| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06291899179806, | |
| "eval_steps": 42, | |
| "global_step": 420, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014980712332871428, | |
| "eval_loss": 1.160882592201233, | |
| "eval_runtime": 311.16, | |
| "eval_samples_per_second": 36.133, | |
| "eval_steps_per_second": 4.519, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00044942136998614283, | |
| "grad_norm": 0.12129199504852295, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.1193, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008988427399722857, | |
| "grad_norm": 0.11971050500869751, | |
| "learning_rate": 3e-05, | |
| "loss": 1.103, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013482641099584285, | |
| "grad_norm": 0.10862895101308823, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.0659, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017976854799445713, | |
| "grad_norm": 0.11977853626012802, | |
| "learning_rate": 4.9997944716957985e-05, | |
| "loss": 1.0914, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0022471068499307144, | |
| "grad_norm": 0.12554779648780823, | |
| "learning_rate": 4.99871554050172e-05, | |
| "loss": 1.1725, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002696528219916857, | |
| "grad_norm": 0.13287784159183502, | |
| "learning_rate": 4.996712222958461e-05, | |
| "loss": 1.1145, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003145949589903, | |
| "grad_norm": 0.1167389452457428, | |
| "learning_rate": 4.993785260182552e-05, | |
| "loss": 1.0956, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0035953709598891426, | |
| "grad_norm": 0.11548212915658951, | |
| "learning_rate": 4.989935734988098e-05, | |
| "loss": 1.12, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004044792329875285, | |
| "grad_norm": 0.12251826375722885, | |
| "learning_rate": 4.9851650714862006e-05, | |
| "loss": 1.0895, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004494213699861429, | |
| "grad_norm": 0.12304849177598953, | |
| "learning_rate": 4.979475034558115e-05, | |
| "loss": 1.1302, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004943635069847571, | |
| "grad_norm": 0.12594439089298248, | |
| "learning_rate": 4.9728677292023405e-05, | |
| "loss": 1.0825, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005393056439833714, | |
| "grad_norm": 0.11802031844854355, | |
| "learning_rate": 4.965345599755887e-05, | |
| "loss": 1.0949, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005842477809819857, | |
| "grad_norm": 0.12052260339260101, | |
| "learning_rate": 4.95691142899001e-05, | |
| "loss": 1.2106, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006291899179806, | |
| "grad_norm": 0.14151117205619812, | |
| "learning_rate": 4.9475683370807326e-05, | |
| "loss": 1.0855, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006291899179806, | |
| "eval_loss": 1.1297273635864258, | |
| "eval_runtime": 313.2801, | |
| "eval_samples_per_second": 35.888, | |
| "eval_steps_per_second": 4.488, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006741320549792143, | |
| "grad_norm": 0.13759616017341614, | |
| "learning_rate": 4.937319780454559e-05, | |
| "loss": 1.1133, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007190741919778285, | |
| "grad_norm": 0.14887671172618866, | |
| "learning_rate": 4.926169550509787e-05, | |
| "loss": 1.1339, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007640163289764428, | |
| "grad_norm": 0.13235358893871307, | |
| "learning_rate": 4.914121772213898e-05, | |
| "loss": 1.0057, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.00808958465975057, | |
| "grad_norm": 0.14951473474502563, | |
| "learning_rate": 4.9011809025775486e-05, | |
| "loss": 1.0919, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.008539006029736713, | |
| "grad_norm": 0.1409119963645935, | |
| "learning_rate": 4.887351729005726e-05, | |
| "loss": 1.143, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.008988427399722857, | |
| "grad_norm": 0.13198496401309967, | |
| "learning_rate": 4.8726393675266716e-05, | |
| "loss": 1.0853, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009437848769709, | |
| "grad_norm": 0.15319645404815674, | |
| "learning_rate": 4.8570492608992325e-05, | |
| "loss": 1.0534, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.009887270139695143, | |
| "grad_norm": 0.1532219797372818, | |
| "learning_rate": 4.8405871765993433e-05, | |
| "loss": 1.1016, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.010336691509681285, | |
| "grad_norm": 0.14198264479637146, | |
| "learning_rate": 4.82325920468638e-05, | |
| "loss": 1.029, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.010786112879667428, | |
| "grad_norm": 0.12415461987257004, | |
| "learning_rate": 4.805071755550177e-05, | |
| "loss": 1.1565, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.01123553424965357, | |
| "grad_norm": 0.1350441873073578, | |
| "learning_rate": 4.7860315575395316e-05, | |
| "loss": 1.1276, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.011684955619639713, | |
| "grad_norm": 0.12075574696063995, | |
| "learning_rate": 4.766145654473095e-05, | |
| "loss": 1.0753, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.012134376989625857, | |
| "grad_norm": 0.11550460755825043, | |
| "learning_rate": 4.745421403033548e-05, | |
| "loss": 1.0078, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.012583798359612, | |
| "grad_norm": 0.12455905228853226, | |
| "learning_rate": 4.72386647004603e-05, | |
| "loss": 1.0373, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.012583798359612, | |
| "eval_loss": 1.1157194375991821, | |
| "eval_runtime": 312.8234, | |
| "eval_samples_per_second": 35.94, | |
| "eval_steps_per_second": 4.495, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.013033219729598143, | |
| "grad_norm": 0.12993893027305603, | |
| "learning_rate": 4.701488829641845e-05, | |
| "loss": 1.1313, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.013482641099584285, | |
| "grad_norm": 0.18705669045448303, | |
| "learning_rate": 4.678296760308474e-05, | |
| "loss": 1.2752, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.013932062469570428, | |
| "grad_norm": 0.14135660231113434, | |
| "learning_rate": 4.6542988418269876e-05, | |
| "loss": 1.1628, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.01438148383955657, | |
| "grad_norm": 0.11707276850938797, | |
| "learning_rate": 4.629503952098011e-05, | |
| "loss": 1.0801, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.014830905209542713, | |
| "grad_norm": 0.14167702198028564, | |
| "learning_rate": 4.6039212638573833e-05, | |
| "loss": 1.0452, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.015280326579528856, | |
| "grad_norm": 0.15983764827251434, | |
| "learning_rate": 4.5775602412827604e-05, | |
| "loss": 1.1844, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.015729747949515, | |
| "grad_norm": 0.12750358879566193, | |
| "learning_rate": 4.55043063649239e-05, | |
| "loss": 1.0877, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.01617916931950114, | |
| "grad_norm": 0.1487520933151245, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 1.1373, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.016628590689487285, | |
| "grad_norm": 0.16089919209480286, | |
| "learning_rate": 4.493906106688712e-05, | |
| "loss": 1.1806, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.017078012059473426, | |
| "grad_norm": 0.158865287899971, | |
| "learning_rate": 4.4645320926206064e-05, | |
| "loss": 1.0689, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.01752743342945957, | |
| "grad_norm": 0.16464003920555115, | |
| "learning_rate": 4.434431310491267e-05, | |
| "loss": 1.1319, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.017976854799445715, | |
| "grad_norm": 0.12468679249286652, | |
| "learning_rate": 4.4036148959228365e-05, | |
| "loss": 1.0237, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.018426276169431856, | |
| "grad_norm": 0.14475342631340027, | |
| "learning_rate": 4.372094249281821e-05, | |
| "loss": 1.1352, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.018875697539418, | |
| "grad_norm": 0.1386341154575348, | |
| "learning_rate": 4.3398810314615876e-05, | |
| "loss": 1.177, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.018875697539418, | |
| "eval_loss": 1.1068843603134155, | |
| "eval_runtime": 312.5635, | |
| "eval_samples_per_second": 35.97, | |
| "eval_steps_per_second": 4.498, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.01932511890940414, | |
| "grad_norm": 0.13838274776935577, | |
| "learning_rate": 4.306987159568479e-05, | |
| "loss": 0.9996, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.019774540279390285, | |
| "grad_norm": 0.14386090636253357, | |
| "learning_rate": 4.273424802513145e-05, | |
| "loss": 0.9947, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.020223961649376426, | |
| "grad_norm": 0.14473505318164825, | |
| "learning_rate": 4.239206376508717e-05, | |
| "loss": 1.1779, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.02067338301936257, | |
| "grad_norm": 0.15975573658943176, | |
| "learning_rate": 4.204344540477499e-05, | |
| "loss": 1.2125, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.021122804389348715, | |
| "grad_norm": 0.12576735019683838, | |
| "learning_rate": 4.16885219136787e-05, | |
| "loss": 1.1312, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.021572225759334856, | |
| "grad_norm": 0.16916967928409576, | |
| "learning_rate": 4.132742459383122e-05, | |
| "loss": 1.0823, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.022021647129321, | |
| "grad_norm": 0.17954471707344055, | |
| "learning_rate": 4.096028703124014e-05, | |
| "loss": 1.0728, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.02247106849930714, | |
| "grad_norm": 0.11972087621688843, | |
| "learning_rate": 4.058724504646834e-05, | |
| "loss": 1.0886, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.022920489869293285, | |
| "grad_norm": 0.14640676975250244, | |
| "learning_rate": 4.0208436644387834e-05, | |
| "loss": 1.0472, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.023369911239279426, | |
| "grad_norm": 0.13775284588336945, | |
| "learning_rate": 3.982400196312564e-05, | |
| "loss": 1.0984, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.02381933260926557, | |
| "grad_norm": 0.14184071123600006, | |
| "learning_rate": 3.943408322222049e-05, | |
| "loss": 1.1431, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.024268753979251715, | |
| "grad_norm": 0.1685701608657837, | |
| "learning_rate": 3.903882467000937e-05, | |
| "loss": 1.1531, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.024718175349237856, | |
| "grad_norm": 0.1468999981880188, | |
| "learning_rate": 3.8638372530263715e-05, | |
| "loss": 1.1069, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.025167596719224, | |
| "grad_norm": 0.13278649747371674, | |
| "learning_rate": 3.823287494809469e-05, | |
| "loss": 1.1124, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.025167596719224, | |
| "eval_loss": 1.1012423038482666, | |
| "eval_runtime": 312.1008, | |
| "eval_samples_per_second": 36.024, | |
| "eval_steps_per_second": 4.505, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.02561701808921014, | |
| "grad_norm": 0.180728018283844, | |
| "learning_rate": 3.782248193514766e-05, | |
| "loss": 1.0867, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.026066439459196285, | |
| "grad_norm": 0.15069565176963806, | |
| "learning_rate": 3.740734531410626e-05, | |
| "loss": 1.0624, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.026515860829182426, | |
| "grad_norm": 0.13892242312431335, | |
| "learning_rate": 3.698761866252635e-05, | |
| "loss": 1.0351, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.02696528219916857, | |
| "grad_norm": 0.1399199515581131, | |
| "learning_rate": 3.656345725602089e-05, | |
| "loss": 1.1609, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.027414703569154715, | |
| "grad_norm": 0.14930486679077148, | |
| "learning_rate": 3.6135018010816477e-05, | |
| "loss": 1.1117, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.027864124939140856, | |
| "grad_norm": 0.15556196868419647, | |
| "learning_rate": 3.570245942570315e-05, | |
| "loss": 1.1169, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.028313546309127, | |
| "grad_norm": 0.17272590100765228, | |
| "learning_rate": 3.526594152339845e-05, | |
| "loss": 1.115, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.02876296767911314, | |
| "grad_norm": 0.17533355951309204, | |
| "learning_rate": 3.4825625791348096e-05, | |
| "loss": 1.1298, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.029212389049099285, | |
| "grad_norm": 0.14778710901737213, | |
| "learning_rate": 3.438167512198436e-05, | |
| "loss": 1.1183, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.029661810419085426, | |
| "grad_norm": 0.14693984389305115, | |
| "learning_rate": 3.393425375246503e-05, | |
| "loss": 1.0647, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.03011123178907157, | |
| "grad_norm": 0.14994005858898163, | |
| "learning_rate": 3.348352720391469e-05, | |
| "loss": 1.0008, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.03056065315905771, | |
| "grad_norm": 0.1611510068178177, | |
| "learning_rate": 3.3029662220191144e-05, | |
| "loss": 1.094, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.031010074529043856, | |
| "grad_norm": 0.19615799188613892, | |
| "learning_rate": 3.2572826706199305e-05, | |
| "loss": 1.051, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.03145949589903, | |
| "grad_norm": 0.15789468586444855, | |
| "learning_rate": 3.211318966577581e-05, | |
| "loss": 1.0302, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.03145949589903, | |
| "eval_loss": 1.0971506834030151, | |
| "eval_runtime": 312.684, | |
| "eval_samples_per_second": 35.956, | |
| "eval_steps_per_second": 4.497, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.031908917269016145, | |
| "grad_norm": 0.15568239986896515, | |
| "learning_rate": 3.165092113916688e-05, | |
| "loss": 1.12, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.03235833863900228, | |
| "grad_norm": 0.16250278055667877, | |
| "learning_rate": 3.118619214012286e-05, | |
| "loss": 1.0651, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.032807760008988426, | |
| "grad_norm": 0.16043943166732788, | |
| "learning_rate": 3.071917459263264e-05, | |
| "loss": 1.1254, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.03325718137897457, | |
| "grad_norm": 0.19213679432868958, | |
| "learning_rate": 3.0250041267321232e-05, | |
| "loss": 1.1082, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.033706602748960715, | |
| "grad_norm": 0.17149952054023743, | |
| "learning_rate": 2.9778965717534313e-05, | |
| "loss": 1.0345, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.03415602411894685, | |
| "grad_norm": 0.19161058962345123, | |
| "learning_rate": 2.9306122215132976e-05, | |
| "loss": 1.2631, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.034605445488933, | |
| "grad_norm": 0.12983594834804535, | |
| "learning_rate": 2.8831685686022897e-05, | |
| "loss": 1.0125, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.03505486685891914, | |
| "grad_norm": 0.1923818439245224, | |
| "learning_rate": 2.8355831645441388e-05, | |
| "loss": 1.1152, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.035504288228905286, | |
| "grad_norm": 0.17539535462856293, | |
| "learning_rate": 2.787873613302649e-05, | |
| "loss": 1.0698, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.03595370959889143, | |
| "grad_norm": 0.20096057653427124, | |
| "learning_rate": 2.7400575647692046e-05, | |
| "loss": 1.0742, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.03640313096887757, | |
| "grad_norm": 0.1583949774503708, | |
| "learning_rate": 2.692152708233292e-05, | |
| "loss": 1.0255, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.03685255233886371, | |
| "grad_norm": 0.13673090934753418, | |
| "learning_rate": 2.6441767658384366e-05, | |
| "loss": 1.1167, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.037301973708849856, | |
| "grad_norm": 0.15132947266101837, | |
| "learning_rate": 2.596147486025996e-05, | |
| "loss": 1.053, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.037751395078836, | |
| "grad_norm": 0.1649513989686966, | |
| "learning_rate": 2.5480826369692178e-05, | |
| "loss": 1.1041, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.037751395078836, | |
| "eval_loss": 1.0942788124084473, | |
| "eval_runtime": 312.947, | |
| "eval_samples_per_second": 35.926, | |
| "eval_steps_per_second": 4.493, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.038200816448822145, | |
| "grad_norm": 0.19113826751708984, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.0117, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.03865023781880828, | |
| "grad_norm": 0.17212168872356415, | |
| "learning_rate": 2.4519173630307825e-05, | |
| "loss": 1.136, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.039099659188794426, | |
| "grad_norm": 0.16413848102092743, | |
| "learning_rate": 2.403852513974004e-05, | |
| "loss": 1.0806, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.03954908055878057, | |
| "grad_norm": 0.15564818680286407, | |
| "learning_rate": 2.3558232341615643e-05, | |
| "loss": 1.0233, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.039998501928766715, | |
| "grad_norm": 0.15014681220054626, | |
| "learning_rate": 2.3078472917667092e-05, | |
| "loss": 1.09, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.04044792329875285, | |
| "grad_norm": 0.1784486323595047, | |
| "learning_rate": 2.2599424352307957e-05, | |
| "loss": 1.0867, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.040897344668739, | |
| "grad_norm": 0.1629609763622284, | |
| "learning_rate": 2.212126386697352e-05, | |
| "loss": 1.0916, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.04134676603872514, | |
| "grad_norm": 0.1595894992351532, | |
| "learning_rate": 2.164416835455862e-05, | |
| "loss": 1.0537, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.041796187408711286, | |
| "grad_norm": 0.16272102296352386, | |
| "learning_rate": 2.11683143139771e-05, | |
| "loss": 1.1907, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.04224560877869743, | |
| "grad_norm": 0.15896858274936676, | |
| "learning_rate": 2.069387778486703e-05, | |
| "loss": 1.0492, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.04269503014868357, | |
| "grad_norm": 0.18164744973182678, | |
| "learning_rate": 2.02210342824657e-05, | |
| "loss": 1.064, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.04314445151866971, | |
| "grad_norm": 0.17921298742294312, | |
| "learning_rate": 1.9749958732678767e-05, | |
| "loss": 1.1456, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.043593872888655856, | |
| "grad_norm": 0.14521931111812592, | |
| "learning_rate": 1.928082540736737e-05, | |
| "loss": 1.1073, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.044043294258642, | |
| "grad_norm": 0.15362174808979034, | |
| "learning_rate": 1.8813807859877147e-05, | |
| "loss": 1.0171, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.044043294258642, | |
| "eval_loss": 1.0923734903335571, | |
| "eval_runtime": 312.595, | |
| "eval_samples_per_second": 35.967, | |
| "eval_steps_per_second": 4.498, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.044492715628628145, | |
| "grad_norm": 0.18710507452487946, | |
| "learning_rate": 1.8349078860833123e-05, | |
| "loss": 1.0978, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.04494213699861428, | |
| "grad_norm": 0.1569843292236328, | |
| "learning_rate": 1.7886810334224192e-05, | |
| "loss": 1.0783, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.045391558368600426, | |
| "grad_norm": 0.14208896458148956, | |
| "learning_rate": 1.74271732938007e-05, | |
| "loss": 1.0512, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.04584097973858657, | |
| "grad_norm": 0.16557104885578156, | |
| "learning_rate": 1.6970337779808862e-05, | |
| "loss": 1.143, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.046290401108572715, | |
| "grad_norm": 0.17679089307785034, | |
| "learning_rate": 1.6516472796085315e-05, | |
| "loss": 1.0428, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.04673982247855885, | |
| "grad_norm": 0.21449750661849976, | |
| "learning_rate": 1.6065746247534984e-05, | |
| "loss": 1.0541, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.047189243848545, | |
| "grad_norm": 0.19140197336673737, | |
| "learning_rate": 1.561832487801565e-05, | |
| "loss": 1.0943, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.04763866521853114, | |
| "grad_norm": 0.21146325767040253, | |
| "learning_rate": 1.5174374208651912e-05, | |
| "loss": 1.1286, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.048088086588517286, | |
| "grad_norm": 0.16576792299747467, | |
| "learning_rate": 1.4734058476601553e-05, | |
| "loss": 1.1543, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.04853750795850343, | |
| "grad_norm": 0.17730730772018433, | |
| "learning_rate": 1.4297540574296869e-05, | |
| "loss": 1.0809, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.04898692932848957, | |
| "grad_norm": 0.16303078830242157, | |
| "learning_rate": 1.386498198918352e-05, | |
| "loss": 1.0781, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.04943635069847571, | |
| "grad_norm": 0.15803277492523193, | |
| "learning_rate": 1.3436542743979125e-05, | |
| "loss": 1.1138, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.049885772068461856, | |
| "grad_norm": 0.161447212100029, | |
| "learning_rate": 1.3012381337473656e-05, | |
| "loss": 1.0087, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.050335193438448, | |
| "grad_norm": 0.14916126430034637, | |
| "learning_rate": 1.2592654685893757e-05, | |
| "loss": 1.0916, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.050335193438448, | |
| "eval_loss": 1.0906805992126465, | |
| "eval_runtime": 312.9768, | |
| "eval_samples_per_second": 35.923, | |
| "eval_steps_per_second": 4.492, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.05078461480843414, | |
| "grad_norm": 0.18624208867549896, | |
| "learning_rate": 1.217751806485235e-05, | |
| "loss": 1.1368, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.05123403617842028, | |
| "grad_norm": 0.18036052584648132, | |
| "learning_rate": 1.1767125051905315e-05, | |
| "loss": 1.0682, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.051683457548406427, | |
| "grad_norm": 0.17344728112220764, | |
| "learning_rate": 1.1361627469736285e-05, | |
| "loss": 1.0299, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.05213287891839257, | |
| "grad_norm": 0.17225950956344604, | |
| "learning_rate": 1.096117532999063e-05, | |
| "loss": 1.0217, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.052582300288378715, | |
| "grad_norm": 0.1770411878824234, | |
| "learning_rate": 1.0565916777779519e-05, | |
| "loss": 1.1027, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.05303172165836485, | |
| "grad_norm": 0.15190331637859344, | |
| "learning_rate": 1.0175998036874356e-05, | |
| "loss": 1.0684, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.053481143028351, | |
| "grad_norm": 0.20575201511383057, | |
| "learning_rate": 9.791563355612172e-06, | |
| "loss": 1.0359, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.05393056439833714, | |
| "grad_norm": 0.2163867950439453, | |
| "learning_rate": 9.412754953531663e-06, | |
| "loss": 1.0943, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.054379985768323286, | |
| "grad_norm": 0.1523335576057434, | |
| "learning_rate": 9.039712968759864e-06, | |
| "loss": 1.1357, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.05482940713830943, | |
| "grad_norm": 0.1748288869857788, | |
| "learning_rate": 8.672575406168782e-06, | |
| "loss": 1.0745, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.05527882850829557, | |
| "grad_norm": 0.16783830523490906, | |
| "learning_rate": 8.3114780863213e-06, | |
| "loss": 1.0432, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.05572824987828171, | |
| "grad_norm": 0.17801252007484436, | |
| "learning_rate": 7.956554595225016e-06, | |
| "loss": 1.0649, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.056177671248267856, | |
| "grad_norm": 0.17944374680519104, | |
| "learning_rate": 7.607936234912841e-06, | |
| "loss": 1.0862, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.056627092618254, | |
| "grad_norm": 0.19096186757087708, | |
| "learning_rate": 7.265751974868554e-06, | |
| "loss": 1.0477, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.056627092618254, | |
| "eval_loss": 1.0896837711334229, | |
| "eval_runtime": 312.799, | |
| "eval_samples_per_second": 35.943, | |
| "eval_steps_per_second": 4.495, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.05707651398824014, | |
| "grad_norm": 0.17599642276763916, | |
| "learning_rate": 6.930128404315214e-06, | |
| "loss": 1.1339, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.05752593535822628, | |
| "grad_norm": 0.16360458731651306, | |
| "learning_rate": 6.601189685384126e-06, | |
| "loss": 1.1844, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.05797535672821243, | |
| "grad_norm": 0.1602054089307785, | |
| "learning_rate": 6.279057507181796e-06, | |
| "loss": 1.0835, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.05842477809819857, | |
| "grad_norm": 0.33288466930389404, | |
| "learning_rate": 5.9638510407716394e-06, | |
| "loss": 1.0366, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.058874199468184715, | |
| "grad_norm": 0.17551077902317047, | |
| "learning_rate": 5.655686895087329e-06, | |
| "loss": 1.0361, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.05932362083817085, | |
| "grad_norm": 0.19817480444908142, | |
| "learning_rate": 5.354679073793942e-06, | |
| "loss": 1.1113, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.059773042208157, | |
| "grad_norm": 0.18397966027259827, | |
| "learning_rate": 5.060938933112891e-06, | |
| "loss": 1.0809, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.06022246357814314, | |
| "grad_norm": 0.18848171830177307, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 1.0232, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.060671884948129286, | |
| "grad_norm": 0.18873141705989838, | |
| "learning_rate": 4.495693635076101e-06, | |
| "loss": 1.0633, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.06112130631811542, | |
| "grad_norm": 0.17433975636959076, | |
| "learning_rate": 4.224397587172402e-06, | |
| "loss": 1.0064, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.06157072768810157, | |
| "grad_norm": 0.2025955468416214, | |
| "learning_rate": 3.9607873614261715e-06, | |
| "loss": 1.1142, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.06202014905808771, | |
| "grad_norm": 0.1579374223947525, | |
| "learning_rate": 3.7049604790198976e-06, | |
| "loss": 1.0722, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.062469570428073856, | |
| "grad_norm": 0.15210741758346558, | |
| "learning_rate": 3.4570115817301243e-06, | |
| "loss": 1.011, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.06291899179806, | |
| "grad_norm": 0.21344028413295746, | |
| "learning_rate": 3.217032396915265e-06, | |
| "loss": 1.1333, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.06291899179806, | |
| "eval_loss": 1.0891081094741821, | |
| "eval_runtime": 312.8277, | |
| "eval_samples_per_second": 35.94, | |
| "eval_steps_per_second": 4.494, | |
| "step": 420 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 42, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3537807518872371e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |