| { | |
| "best_metric": 2.9971697330474854, | |
| "best_model_checkpoint": "mobilebert_add_pre-training-complete/checkpoint-293068", | |
| "epoch": 167.87912702853944, | |
| "global_step": 300000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.971873957985996e-05, | |
| "loss": 4.8119, | |
| "step": 1787 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.31985974754558205, | |
| "eval_loss": 4.369968414306641, | |
| "eval_runtime": 3.3492, | |
| "eval_samples_per_second": 143.018, | |
| "eval_steps_per_second": 1.194, | |
| "step": 1787 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.942080693564522e-05, | |
| "loss": 4.2649, | |
| "step": 3574 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3444790701591847, | |
| "eval_loss": 4.09299373626709, | |
| "eval_runtime": 2.6635, | |
| "eval_samples_per_second": 179.842, | |
| "eval_steps_per_second": 1.502, | |
| "step": 3574 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.912287429143048e-05, | |
| "loss": 4.0457, | |
| "step": 5361 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3544818746691187, | |
| "eval_loss": 3.937490224838257, | |
| "eval_runtime": 2.6837, | |
| "eval_samples_per_second": 178.487, | |
| "eval_steps_per_second": 1.491, | |
| "step": 5361 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.882494164721574e-05, | |
| "loss": 3.9099, | |
| "step": 7148 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3643615542831731, | |
| "eval_loss": 3.853400468826294, | |
| "eval_runtime": 2.6447, | |
| "eval_samples_per_second": 181.115, | |
| "eval_steps_per_second": 1.512, | |
| "step": 7148 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.8527009003001e-05, | |
| "loss": 3.8193, | |
| "step": 8935 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.3669499105545617, | |
| "eval_loss": 3.7993216514587402, | |
| "eval_runtime": 2.8341, | |
| "eval_samples_per_second": 169.013, | |
| "eval_steps_per_second": 1.411, | |
| "step": 8935 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.822907635878626e-05, | |
| "loss": 3.7517, | |
| "step": 10722 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.3729702583561185, | |
| "eval_loss": 3.7414000034332275, | |
| "eval_runtime": 2.6482, | |
| "eval_samples_per_second": 180.878, | |
| "eval_steps_per_second": 1.51, | |
| "step": 10722 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.7931143714571526e-05, | |
| "loss": 3.6983, | |
| "step": 12509 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.38179712437501767, | |
| "eval_loss": 3.673661708831787, | |
| "eval_runtime": 2.6433, | |
| "eval_samples_per_second": 181.216, | |
| "eval_steps_per_second": 1.513, | |
| "step": 12509 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.7633211070356786e-05, | |
| "loss": 3.6565, | |
| "step": 14296 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.3794307568661142, | |
| "eval_loss": 3.6657235622406006, | |
| "eval_runtime": 2.6602, | |
| "eval_samples_per_second": 180.063, | |
| "eval_steps_per_second": 1.504, | |
| "step": 14296 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.7335278426142046e-05, | |
| "loss": 3.619, | |
| "step": 16083 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.38690059135113924, | |
| "eval_loss": 3.6128811836242676, | |
| "eval_runtime": 2.9694, | |
| "eval_samples_per_second": 161.314, | |
| "eval_steps_per_second": 1.347, | |
| "step": 16083 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.703734578192731e-05, | |
| "loss": 3.5899, | |
| "step": 17870 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.39099787685774945, | |
| "eval_loss": 3.580448627471924, | |
| "eval_runtime": 2.6649, | |
| "eval_samples_per_second": 179.741, | |
| "eval_steps_per_second": 1.501, | |
| "step": 17870 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.673941313771257e-05, | |
| "loss": 3.5597, | |
| "step": 19657 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.3964062763624093, | |
| "eval_loss": 3.5432231426239014, | |
| "eval_runtime": 2.6576, | |
| "eval_samples_per_second": 180.239, | |
| "eval_steps_per_second": 1.505, | |
| "step": 19657 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.644148049349783e-05, | |
| "loss": 3.5329, | |
| "step": 21444 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.39582186502256966, | |
| "eval_loss": 3.539653778076172, | |
| "eval_runtime": 2.6515, | |
| "eval_samples_per_second": 180.65, | |
| "eval_steps_per_second": 1.509, | |
| "step": 21444 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.61435478492831e-05, | |
| "loss": 3.5088, | |
| "step": 23231 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4010702757800555, | |
| "eval_loss": 3.48960542678833, | |
| "eval_runtime": 2.671, | |
| "eval_samples_per_second": 179.334, | |
| "eval_steps_per_second": 1.498, | |
| "step": 23231 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.584561520506836e-05, | |
| "loss": 3.4904, | |
| "step": 25018 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.39997756086615055, | |
| "eval_loss": 3.473088502883911, | |
| "eval_runtime": 2.9516, | |
| "eval_samples_per_second": 162.282, | |
| "eval_steps_per_second": 1.355, | |
| "step": 25018 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.5547682560853625e-05, | |
| "loss": 3.4703, | |
| "step": 26805 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.39938999029530015, | |
| "eval_loss": 3.4971117973327637, | |
| "eval_runtime": 2.873, | |
| "eval_samples_per_second": 166.723, | |
| "eval_steps_per_second": 1.392, | |
| "step": 26805 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 4.5249749916638885e-05, | |
| "loss": 3.4533, | |
| "step": 28592 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4049408937204818, | |
| "eval_loss": 3.460916519165039, | |
| "eval_runtime": 3.1252, | |
| "eval_samples_per_second": 153.27, | |
| "eval_steps_per_second": 1.28, | |
| "step": 28592 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 4.4951817272424145e-05, | |
| "loss": 3.4369, | |
| "step": 30379 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.4066726276964346, | |
| "eval_loss": 3.441118001937866, | |
| "eval_runtime": 2.8852, | |
| "eval_samples_per_second": 166.017, | |
| "eval_steps_per_second": 1.386, | |
| "step": 30379 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 4.4653884628209404e-05, | |
| "loss": 3.423, | |
| "step": 32166 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.40659769666211204, | |
| "eval_loss": 3.4219350814819336, | |
| "eval_runtime": 2.9284, | |
| "eval_samples_per_second": 163.569, | |
| "eval_steps_per_second": 1.366, | |
| "step": 32166 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 4.4355951983994664e-05, | |
| "loss": 3.4084, | |
| "step": 33953 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.40138222849083216, | |
| "eval_loss": 3.4476888179779053, | |
| "eval_runtime": 2.8209, | |
| "eval_samples_per_second": 169.805, | |
| "eval_steps_per_second": 1.418, | |
| "step": 33953 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.4058019339779924e-05, | |
| "loss": 3.3949, | |
| "step": 35740 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.40872225184519967, | |
| "eval_loss": 3.4012813568115234, | |
| "eval_runtime": 2.7502, | |
| "eval_samples_per_second": 174.171, | |
| "eval_steps_per_second": 1.454, | |
| "step": 35740 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 4.376008669556519e-05, | |
| "loss": 3.3811, | |
| "step": 37527 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.4130312412046158, | |
| "eval_loss": 3.3642032146453857, | |
| "eval_runtime": 2.8758, | |
| "eval_samples_per_second": 166.565, | |
| "eval_steps_per_second": 1.391, | |
| "step": 37527 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 4.346215405135045e-05, | |
| "loss": 3.3688, | |
| "step": 39314 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.403096026951026, | |
| "eval_loss": 3.417304277420044, | |
| "eval_runtime": 2.7385, | |
| "eval_samples_per_second": 174.915, | |
| "eval_steps_per_second": 1.461, | |
| "step": 39314 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 4.316422140713571e-05, | |
| "loss": 3.3598, | |
| "step": 41101 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.4101078204663862, | |
| "eval_loss": 3.401829481124878, | |
| "eval_runtime": 2.6232, | |
| "eval_samples_per_second": 182.602, | |
| "eval_steps_per_second": 1.525, | |
| "step": 41101 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.286628876292098e-05, | |
| "loss": 3.3484, | |
| "step": 42888 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.4142865190693482, | |
| "eval_loss": 3.3499021530151367, | |
| "eval_runtime": 2.8522, | |
| "eval_samples_per_second": 167.94, | |
| "eval_steps_per_second": 1.402, | |
| "step": 42888 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 4.2568356118706237e-05, | |
| "loss": 3.3363, | |
| "step": 44675 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.4118788492364802, | |
| "eval_loss": 3.3674731254577637, | |
| "eval_runtime": 2.7234, | |
| "eval_samples_per_second": 175.884, | |
| "eval_steps_per_second": 1.469, | |
| "step": 44675 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 4.2270423474491496e-05, | |
| "loss": 3.3274, | |
| "step": 46462 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.41535205305488926, | |
| "eval_loss": 3.356222629547119, | |
| "eval_runtime": 2.6874, | |
| "eval_samples_per_second": 178.241, | |
| "eval_steps_per_second": 1.488, | |
| "step": 46462 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 4.197249083027676e-05, | |
| "loss": 3.3161, | |
| "step": 48249 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.41593196314670444, | |
| "eval_loss": 3.3487422466278076, | |
| "eval_runtime": 2.6979, | |
| "eval_samples_per_second": 177.545, | |
| "eval_steps_per_second": 1.483, | |
| "step": 48249 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 4.167455818606202e-05, | |
| "loss": 3.3073, | |
| "step": 50036 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.4159050645369928, | |
| "eval_loss": 3.329265832901001, | |
| "eval_runtime": 2.6601, | |
| "eval_samples_per_second": 180.065, | |
| "eval_steps_per_second": 1.504, | |
| "step": 50036 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 4.137662554184728e-05, | |
| "loss": 3.2991, | |
| "step": 51823 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.41597842575425586, | |
| "eval_loss": 3.3317177295684814, | |
| "eval_runtime": 2.632, | |
| "eval_samples_per_second": 181.991, | |
| "eval_steps_per_second": 1.52, | |
| "step": 51823 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 4.107869289763255e-05, | |
| "loss": 3.2899, | |
| "step": 53610 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.4182503044549548, | |
| "eval_loss": 3.3058271408081055, | |
| "eval_runtime": 2.6549, | |
| "eval_samples_per_second": 180.418, | |
| "eval_steps_per_second": 1.507, | |
| "step": 53610 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 4.078076025341781e-05, | |
| "loss": 3.2814, | |
| "step": 55397 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.42345443682608325, | |
| "eval_loss": 3.2795028686523438, | |
| "eval_runtime": 2.6768, | |
| "eval_samples_per_second": 178.945, | |
| "eval_steps_per_second": 1.494, | |
| "step": 55397 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 4.0482827609203076e-05, | |
| "loss": 3.2734, | |
| "step": 57184 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.4142510746169955, | |
| "eval_loss": 3.318493366241455, | |
| "eval_runtime": 2.6511, | |
| "eval_samples_per_second": 180.679, | |
| "eval_steps_per_second": 1.509, | |
| "step": 57184 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 4.018489496498833e-05, | |
| "loss": 3.266, | |
| "step": 58971 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.4268454481298518, | |
| "eval_loss": 3.268219232559204, | |
| "eval_runtime": 2.8163, | |
| "eval_samples_per_second": 170.079, | |
| "eval_steps_per_second": 1.42, | |
| "step": 58971 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 3.988696232077359e-05, | |
| "loss": 3.2578, | |
| "step": 60758 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.4180501984459724, | |
| "eval_loss": 3.3144567012786865, | |
| "eval_runtime": 2.6553, | |
| "eval_samples_per_second": 180.397, | |
| "eval_steps_per_second": 1.506, | |
| "step": 60758 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 3.9589029676558855e-05, | |
| "loss": 3.2506, | |
| "step": 62545 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.423013128672233, | |
| "eval_loss": 3.272632598876953, | |
| "eval_runtime": 2.6457, | |
| "eval_samples_per_second": 181.048, | |
| "eval_steps_per_second": 1.512, | |
| "step": 62545 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 3.9291097032344115e-05, | |
| "loss": 3.2423, | |
| "step": 64332 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.42176717460496294, | |
| "eval_loss": 3.273455858230591, | |
| "eval_runtime": 2.6217, | |
| "eval_samples_per_second": 182.708, | |
| "eval_steps_per_second": 1.526, | |
| "step": 64332 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 3.8993164388129375e-05, | |
| "loss": 3.2359, | |
| "step": 66119 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.417536709284797, | |
| "eval_loss": 3.284508228302002, | |
| "eval_runtime": 2.7995, | |
| "eval_samples_per_second": 171.1, | |
| "eval_steps_per_second": 1.429, | |
| "step": 66119 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 3.869523174391464e-05, | |
| "loss": 3.2293, | |
| "step": 67906 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.4193099997219983, | |
| "eval_loss": 3.306713581085205, | |
| "eval_runtime": 2.606, | |
| "eval_samples_per_second": 183.804, | |
| "eval_steps_per_second": 1.535, | |
| "step": 67906 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 3.83972990996999e-05, | |
| "loss": 3.2207, | |
| "step": 69693 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.42573705623362873, | |
| "eval_loss": 3.2586092948913574, | |
| "eval_runtime": 2.8824, | |
| "eval_samples_per_second": 166.182, | |
| "eval_steps_per_second": 1.388, | |
| "step": 69693 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.809936645548516e-05, | |
| "loss": 3.2138, | |
| "step": 71480 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.4249552472588946, | |
| "eval_loss": 3.2543227672576904, | |
| "eval_runtime": 2.8002, | |
| "eval_samples_per_second": 171.061, | |
| "eval_steps_per_second": 1.428, | |
| "step": 71480 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 3.780143381127043e-05, | |
| "loss": 3.2077, | |
| "step": 73267 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.42259816679868734, | |
| "eval_loss": 3.239523410797119, | |
| "eval_runtime": 2.8097, | |
| "eval_samples_per_second": 170.48, | |
| "eval_steps_per_second": 1.424, | |
| "step": 73267 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 3.750350116705569e-05, | |
| "loss": 3.202, | |
| "step": 75054 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.4270068903702874, | |
| "eval_loss": 3.222418785095215, | |
| "eval_runtime": 2.7468, | |
| "eval_samples_per_second": 174.388, | |
| "eval_steps_per_second": 1.456, | |
| "step": 75054 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 3.720556852284095e-05, | |
| "loss": 3.1964, | |
| "step": 76841 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.4233582733012544, | |
| "eval_loss": 3.256213426589966, | |
| "eval_runtime": 2.7921, | |
| "eval_samples_per_second": 171.556, | |
| "eval_steps_per_second": 1.433, | |
| "step": 76841 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 3.6907635878626214e-05, | |
| "loss": 3.1925, | |
| "step": 78628 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.4251221214235869, | |
| "eval_loss": 3.2543723583221436, | |
| "eval_runtime": 2.7441, | |
| "eval_samples_per_second": 174.557, | |
| "eval_steps_per_second": 1.458, | |
| "step": 78628 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 3.660970323441147e-05, | |
| "loss": 3.1865, | |
| "step": 80415 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.43534812547819435, | |
| "eval_loss": 3.204282522201538, | |
| "eval_runtime": 2.8747, | |
| "eval_samples_per_second": 166.629, | |
| "eval_steps_per_second": 1.391, | |
| "step": 80415 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 3.631177059019673e-05, | |
| "loss": 3.1812, | |
| "step": 82202 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.42858336117607754, | |
| "eval_loss": 3.2280006408691406, | |
| "eval_runtime": 2.742, | |
| "eval_samples_per_second": 174.687, | |
| "eval_steps_per_second": 1.459, | |
| "step": 82202 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 3.601383794598199e-05, | |
| "loss": 3.1744, | |
| "step": 83989 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.427574415606256, | |
| "eval_loss": 3.21743106842041, | |
| "eval_runtime": 2.7215, | |
| "eval_samples_per_second": 176.009, | |
| "eval_steps_per_second": 1.47, | |
| "step": 83989 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 3.571590530176725e-05, | |
| "loss": 3.1699, | |
| "step": 85776 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.4317117218804673, | |
| "eval_loss": 3.1971514225006104, | |
| "eval_runtime": 2.9267, | |
| "eval_samples_per_second": 163.664, | |
| "eval_steps_per_second": 1.367, | |
| "step": 85776 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 3.541797265755252e-05, | |
| "loss": 3.1652, | |
| "step": 87563 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.43024569330697543, | |
| "eval_loss": 3.201594114303589, | |
| "eval_runtime": 2.8821, | |
| "eval_samples_per_second": 166.197, | |
| "eval_steps_per_second": 1.388, | |
| "step": 87563 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 3.512004001333778e-05, | |
| "loss": 3.1609, | |
| "step": 89350 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.4337845459672871, | |
| "eval_loss": 3.201768636703491, | |
| "eval_runtime": 2.7518, | |
| "eval_samples_per_second": 174.066, | |
| "eval_steps_per_second": 1.454, | |
| "step": 89350 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "learning_rate": 3.482210736912304e-05, | |
| "loss": 3.1548, | |
| "step": 91137 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.43272542487719495, | |
| "eval_loss": 3.1950149536132812, | |
| "eval_runtime": 2.6564, | |
| "eval_samples_per_second": 180.321, | |
| "eval_steps_per_second": 1.506, | |
| "step": 91137 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 3.4524174724908306e-05, | |
| "loss": 3.1508, | |
| "step": 92924 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.42785334961519894, | |
| "eval_loss": 3.212803363800049, | |
| "eval_runtime": 2.8096, | |
| "eval_samples_per_second": 170.486, | |
| "eval_steps_per_second": 1.424, | |
| "step": 92924 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "learning_rate": 3.4226242080693565e-05, | |
| "loss": 3.1478, | |
| "step": 94711 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.4303176427710337, | |
| "eval_loss": 3.202669382095337, | |
| "eval_runtime": 2.727, | |
| "eval_samples_per_second": 175.65, | |
| "eval_steps_per_second": 1.467, | |
| "step": 94711 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "learning_rate": 3.3928309436478825e-05, | |
| "loss": 3.1423, | |
| "step": 96498 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.43117465657415194, | |
| "eval_loss": 3.195861577987671, | |
| "eval_runtime": 2.7557, | |
| "eval_samples_per_second": 173.823, | |
| "eval_steps_per_second": 1.452, | |
| "step": 96498 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 3.363037679226409e-05, | |
| "loss": 3.1383, | |
| "step": 98285 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.4340061025109873, | |
| "eval_loss": 3.1911423206329346, | |
| "eval_runtime": 2.754, | |
| "eval_samples_per_second": 173.929, | |
| "eval_steps_per_second": 1.452, | |
| "step": 98285 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 3.333244414804935e-05, | |
| "loss": 3.1336, | |
| "step": 100072 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.43203597021216805, | |
| "eval_loss": 3.1913583278656006, | |
| "eval_runtime": 2.6171, | |
| "eval_samples_per_second": 183.026, | |
| "eval_steps_per_second": 1.528, | |
| "step": 100072 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "learning_rate": 3.303451150383461e-05, | |
| "loss": 3.129, | |
| "step": 101859 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.43117934403349617, | |
| "eval_loss": 3.185468912124634, | |
| "eval_runtime": 2.8993, | |
| "eval_samples_per_second": 165.21, | |
| "eval_steps_per_second": 1.38, | |
| "step": 101859 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "learning_rate": 3.273657885961988e-05, | |
| "loss": 3.1233, | |
| "step": 103646 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.4336863338376198, | |
| "eval_loss": 3.1569876670837402, | |
| "eval_runtime": 2.7946, | |
| "eval_samples_per_second": 171.403, | |
| "eval_steps_per_second": 1.431, | |
| "step": 103646 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "learning_rate": 3.243864621540514e-05, | |
| "loss": 3.1198, | |
| "step": 105433 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.4307147438578878, | |
| "eval_loss": 3.2042369842529297, | |
| "eval_runtime": 2.9712, | |
| "eval_samples_per_second": 161.213, | |
| "eval_steps_per_second": 1.346, | |
| "step": 105433 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 3.21407135711904e-05, | |
| "loss": 3.1153, | |
| "step": 107220 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.4389830036996857, | |
| "eval_loss": 3.1370162963867188, | |
| "eval_runtime": 2.6328, | |
| "eval_samples_per_second": 181.937, | |
| "eval_steps_per_second": 1.519, | |
| "step": 107220 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "learning_rate": 3.1842780926975664e-05, | |
| "loss": 3.1122, | |
| "step": 109007 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.4412110687878109, | |
| "eval_loss": 3.1612205505371094, | |
| "eval_runtime": 2.8382, | |
| "eval_samples_per_second": 168.771, | |
| "eval_steps_per_second": 1.409, | |
| "step": 109007 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "learning_rate": 3.154484828276092e-05, | |
| "loss": 3.1093, | |
| "step": 110794 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.4347947500698129, | |
| "eval_loss": 3.164184331893921, | |
| "eval_runtime": 2.8661, | |
| "eval_samples_per_second": 167.128, | |
| "eval_steps_per_second": 1.396, | |
| "step": 110794 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "learning_rate": 3.1246915638546184e-05, | |
| "loss": 3.1048, | |
| "step": 112581 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.4325971058644326, | |
| "eval_loss": 3.1806650161743164, | |
| "eval_runtime": 2.8065, | |
| "eval_samples_per_second": 170.676, | |
| "eval_steps_per_second": 1.425, | |
| "step": 112581 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "learning_rate": 3.0948982994331444e-05, | |
| "loss": 3.1013, | |
| "step": 114368 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.4358816103240286, | |
| "eval_loss": 3.144869089126587, | |
| "eval_runtime": 2.6572, | |
| "eval_samples_per_second": 180.267, | |
| "eval_steps_per_second": 1.505, | |
| "step": 114368 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 3.06510503501167e-05, | |
| "loss": 3.0977, | |
| "step": 116155 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.43795185846729606, | |
| "eval_loss": 3.1408073902130127, | |
| "eval_runtime": 2.8767, | |
| "eval_samples_per_second": 166.508, | |
| "eval_steps_per_second": 1.39, | |
| "step": 116155 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "learning_rate": 3.0353117705901967e-05, | |
| "loss": 3.0926, | |
| "step": 117942 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.43651985318651987, | |
| "eval_loss": 3.172287702560425, | |
| "eval_runtime": 2.6811, | |
| "eval_samples_per_second": 178.655, | |
| "eval_steps_per_second": 1.492, | |
| "step": 117942 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "learning_rate": 3.005518506168723e-05, | |
| "loss": 3.0901, | |
| "step": 119729 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.43799220873854433, | |
| "eval_loss": 3.1473004817962646, | |
| "eval_runtime": 2.8395, | |
| "eval_samples_per_second": 168.689, | |
| "eval_steps_per_second": 1.409, | |
| "step": 119729 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "learning_rate": 2.9757252417472493e-05, | |
| "loss": 3.0882, | |
| "step": 121516 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.43776389123458875, | |
| "eval_loss": 3.140061378479004, | |
| "eval_runtime": 2.8036, | |
| "eval_samples_per_second": 170.853, | |
| "eval_steps_per_second": 1.427, | |
| "step": 121516 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "learning_rate": 2.9459319773257753e-05, | |
| "loss": 3.0839, | |
| "step": 123303 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.43737838066499335, | |
| "eval_loss": 3.12809157371521, | |
| "eval_runtime": 2.7834, | |
| "eval_samples_per_second": 172.089, | |
| "eval_steps_per_second": 1.437, | |
| "step": 123303 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 2.9161387129043016e-05, | |
| "loss": 3.0794, | |
| "step": 125090 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.436696631101403, | |
| "eval_loss": 3.1356077194213867, | |
| "eval_runtime": 2.7463, | |
| "eval_samples_per_second": 174.417, | |
| "eval_steps_per_second": 1.457, | |
| "step": 125090 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "learning_rate": 2.886345448482828e-05, | |
| "loss": 3.0766, | |
| "step": 126877 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.4397433382835047, | |
| "eval_loss": 3.1019225120544434, | |
| "eval_runtime": 2.7446, | |
| "eval_samples_per_second": 174.525, | |
| "eval_steps_per_second": 1.457, | |
| "step": 126877 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "learning_rate": 2.856552184061354e-05, | |
| "loss": 3.074, | |
| "step": 128664 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.43546703529212627, | |
| "eval_loss": 3.162637948989868, | |
| "eval_runtime": 2.7735, | |
| "eval_samples_per_second": 172.704, | |
| "eval_steps_per_second": 1.442, | |
| "step": 128664 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "learning_rate": 2.8267589196398802e-05, | |
| "loss": 3.0702, | |
| "step": 130451 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.4387263241465351, | |
| "eval_loss": 3.1287012100219727, | |
| "eval_runtime": 2.7531, | |
| "eval_samples_per_second": 173.986, | |
| "eval_steps_per_second": 1.453, | |
| "step": 130451 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "learning_rate": 2.7969656552184065e-05, | |
| "loss": 3.0676, | |
| "step": 132238 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.43789707310306564, | |
| "eval_loss": 3.136582136154175, | |
| "eval_runtime": 2.7895, | |
| "eval_samples_per_second": 171.718, | |
| "eval_steps_per_second": 1.434, | |
| "step": 132238 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 2.767172390796933e-05, | |
| "loss": 3.0648, | |
| "step": 134025 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.43458386755114553, | |
| "eval_loss": 3.178231716156006, | |
| "eval_runtime": 2.7934, | |
| "eval_samples_per_second": 171.478, | |
| "eval_steps_per_second": 1.432, | |
| "step": 134025 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "learning_rate": 2.7373791263754585e-05, | |
| "loss": 3.0624, | |
| "step": 135812 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.44267685994547346, | |
| "eval_loss": 3.1229066848754883, | |
| "eval_runtime": 2.7648, | |
| "eval_samples_per_second": 173.25, | |
| "eval_steps_per_second": 1.447, | |
| "step": 135812 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "learning_rate": 2.7075858619539845e-05, | |
| "loss": 3.0575, | |
| "step": 137599 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.44304284497210544, | |
| "eval_loss": 3.11391282081604, | |
| "eval_runtime": 2.8016, | |
| "eval_samples_per_second": 170.976, | |
| "eval_steps_per_second": 1.428, | |
| "step": 137599 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "learning_rate": 2.6777925975325108e-05, | |
| "loss": 3.0549, | |
| "step": 139386 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.4431432021793468, | |
| "eval_loss": 3.0947771072387695, | |
| "eval_runtime": 2.8076, | |
| "eval_samples_per_second": 170.609, | |
| "eval_steps_per_second": 1.425, | |
| "step": 139386 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "learning_rate": 2.647999333111037e-05, | |
| "loss": 3.052, | |
| "step": 141173 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.4451516602360098, | |
| "eval_loss": 3.1029744148254395, | |
| "eval_runtime": 2.6939, | |
| "eval_samples_per_second": 177.81, | |
| "eval_steps_per_second": 1.485, | |
| "step": 141173 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 2.618206068689563e-05, | |
| "loss": 3.0527, | |
| "step": 142960 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.4447775411856999, | |
| "eval_loss": 3.0929136276245117, | |
| "eval_runtime": 2.7294, | |
| "eval_samples_per_second": 175.498, | |
| "eval_steps_per_second": 1.466, | |
| "step": 142960 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "learning_rate": 2.5884128042680894e-05, | |
| "loss": 3.0466, | |
| "step": 144747 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.44276007765216396, | |
| "eval_loss": 3.08884334564209, | |
| "eval_runtime": 2.9041, | |
| "eval_samples_per_second": 164.938, | |
| "eval_steps_per_second": 1.377, | |
| "step": 144747 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "learning_rate": 2.5586195398466157e-05, | |
| "loss": 3.0439, | |
| "step": 146534 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.44138026993182133, | |
| "eval_loss": 3.103548765182495, | |
| "eval_runtime": 2.7889, | |
| "eval_samples_per_second": 171.752, | |
| "eval_steps_per_second": 1.434, | |
| "step": 146534 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "learning_rate": 2.5288262754251417e-05, | |
| "loss": 3.0409, | |
| "step": 148321 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.4411418975650714, | |
| "eval_loss": 3.1111607551574707, | |
| "eval_runtime": 2.7759, | |
| "eval_samples_per_second": 172.554, | |
| "eval_steps_per_second": 1.441, | |
| "step": 148321 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "learning_rate": 2.499033011003668e-05, | |
| "loss": 3.041, | |
| "step": 150108 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.43987652588747017, | |
| "eval_loss": 3.129586696624756, | |
| "eval_runtime": 2.8127, | |
| "eval_samples_per_second": 170.3, | |
| "eval_steps_per_second": 1.422, | |
| "step": 150108 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 2.4692397465821944e-05, | |
| "loss": 3.0379, | |
| "step": 151895 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.44284645440186216, | |
| "eval_loss": 3.122410297393799, | |
| "eval_runtime": 2.8313, | |
| "eval_samples_per_second": 169.183, | |
| "eval_steps_per_second": 1.413, | |
| "step": 151895 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "learning_rate": 2.4394464821607203e-05, | |
| "loss": 3.0332, | |
| "step": 153682 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.43977575332866153, | |
| "eval_loss": 3.1100828647613525, | |
| "eval_runtime": 2.7772, | |
| "eval_samples_per_second": 172.476, | |
| "eval_steps_per_second": 1.44, | |
| "step": 153682 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "learning_rate": 2.4096532177392463e-05, | |
| "loss": 3.0315, | |
| "step": 155469 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.4423447851731753, | |
| "eval_loss": 3.1045453548431396, | |
| "eval_runtime": 2.6529, | |
| "eval_samples_per_second": 180.554, | |
| "eval_steps_per_second": 1.508, | |
| "step": 155469 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "learning_rate": 2.3798599533177726e-05, | |
| "loss": 3.0302, | |
| "step": 157256 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.4446285634040163, | |
| "eval_loss": 3.0912954807281494, | |
| "eval_runtime": 2.7592, | |
| "eval_samples_per_second": 173.599, | |
| "eval_steps_per_second": 1.45, | |
| "step": 157256 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "learning_rate": 2.350066688896299e-05, | |
| "loss": 3.0265, | |
| "step": 159043 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.44469112504856523, | |
| "eval_loss": 3.074544906616211, | |
| "eval_runtime": 2.879, | |
| "eval_samples_per_second": 166.379, | |
| "eval_steps_per_second": 1.389, | |
| "step": 159043 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 2.320273424474825e-05, | |
| "loss": 3.0243, | |
| "step": 160830 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.4443120079831467, | |
| "eval_loss": 3.0942282676696777, | |
| "eval_runtime": 2.7539, | |
| "eval_samples_per_second": 173.935, | |
| "eval_steps_per_second": 1.452, | |
| "step": 160830 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "learning_rate": 2.2904801600533513e-05, | |
| "loss": 3.0222, | |
| "step": 162617 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.4432415712960099, | |
| "eval_loss": 3.0821101665496826, | |
| "eval_runtime": 2.9525, | |
| "eval_samples_per_second": 162.233, | |
| "eval_steps_per_second": 1.355, | |
| "step": 162617 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "learning_rate": 2.2606868956318776e-05, | |
| "loss": 3.021, | |
| "step": 164404 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.4472506123828026, | |
| "eval_loss": 3.0616304874420166, | |
| "eval_runtime": 2.7386, | |
| "eval_samples_per_second": 174.904, | |
| "eval_steps_per_second": 1.461, | |
| "step": 164404 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "learning_rate": 2.2308936312104036e-05, | |
| "loss": 3.0183, | |
| "step": 166191 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.4450408140445041, | |
| "eval_loss": 3.102149724960327, | |
| "eval_runtime": 2.7638, | |
| "eval_samples_per_second": 173.309, | |
| "eval_steps_per_second": 1.447, | |
| "step": 166191 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "learning_rate": 2.2011003667889295e-05, | |
| "loss": 3.0155, | |
| "step": 167978 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.44215097425485717, | |
| "eval_loss": 3.116255283355713, | |
| "eval_runtime": 2.7634, | |
| "eval_samples_per_second": 173.336, | |
| "eval_steps_per_second": 1.447, | |
| "step": 167978 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "learning_rate": 2.171307102367456e-05, | |
| "loss": 3.0132, | |
| "step": 169765 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.4493496925561758, | |
| "eval_loss": 3.0645430088043213, | |
| "eval_runtime": 2.9971, | |
| "eval_samples_per_second": 159.823, | |
| "eval_steps_per_second": 1.335, | |
| "step": 169765 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "learning_rate": 2.1415138379459822e-05, | |
| "loss": 3.0118, | |
| "step": 171552 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.44202857943401513, | |
| "eval_loss": 3.092226982116699, | |
| "eval_runtime": 2.7558, | |
| "eval_samples_per_second": 173.815, | |
| "eval_steps_per_second": 1.451, | |
| "step": 171552 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "learning_rate": 2.111720573524508e-05, | |
| "loss": 3.0105, | |
| "step": 173339 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.4422707131510743, | |
| "eval_loss": 3.118738889694214, | |
| "eval_runtime": 2.8983, | |
| "eval_samples_per_second": 165.268, | |
| "eval_steps_per_second": 1.38, | |
| "step": 173339 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "learning_rate": 2.0819273091030345e-05, | |
| "loss": 3.0063, | |
| "step": 175126 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.44618075143856484, | |
| "eval_loss": 3.1060523986816406, | |
| "eval_runtime": 2.8061, | |
| "eval_samples_per_second": 170.697, | |
| "eval_steps_per_second": 1.425, | |
| "step": 175126 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "learning_rate": 2.0521340446815608e-05, | |
| "loss": 3.0035, | |
| "step": 176913 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.4423852183650616, | |
| "eval_loss": 3.1097826957702637, | |
| "eval_runtime": 3.1412, | |
| "eval_samples_per_second": 152.491, | |
| "eval_steps_per_second": 1.273, | |
| "step": 176913 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 2.0223407802600868e-05, | |
| "loss": 3.0025, | |
| "step": 178700 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.4454137587238285, | |
| "eval_loss": 3.0856051445007324, | |
| "eval_runtime": 2.8018, | |
| "eval_samples_per_second": 170.961, | |
| "eval_steps_per_second": 1.428, | |
| "step": 178700 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "learning_rate": 1.992547515838613e-05, | |
| "loss": 3.0001, | |
| "step": 180487 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_accuracy": 0.4503842392063714, | |
| "eval_loss": 3.0584394931793213, | |
| "eval_runtime": 2.8738, | |
| "eval_samples_per_second": 166.676, | |
| "eval_steps_per_second": 1.392, | |
| "step": 180487 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "learning_rate": 1.962754251417139e-05, | |
| "loss": 2.9979, | |
| "step": 182274 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_accuracy": 0.4435431811165062, | |
| "eval_loss": 3.089740753173828, | |
| "eval_runtime": 3.0249, | |
| "eval_samples_per_second": 158.354, | |
| "eval_steps_per_second": 1.322, | |
| "step": 182274 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "learning_rate": 1.9329609869956654e-05, | |
| "loss": 2.9963, | |
| "step": 184061 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_accuracy": 0.4437190013170062, | |
| "eval_loss": 3.0712223052978516, | |
| "eval_runtime": 2.8272, | |
| "eval_samples_per_second": 169.429, | |
| "eval_steps_per_second": 1.415, | |
| "step": 184061 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "learning_rate": 1.9031677225741914e-05, | |
| "loss": 2.9944, | |
| "step": 185848 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_accuracy": 0.445785838620922, | |
| "eval_loss": 3.085341453552246, | |
| "eval_runtime": 2.8252, | |
| "eval_samples_per_second": 169.547, | |
| "eval_steps_per_second": 1.416, | |
| "step": 185848 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "learning_rate": 1.8733744581527177e-05, | |
| "loss": 2.9931, | |
| "step": 187635 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_accuracy": 0.44751641410643545, | |
| "eval_loss": 3.0809359550476074, | |
| "eval_runtime": 2.5855, | |
| "eval_samples_per_second": 185.266, | |
| "eval_steps_per_second": 1.547, | |
| "step": 187635 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "learning_rate": 1.843581193731244e-05, | |
| "loss": 2.992, | |
| "step": 189422 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_accuracy": 0.44257175014068656, | |
| "eval_loss": 3.0910277366638184, | |
| "eval_runtime": 2.6969, | |
| "eval_samples_per_second": 177.61, | |
| "eval_steps_per_second": 1.483, | |
| "step": 189422 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "learning_rate": 1.81378792930977e-05, | |
| "loss": 2.9886, | |
| "step": 191209 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_accuracy": 0.44900508104118764, | |
| "eval_loss": 3.0693163871765137, | |
| "eval_runtime": 2.7589, | |
| "eval_samples_per_second": 173.62, | |
| "eval_steps_per_second": 1.45, | |
| "step": 191209 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "learning_rate": 1.7839946648882963e-05, | |
| "loss": 2.986, | |
| "step": 192996 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_accuracy": 0.4444630171333055, | |
| "eval_loss": 3.0906262397766113, | |
| "eval_runtime": 3.2348, | |
| "eval_samples_per_second": 148.078, | |
| "eval_steps_per_second": 1.237, | |
| "step": 192996 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "learning_rate": 1.7542014004668223e-05, | |
| "loss": 2.9834, | |
| "step": 194783 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_accuracy": 0.4537605471925546, | |
| "eval_loss": 3.0319700241088867, | |
| "eval_runtime": 3.1336, | |
| "eval_samples_per_second": 152.86, | |
| "eval_steps_per_second": 1.276, | |
| "step": 194783 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "learning_rate": 1.7244081360453486e-05, | |
| "loss": 2.9829, | |
| "step": 196570 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_accuracy": 0.44560168895144264, | |
| "eval_loss": 3.0759708881378174, | |
| "eval_runtime": 2.6847, | |
| "eval_samples_per_second": 178.418, | |
| "eval_steps_per_second": 1.49, | |
| "step": 196570 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "learning_rate": 1.6946148716238746e-05, | |
| "loss": 2.9814, | |
| "step": 198357 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_accuracy": 0.45036670646426746, | |
| "eval_loss": 3.0422720909118652, | |
| "eval_runtime": 2.9828, | |
| "eval_samples_per_second": 160.59, | |
| "eval_steps_per_second": 1.341, | |
| "step": 198357 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "learning_rate": 1.664821607202401e-05, | |
| "loss": 2.9795, | |
| "step": 200144 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_accuracy": 0.452860867371254, | |
| "eval_loss": 3.0410661697387695, | |
| "eval_runtime": 2.9476, | |
| "eval_samples_per_second": 162.504, | |
| "eval_steps_per_second": 1.357, | |
| "step": 200144 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "learning_rate": 1.6350283427809272e-05, | |
| "loss": 2.979, | |
| "step": 201931 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_accuracy": 0.4462770034348653, | |
| "eval_loss": 3.0784435272216797, | |
| "eval_runtime": 3.0447, | |
| "eval_samples_per_second": 157.321, | |
| "eval_steps_per_second": 1.314, | |
| "step": 201931 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "learning_rate": 1.6052350783594532e-05, | |
| "loss": 2.9781, | |
| "step": 203718 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_accuracy": 0.453679165491965, | |
| "eval_loss": 3.0525529384613037, | |
| "eval_runtime": 2.985, | |
| "eval_samples_per_second": 160.472, | |
| "eval_steps_per_second": 1.34, | |
| "step": 203718 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "learning_rate": 1.5754418139379795e-05, | |
| "loss": 2.9751, | |
| "step": 205505 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_accuracy": 0.4512479201331115, | |
| "eval_loss": 3.0478885173797607, | |
| "eval_runtime": 3.2329, | |
| "eval_samples_per_second": 148.165, | |
| "eval_steps_per_second": 1.237, | |
| "step": 205505 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "learning_rate": 1.5456485495165055e-05, | |
| "loss": 2.9749, | |
| "step": 207292 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_accuracy": 0.44932773109243695, | |
| "eval_loss": 3.054450511932373, | |
| "eval_runtime": 2.6607, | |
| "eval_samples_per_second": 180.027, | |
| "eval_steps_per_second": 1.503, | |
| "step": 207292 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "learning_rate": 1.5158552850950317e-05, | |
| "loss": 2.9735, | |
| "step": 209079 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_accuracy": 0.44851187971612105, | |
| "eval_loss": 3.0529181957244873, | |
| "eval_runtime": 2.6442, | |
| "eval_samples_per_second": 181.151, | |
| "eval_steps_per_second": 1.513, | |
| "step": 209079 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "learning_rate": 1.4860620206735578e-05, | |
| "loss": 2.9705, | |
| "step": 210866 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "eval_accuracy": 0.4580500769338369, | |
| "eval_loss": 3.008023977279663, | |
| "eval_runtime": 2.8363, | |
| "eval_samples_per_second": 168.883, | |
| "eval_steps_per_second": 1.41, | |
| "step": 210866 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "learning_rate": 1.4562687562520841e-05, | |
| "loss": 2.9698, | |
| "step": 212653 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "eval_accuracy": 0.4536538892624972, | |
| "eval_loss": 3.0271081924438477, | |
| "eval_runtime": 2.5889, | |
| "eval_samples_per_second": 185.019, | |
| "eval_steps_per_second": 1.545, | |
| "step": 212653 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "learning_rate": 1.4264754918306103e-05, | |
| "loss": 2.9674, | |
| "step": 214440 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_accuracy": 0.4481896208719377, | |
| "eval_loss": 3.0476975440979004, | |
| "eval_runtime": 2.6869, | |
| "eval_samples_per_second": 178.272, | |
| "eval_steps_per_second": 1.489, | |
| "step": 214440 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "learning_rate": 1.3966822274091364e-05, | |
| "loss": 2.9666, | |
| "step": 216227 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "eval_accuracy": 0.45575815202192516, | |
| "eval_loss": 3.032849073410034, | |
| "eval_runtime": 2.9433, | |
| "eval_samples_per_second": 162.744, | |
| "eval_steps_per_second": 1.359, | |
| "step": 216227 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "learning_rate": 1.3668889629876628e-05, | |
| "loss": 2.9664, | |
| "step": 218014 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "eval_accuracy": 0.4462809917355372, | |
| "eval_loss": 3.068892240524292, | |
| "eval_runtime": 2.5675, | |
| "eval_samples_per_second": 186.559, | |
| "eval_steps_per_second": 1.558, | |
| "step": 218014 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "learning_rate": 1.3370956985661887e-05, | |
| "loss": 2.9639, | |
| "step": 219801 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "eval_accuracy": 0.44586561487533455, | |
| "eval_loss": 3.0748960971832275, | |
| "eval_runtime": 2.796, | |
| "eval_samples_per_second": 171.315, | |
| "eval_steps_per_second": 1.431, | |
| "step": 219801 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "learning_rate": 1.3073024341447149e-05, | |
| "loss": 2.9633, | |
| "step": 221588 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "eval_accuracy": 0.4488954922628392, | |
| "eval_loss": 3.0504775047302246, | |
| "eval_runtime": 2.7162, | |
| "eval_samples_per_second": 176.347, | |
| "eval_steps_per_second": 1.473, | |
| "step": 221588 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "learning_rate": 1.277509169723241e-05, | |
| "loss": 2.9618, | |
| "step": 223375 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_accuracy": 0.45345192714951293, | |
| "eval_loss": 3.025569438934326, | |
| "eval_runtime": 2.7094, | |
| "eval_samples_per_second": 176.794, | |
| "eval_steps_per_second": 1.476, | |
| "step": 223375 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "learning_rate": 1.2477159053017674e-05, | |
| "loss": 2.9589, | |
| "step": 225162 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "eval_accuracy": 0.4495620785180625, | |
| "eval_loss": 3.052183151245117, | |
| "eval_runtime": 2.6479, | |
| "eval_samples_per_second": 180.901, | |
| "eval_steps_per_second": 1.511, | |
| "step": 225162 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "learning_rate": 1.2179226408802935e-05, | |
| "loss": 2.9584, | |
| "step": 226949 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "eval_accuracy": 0.45301326453349783, | |
| "eval_loss": 3.0450875759124756, | |
| "eval_runtime": 2.6347, | |
| "eval_samples_per_second": 181.807, | |
| "eval_steps_per_second": 1.518, | |
| "step": 226949 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "learning_rate": 1.1881293764588197e-05, | |
| "loss": 2.9589, | |
| "step": 228736 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "eval_accuracy": 0.4501640457065279, | |
| "eval_loss": 3.065441846847534, | |
| "eval_runtime": 2.6108, | |
| "eval_samples_per_second": 183.467, | |
| "eval_steps_per_second": 1.532, | |
| "step": 228736 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "learning_rate": 1.1583361120373458e-05, | |
| "loss": 2.9581, | |
| "step": 230523 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "eval_accuracy": 0.45803146932307, | |
| "eval_loss": 2.998933792114258, | |
| "eval_runtime": 2.5885, | |
| "eval_samples_per_second": 185.049, | |
| "eval_steps_per_second": 1.545, | |
| "step": 230523 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "learning_rate": 1.128542847615872e-05, | |
| "loss": 2.9554, | |
| "step": 232310 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "eval_accuracy": 0.45082426825165417, | |
| "eval_loss": 3.0346689224243164, | |
| "eval_runtime": 2.6119, | |
| "eval_samples_per_second": 183.394, | |
| "eval_steps_per_second": 1.531, | |
| "step": 232310 | |
| }, | |
| { | |
| "epoch": 131.0, | |
| "learning_rate": 1.0987495831943983e-05, | |
| "loss": 2.9565, | |
| "step": 234097 | |
| }, | |
| { | |
| "epoch": 131.0, | |
| "eval_accuracy": 0.44976425684777727, | |
| "eval_loss": 3.0585811138153076, | |
| "eval_runtime": 2.5925, | |
| "eval_samples_per_second": 184.76, | |
| "eval_steps_per_second": 1.543, | |
| "step": 234097 | |
| }, | |
| { | |
| "epoch": 132.0, | |
| "learning_rate": 1.0689563187729243e-05, | |
| "loss": 2.9548, | |
| "step": 235884 | |
| }, | |
| { | |
| "epoch": 132.0, | |
| "eval_accuracy": 0.4535522171743917, | |
| "eval_loss": 3.016965389251709, | |
| "eval_runtime": 2.5996, | |
| "eval_samples_per_second": 184.261, | |
| "eval_steps_per_second": 1.539, | |
| "step": 235884 | |
| }, | |
| { | |
| "epoch": 133.0, | |
| "learning_rate": 1.0391630543514506e-05, | |
| "loss": 2.9515, | |
| "step": 237671 | |
| }, | |
| { | |
| "epoch": 133.0, | |
| "eval_accuracy": 0.44919200987543484, | |
| "eval_loss": 3.046969175338745, | |
| "eval_runtime": 2.7591, | |
| "eval_samples_per_second": 173.609, | |
| "eval_steps_per_second": 1.45, | |
| "step": 237671 | |
| }, | |
| { | |
| "epoch": 134.0, | |
| "learning_rate": 1.0093697899299767e-05, | |
| "loss": 2.9499, | |
| "step": 239458 | |
| }, | |
| { | |
| "epoch": 134.0, | |
| "eval_accuracy": 0.4514692787177204, | |
| "eval_loss": 3.033890724182129, | |
| "eval_runtime": 2.5902, | |
| "eval_samples_per_second": 184.93, | |
| "eval_steps_per_second": 1.544, | |
| "step": 239458 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "learning_rate": 9.795765255085029e-06, | |
| "loss": 2.9514, | |
| "step": 241245 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "eval_accuracy": 0.44730392156862747, | |
| "eval_loss": 3.047365665435791, | |
| "eval_runtime": 2.5837, | |
| "eval_samples_per_second": 185.39, | |
| "eval_steps_per_second": 1.548, | |
| "step": 241245 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "learning_rate": 9.49783261087029e-06, | |
| "loss": 2.9486, | |
| "step": 243032 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "eval_accuracy": 0.4492987983383054, | |
| "eval_loss": 3.0426554679870605, | |
| "eval_runtime": 2.6436, | |
| "eval_samples_per_second": 181.191, | |
| "eval_steps_per_second": 1.513, | |
| "step": 243032 | |
| }, | |
| { | |
| "epoch": 137.0, | |
| "learning_rate": 9.199899966655552e-06, | |
| "loss": 2.9483, | |
| "step": 244819 | |
| }, | |
| { | |
| "epoch": 137.0, | |
| "eval_accuracy": 0.45336896891264594, | |
| "eval_loss": 3.033630847930908, | |
| "eval_runtime": 2.6114, | |
| "eval_samples_per_second": 183.424, | |
| "eval_steps_per_second": 1.532, | |
| "step": 244819 | |
| }, | |
| { | |
| "epoch": 138.0, | |
| "learning_rate": 8.901967322440815e-06, | |
| "loss": 2.9491, | |
| "step": 246606 | |
| }, | |
| { | |
| "epoch": 138.0, | |
| "eval_accuracy": 0.4516002576092739, | |
| "eval_loss": 3.027387857437134, | |
| "eval_runtime": 2.5975, | |
| "eval_samples_per_second": 184.405, | |
| "eval_steps_per_second": 1.54, | |
| "step": 246606 | |
| }, | |
| { | |
| "epoch": 139.0, | |
| "learning_rate": 8.604034678226076e-06, | |
| "loss": 2.9465, | |
| "step": 248393 | |
| }, | |
| { | |
| "epoch": 139.0, | |
| "eval_accuracy": 0.45385626765882453, | |
| "eval_loss": 3.0354230403900146, | |
| "eval_runtime": 2.5982, | |
| "eval_samples_per_second": 184.359, | |
| "eval_steps_per_second": 1.54, | |
| "step": 248393 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "learning_rate": 8.306102034011338e-06, | |
| "loss": 2.9447, | |
| "step": 250180 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "eval_accuracy": 0.4525785166095551, | |
| "eval_loss": 3.013915538787842, | |
| "eval_runtime": 2.7656, | |
| "eval_samples_per_second": 173.197, | |
| "eval_steps_per_second": 1.446, | |
| "step": 250180 | |
| }, | |
| { | |
| "epoch": 141.0, | |
| "learning_rate": 8.0081693897966e-06, | |
| "loss": 2.9449, | |
| "step": 251967 | |
| }, | |
| { | |
| "epoch": 141.0, | |
| "eval_accuracy": 0.4547931354099374, | |
| "eval_loss": 3.016339063644409, | |
| "eval_runtime": 2.7347, | |
| "eval_samples_per_second": 175.155, | |
| "eval_steps_per_second": 1.463, | |
| "step": 251967 | |
| }, | |
| { | |
| "epoch": 142.0, | |
| "learning_rate": 7.710236745581861e-06, | |
| "loss": 2.9439, | |
| "step": 253754 | |
| }, | |
| { | |
| "epoch": 142.0, | |
| "eval_accuracy": 0.45336875423920414, | |
| "eval_loss": 3.0307540893554688, | |
| "eval_runtime": 2.688, | |
| "eval_samples_per_second": 178.198, | |
| "eval_steps_per_second": 1.488, | |
| "step": 253754 | |
| }, | |
| { | |
| "epoch": 143.0, | |
| "learning_rate": 7.412304101367122e-06, | |
| "loss": 2.9435, | |
| "step": 255541 | |
| }, | |
| { | |
| "epoch": 143.0, | |
| "eval_accuracy": 0.4578975260089811, | |
| "eval_loss": 3.0242276191711426, | |
| "eval_runtime": 2.663, | |
| "eval_samples_per_second": 179.874, | |
| "eval_steps_per_second": 1.502, | |
| "step": 255541 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "learning_rate": 7.114371457152384e-06, | |
| "loss": 2.943, | |
| "step": 257328 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "eval_accuracy": 0.45133795837462837, | |
| "eval_loss": 3.043705463409424, | |
| "eval_runtime": 2.7686, | |
| "eval_samples_per_second": 173.01, | |
| "eval_steps_per_second": 1.445, | |
| "step": 257328 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "learning_rate": 6.816438812937646e-06, | |
| "loss": 2.943, | |
| "step": 259115 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "eval_accuracy": 0.4544336352454434, | |
| "eval_loss": 3.022679328918457, | |
| "eval_runtime": 2.8352, | |
| "eval_samples_per_second": 168.947, | |
| "eval_steps_per_second": 1.411, | |
| "step": 259115 | |
| }, | |
| { | |
| "epoch": 146.0, | |
| "learning_rate": 6.518506168722909e-06, | |
| "loss": 2.9403, | |
| "step": 260902 | |
| }, | |
| { | |
| "epoch": 146.0, | |
| "eval_accuracy": 0.4477586597237944, | |
| "eval_loss": 3.0463666915893555, | |
| "eval_runtime": 2.8089, | |
| "eval_samples_per_second": 170.531, | |
| "eval_steps_per_second": 1.424, | |
| "step": 260902 | |
| }, | |
| { | |
| "epoch": 147.0, | |
| "learning_rate": 6.22057352450817e-06, | |
| "loss": 2.9407, | |
| "step": 262689 | |
| }, | |
| { | |
| "epoch": 147.0, | |
| "eval_accuracy": 0.4465163301412564, | |
| "eval_loss": 3.0717713832855225, | |
| "eval_runtime": 2.6924, | |
| "eval_samples_per_second": 177.907, | |
| "eval_steps_per_second": 1.486, | |
| "step": 262689 | |
| }, | |
| { | |
| "epoch": 148.0, | |
| "learning_rate": 5.922640880293432e-06, | |
| "loss": 2.9397, | |
| "step": 264476 | |
| }, | |
| { | |
| "epoch": 148.0, | |
| "eval_accuracy": 0.4487103426844083, | |
| "eval_loss": 3.0518863201141357, | |
| "eval_runtime": 2.6462, | |
| "eval_samples_per_second": 181.012, | |
| "eval_steps_per_second": 1.512, | |
| "step": 264476 | |
| }, | |
| { | |
| "epoch": 149.0, | |
| "learning_rate": 5.624708236078693e-06, | |
| "loss": 2.9392, | |
| "step": 266263 | |
| }, | |
| { | |
| "epoch": 149.0, | |
| "eval_accuracy": 0.45580133672641854, | |
| "eval_loss": 3.0162956714630127, | |
| "eval_runtime": 2.8146, | |
| "eval_samples_per_second": 170.186, | |
| "eval_steps_per_second": 1.421, | |
| "step": 266263 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "learning_rate": 5.326775591863955e-06, | |
| "loss": 2.9377, | |
| "step": 268050 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "eval_accuracy": 0.45181576114667726, | |
| "eval_loss": 3.015916585922241, | |
| "eval_runtime": 2.7189, | |
| "eval_samples_per_second": 176.176, | |
| "eval_steps_per_second": 1.471, | |
| "step": 268050 | |
| }, | |
| { | |
| "epoch": 151.0, | |
| "learning_rate": 5.028842947649216e-06, | |
| "loss": 2.9386, | |
| "step": 269837 | |
| }, | |
| { | |
| "epoch": 151.0, | |
| "eval_accuracy": 0.45453775343084657, | |
| "eval_loss": 3.0009806156158447, | |
| "eval_runtime": 2.8171, | |
| "eval_samples_per_second": 170.031, | |
| "eval_steps_per_second": 1.42, | |
| "step": 269837 | |
| }, | |
| { | |
| "epoch": 152.0, | |
| "learning_rate": 4.7309103034344784e-06, | |
| "loss": 2.9391, | |
| "step": 271624 | |
| }, | |
| { | |
| "epoch": 152.0, | |
| "eval_accuracy": 0.4530369705973036, | |
| "eval_loss": 3.034574270248413, | |
| "eval_runtime": 2.7339, | |
| "eval_samples_per_second": 175.207, | |
| "eval_steps_per_second": 1.463, | |
| "step": 271624 | |
| }, | |
| { | |
| "epoch": 153.0, | |
| "learning_rate": 4.43297765921974e-06, | |
| "loss": 2.9364, | |
| "step": 273411 | |
| }, | |
| { | |
| "epoch": 153.0, | |
| "eval_accuracy": 0.45406984833727565, | |
| "eval_loss": 3.00394606590271, | |
| "eval_runtime": 2.6952, | |
| "eval_samples_per_second": 177.722, | |
| "eval_steps_per_second": 1.484, | |
| "step": 273411 | |
| }, | |
| { | |
| "epoch": 154.0, | |
| "learning_rate": 4.135045015005002e-06, | |
| "loss": 2.9359, | |
| "step": 275198 | |
| }, | |
| { | |
| "epoch": 154.0, | |
| "eval_accuracy": 0.4519481963203824, | |
| "eval_loss": 3.041689157485962, | |
| "eval_runtime": 2.7367, | |
| "eval_samples_per_second": 175.028, | |
| "eval_steps_per_second": 1.462, | |
| "step": 275198 | |
| }, | |
| { | |
| "epoch": 155.0, | |
| "learning_rate": 3.837112370790264e-06, | |
| "loss": 2.9359, | |
| "step": 276985 | |
| }, | |
| { | |
| "epoch": 155.0, | |
| "eval_accuracy": 0.45435859894132224, | |
| "eval_loss": 3.0161099433898926, | |
| "eval_runtime": 2.74, | |
| "eval_samples_per_second": 174.817, | |
| "eval_steps_per_second": 1.46, | |
| "step": 276985 | |
| }, | |
| { | |
| "epoch": 156.0, | |
| "learning_rate": 3.5391797265755257e-06, | |
| "loss": 2.936, | |
| "step": 278772 | |
| }, | |
| { | |
| "epoch": 156.0, | |
| "eval_accuracy": 0.45336758628392715, | |
| "eval_loss": 3.0168893337249756, | |
| "eval_runtime": 2.8607, | |
| "eval_samples_per_second": 167.443, | |
| "eval_steps_per_second": 1.398, | |
| "step": 278772 | |
| }, | |
| { | |
| "epoch": 157.0, | |
| "learning_rate": 3.241247082360787e-06, | |
| "loss": 2.9329, | |
| "step": 280559 | |
| }, | |
| { | |
| "epoch": 157.0, | |
| "eval_accuracy": 0.4478249866434215, | |
| "eval_loss": 3.059436082839966, | |
| "eval_runtime": 2.856, | |
| "eval_samples_per_second": 167.714, | |
| "eval_steps_per_second": 1.401, | |
| "step": 280559 | |
| }, | |
| { | |
| "epoch": 158.0, | |
| "learning_rate": 2.9433144381460487e-06, | |
| "loss": 2.9336, | |
| "step": 282346 | |
| }, | |
| { | |
| "epoch": 158.0, | |
| "eval_accuracy": 0.45551214066424783, | |
| "eval_loss": 3.0264980792999268, | |
| "eval_runtime": 2.9513, | |
| "eval_samples_per_second": 162.304, | |
| "eval_steps_per_second": 1.355, | |
| "step": 282346 | |
| }, | |
| { | |
| "epoch": 159.0, | |
| "learning_rate": 2.6453817939313106e-06, | |
| "loss": 2.9341, | |
| "step": 284133 | |
| }, | |
| { | |
| "epoch": 159.0, | |
| "eval_accuracy": 0.4542034031560622, | |
| "eval_loss": 3.0276126861572266, | |
| "eval_runtime": 2.8692, | |
| "eval_samples_per_second": 166.946, | |
| "eval_steps_per_second": 1.394, | |
| "step": 284133 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "learning_rate": 2.347449149716572e-06, | |
| "loss": 2.933, | |
| "step": 285920 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "eval_accuracy": 0.4524090960261173, | |
| "eval_loss": 3.032360553741455, | |
| "eval_runtime": 2.7445, | |
| "eval_samples_per_second": 174.528, | |
| "eval_steps_per_second": 1.457, | |
| "step": 285920 | |
| }, | |
| { | |
| "epoch": 161.0, | |
| "learning_rate": 2.049516505501834e-06, | |
| "loss": 2.9325, | |
| "step": 287707 | |
| }, | |
| { | |
| "epoch": 161.0, | |
| "eval_accuracy": 0.4489003880983182, | |
| "eval_loss": 3.024897813796997, | |
| "eval_runtime": 2.949, | |
| "eval_samples_per_second": 162.427, | |
| "eval_steps_per_second": 1.356, | |
| "step": 287707 | |
| }, | |
| { | |
| "epoch": 162.0, | |
| "learning_rate": 1.7515838612870958e-06, | |
| "loss": 2.932, | |
| "step": 289494 | |
| }, | |
| { | |
| "epoch": 162.0, | |
| "eval_accuracy": 0.4518854201633658, | |
| "eval_loss": 3.0444188117980957, | |
| "eval_runtime": 3.2716, | |
| "eval_samples_per_second": 146.412, | |
| "eval_steps_per_second": 1.223, | |
| "step": 289494 | |
| }, | |
| { | |
| "epoch": 163.0, | |
| "learning_rate": 1.4536512170723575e-06, | |
| "loss": 2.9334, | |
| "step": 291281 | |
| }, | |
| { | |
| "epoch": 163.0, | |
| "eval_accuracy": 0.4493931664657903, | |
| "eval_loss": 3.0419514179229736, | |
| "eval_runtime": 3.072, | |
| "eval_samples_per_second": 155.926, | |
| "eval_steps_per_second": 1.302, | |
| "step": 291281 | |
| }, | |
| { | |
| "epoch": 164.0, | |
| "learning_rate": 1.1557185728576192e-06, | |
| "loss": 2.9318, | |
| "step": 293068 | |
| }, | |
| { | |
| "epoch": 164.0, | |
| "eval_accuracy": 0.454113304625021, | |
| "eval_loss": 2.9971697330474854, | |
| "eval_runtime": 3.0501, | |
| "eval_samples_per_second": 157.044, | |
| "eval_steps_per_second": 1.311, | |
| "step": 293068 | |
| }, | |
| { | |
| "epoch": 165.0, | |
| "learning_rate": 8.57785928642881e-07, | |
| "loss": 2.9316, | |
| "step": 294855 | |
| }, | |
| { | |
| "epoch": 165.0, | |
| "eval_accuracy": 0.4525653024759636, | |
| "eval_loss": 2.997295618057251, | |
| "eval_runtime": 2.7549, | |
| "eval_samples_per_second": 173.872, | |
| "eval_steps_per_second": 1.452, | |
| "step": 294855 | |
| }, | |
| { | |
| "epoch": 166.0, | |
| "learning_rate": 5.598532844281427e-07, | |
| "loss": 2.9318, | |
| "step": 296642 | |
| }, | |
| { | |
| "epoch": 166.0, | |
| "eval_accuracy": 0.45290194408968354, | |
| "eval_loss": 3.0388541221618652, | |
| "eval_runtime": 3.0075, | |
| "eval_samples_per_second": 159.266, | |
| "eval_steps_per_second": 1.33, | |
| "step": 296642 | |
| }, | |
| { | |
| "epoch": 167.0, | |
| "learning_rate": 2.619206402134045e-07, | |
| "loss": 2.9301, | |
| "step": 298429 | |
| }, | |
| { | |
| "epoch": 167.0, | |
| "eval_accuracy": 0.4556901408450704, | |
| "eval_loss": 3.013132095336914, | |
| "eval_runtime": 2.9991, | |
| "eval_samples_per_second": 159.713, | |
| "eval_steps_per_second": 1.334, | |
| "step": 298429 | |
| }, | |
| { | |
| "epoch": 167.88, | |
| "learning_rate": 0.0, | |
| "loss": 2.9291, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 167.88, | |
| "eval_accuracy": 0.4548123706727812, | |
| "eval_loss": 3.006730794906616, | |
| "eval_runtime": 3.1035, | |
| "eval_samples_per_second": 154.341, | |
| "eval_steps_per_second": 1.289, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 167.88, | |
| "step": 300000, | |
| "total_flos": 3.687416469441741e+18, | |
| "train_loss": 3.1306004736328124, | |
| "train_runtime": 219827.3924, | |
| "train_samples_per_second": 174.683, | |
| "train_steps_per_second": 1.365 | |
| } | |
| ], | |
| "max_steps": 300000, | |
| "num_train_epochs": 168, | |
| "total_flos": 3.687416469441741e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |