| { | |
| "best_metric": 1.2635489702224731, | |
| "best_model_checkpoint": "data/Llama-31-8B_task-1_120-samples_config-4/checkpoint-137", | |
| "epoch": 32.0, | |
| "eval_steps": 500, | |
| "global_step": 176, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 1.874562382698059, | |
| "learning_rate": 1.3333333333333336e-07, | |
| "loss": 2.2898, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 1.8042479753494263, | |
| "learning_rate": 2.666666666666667e-07, | |
| "loss": 2.0811, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 1.760155200958252, | |
| "learning_rate": 5.333333333333335e-07, | |
| "loss": 2.121, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "eval_loss": 2.101999044418335, | |
| "eval_runtime": 9.6381, | |
| "eval_samples_per_second": 2.49, | |
| "eval_steps_per_second": 2.49, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 1.5958633422851562, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 1.9468, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 1.8069952726364136, | |
| "learning_rate": 1.066666666666667e-06, | |
| "loss": 2.1471, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 1.736191749572754, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 2.0709, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.0930726528167725, | |
| "eval_runtime": 9.6259, | |
| "eval_samples_per_second": 2.493, | |
| "eval_steps_per_second": 2.493, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": 1.6809439659118652, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 2.1306, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.5454545454545454, | |
| "grad_norm": 1.747848391532898, | |
| "learning_rate": 1.8666666666666669e-06, | |
| "loss": 2.0776, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 1.8399686813354492, | |
| "learning_rate": 2.133333333333334e-06, | |
| "loss": 2.0454, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "eval_loss": 2.075482130050659, | |
| "eval_runtime": 9.6366, | |
| "eval_samples_per_second": 2.491, | |
| "eval_steps_per_second": 2.491, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 3.2727272727272725, | |
| "grad_norm": 1.8816026449203491, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 2.1284, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.6363636363636362, | |
| "grad_norm": 1.5757534503936768, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 2.03, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.9466415643692017, | |
| "learning_rate": 2.9333333333333338e-06, | |
| "loss": 2.0502, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.0472075939178467, | |
| "eval_runtime": 9.6277, | |
| "eval_samples_per_second": 2.493, | |
| "eval_steps_per_second": 2.493, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 4.363636363636363, | |
| "grad_norm": 1.6615264415740967, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 2.0197, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.7272727272727275, | |
| "grad_norm": 1.7619231939315796, | |
| "learning_rate": 3.4666666666666672e-06, | |
| "loss": 2.0511, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.909090909090909, | |
| "eval_loss": 2.0100386142730713, | |
| "eval_runtime": 9.6313, | |
| "eval_samples_per_second": 2.492, | |
| "eval_steps_per_second": 2.492, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 5.090909090909091, | |
| "grad_norm": 1.8135912418365479, | |
| "learning_rate": 3.7333333333333337e-06, | |
| "loss": 1.9759, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 5.454545454545454, | |
| "grad_norm": 1.8354995250701904, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.0128, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.818181818181818, | |
| "grad_norm": 1.8015000820159912, | |
| "learning_rate": 4.266666666666668e-06, | |
| "loss": 1.9554, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.9471648931503296, | |
| "eval_runtime": 9.6325, | |
| "eval_samples_per_second": 2.492, | |
| "eval_steps_per_second": 2.492, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 6.181818181818182, | |
| "grad_norm": 1.7802411317825317, | |
| "learning_rate": 4.533333333333334e-06, | |
| "loss": 1.9607, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 6.545454545454545, | |
| "grad_norm": 1.5615451335906982, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.9032, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 6.909090909090909, | |
| "grad_norm": 1.8741137981414795, | |
| "learning_rate": 5.0666666666666676e-06, | |
| "loss": 1.8921, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 6.909090909090909, | |
| "eval_loss": 1.8795281648635864, | |
| "eval_runtime": 9.6403, | |
| "eval_samples_per_second": 2.49, | |
| "eval_steps_per_second": 2.49, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 7.2727272727272725, | |
| "grad_norm": 1.7604111433029175, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 1.8681, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 7.636363636363637, | |
| "grad_norm": 1.6821084022521973, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 1.769, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 1.665964126586914, | |
| "learning_rate": 5.8666666666666675e-06, | |
| "loss": 1.8104, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.7812843322753906, | |
| "eval_runtime": 9.6236, | |
| "eval_samples_per_second": 2.494, | |
| "eval_steps_per_second": 2.494, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 8.363636363636363, | |
| "grad_norm": 1.5216890573501587, | |
| "learning_rate": 6.133333333333334e-06, | |
| "loss": 1.7145, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 8.727272727272727, | |
| "grad_norm": 1.4722410440444946, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 1.7636, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 8.909090909090908, | |
| "eval_loss": 1.6937414407730103, | |
| "eval_runtime": 9.6259, | |
| "eval_samples_per_second": 2.493, | |
| "eval_steps_per_second": 2.493, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 9.090909090909092, | |
| "grad_norm": 1.2136281728744507, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.659, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 9.454545454545455, | |
| "grad_norm": 1.0023685693740845, | |
| "learning_rate": 6.9333333333333344e-06, | |
| "loss": 1.6509, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 9.818181818181818, | |
| "grad_norm": 1.0440162420272827, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 1.6011, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.6141911745071411, | |
| "eval_runtime": 9.6302, | |
| "eval_samples_per_second": 2.492, | |
| "eval_steps_per_second": 2.492, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 10.181818181818182, | |
| "grad_norm": 0.7877157926559448, | |
| "learning_rate": 7.4666666666666675e-06, | |
| "loss": 1.5814, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 10.545454545454545, | |
| "grad_norm": 0.6534942984580994, | |
| "learning_rate": 7.733333333333334e-06, | |
| "loss": 1.5824, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 10.909090909090908, | |
| "grad_norm": 0.6240991950035095, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.5128, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.909090909090908, | |
| "eval_loss": 1.5751093626022339, | |
| "eval_runtime": 9.6475, | |
| "eval_samples_per_second": 2.488, | |
| "eval_steps_per_second": 2.488, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 11.272727272727273, | |
| "grad_norm": 0.6224139928817749, | |
| "learning_rate": 8.266666666666667e-06, | |
| "loss": 1.5444, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 11.636363636363637, | |
| "grad_norm": 0.6345284581184387, | |
| "learning_rate": 8.533333333333335e-06, | |
| "loss": 1.5682, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.5680299997329712, | |
| "learning_rate": 8.8e-06, | |
| "loss": 1.4277, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.5352739095687866, | |
| "eval_runtime": 9.6312, | |
| "eval_samples_per_second": 2.492, | |
| "eval_steps_per_second": 2.492, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 12.363636363636363, | |
| "grad_norm": 0.5991209745407104, | |
| "learning_rate": 9.066666666666667e-06, | |
| "loss": 1.4703, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 12.727272727272727, | |
| "grad_norm": 0.5993205308914185, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 1.4998, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 12.909090909090908, | |
| "eval_loss": 1.5001062154769897, | |
| "eval_runtime": 9.6248, | |
| "eval_samples_per_second": 2.494, | |
| "eval_steps_per_second": 2.494, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 13.090909090909092, | |
| "grad_norm": 0.5633314251899719, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.445, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 13.454545454545455, | |
| "grad_norm": 0.5419648885726929, | |
| "learning_rate": 9.866666666666668e-06, | |
| "loss": 1.4256, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 13.818181818181818, | |
| "grad_norm": 0.5384172201156616, | |
| "learning_rate": 9.999945845889795e-06, | |
| "loss": 1.4154, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.4582971334457397, | |
| "eval_runtime": 9.6218, | |
| "eval_samples_per_second": 2.494, | |
| "eval_steps_per_second": 2.494, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 14.181818181818182, | |
| "grad_norm": 0.6161755323410034, | |
| "learning_rate": 9.999512620046523e-06, | |
| "loss": 1.4459, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 14.545454545454545, | |
| "grad_norm": 0.5570430159568787, | |
| "learning_rate": 9.99864620589731e-06, | |
| "loss": 1.3661, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 14.909090909090908, | |
| "grad_norm": 0.5637471675872803, | |
| "learning_rate": 9.99734667851357e-06, | |
| "loss": 1.4201, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 14.909090909090908, | |
| "eval_loss": 1.4252301454544067, | |
| "eval_runtime": 9.6319, | |
| "eval_samples_per_second": 2.492, | |
| "eval_steps_per_second": 2.492, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 15.272727272727273, | |
| "grad_norm": 0.5539014935493469, | |
| "learning_rate": 9.995614150494293e-06, | |
| "loss": 1.3497, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 15.636363636363637, | |
| "grad_norm": 0.5583813786506653, | |
| "learning_rate": 9.993448771956285e-06, | |
| "loss": 1.3512, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 0.5377728939056396, | |
| "learning_rate": 9.99085073052117e-06, | |
| "loss": 1.3364, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.3921159505844116, | |
| "eval_runtime": 9.635, | |
| "eval_samples_per_second": 2.491, | |
| "eval_steps_per_second": 2.491, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 16.363636363636363, | |
| "grad_norm": 0.5390649437904358, | |
| "learning_rate": 9.987820251299121e-06, | |
| "loss": 1.3614, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 16.727272727272727, | |
| "grad_norm": 0.5126790404319763, | |
| "learning_rate": 9.984357596869369e-06, | |
| "loss": 1.2762, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 16.90909090909091, | |
| "eval_loss": 1.3691315650939941, | |
| "eval_runtime": 9.6319, | |
| "eval_samples_per_second": 2.492, | |
| "eval_steps_per_second": 2.492, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 17.09090909090909, | |
| "grad_norm": 0.5642189383506775, | |
| "learning_rate": 9.980463067257437e-06, | |
| "loss": 1.2961, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 17.454545454545453, | |
| "grad_norm": 0.5290245413780212, | |
| "learning_rate": 9.976136999909156e-06, | |
| "loss": 1.1987, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 17.818181818181817, | |
| "grad_norm": 0.5963008403778076, | |
| "learning_rate": 9.971379769661422e-06, | |
| "loss": 1.2851, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.3436861038208008, | |
| "eval_runtime": 9.6214, | |
| "eval_samples_per_second": 2.494, | |
| "eval_steps_per_second": 2.494, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 18.181818181818183, | |
| "grad_norm": 0.5820615291595459, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 1.329, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 18.545454545454547, | |
| "grad_norm": 0.5619508624076843, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 1.2428, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 18.90909090909091, | |
| "grad_norm": 0.5272645950317383, | |
| "learning_rate": 9.95452541005172e-06, | |
| "loss": 1.2239, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 18.90909090909091, | |
| "eval_loss": 1.3261139392852783, | |
| "eval_runtime": 9.6475, | |
| "eval_samples_per_second": 2.488, | |
| "eval_steps_per_second": 2.488, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 19.272727272727273, | |
| "grad_norm": 0.5720901489257812, | |
| "learning_rate": 9.948048023191728e-06, | |
| "loss": 1.1753, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 19.636363636363637, | |
| "grad_norm": 0.5877869725227356, | |
| "learning_rate": 9.941141907232766e-06, | |
| "loss": 1.2334, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.5674625039100647, | |
| "learning_rate": 9.933807660562898e-06, | |
| "loss": 1.221, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.308407187461853, | |
| "eval_runtime": 9.6226, | |
| "eval_samples_per_second": 2.494, | |
| "eval_steps_per_second": 2.494, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 20.363636363636363, | |
| "grad_norm": 0.5934170484542847, | |
| "learning_rate": 9.926045918666045e-06, | |
| "loss": 1.1685, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 20.727272727272727, | |
| "grad_norm": 0.6199212670326233, | |
| "learning_rate": 9.91785735406693e-06, | |
| "loss": 1.2011, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 20.90909090909091, | |
| "eval_loss": 1.2950953245162964, | |
| "eval_runtime": 9.6285, | |
| "eval_samples_per_second": 2.493, | |
| "eval_steps_per_second": 2.493, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 21.09090909090909, | |
| "grad_norm": 0.5995011329650879, | |
| "learning_rate": 9.909242676272797e-06, | |
| "loss": 1.1717, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 21.454545454545453, | |
| "grad_norm": 0.6024748682975769, | |
| "learning_rate": 9.90020263171194e-06, | |
| "loss": 1.1654, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 21.818181818181817, | |
| "grad_norm": 0.6147428750991821, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 1.1433, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 1.2823587656021118, | |
| "eval_runtime": 9.6228, | |
| "eval_samples_per_second": 2.494, | |
| "eval_steps_per_second": 2.494, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 22.181818181818183, | |
| "grad_norm": 0.612140953540802, | |
| "learning_rate": 9.880849612217238e-06, | |
| "loss": 1.0765, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 22.545454545454547, | |
| "grad_norm": 0.647298276424408, | |
| "learning_rate": 9.870538314147194e-06, | |
| "loss": 1.1183, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 22.90909090909091, | |
| "grad_norm": 0.6705971360206604, | |
| "learning_rate": 9.859805002892733e-06, | |
| "loss": 1.1579, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 22.90909090909091, | |
| "eval_loss": 1.2746213674545288, | |
| "eval_runtime": 9.6328, | |
| "eval_samples_per_second": 2.491, | |
| "eval_steps_per_second": 2.491, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 23.272727272727273, | |
| "grad_norm": 0.670023500919342, | |
| "learning_rate": 9.84865060845349e-06, | |
| "loss": 1.0965, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 23.636363636363637, | |
| "grad_norm": 0.6824691891670227, | |
| "learning_rate": 9.83707609731432e-06, | |
| "loss": 1.061, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 0.6598721146583557, | |
| "learning_rate": 9.825082472361558e-06, | |
| "loss": 1.0871, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 1.268039345741272, | |
| "eval_runtime": 9.6219, | |
| "eval_samples_per_second": 2.494, | |
| "eval_steps_per_second": 2.494, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 24.363636363636363, | |
| "grad_norm": 0.6824683547019958, | |
| "learning_rate": 9.812670772796113e-06, | |
| "loss": 1.0733, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 24.727272727272727, | |
| "grad_norm": 0.7309969663619995, | |
| "learning_rate": 9.799842074043438e-06, | |
| "loss": 1.0745, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 24.90909090909091, | |
| "eval_loss": 1.2635489702224731, | |
| "eval_runtime": 9.6334, | |
| "eval_samples_per_second": 2.491, | |
| "eval_steps_per_second": 2.491, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 25.09090909090909, | |
| "grad_norm": 0.8717047572135925, | |
| "learning_rate": 9.786597487660336e-06, | |
| "loss": 1.0049, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 25.454545454545453, | |
| "grad_norm": 0.7290262579917908, | |
| "learning_rate": 9.77293816123866e-06, | |
| "loss": 1.0355, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 25.818181818181817, | |
| "grad_norm": 0.8125291466712952, | |
| "learning_rate": 9.75886527830587e-06, | |
| "loss": 1.0006, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 1.2674241065979004, | |
| "eval_runtime": 9.6242, | |
| "eval_samples_per_second": 2.494, | |
| "eval_steps_per_second": 2.494, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 26.181818181818183, | |
| "grad_norm": 0.777037501335144, | |
| "learning_rate": 9.744380058222483e-06, | |
| "loss": 1.0235, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 26.545454545454547, | |
| "grad_norm": 0.7910988330841064, | |
| "learning_rate": 9.729483756076436e-06, | |
| "loss": 1.0119, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 26.90909090909091, | |
| "grad_norm": 0.8250744342803955, | |
| "learning_rate": 9.714177662574316e-06, | |
| "loss": 0.9628, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 26.90909090909091, | |
| "eval_loss": 1.2688733339309692, | |
| "eval_runtime": 9.6388, | |
| "eval_samples_per_second": 2.49, | |
| "eval_steps_per_second": 2.49, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 27.272727272727273, | |
| "grad_norm": 0.9542063474655151, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.9176, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 27.636363636363637, | |
| "grad_norm": 0.8577086925506592, | |
| "learning_rate": 9.682341441747446e-06, | |
| "loss": 0.9908, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "grad_norm": 0.8569504022598267, | |
| "learning_rate": 9.665814072907293e-06, | |
| "loss": 0.9237, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 1.2716994285583496, | |
| "eval_runtime": 9.6271, | |
| "eval_samples_per_second": 2.493, | |
| "eval_steps_per_second": 2.493, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 28.363636363636363, | |
| "grad_norm": 0.933702826499939, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 0.9053, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 28.727272727272727, | |
| "grad_norm": 1.002100944519043, | |
| "learning_rate": 9.63154797841033e-06, | |
| "loss": 0.8824, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 28.90909090909091, | |
| "eval_loss": 1.2879880666732788, | |
| "eval_runtime": 9.6501, | |
| "eval_samples_per_second": 2.487, | |
| "eval_steps_per_second": 2.487, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 29.09090909090909, | |
| "grad_norm": 0.9883065819740295, | |
| "learning_rate": 9.613812221777212e-06, | |
| "loss": 0.9089, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 29.454545454545453, | |
| "grad_norm": 1.0561895370483398, | |
| "learning_rate": 9.595676696276173e-06, | |
| "loss": 0.9285, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 29.818181818181817, | |
| "grad_norm": 1.1776067018508911, | |
| "learning_rate": 9.577142973279896e-06, | |
| "loss": 0.8706, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 1.296054482460022, | |
| "eval_runtime": 9.6279, | |
| "eval_samples_per_second": 2.493, | |
| "eval_steps_per_second": 2.493, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 30.181818181818183, | |
| "grad_norm": 1.0879513025283813, | |
| "learning_rate": 9.55821265866333e-06, | |
| "loss": 0.7961, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 30.545454545454547, | |
| "grad_norm": 1.1668307781219482, | |
| "learning_rate": 9.538887392664544e-06, | |
| "loss": 0.7865, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 30.90909090909091, | |
| "grad_norm": 1.065364956855774, | |
| "learning_rate": 9.519168849742603e-06, | |
| "loss": 0.8328, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 30.90909090909091, | |
| "eval_loss": 1.326621174812317, | |
| "eval_runtime": 9.6286, | |
| "eval_samples_per_second": 2.493, | |
| "eval_steps_per_second": 2.493, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 31.272727272727273, | |
| "grad_norm": 1.143373727798462, | |
| "learning_rate": 9.499058738432492e-06, | |
| "loss": 0.8381, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 31.636363636363637, | |
| "grad_norm": 1.1452257633209229, | |
| "learning_rate": 9.478558801197065e-06, | |
| "loss": 0.7725, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "grad_norm": 1.2163513898849487, | |
| "learning_rate": 9.457670814276083e-06, | |
| "loss": 0.7667, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 1.344734787940979, | |
| "eval_runtime": 9.6252, | |
| "eval_samples_per_second": 2.493, | |
| "eval_steps_per_second": 2.493, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "step": 176, | |
| "total_flos": 4.322507713465549e+16, | |
| "train_loss": 1.4077397015961735, | |
| "train_runtime": 3298.1261, | |
| "train_samples_per_second": 4.002, | |
| "train_steps_per_second": 0.227 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 750, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 150, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 7, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.322507713465549e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |