 1.4769032001495361, | |
| "eval_runtime": 136.7534, | |
| "eval_samples_per_second": 10.888, | |
| "eval_steps_per_second": 2.728, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.311827956989248e-05, | |
| "loss": 1.5416, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.39489591121673584, | |
| "eval_loss": 1.4772460460662842, | |
| "eval_runtime": 137.0691, | |
| "eval_samples_per_second": 10.863, | |
| "eval_steps_per_second": 2.721, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.177419354838711e-05, | |
| "loss": 1.5997, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.4278039038181305, | |
| "eval_loss": 1.4428460597991943, | |
| "eval_runtime": 137.003, | |
| "eval_samples_per_second": 10.868, | |
| "eval_steps_per_second": 2.723, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.043010752688173e-05, | |
| "loss": 1.4337, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.41235730051994324, | |
| "eval_loss": 1.435219645500183, | |
| "eval_runtime": 137.007, | |
| "eval_samples_per_second": 10.868, | |
| "eval_steps_per_second": 2.722, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.908602150537635e-05, | |
| "loss": 1.415, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.4157152473926544, | |
| "eval_loss": 1.4404770135879517, | |
| "eval_runtime": 137.0627, | |
| "eval_samples_per_second": 10.864, | |
| "eval_steps_per_second": 2.721, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.774193548387096e-05, | |
| "loss": 1.5196, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.40429818630218506, | |
| "eval_loss": 1.4196510314941406, | |
| "eval_runtime": 136.8253, | |
| "eval_samples_per_second": 10.882, | |
| "eval_steps_per_second": 2.726, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.63978494623656e-05, | |
| "loss": 1.3866, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.37340497970581055, | |
| "eval_loss": 1.524086833000183, | |
| "eval_runtime": 137.3465, | |
| "eval_samples_per_second": 10.841, | |
| "eval_steps_per_second": 2.716, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.505376344086021e-05, | |
| "loss": 1.3041, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.40429818630218506, | |
| "eval_loss": 1.5703184604644775, | |
| "eval_runtime": 136.9308, | |
| "eval_samples_per_second": 10.874, | |
| "eval_steps_per_second": 2.724, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.370967741935485e-05, | |
| "loss": 1.3618, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.4284754991531372, | |
| "eval_loss": 1.3963350057601929, | |
| "eval_runtime": 136.0816, | |
| "eval_samples_per_second": 10.942, | |
| "eval_steps_per_second": 2.741, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.236559139784946e-05, | |
| "loss": 1.3293, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.4506380259990692, | |
| "eval_loss": 1.3478150367736816, | |
| "eval_runtime": 135.9673, | |
| "eval_samples_per_second": 10.951, | |
| "eval_steps_per_second": 2.743, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.102150537634409e-05, | |
| "loss": 1.2215, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.3841504454612732, | |
| "eval_loss": 1.5994166135787964, | |
| "eval_runtime": 136.1871, | |
| "eval_samples_per_second": 10.933, | |
| "eval_steps_per_second": 2.739, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 5.9677419354838715e-05, | |
| "loss": 1.6618, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.2276695817708969, | |
| "eval_loss": 1.7750705480575562, | |
| "eval_runtime": 136.1639, | |
| "eval_samples_per_second": 10.935, | |
| "eval_steps_per_second": 2.739, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.8467741935483876e-05, | |
| "loss": 1.5349, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.40362659096717834, | |
| "eval_loss": 1.6090513467788696, | |
| "eval_runtime": 136.1264, | |
| "eval_samples_per_second": 10.938, | |
| "eval_steps_per_second": 2.74, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.71236559139785e-05, | |
| "loss": 1.4037, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.4445936977863312, | |
| "eval_loss": 1.4741053581237793, | |
| "eval_runtime": 136.0584, | |
| "eval_samples_per_second": 10.944, | |
| "eval_steps_per_second": 2.741, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.577956989247311e-05, | |
| "loss": 1.4844, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.4398925304412842, | |
| "eval_loss": 1.4170390367507935, | |
| "eval_runtime": 136.1183, | |
| "eval_samples_per_second": 10.939, | |
| "eval_steps_per_second": 2.74, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.443548387096774e-05, | |
| "loss": 1.2806, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.5050369501113892, | |
| "eval_loss": 1.2886841297149658, | |
| "eval_runtime": 136.1309, | |
| "eval_samples_per_second": 10.938, | |
| "eval_steps_per_second": 2.74, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.309139784946236e-05, | |
| "loss": 1.3818, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.501679003238678, | |
| "eval_loss": 1.2668293714523315, | |
| "eval_runtime": 135.9509, | |
| "eval_samples_per_second": 10.952, | |
| "eval_steps_per_second": 2.744, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.174731182795699e-05, | |
| "loss": 1.3491, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.4593687057495117, | |
| "eval_loss": 1.4720617532730103, | |
| "eval_runtime": 136.1018, | |
| "eval_samples_per_second": 10.94, | |
| "eval_steps_per_second": 2.741, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.040322580645161e-05, | |
| "loss": 1.2347, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.5245131254196167, | |
| "eval_loss": 1.2187544107437134, | |
| "eval_runtime": 136.1642, | |
| "eval_samples_per_second": 10.935, | |
| "eval_steps_per_second": 2.739, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.905913978494624e-05, | |
| "loss": 1.2182, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.45668232440948486, | |
| "eval_loss": 1.3813459873199463, | |
| "eval_runtime": 136.1044, | |
| "eval_samples_per_second": 10.94, | |
| "eval_steps_per_second": 2.741, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.771505376344086e-05, | |
| "loss": 1.2513, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.5204835534095764, | |
| "eval_loss": 1.2110750675201416, | |
| "eval_runtime": 136.1563, | |
| "eval_samples_per_second": 10.936, | |
| "eval_steps_per_second": 2.739, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.637096774193548e-05, | |
| "loss": 1.2447, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.546004056930542, | |
| "eval_loss": 1.2230509519577026, | |
| "eval_runtime": 136.1489, | |
| "eval_samples_per_second": 10.937, | |
| "eval_steps_per_second": 2.74, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.516129032258064e-05, | |
| "loss": 1.038, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.5372733473777771, | |
| "eval_loss": 1.2562698125839233, | |
| "eval_runtime": 136.2823, | |
| "eval_samples_per_second": 10.926, | |
| "eval_steps_per_second": 2.737, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.381720430107527e-05, | |
| "loss": 1.2409, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.4936198890209198, | |
| "eval_loss": 1.344766616821289, | |
| "eval_runtime": 136.1885, | |
| "eval_samples_per_second": 10.933, | |
| "eval_steps_per_second": 2.739, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.247311827956989e-05, | |
| "loss": 1.2279, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.5486903786659241, | |
| "eval_loss": 1.1971595287322998, | |
| "eval_runtime": 136.416, | |
| "eval_samples_per_second": 10.915, | |
| "eval_steps_per_second": 2.734, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.112903225806452e-05, | |
| "loss": 1.3256, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.5742108821868896, | |
| "eval_loss": 1.1706324815750122, | |
| "eval_runtime": 136.371, | |
| "eval_samples_per_second": 10.919, | |
| "eval_steps_per_second": 2.735, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.978494623655914e-05, | |
| "loss": 1.2866, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.5003358125686646, | |
| "eval_loss": 1.309117078781128, | |
| "eval_runtime": 136.1709, | |
| "eval_samples_per_second": 10.935, | |
| "eval_steps_per_second": 2.739, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.844086021505376e-05, | |
| "loss": 1.0574, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.5500335693359375, | |
| "eval_loss": 1.2074663639068604, | |
| "eval_runtime": 136.5936, | |
| "eval_samples_per_second": 10.901, | |
| "eval_steps_per_second": 2.731, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.7096774193548386e-05, | |
| "loss": 1.2744, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.5171256065368652, | |
| "eval_loss": 1.2830621004104614, | |
| "eval_runtime": 136.8418, | |
| "eval_samples_per_second": 10.881, | |
| "eval_steps_per_second": 2.726, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.575268817204301e-05, | |
| "loss": 1.0836, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.5607790350914001, | |
| "eval_loss": 1.1768107414245605, | |
| "eval_runtime": 136.4906, | |
| "eval_samples_per_second": 10.909, | |
| "eval_steps_per_second": 2.733, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.4408602150537636e-05, | |
| "loss": 1.135, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_accuracy": 0.5775688290596008, | |
| "eval_loss": 1.1407707929611206, | |
| "eval_runtime": 136.5812, | |
| "eval_samples_per_second": 10.902, | |
| "eval_steps_per_second": 2.731, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.306451612903226e-05, | |
| "loss": 1.1303, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.5540631413459778, | |
| "eval_loss": 1.2319557666778564, | |
| "eval_runtime": 136.447, | |
| "eval_samples_per_second": 10.913, | |
| "eval_steps_per_second": 2.734, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.172043010752688e-05, | |
| "loss": 1.2068, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.5795835852622986, | |
| "eval_loss": 1.1379237174987793, | |
| "eval_runtime": 139.7377, | |
| "eval_samples_per_second": 10.656, | |
| "eval_steps_per_second": 2.669, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.0376344086021508e-05, | |
| "loss": 1.1347, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_accuracy": 0.5896574854850769, | |
| "eval_loss": 1.112443447113037, | |
| "eval_runtime": 135.8322, | |
| "eval_samples_per_second": 10.962, | |
| "eval_steps_per_second": 2.746, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.9032258064516133e-05, | |
| "loss": 1.1846, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.5802552103996277, | |
| "eval_loss": 1.1337865591049194, | |
| "eval_runtime": 136.0081, | |
| "eval_samples_per_second": 10.948, | |
| "eval_steps_per_second": 2.742, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.768817204301075e-05, | |
| "loss": 1.2409, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.5789120197296143, | |
| "eval_loss": 1.1259396076202393, | |
| "eval_runtime": 136.2241, | |
| "eval_samples_per_second": 10.931, | |
| "eval_steps_per_second": 2.738, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.6344086021505376e-05, | |
| "loss": 1.0664, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.6037608981132507, | |
| "eval_loss": 1.065294861793518, | |
| "eval_runtime": 136.1781, | |
| "eval_samples_per_second": 10.934, | |
| "eval_steps_per_second": 2.739, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.1637, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.5977165699005127, | |
| "eval_loss": 1.0549540519714355, | |
| "eval_runtime": 135.9124, | |
| "eval_samples_per_second": 10.956, | |
| "eval_steps_per_second": 2.744, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.3655913978494626e-05, | |
| "loss": 1.0707, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.5715245008468628, | |
| "eval_loss": 1.0996488332748413, | |
| "eval_runtime": 136.1326, | |
| "eval_samples_per_second": 10.938, | |
| "eval_steps_per_second": 2.74, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.2311827956989248e-05, | |
| "loss": 1.2258, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_accuracy": 0.5977165699005127, | |
| "eval_loss": 1.080415964126587, | |
| "eval_runtime": 135.8671, | |
| "eval_samples_per_second": 10.959, | |
| "eval_steps_per_second": 2.745, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.0967741935483873e-05, | |
| "loss": 0.9256, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.580926775932312, | |
| "eval_loss": 1.1501046419143677, | |
| "eval_runtime": 135.8439, | |
| "eval_samples_per_second": 10.961, | |
| "eval_steps_per_second": 2.746, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.9623655913978494e-05, | |
| "loss": 1.1542, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.5957018136978149, | |
| "eval_loss": 1.1089370250701904, | |
| "eval_runtime": 137.3702, | |
| "eval_samples_per_second": 10.839, | |
| "eval_steps_per_second": 2.715, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.827956989247312e-05, | |
| "loss": 1.3931, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_accuracy": 0.5856279134750366, | |
| "eval_loss": 1.138110876083374, | |
| "eval_runtime": 135.8089, | |
| "eval_samples_per_second": 10.964, | |
| "eval_steps_per_second": 2.747, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.693548387096774e-05, | |
| "loss": 1.1117, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.6030893325805664, | |
| "eval_loss": 1.0933294296264648, | |
| "eval_runtime": 135.7612, | |
| "eval_samples_per_second": 10.968, | |
| "eval_steps_per_second": 2.747, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.5591397849462366e-05, | |
| "loss": 1.1433, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.6218938827514648, | |
| "eval_loss": 1.0175174474716187, | |
| "eval_runtime": 135.6802, | |
| "eval_samples_per_second": 10.974, | |
| "eval_steps_per_second": 2.749, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4247311827956991e-05, | |
| "loss": 1.0325, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.6239086389541626, | |
| "eval_loss": 0.9885073304176331, | |
| "eval_runtime": 135.5378, | |
| "eval_samples_per_second": 10.986, | |
| "eval_steps_per_second": 2.752, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.2903225806451613e-05, | |
| "loss": 1.111, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.6259234547615051, | |
| "eval_loss": 1.004755973815918, | |
| "eval_runtime": 135.7521, | |
| "eval_samples_per_second": 10.969, | |
| "eval_steps_per_second": 2.748, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.1559139784946236e-05, | |
| "loss": 0.8125, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.6165211796760559, | |
| "eval_loss": 1.0176496505737305, | |
| "eval_runtime": 135.5622, | |
| "eval_samples_per_second": 10.984, | |
| "eval_steps_per_second": 2.752, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.0215053763440861e-05, | |
| "loss": 1.0414, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.6185359358787537, | |
| "eval_loss": 1.0289984941482544, | |
| "eval_runtime": 135.9417, | |
| "eval_samples_per_second": 10.953, | |
| "eval_steps_per_second": 2.744, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 8.870967741935484e-06, | |
| "loss": 1.0037, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.625251829624176, | |
| "eval_loss": 1.0268802642822266, | |
| "eval_runtime": 135.7529, | |
| "eval_samples_per_second": 10.968, | |
| "eval_steps_per_second": 2.748, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.526881720430108e-06, | |
| "loss": 0.9406, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.6272666454315186, | |
| "eval_loss": 1.0300624370574951, | |
| "eval_runtime": 137.5757, | |
| "eval_samples_per_second": 10.823, | |
| "eval_steps_per_second": 2.711, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 6.182795698924732e-06, | |
| "loss": 1.0129, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.6326393485069275, | |
| "eval_loss": 1.0238244533538818, | |
| "eval_runtime": 135.84, | |
| "eval_samples_per_second": 10.961, | |
| "eval_steps_per_second": 2.746, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.838709677419355e-06, | |
| "loss": 1.2213, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.6272666454315186, | |
| "eval_loss": 1.018078088760376, | |
| "eval_runtime": 135.9017, | |
| "eval_samples_per_second": 10.956, | |
| "eval_steps_per_second": 2.745, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.4946236559139785e-06, | |
| "loss": 1.2519, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.6265950202941895, | |
| "eval_loss": 1.0160512924194336, | |
| "eval_runtime": 135.809, | |
| "eval_samples_per_second": 10.964, | |
| "eval_steps_per_second": 2.747, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.1505376344086023e-06, | |
| "loss": 0.9932, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_accuracy": 0.6279382109642029, | |
| "eval_loss": 1.0112457275390625, | |
| "eval_runtime": 136.0311, | |
| "eval_samples_per_second": 10.946, | |
| "eval_steps_per_second": 2.742, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 8.064516129032258e-07, | |
| "loss": 1.0135, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.6312961578369141, | |
| "eval_loss": 1.010461449623108, | |
| "eval_runtime": 136.2447, | |
| "eval_samples_per_second": 10.929, | |
| "eval_steps_per_second": 2.738, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 744, | |
| "total_flos": 1.673551838186588e+17, | |
| "train_loss": 1.320114940725347, | |
| "train_runtime": 11616.0305, | |
| "train_samples_per_second": 0.512, | |
| "train_steps_per_second": 0.064 | |
| } | |
| ], | |
| "max_steps": 744, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.673551838186588e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |