| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.76056338028169, | |
| "eval_steps": 42, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0035211267605633804, | |
| "eval_loss": 0.71390700340271, | |
| "eval_runtime": 33.4366, | |
| "eval_samples_per_second": 57.213, | |
| "eval_steps_per_second": 1.794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01056338028169014, | |
| "grad_norm": 17.077974319458008, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.8897, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02112676056338028, | |
| "grad_norm": 11.338067054748535, | |
| "learning_rate": 3e-05, | |
| "loss": 2.4422, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03169014084507042, | |
| "grad_norm": 4.915891170501709, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.4287, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04225352112676056, | |
| "grad_norm": 4.167311668395996, | |
| "learning_rate": 4.9997944716957985e-05, | |
| "loss": 1.0401, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0528169014084507, | |
| "grad_norm": 3.024125576019287, | |
| "learning_rate": 4.99871554050172e-05, | |
| "loss": 0.8671, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06338028169014084, | |
| "grad_norm": 3.4865105152130127, | |
| "learning_rate": 4.996712222958461e-05, | |
| "loss": 0.8196, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07394366197183098, | |
| "grad_norm": 2.5807318687438965, | |
| "learning_rate": 4.993785260182552e-05, | |
| "loss": 0.78, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08450704225352113, | |
| "grad_norm": 2.547455310821533, | |
| "learning_rate": 4.989935734988098e-05, | |
| "loss": 0.7355, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09507042253521127, | |
| "grad_norm": 2.533689022064209, | |
| "learning_rate": 4.9851650714862006e-05, | |
| "loss": 0.7632, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1056338028169014, | |
| "grad_norm": 2.3361666202545166, | |
| "learning_rate": 4.979475034558115e-05, | |
| "loss": 0.6511, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11619718309859155, | |
| "grad_norm": 2.409919023513794, | |
| "learning_rate": 4.9728677292023405e-05, | |
| "loss": 0.7696, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1267605633802817, | |
| "grad_norm": 2.3986947536468506, | |
| "learning_rate": 4.965345599755887e-05, | |
| "loss": 0.7176, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.13732394366197184, | |
| "grad_norm": 2.424473762512207, | |
| "learning_rate": 4.95691142899001e-05, | |
| "loss": 0.657, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14788732394366197, | |
| "grad_norm": 2.3283729553222656, | |
| "learning_rate": 4.9475683370807326e-05, | |
| "loss": 0.6722, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14788732394366197, | |
| "eval_loss": 0.16498678922653198, | |
| "eval_runtime": 33.548, | |
| "eval_samples_per_second": 57.023, | |
| "eval_steps_per_second": 1.788, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.15845070422535212, | |
| "grad_norm": 2.373122215270996, | |
| "learning_rate": 4.937319780454559e-05, | |
| "loss": 0.6457, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": 2.525294303894043, | |
| "learning_rate": 4.926169550509787e-05, | |
| "loss": 0.7483, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1795774647887324, | |
| "grad_norm": 1.940788745880127, | |
| "learning_rate": 4.914121772213898e-05, | |
| "loss": 0.6246, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.19014084507042253, | |
| "grad_norm": 4.233572483062744, | |
| "learning_rate": 4.9011809025775486e-05, | |
| "loss": 0.7226, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2007042253521127, | |
| "grad_norm": 1.9542790651321411, | |
| "learning_rate": 4.887351729005726e-05, | |
| "loss": 0.6427, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2112676056338028, | |
| "grad_norm": 1.8455359935760498, | |
| "learning_rate": 4.8726393675266716e-05, | |
| "loss": 0.5821, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22183098591549297, | |
| "grad_norm": 1.9550554752349854, | |
| "learning_rate": 4.8570492608992325e-05, | |
| "loss": 0.6654, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2323943661971831, | |
| "grad_norm": 2.3653812408447266, | |
| "learning_rate": 4.8405871765993433e-05, | |
| "loss": 0.6337, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.24295774647887325, | |
| "grad_norm": 2.590679883956909, | |
| "learning_rate": 4.82325920468638e-05, | |
| "loss": 0.6181, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2535211267605634, | |
| "grad_norm": 1.894047737121582, | |
| "learning_rate": 4.805071755550177e-05, | |
| "loss": 0.5873, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2640845070422535, | |
| "grad_norm": 1.9947123527526855, | |
| "learning_rate": 4.7860315575395316e-05, | |
| "loss": 0.5982, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2746478873239437, | |
| "grad_norm": 1.8202632665634155, | |
| "learning_rate": 4.766145654473095e-05, | |
| "loss": 0.6069, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.2852112676056338, | |
| "grad_norm": 1.9413880109786987, | |
| "learning_rate": 4.745421403033548e-05, | |
| "loss": 0.5623, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.29577464788732394, | |
| "grad_norm": 2.8411378860473633, | |
| "learning_rate": 4.72386647004603e-05, | |
| "loss": 0.6329, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.29577464788732394, | |
| "eval_loss": 0.1504964828491211, | |
| "eval_runtime": 33.5299, | |
| "eval_samples_per_second": 57.054, | |
| "eval_steps_per_second": 1.789, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.30633802816901406, | |
| "grad_norm": 1.8375580310821533, | |
| "learning_rate": 4.701488829641845e-05, | |
| "loss": 0.6443, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.31690140845070425, | |
| "grad_norm": 1.757625699043274, | |
| "learning_rate": 4.678296760308474e-05, | |
| "loss": 0.59, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3274647887323944, | |
| "grad_norm": 2.1442489624023438, | |
| "learning_rate": 4.6542988418269876e-05, | |
| "loss": 0.5946, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": 1.9878476858139038, | |
| "learning_rate": 4.629503952098011e-05, | |
| "loss": 0.6107, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3485915492957746, | |
| "grad_norm": 1.8092180490493774, | |
| "learning_rate": 4.6039212638573833e-05, | |
| "loss": 0.6134, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3591549295774648, | |
| "grad_norm": 2.0128672122955322, | |
| "learning_rate": 4.5775602412827604e-05, | |
| "loss": 0.5717, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.36971830985915494, | |
| "grad_norm": 2.2072324752807617, | |
| "learning_rate": 4.55043063649239e-05, | |
| "loss": 0.5671, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.38028169014084506, | |
| "grad_norm": 1.711063027381897, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.6111, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.3908450704225352, | |
| "grad_norm": 2.159810781478882, | |
| "learning_rate": 4.493906106688712e-05, | |
| "loss": 0.5901, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.4014084507042254, | |
| "grad_norm": 1.8703676462173462, | |
| "learning_rate": 4.4645320926206064e-05, | |
| "loss": 0.5546, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.4119718309859155, | |
| "grad_norm": 2.7771778106689453, | |
| "learning_rate": 4.434431310491267e-05, | |
| "loss": 0.5974, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.4225352112676056, | |
| "grad_norm": 2.062894105911255, | |
| "learning_rate": 4.4036148959228365e-05, | |
| "loss": 0.592, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.43309859154929575, | |
| "grad_norm": 4.134242534637451, | |
| "learning_rate": 4.372094249281821e-05, | |
| "loss": 0.5704, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.44366197183098594, | |
| "grad_norm": 2.1971914768218994, | |
| "learning_rate": 4.3398810314615876e-05, | |
| "loss": 0.5936, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.44366197183098594, | |
| "eval_loss": 0.1457224041223526, | |
| "eval_runtime": 33.5854, | |
| "eval_samples_per_second": 56.959, | |
| "eval_steps_per_second": 1.786, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.45422535211267606, | |
| "grad_norm": 2.5988810062408447, | |
| "learning_rate": 4.306987159568479e-05, | |
| "loss": 0.618, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.4647887323943662, | |
| "grad_norm": 1.7022452354431152, | |
| "learning_rate": 4.273424802513145e-05, | |
| "loss": 0.5488, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.4753521126760563, | |
| "grad_norm": 7.090500831604004, | |
| "learning_rate": 4.239206376508717e-05, | |
| "loss": 0.6025, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.4859154929577465, | |
| "grad_norm": 13.125855445861816, | |
| "learning_rate": 4.204344540477499e-05, | |
| "loss": 0.5575, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.4964788732394366, | |
| "grad_norm": 2.1748900413513184, | |
| "learning_rate": 4.16885219136787e-05, | |
| "loss": 0.5685, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.5070422535211268, | |
| "grad_norm": 1.8787870407104492, | |
| "learning_rate": 4.132742459383122e-05, | |
| "loss": 0.5615, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.5176056338028169, | |
| "grad_norm": 1.8326219320297241, | |
| "learning_rate": 4.096028703124014e-05, | |
| "loss": 0.5695, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.528169014084507, | |
| "grad_norm": 1.6756395101547241, | |
| "learning_rate": 4.058724504646834e-05, | |
| "loss": 0.5926, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5387323943661971, | |
| "grad_norm": 1.572495937347412, | |
| "learning_rate": 4.0208436644387834e-05, | |
| "loss": 0.6206, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.5492957746478874, | |
| "grad_norm": 1.5724139213562012, | |
| "learning_rate": 3.982400196312564e-05, | |
| "loss": 0.6059, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.5598591549295775, | |
| "grad_norm": 2.1546130180358887, | |
| "learning_rate": 3.943408322222049e-05, | |
| "loss": 0.6087, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.5704225352112676, | |
| "grad_norm": 1.74432373046875, | |
| "learning_rate": 3.903882467000937e-05, | |
| "loss": 0.5395, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.5809859154929577, | |
| "grad_norm": 2.2862908840179443, | |
| "learning_rate": 3.8638372530263715e-05, | |
| "loss": 0.5786, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.5915492957746479, | |
| "grad_norm": 1.8650025129318237, | |
| "learning_rate": 3.823287494809469e-05, | |
| "loss": 0.5783, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.5915492957746479, | |
| "eval_loss": 0.14048069715499878, | |
| "eval_runtime": 33.5379, | |
| "eval_samples_per_second": 57.04, | |
| "eval_steps_per_second": 1.789, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.602112676056338, | |
| "grad_norm": 1.719423770904541, | |
| "learning_rate": 3.782248193514766e-05, | |
| "loss": 0.5673, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.6126760563380281, | |
| "grad_norm": 1.777215600013733, | |
| "learning_rate": 3.740734531410626e-05, | |
| "loss": 0.5777, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.6232394366197183, | |
| "grad_norm": 1.7212867736816406, | |
| "learning_rate": 3.698761866252635e-05, | |
| "loss": 0.5956, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.6338028169014085, | |
| "grad_norm": 1.849625825881958, | |
| "learning_rate": 3.656345725602089e-05, | |
| "loss": 0.5805, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6443661971830986, | |
| "grad_norm": 1.5129181146621704, | |
| "learning_rate": 3.6135018010816477e-05, | |
| "loss": 0.5271, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.6549295774647887, | |
| "grad_norm": 1.7070224285125732, | |
| "learning_rate": 3.570245942570315e-05, | |
| "loss": 0.5715, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.6654929577464789, | |
| "grad_norm": 1.416464924812317, | |
| "learning_rate": 3.526594152339845e-05, | |
| "loss": 0.528, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.676056338028169, | |
| "grad_norm": 1.569150686264038, | |
| "learning_rate": 3.4825625791348096e-05, | |
| "loss": 0.5646, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.6866197183098591, | |
| "grad_norm": 1.3740211725234985, | |
| "learning_rate": 3.438167512198436e-05, | |
| "loss": 0.5574, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.6971830985915493, | |
| "grad_norm": 1.7749651670455933, | |
| "learning_rate": 3.393425375246503e-05, | |
| "loss": 0.5988, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.7077464788732394, | |
| "grad_norm": 1.5180374383926392, | |
| "learning_rate": 3.348352720391469e-05, | |
| "loss": 0.5696, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.7183098591549296, | |
| "grad_norm": 1.4863420724868774, | |
| "learning_rate": 3.3029662220191144e-05, | |
| "loss": 0.5903, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.7288732394366197, | |
| "grad_norm": 1.5769625902175903, | |
| "learning_rate": 3.2572826706199305e-05, | |
| "loss": 0.5445, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.7394366197183099, | |
| "grad_norm": 1.7347217798233032, | |
| "learning_rate": 3.211318966577581e-05, | |
| "loss": 0.5684, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7394366197183099, | |
| "eval_loss": 0.13805150985717773, | |
| "eval_runtime": 33.5478, | |
| "eval_samples_per_second": 57.023, | |
| "eval_steps_per_second": 1.788, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 2.053368330001831, | |
| "learning_rate": 3.165092113916688e-05, | |
| "loss": 0.573, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.7605633802816901, | |
| "grad_norm": 1.5371932983398438, | |
| "learning_rate": 3.118619214012286e-05, | |
| "loss": 0.5915, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.7711267605633803, | |
| "grad_norm": 1.4873214960098267, | |
| "learning_rate": 3.071917459263264e-05, | |
| "loss": 0.5577, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.7816901408450704, | |
| "grad_norm": 1.5104900598526, | |
| "learning_rate": 3.0250041267321232e-05, | |
| "loss": 0.5432, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.7922535211267606, | |
| "grad_norm": 1.6719636917114258, | |
| "learning_rate": 2.9778965717534313e-05, | |
| "loss": 0.5495, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8028169014084507, | |
| "grad_norm": 1.4213000535964966, | |
| "learning_rate": 2.9306122215132976e-05, | |
| "loss": 0.5193, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.8133802816901409, | |
| "grad_norm": 1.4301376342773438, | |
| "learning_rate": 2.8831685686022897e-05, | |
| "loss": 0.5207, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.823943661971831, | |
| "grad_norm": 1.6136512756347656, | |
| "learning_rate": 2.8355831645441388e-05, | |
| "loss": 0.5428, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.8345070422535211, | |
| "grad_norm": 1.4768859148025513, | |
| "learning_rate": 2.787873613302649e-05, | |
| "loss": 0.5475, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.8450704225352113, | |
| "grad_norm": 1.5305073261260986, | |
| "learning_rate": 2.7400575647692046e-05, | |
| "loss": 0.5587, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8556338028169014, | |
| "grad_norm": 1.3817962408065796, | |
| "learning_rate": 2.692152708233292e-05, | |
| "loss": 0.5434, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.8661971830985915, | |
| "grad_norm": 1.2823965549468994, | |
| "learning_rate": 2.6441767658384366e-05, | |
| "loss": 0.5301, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.8767605633802817, | |
| "grad_norm": 1.4110352993011475, | |
| "learning_rate": 2.596147486025996e-05, | |
| "loss": 0.5135, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.8873239436619719, | |
| "grad_norm": 1.5290179252624512, | |
| "learning_rate": 2.5480826369692178e-05, | |
| "loss": 0.5662, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.8873239436619719, | |
| "eval_loss": 0.13341283798217773, | |
| "eval_runtime": 33.5418, | |
| "eval_samples_per_second": 57.033, | |
| "eval_steps_per_second": 1.789, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.897887323943662, | |
| "grad_norm": 1.5652258396148682, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.5204, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.9084507042253521, | |
| "grad_norm": 1.7161169052124023, | |
| "learning_rate": 2.4519173630307825e-05, | |
| "loss": 0.5507, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.9190140845070423, | |
| "grad_norm": 1.455829381942749, | |
| "learning_rate": 2.403852513974004e-05, | |
| "loss": 0.5352, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.9295774647887324, | |
| "grad_norm": 1.7038428783416748, | |
| "learning_rate": 2.3558232341615643e-05, | |
| "loss": 0.5343, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.9401408450704225, | |
| "grad_norm": 1.3477355241775513, | |
| "learning_rate": 2.3078472917667092e-05, | |
| "loss": 0.5213, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.9507042253521126, | |
| "grad_norm": 1.510071039199829, | |
| "learning_rate": 2.2599424352307957e-05, | |
| "loss": 0.5502, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9612676056338029, | |
| "grad_norm": 1.5797042846679688, | |
| "learning_rate": 2.212126386697352e-05, | |
| "loss": 0.5568, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.971830985915493, | |
| "grad_norm": 1.6164652109146118, | |
| "learning_rate": 2.164416835455862e-05, | |
| "loss": 0.5321, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.9823943661971831, | |
| "grad_norm": 1.586676836013794, | |
| "learning_rate": 2.11683143139771e-05, | |
| "loss": 0.5525, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.9929577464788732, | |
| "grad_norm": 1.4788326025009155, | |
| "learning_rate": 2.069387778486703e-05, | |
| "loss": 0.5534, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 1.0035211267605635, | |
| "grad_norm": 1.3445155620574951, | |
| "learning_rate": 2.02210342824657e-05, | |
| "loss": 0.5317, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.0140845070422535, | |
| "grad_norm": 1.3771849870681763, | |
| "learning_rate": 1.9749958732678767e-05, | |
| "loss": 0.5034, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.0246478873239437, | |
| "grad_norm": 1.3646653890609741, | |
| "learning_rate": 1.928082540736737e-05, | |
| "loss": 0.4771, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 1.0352112676056338, | |
| "grad_norm": 1.2086783647537231, | |
| "learning_rate": 1.8813807859877147e-05, | |
| "loss": 0.4207, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.0352112676056338, | |
| "eval_loss": 0.13161411881446838, | |
| "eval_runtime": 33.5416, | |
| "eval_samples_per_second": 57.034, | |
| "eval_steps_per_second": 1.789, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.045774647887324, | |
| "grad_norm": 1.3563522100448608, | |
| "learning_rate": 1.8349078860833123e-05, | |
| "loss": 0.4868, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 1.056338028169014, | |
| "grad_norm": 1.4925919771194458, | |
| "learning_rate": 1.7886810334224192e-05, | |
| "loss": 0.4677, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0669014084507042, | |
| "grad_norm": 1.559565544128418, | |
| "learning_rate": 1.74271732938007e-05, | |
| "loss": 0.4977, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 1.0774647887323943, | |
| "grad_norm": 1.6586874723434448, | |
| "learning_rate": 1.6970337779808862e-05, | |
| "loss": 0.4578, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 1.0880281690140845, | |
| "grad_norm": 1.4285913705825806, | |
| "learning_rate": 1.6516472796085315e-05, | |
| "loss": 0.4942, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 1.0985915492957747, | |
| "grad_norm": 1.3942043781280518, | |
| "learning_rate": 1.6065746247534984e-05, | |
| "loss": 0.4937, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.1091549295774648, | |
| "grad_norm": 1.3517378568649292, | |
| "learning_rate": 1.561832487801565e-05, | |
| "loss": 0.5066, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.119718309859155, | |
| "grad_norm": 1.447427749633789, | |
| "learning_rate": 1.5174374208651912e-05, | |
| "loss": 0.4476, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.130281690140845, | |
| "grad_norm": 1.5619040727615356, | |
| "learning_rate": 1.4734058476601553e-05, | |
| "loss": 0.4542, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 1.1408450704225352, | |
| "grad_norm": 1.5647931098937988, | |
| "learning_rate": 1.4297540574296869e-05, | |
| "loss": 0.4721, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.1514084507042253, | |
| "grad_norm": 1.5523713827133179, | |
| "learning_rate": 1.386498198918352e-05, | |
| "loss": 0.4627, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 1.1619718309859155, | |
| "grad_norm": 1.444485068321228, | |
| "learning_rate": 1.3436542743979125e-05, | |
| "loss": 0.4618, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.1725352112676055, | |
| "grad_norm": 1.5264121294021606, | |
| "learning_rate": 1.3012381337473656e-05, | |
| "loss": 0.465, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.1830985915492958, | |
| "grad_norm": 1.390081763267517, | |
| "learning_rate": 1.2592654685893757e-05, | |
| "loss": 0.4356, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.1830985915492958, | |
| "eval_loss": 0.13032591342926025, | |
| "eval_runtime": 33.5427, | |
| "eval_samples_per_second": 57.032, | |
| "eval_steps_per_second": 1.789, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.193661971830986, | |
| "grad_norm": 1.4353517293930054, | |
| "learning_rate": 1.217751806485235e-05, | |
| "loss": 0.4514, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 1.204225352112676, | |
| "grad_norm": 1.5341055393218994, | |
| "learning_rate": 1.1767125051905315e-05, | |
| "loss": 0.4656, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.2147887323943662, | |
| "grad_norm": 4.069514274597168, | |
| "learning_rate": 1.1361627469736285e-05, | |
| "loss": 0.4822, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.2253521126760563, | |
| "grad_norm": 1.6193852424621582, | |
| "learning_rate": 1.096117532999063e-05, | |
| "loss": 0.4966, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 1.2359154929577465, | |
| "grad_norm": 1.5094631910324097, | |
| "learning_rate": 1.0565916777779519e-05, | |
| "loss": 0.4881, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.2464788732394365, | |
| "grad_norm": 1.4816490411758423, | |
| "learning_rate": 1.0175998036874356e-05, | |
| "loss": 0.4703, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 1.2570422535211268, | |
| "grad_norm": 1.4219728708267212, | |
| "learning_rate": 9.791563355612172e-06, | |
| "loss": 0.4566, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 1.267605633802817, | |
| "grad_norm": 1.435050129890442, | |
| "learning_rate": 9.412754953531663e-06, | |
| "loss": 0.4399, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.278169014084507, | |
| "grad_norm": 1.5008336305618286, | |
| "learning_rate": 9.039712968759864e-06, | |
| "loss": 0.4941, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 1.2887323943661972, | |
| "grad_norm": 1.4802623987197876, | |
| "learning_rate": 8.672575406168782e-06, | |
| "loss": 0.464, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 1.2992957746478873, | |
| "grad_norm": 1.5385937690734863, | |
| "learning_rate": 8.3114780863213e-06, | |
| "loss": 0.4723, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.3098591549295775, | |
| "grad_norm": 1.5559135675430298, | |
| "learning_rate": 7.956554595225016e-06, | |
| "loss": 0.4874, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.3204225352112675, | |
| "grad_norm": 2.4486403465270996, | |
| "learning_rate": 7.607936234912841e-06, | |
| "loss": 0.4517, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.3309859154929577, | |
| "grad_norm": 1.5418450832366943, | |
| "learning_rate": 7.265751974868554e-06, | |
| "loss": 0.4508, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.3309859154929577, | |
| "eval_loss": 0.12915180623531342, | |
| "eval_runtime": 33.5598, | |
| "eval_samples_per_second": 57.003, | |
| "eval_steps_per_second": 1.788, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.341549295774648, | |
| "grad_norm": 1.704418420791626, | |
| "learning_rate": 6.930128404315214e-06, | |
| "loss": 0.4565, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 1.352112676056338, | |
| "grad_norm": 1.593887448310852, | |
| "learning_rate": 6.601189685384126e-06, | |
| "loss": 0.442, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.3626760563380282, | |
| "grad_norm": 1.6920288801193237, | |
| "learning_rate": 6.279057507181796e-06, | |
| "loss": 0.4766, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 1.3732394366197183, | |
| "grad_norm": 1.4904849529266357, | |
| "learning_rate": 5.9638510407716394e-06, | |
| "loss": 0.4798, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.3838028169014085, | |
| "grad_norm": 1.403585433959961, | |
| "learning_rate": 5.655686895087329e-06, | |
| "loss": 0.4288, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.3943661971830985, | |
| "grad_norm": 1.7020981311798096, | |
| "learning_rate": 5.354679073793942e-06, | |
| "loss": 0.4431, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.4049295774647887, | |
| "grad_norm": 1.389512538909912, | |
| "learning_rate": 5.060938933112891e-06, | |
| "loss": 0.4269, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 1.415492957746479, | |
| "grad_norm": 1.4572571516036987, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.4362, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.426056338028169, | |
| "grad_norm": 1.386979341506958, | |
| "learning_rate": 4.495693635076101e-06, | |
| "loss": 0.4528, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.436619718309859, | |
| "grad_norm": 1.5919663906097412, | |
| "learning_rate": 4.224397587172402e-06, | |
| "loss": 0.4448, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.4471830985915493, | |
| "grad_norm": 1.4099351167678833, | |
| "learning_rate": 3.9607873614261715e-06, | |
| "loss": 0.4233, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 1.4577464788732395, | |
| "grad_norm": 1.6724328994750977, | |
| "learning_rate": 3.7049604790198976e-06, | |
| "loss": 0.4849, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.4683098591549295, | |
| "grad_norm": 1.8909960985183716, | |
| "learning_rate": 3.4570115817301243e-06, | |
| "loss": 0.4443, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 1.4788732394366197, | |
| "grad_norm": 1.5311111211776733, | |
| "learning_rate": 3.217032396915265e-06, | |
| "loss": 0.4651, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.4788732394366197, | |
| "eval_loss": 0.12859447300434113, | |
| "eval_runtime": 33.526, | |
| "eval_samples_per_second": 57.06, | |
| "eval_steps_per_second": 1.79, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.48943661971831, | |
| "grad_norm": 1.5658754110336304, | |
| "learning_rate": 2.98511170358155e-06, | |
| "loss": 0.452, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 1.5586401224136353, | |
| "learning_rate": 2.7613352995397078e-06, | |
| "loss": 0.4307, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.51056338028169, | |
| "grad_norm": 1.8097403049468994, | |
| "learning_rate": 2.545785969664524e-06, | |
| "loss": 0.4415, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.5211267605633803, | |
| "grad_norm": 2.813575267791748, | |
| "learning_rate": 2.338543455269046e-06, | |
| "loss": 0.4346, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.5316901408450705, | |
| "grad_norm": 1.5137277841567993, | |
| "learning_rate": 2.1396844246046903e-06, | |
| "loss": 0.4203, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.5422535211267605, | |
| "grad_norm": 1.5360363721847534, | |
| "learning_rate": 1.949282444498238e-06, | |
| "loss": 0.4264, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.5528169014084507, | |
| "grad_norm": 1.4588457345962524, | |
| "learning_rate": 1.767407953136202e-06, | |
| "loss": 0.4363, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 1.563380281690141, | |
| "grad_norm": 1.5039774179458618, | |
| "learning_rate": 1.59412823400657e-06, | |
| "loss": 0.4399, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.573943661971831, | |
| "grad_norm": 1.6695863008499146, | |
| "learning_rate": 1.4295073910076757e-06, | |
| "loss": 0.4678, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 1.584507042253521, | |
| "grad_norm": 1.5582469701766968, | |
| "learning_rate": 1.273606324733284e-06, | |
| "loss": 0.4264, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.5950704225352113, | |
| "grad_norm": 1.6020346879959106, | |
| "learning_rate": 1.1264827099427417e-06, | |
| "loss": 0.4423, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 1.6056338028169015, | |
| "grad_norm": 1.8120399713516235, | |
| "learning_rate": 9.881909742245177e-07, | |
| "loss": 0.4793, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.6161971830985915, | |
| "grad_norm": 1.804922342300415, | |
| "learning_rate": 8.587822778610283e-07, | |
| "loss": 0.4396, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.6267605633802817, | |
| "grad_norm": 1.4649447202682495, | |
| "learning_rate": 7.383044949021339e-07, | |
| "loss": 0.4505, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.6267605633802817, | |
| "eval_loss": 0.12798862159252167, | |
| "eval_runtime": 33.5293, | |
| "eval_samples_per_second": 57.055, | |
| "eval_steps_per_second": 1.789, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.637323943661972, | |
| "grad_norm": 1.6809414625167847, | |
| "learning_rate": 6.268021954544096e-07, | |
| "loss": 0.4512, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.647887323943662, | |
| "grad_norm": 1.5099436044692993, | |
| "learning_rate": 5.243166291926782e-07, | |
| "loss": 0.4482, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.658450704225352, | |
| "grad_norm": 1.7300583124160767, | |
| "learning_rate": 4.308857100999042e-07, | |
| "loss": 0.465, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 1.6690140845070423, | |
| "grad_norm": 1.4459805488586426, | |
| "learning_rate": 3.465440024411265e-07, | |
| "loss": 0.4559, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.6795774647887325, | |
| "grad_norm": 1.5714209079742432, | |
| "learning_rate": 2.7132270797659563e-07, | |
| "loss": 0.4662, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 1.6901408450704225, | |
| "grad_norm": 1.716829776763916, | |
| "learning_rate": 2.052496544188487e-07, | |
| "loss": 0.4866, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.7007042253521125, | |
| "grad_norm": 1.6884804964065552, | |
| "learning_rate": 1.483492851379914e-07, | |
| "loss": 0.4441, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.711267605633803, | |
| "grad_norm": 1.439448356628418, | |
| "learning_rate": 1.006426501190233e-07, | |
| "loss": 0.4588, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.721830985915493, | |
| "grad_norm": 1.6845688819885254, | |
| "learning_rate": 6.214739817448633e-08, | |
| "loss": 0.4704, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 1.732394366197183, | |
| "grad_norm": 2.208343029022217, | |
| "learning_rate": 3.287777041539042e-08, | |
| "loss": 0.469, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.7429577464788732, | |
| "grad_norm": 1.6495448350906372, | |
| "learning_rate": 1.284459498280266e-08, | |
| "loss": 0.4331, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.7535211267605635, | |
| "grad_norm": 1.6916940212249756, | |
| "learning_rate": 2.055283042018408e-09, | |
| "loss": 0.466, | |
| "step": 498 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 42, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.193006204764553e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |