| { | |
| "best_metric": 0.5638297872340425, | |
| "best_model_checkpoint": "/train/checkpoint-1024", | |
| "epoch": 341.29285714285714, | |
| "global_step": 1024, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0001, | |
| "loss": 4.1011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3519, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1196, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4391, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1683, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7667, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7144, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5931, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5607, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 13.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.551, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4825, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 15.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4402, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 17.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4526, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 18.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3934, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 19.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3704, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 21.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.38, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 21.29, | |
| "eval_exact_match": 0.3027079303675048, | |
| "eval_exec": 0.3288201160541586, | |
| "eval_loss": 0.2835688591003418, | |
| "eval_runtime": 193.4557, | |
| "eval_samples_per_second": 5.345, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 22.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3326, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 23.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3117, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 25.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3228, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 26.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3031, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 27.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2792, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 29.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2907, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 30.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.251, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 31.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2461, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 33.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2551, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 34.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2258, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 35.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2215, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 37.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2294, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 38.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1983, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 39.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1901, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 41.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2023, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 42.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.186, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 42.59, | |
| "eval_exact_match": 0.3694390715667311, | |
| "eval_exec": 0.39748549323017407, | |
| "eval_loss": 0.22650450468063354, | |
| "eval_runtime": 230.9184, | |
| "eval_samples_per_second": 4.478, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 43.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1696, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 45.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.179, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 46.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.164, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 47.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1539, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 49.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1618, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 50.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1492, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 51.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1346, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 53.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1457, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 54.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1335, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 55.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1339, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 57.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1349, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 58.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1202, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 59.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1205, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 61.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.126, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 62.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1136, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 63.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1094, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 63.88, | |
| "eval_exact_match": 0.4632495164410058, | |
| "eval_exec": 0.5067698259187621, | |
| "eval_loss": 0.2031930387020111, | |
| "eval_runtime": 283.9671, | |
| "eval_samples_per_second": 3.641, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 65.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1155, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 66.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1065, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 67.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1055, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 69.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1078, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 70.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.098, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 71.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0956, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 73.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1007, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 74.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0923, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 75.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0912, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 77.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0947, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 78.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0858, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 79.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.083, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 81.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0869, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 82.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0772, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 83.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.082, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 85.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0841, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 85.29, | |
| "eval_exact_match": 0.437137330754352, | |
| "eval_exec": 0.4825918762088975, | |
| "eval_loss": 0.22934624552726746, | |
| "eval_runtime": 282.9831, | |
| "eval_samples_per_second": 3.654, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 86.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0767, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 87.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0734, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 89.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0766, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 90.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0692, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 91.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0656, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 93.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0728, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 94.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0644, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 95.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0653, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 97.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0695, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 98.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0583, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 99.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0565, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 101.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0623, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 102.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0562, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 103.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0571, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 105.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0608, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 106.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0551, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 106.59, | |
| "eval_exact_match": 0.4922630560928433, | |
| "eval_exec": 0.52321083172147, | |
| "eval_loss": 0.21860136091709137, | |
| "eval_runtime": 287.9853, | |
| "eval_samples_per_second": 3.59, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 107.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0538, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 109.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0562, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 110.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0496, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 111.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0485, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 113.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0528, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 114.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0468, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 115.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0494, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 117.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0521, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 118.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0446, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 119.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0417, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 121.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0454, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 122.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0429, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 123.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0401, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 125.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0436, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 126.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0418, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 127.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0384, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 127.88, | |
| "eval_exact_match": 0.4990328820116054, | |
| "eval_exec": 0.5261121856866537, | |
| "eval_loss": 0.23891018331050873, | |
| "eval_runtime": 280.1192, | |
| "eval_samples_per_second": 3.691, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 129.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0396, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 130.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0358, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 131.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0353, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 133.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0395, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 134.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0368, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 135.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0344, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 137.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0373, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 138.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0369, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 139.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0321, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 141.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0323, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 142.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0289, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 143.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0301, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 145.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.035, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 146.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0307, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 147.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0267, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 149.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0286, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 149.29, | |
| "eval_exact_match": 0.5328820116054158, | |
| "eval_exec": 0.558027079303675, | |
| "eval_loss": 0.25370854139328003, | |
| "eval_runtime": 273.1503, | |
| "eval_samples_per_second": 3.785, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 150.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0267, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 151.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.027, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 153.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0277, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 154.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0256, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 155.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0276, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 157.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0278, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 158.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0235, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 159.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0235, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 161.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0241, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 162.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0224, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 163.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0223, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 165.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0251, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 166.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.027, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 167.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0242, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 169.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.025, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 170.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0216, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 170.59, | |
| "eval_exact_match": 0.5386847195357833, | |
| "eval_exec": 0.5686653771760155, | |
| "eval_loss": 0.26241806149482727, | |
| "eval_runtime": 268.9064, | |
| "eval_samples_per_second": 3.845, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 171.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0201, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 173.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0213, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 174.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0194, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 175.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0193, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 177.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0206, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 178.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0186, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 179.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0178, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 181.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0186, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 182.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0177, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 183.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.017, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 185.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0184, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 186.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0175, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 187.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0166, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 189.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.018, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 190.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0157, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 191.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0148, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 191.88, | |
| "eval_exact_match": 0.5377176015473888, | |
| "eval_exec": 0.5599613152804642, | |
| "eval_loss": 0.28443169593811035, | |
| "eval_runtime": 270.9444, | |
| "eval_samples_per_second": 3.816, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 193.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0165, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 194.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0152, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 195.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0147, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 197.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.016, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 198.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0149, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 199.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0137, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 201.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0149, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 202.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0132, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 203.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0128, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 205.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0144, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 206.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0141, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 207.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0164, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 209.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0145, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 210.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0129, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 211.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.012, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 213.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0122, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 213.29, | |
| "eval_exact_match": 0.5512572533849129, | |
| "eval_exec": 0.5754352030947776, | |
| "eval_loss": 0.2961784601211548, | |
| "eval_runtime": 284.015, | |
| "eval_samples_per_second": 3.641, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 214.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0112, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 215.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0117, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 217.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0122, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 218.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0105, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 219.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0105, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 221.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0116, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 222.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0101, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 223.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0096, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 225.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0106, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 226.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0126, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 227.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0117, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 229.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0108, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 230.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0093, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 231.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0093, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 233.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0102, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 234.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0089, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 234.59, | |
| "eval_exact_match": 0.5541586073500967, | |
| "eval_exec": 0.5705996131528046, | |
| "eval_loss": 0.3015965521335602, | |
| "eval_runtime": 262.7972, | |
| "eval_samples_per_second": 3.935, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 235.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0088, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 237.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0105, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 238.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0097, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 239.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0088, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 241.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0091, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 242.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0084, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 243.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0084, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 245.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0089, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 246.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0078, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 247.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0082, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 249.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0085, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 250.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0079, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 251.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0076, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 253.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0083, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 254.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0074, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 255.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0068, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 255.88, | |
| "eval_exact_match": 0.539651837524178, | |
| "eval_exec": 0.5638297872340425, | |
| "eval_loss": 0.31391018629074097, | |
| "eval_runtime": 267.4324, | |
| "eval_samples_per_second": 3.866, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 257.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0082, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 258.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0075, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 259.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0075, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 261.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0072, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 262.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0064, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 263.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0069, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 265.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0076, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 266.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0068, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 267.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.007, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 269.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0109, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 270.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0085, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 271.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0063, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 273.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.007, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 274.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0116, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 275.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0066, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 277.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0063, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 277.29, | |
| "eval_exact_match": 0.5435203094777563, | |
| "eval_exec": 0.5725338491295938, | |
| "eval_loss": 0.3146398961544037, | |
| "eval_runtime": 268.4091, | |
| "eval_samples_per_second": 3.852, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 278.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.006, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 279.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0057, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 281.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0058, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 282.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0055, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 283.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0057, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 285.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0059, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 286.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0059, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 287.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0074, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 289.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.007, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 290.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0053, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 291.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0049, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 293.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0057, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 294.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0046, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 295.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0051, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 297.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0056, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 298.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0053, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 298.59, | |
| "eval_exact_match": 0.5618955512572534, | |
| "eval_exec": 0.5870406189555126, | |
| "eval_loss": 0.32914912700653076, | |
| "eval_runtime": 267.6158, | |
| "eval_samples_per_second": 3.864, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 299.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0047, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 301.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.005, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 302.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0045, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 303.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0049, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 305.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0051, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 306.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0046, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 307.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.005, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 309.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0049, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 310.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0045, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 311.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0045, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 313.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 314.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0041, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 315.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0045, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 317.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0045, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 318.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0043, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 319.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0039, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 319.88, | |
| "eval_exact_match": 0.5560928433268859, | |
| "eval_exec": 0.5793036750483559, | |
| "eval_loss": 0.33885231614112854, | |
| "eval_runtime": 265.1484, | |
| "eval_samples_per_second": 3.9, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 321.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0046, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 322.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0041, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 323.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0043, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 325.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0042, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 326.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.004, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 327.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0041, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 329.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0041, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 330.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0037, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 331.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0036, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 333.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0041, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 334.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0039, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 335.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 337.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 338.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0036, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 339.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0036, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 341.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.004, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 341.29, | |
| "eval_exact_match": 0.5638297872340425, | |
| "eval_exec": 0.59284332688588, | |
| "eval_loss": 0.3441130816936493, | |
| "eval_runtime": 266.7629, | |
| "eval_samples_per_second": 3.876, | |
| "step": 1024 | |
| } | |
| ], | |
| "max_steps": 9216, | |
| "num_train_epochs": 3072, | |
| "total_flos": 1.369738171126656e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |