| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9916434540389972, | |
| "eval_steps": 5, | |
| "global_step": 89, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 1.5038223266601562, | |
| "eval_runtime": 44.7062, | |
| "eval_samples_per_second": 6.822, | |
| "eval_steps_per_second": 3.422, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4e-05, | |
| "loss": 1.491, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4859, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8e-05, | |
| "loss": 1.4147, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3662, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.4103038311004639, | |
| "eval_runtime": 44.789, | |
| "eval_samples_per_second": 6.81, | |
| "eval_steps_per_second": 3.416, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3399, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00014, | |
| "loss": 1.346, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3327, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3466, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1836, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.3055061101913452, | |
| "eval_runtime": 44.7824, | |
| "eval_samples_per_second": 6.811, | |
| "eval_steps_per_second": 3.417, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019992093972273018, | |
| "loss": 1.3094, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001996838839014696, | |
| "loss": 1.3395, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019928920737019733, | |
| "loss": 1.2689, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019873753419363336, | |
| "loss": 1.2584, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00019802973668046363, | |
| "loss": 1.2761, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.2809727191925049, | |
| "eval_runtime": 44.7653, | |
| "eval_samples_per_second": 6.813, | |
| "eval_steps_per_second": 3.418, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.000197166934004041, | |
| "loss": 1.2508, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019615049043274205, | |
| "loss": 1.151, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019498201317277828, | |
| "loss": 1.2186, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001936633498268728, | |
| "loss": 1.2416, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00019219658547282067, | |
| "loss": 1.1779, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.2696019411087036, | |
| "eval_runtime": 44.7761, | |
| "eval_samples_per_second": 6.812, | |
| "eval_steps_per_second": 3.417, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00019058403936655233, | |
| "loss": 1.2289, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001888282612749132, | |
| "loss": 1.2383, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00018693202744395827, | |
| "loss": 1.2303, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00018489833620913642, | |
| "loss": 1.0146, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00018273040325430574, | |
| "loss": 1.1242, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.264197587966919, | |
| "eval_runtime": 44.7709, | |
| "eval_samples_per_second": 6.812, | |
| "eval_steps_per_second": 3.417, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00018043165652707649, | |
| "loss": 1.1922, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00017800573081852122, | |
| "loss": 1.2137, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00017545646201582303, | |
| "loss": 1.2167, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00017278788103694943, | |
| "loss": 1.2603, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00017000420745694254, | |
| "loss": 1.2414, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.2588073015213013, | |
| "eval_runtime": 44.7874, | |
| "eval_samples_per_second": 6.81, | |
| "eval_steps_per_second": 3.416, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001671098428359037, | |
| "loss": 1.187, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.000164109363759222, | |
| "loss": 1.165, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00016100751460105243, | |
| "loss": 1.1853, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00015780920002248484, | |
| "loss": 1.0538, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00015451947721626676, | |
| "loss": 1.1382, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.2555344104766846, | |
| "eval_runtime": 44.7839, | |
| "eval_samples_per_second": 6.81, | |
| "eval_steps_per_second": 3.416, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00015114354791034225, | |
| "loss": 1.1604, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00014768675014285062, | |
| "loss": 1.1631, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0001441545498215912, | |
| "loss": 1.2075, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00014055253208129938, | |
| "loss": 1.1602, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00013688639245240078, | |
| "loss": 1.2094, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.2520103454589844, | |
| "eval_runtime": 44.7798, | |
| "eval_samples_per_second": 6.811, | |
| "eval_steps_per_second": 3.417, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001331619278552068, | |
| "loss": 1.1457, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00012938502743379212, | |
| "loss": 1.0895, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0001255616632440475, | |
| "loss": 1.0843, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001216978808106318, | |
| "loss": 1.1428, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00011779978956775506, | |
| "loss": 1.1049, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.2504087686538696, | |
| "eval_runtime": 44.7786, | |
| "eval_samples_per_second": 6.811, | |
| "eval_steps_per_second": 3.417, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00011387355319890685, | |
| "loss": 1.0035, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00010992537989080618, | |
| "loss": 1.1693, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00010596151251698199, | |
| "loss": 1.0852, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00010198821876650701, | |
| "loss": 1.0954, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.801178123349298e-05, | |
| "loss": 1.1709, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.2487094402313232, | |
| "eval_runtime": 44.7848, | |
| "eval_samples_per_second": 6.81, | |
| "eval_steps_per_second": 3.416, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.403848748301802e-05, | |
| "loss": 1.1668, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.007462010919386e-05, | |
| "loss": 1.1643, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.612644680109319e-05, | |
| "loss": 1.1938, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.2200210432245e-05, | |
| "loss": 1.1062, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.83021191893682e-05, | |
| "loss": 1.0981, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.2463428974151611, | |
| "eval_runtime": 44.7606, | |
| "eval_samples_per_second": 6.814, | |
| "eval_steps_per_second": 3.418, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.443833675595255e-05, | |
| "loss": 1.1809, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.061497256620793e-05, | |
| "loss": 1.1515, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 6.683807214479323e-05, | |
| "loss": 1.1226, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 6.311360754759923e-05, | |
| "loss": 1.1952, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.9447467918700614e-05, | |
| "loss": 1.1902, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.2446388006210327, | |
| "eval_runtime": 44.7804, | |
| "eval_samples_per_second": 6.811, | |
| "eval_steps_per_second": 3.417, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 5.584545017840885e-05, | |
| "loss": 1.1506, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5.2313249857149414e-05, | |
| "loss": 1.1505, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.885645208965779e-05, | |
| "loss": 1.1414, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.548052278373327e-05, | |
| "loss": 1.2361, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.219079997751515e-05, | |
| "loss": 1.1526, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.244616150856018, | |
| "eval_runtime": 44.7366, | |
| "eval_samples_per_second": 6.818, | |
| "eval_steps_per_second": 3.42, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.899248539894757e-05, | |
| "loss": 1.1942, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.589063624077802e-05, | |
| "loss": 1.1018, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.289015716409631e-05, | |
| "loss": 1.2284, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.9995792543057478e-05, | |
| "loss": 1.1665, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.7212118963050592e-05, | |
| "loss": 1.1319, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.2439743280410767, | |
| "eval_runtime": 44.7492, | |
| "eval_samples_per_second": 6.816, | |
| "eval_steps_per_second": 3.419, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.4543537984176978e-05, | |
| "loss": 1.067, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.19942691814788e-05, | |
| "loss": 1.1465, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.9568343472923524e-05, | |
| "loss": 1.227, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.7269596745694295e-05, | |
| "loss": 1.1989, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.5101663790863596e-05, | |
| "loss": 1.1913, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.2430416345596313, | |
| "eval_runtime": 44.7589, | |
| "eval_samples_per_second": 6.814, | |
| "eval_steps_per_second": 3.418, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.3067972556041752e-05, | |
| "loss": 1.154, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.1171738725086833e-05, | |
| "loss": 1.055, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.415960633447674e-06, | |
| "loss": 1.1523, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 7.803414527179343e-06, | |
| "loss": 1.1057, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.336650173127223e-06, | |
| "loss": 1.1875, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.2423635721206665, | |
| "eval_runtime": 44.7706, | |
| "eval_samples_per_second": 6.813, | |
| "eval_steps_per_second": 3.417, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.017986827221733e-06, | |
| "loss": 1.2235, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.849509567257959e-06, | |
| "loss": 1.1457, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.8330659959589946e-06, | |
| "loss": 1.1552, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.9702633195363917e-06, | |
| "loss": 1.1497, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.2624658063666639e-06, | |
| "loss": 1.1454, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.2422702312469482, | |
| "eval_runtime": 44.7707, | |
| "eval_samples_per_second": 6.812, | |
| "eval_steps_per_second": 3.417, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.10792629802659e-07, | |
| "loss": 1.2008, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.161160985304168e-07, | |
| "loss": 1.15, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.906027726981568e-08, | |
| "loss": 1.2256, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0, | |
| "loss": 1.2861, | |
| "step": 89 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 89, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 2.5178194955363942e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |