Llama-2-13B-fp16-french / QLoRA /trainer_log.jsonl
Nekochu's picture
QLoRA merge
719771a
raw
history blame
17.6 kB
{"current_steps": 5, "total_steps": 351, "loss": 4.067, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.997496987311431e-05, "epoch": 0.04, "percentage": 1.42, "elapsed_time": "0:00:58", "remaining_time": "1:07:26"}
{"current_steps": 10, "total_steps": 351, "loss": 4.1952, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.989992961303738e-05, "epoch": 0.08, "percentage": 2.85, "elapsed_time": "0:01:37", "remaining_time": "0:55:21"}
{"current_steps": 15, "total_steps": 351, "loss": 3.8727, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.977502948114772e-05, "epoch": 0.13, "percentage": 4.27, "elapsed_time": "0:02:13", "remaining_time": "0:49:41"}
{"current_steps": 20, "total_steps": 351, "loss": 3.894, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.960051957873725e-05, "epoch": 0.17, "percentage": 5.7, "elapsed_time": "0:02:49", "remaining_time": "0:46:49"}
{"current_steps": 25, "total_steps": 351, "loss": 3.7174, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9376749346206006e-05, "epoch": 0.21, "percentage": 7.12, "elapsed_time": "0:03:23", "remaining_time": "0:44:19"}
{"current_steps": 30, "total_steps": 351, "loss": 3.7136, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.910416686333906e-05, "epoch": 0.25, "percentage": 8.55, "elapsed_time": "0:03:59", "remaining_time": "0:42:38"}
{"current_steps": 35, "total_steps": 351, "loss": 3.4754, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.878331795206705e-05, "epoch": 0.3, "percentage": 9.97, "elapsed_time": "0:04:34", "remaining_time": "0:41:21"}
{"current_steps": 40, "total_steps": 351, "loss": 3.6711, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.841484508350679e-05, "epoch": 0.34, "percentage": 11.4, "elapsed_time": "0:05:07", "remaining_time": "0:39:50"}
{"current_steps": 45, "total_steps": 351, "loss": 3.4796, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.799948609147061e-05, "epoch": 0.38, "percentage": 12.82, "elapsed_time": "0:05:40", "remaining_time": "0:38:36"}
{"current_steps": 50, "total_steps": 351, "loss": 3.4441, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.753807269502041e-05, "epoch": 0.42, "percentage": 14.25, "elapsed_time": "0:06:20", "remaining_time": "0:38:11"}
{"current_steps": 55, "total_steps": 351, "loss": 3.603, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7031528833024976e-05, "epoch": 0.47, "percentage": 15.67, "elapsed_time": "0:06:55", "remaining_time": "0:37:17"}
{"current_steps": 60, "total_steps": 351, "loss": 3.4614, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6480868814055424e-05, "epoch": 0.51, "percentage": 17.09, "elapsed_time": "0:07:31", "remaining_time": "0:36:30"}
{"current_steps": 65, "total_steps": 351, "loss": 3.4613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.588719528532342e-05, "epoch": 0.55, "percentage": 18.52, "elapsed_time": "0:08:09", "remaining_time": "0:35:55"}
{"current_steps": 70, "total_steps": 351, "loss": 3.55, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5251697024729165e-05, "epoch": 0.59, "percentage": 19.94, "elapsed_time": "0:08:46", "remaining_time": "0:35:12"}
{"current_steps": 75, "total_steps": 351, "loss": 3.3352, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.457564656044056e-05, "epoch": 0.64, "percentage": 21.37, "elapsed_time": "0:09:21", "remaining_time": "0:34:26"}
{"current_steps": 80, "total_steps": 351, "loss": 3.3781, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3860397622769756e-05, "epoch": 0.68, "percentage": 22.79, "elapsed_time": "0:09:57", "remaining_time": "0:33:44"}
{"current_steps": 85, "total_steps": 351, "loss": 3.3805, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.310738243344996e-05, "epoch": 0.72, "percentage": 24.22, "elapsed_time": "0:10:34", "remaining_time": "0:33:07"}
{"current_steps": 90, "total_steps": 351, "loss": 3.2995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.231810883773999e-05, "epoch": 0.76, "percentage": 25.64, "elapsed_time": "0:11:13", "remaining_time": "0:32:32"}
{"current_steps": 95, "total_steps": 351, "loss": 3.1648, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.149415728509971e-05, "epoch": 0.81, "percentage": 27.07, "elapsed_time": "0:11:49", "remaining_time": "0:31:51"}
{"current_steps": 100, "total_steps": 351, "loss": 3.3295, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.063717766448194e-05, "epoch": 0.85, "percentage": 28.49, "elapsed_time": "0:12:23", "remaining_time": "0:31:05"}
{"current_steps": 105, "total_steps": 351, "loss": 3.2847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.974888600057808e-05, "epoch": 0.89, "percentage": 29.91, "elapsed_time": "0:13:00", "remaining_time": "0:30:28"}
{"current_steps": 110, "total_steps": 351, "loss": 3.25, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.883106101763285e-05, "epoch": 0.93, "percentage": 31.34, "elapsed_time": "0:13:37", "remaining_time": "0:29:51"}
{"current_steps": 115, "total_steps": 351, "loss": 3.2399, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7885540577708804e-05, "epoch": 0.98, "percentage": 32.76, "elapsed_time": "0:14:13", "remaining_time": "0:29:11"}
{"current_steps": 120, "total_steps": 351, "loss": 3.2125, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.69142180005327e-05, "epoch": 1.02, "percentage": 34.19, "elapsed_time": "0:14:50", "remaining_time": "0:28:33"}
{"current_steps": 125, "total_steps": 351, "loss": 3.3815, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.591903827229282e-05, "epoch": 1.06, "percentage": 35.61, "elapsed_time": "0:15:26", "remaining_time": "0:27:55"}
{"current_steps": 130, "total_steps": 351, "loss": 3.2365, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.490199415097892e-05, "epoch": 1.1, "percentage": 37.04, "elapsed_time": "0:16:04", "remaining_time": "0:27:20"}
{"current_steps": 135, "total_steps": 351, "loss": 3.2755, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.386512217606339e-05, "epoch": 1.15, "percentage": 38.46, "elapsed_time": "0:16:38", "remaining_time": "0:26:38"}
{"current_steps": 140, "total_steps": 351, "loss": 3.17, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.281049859051394e-05, "epoch": 1.19, "percentage": 39.89, "elapsed_time": "0:17:15", "remaining_time": "0:26:00"}
{"current_steps": 145, "total_steps": 351, "loss": 3.1125, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.17402351833036e-05, "epoch": 1.23, "percentage": 41.31, "elapsed_time": "0:17:53", "remaining_time": "0:25:25"}
{"current_steps": 150, "total_steps": 351, "loss": 3.3456, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0656475060743055e-05, "epoch": 1.27, "percentage": 42.74, "elapsed_time": "0:18:30", "remaining_time": "0:24:48"}
{"current_steps": 155, "total_steps": 351, "loss": 3.294, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.956138835510282e-05, "epoch": 1.32, "percentage": 44.16, "elapsed_time": "0:19:06", "remaining_time": "0:24:10"}
{"current_steps": 160, "total_steps": 351, "loss": 3.1764, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.845716787911833e-05, "epoch": 1.36, "percentage": 45.58, "elapsed_time": "0:19:43", "remaining_time": "0:23:32"}
{"current_steps": 165, "total_steps": 351, "loss": 3.3249, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7346024735079486e-05, "epoch": 1.4, "percentage": 47.01, "elapsed_time": "0:20:20", "remaining_time": "0:22:55"}
{"current_steps": 170, "total_steps": 351, "loss": 3.1499, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6230183887296955e-05, "epoch": 1.44, "percentage": 48.43, "elapsed_time": "0:20:57", "remaining_time": "0:22:18"}
{"current_steps": 175, "total_steps": 351, "loss": 3.1101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5111879706811087e-05, "epoch": 1.49, "percentage": 49.86, "elapsed_time": "0:21:31", "remaining_time": "0:21:39"}
{"current_steps": 180, "total_steps": 351, "loss": 3.266, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.399335149726463e-05, "epoch": 1.53, "percentage": 51.28, "elapsed_time": "0:22:06", "remaining_time": "0:20:59"}
{"current_steps": 185, "total_steps": 351, "loss": 3.2329, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2876839010898377e-05, "epoch": 1.57, "percentage": 52.71, "elapsed_time": "0:22:44", "remaining_time": "0:20:24"}
{"current_steps": 190, "total_steps": 351, "loss": 3.2465, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1764577963648614e-05, "epoch": 1.61, "percentage": 54.13, "elapsed_time": "0:23:21", "remaining_time": "0:19:47"}
{"current_steps": 195, "total_steps": 351, "loss": 3.2541, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0658795558326743e-05, "epoch": 1.66, "percentage": 55.56, "elapsed_time": "0:23:57", "remaining_time": "0:19:10"}
{"current_steps": 200, "total_steps": 351, "loss": 3.3382, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.956170602484582e-05, "epoch": 1.7, "percentage": 56.98, "elapsed_time": "0:24:33", "remaining_time": "0:18:32"}
{"current_steps": 205, "total_steps": 351, "loss": 3.3049, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8475506186424074e-05, "epoch": 1.74, "percentage": 58.4, "elapsed_time": "0:25:08", "remaining_time": "0:17:54"}
{"current_steps": 210, "total_steps": 351, "loss": 3.048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.740237106064383e-05, "epoch": 1.78, "percentage": 59.83, "elapsed_time": "0:25:46", "remaining_time": "0:17:18"}
{"current_steps": 215, "total_steps": 351, "loss": 3.2414, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6344449504174193e-05, "epoch": 1.83, "percentage": 61.25, "elapsed_time": "0:26:21", "remaining_time": "0:16:40"}
{"current_steps": 220, "total_steps": 351, "loss": 3.291, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.530385990987863e-05, "epoch": 1.87, "percentage": 62.68, "elapsed_time": "0:26:57", "remaining_time": "0:16:03"}
{"current_steps": 225, "total_steps": 351, "loss": 3.2234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4282685964923642e-05, "epoch": 1.91, "percentage": 64.1, "elapsed_time": "0:27:32", "remaining_time": "0:15:25"}
{"current_steps": 230, "total_steps": 351, "loss": 3.3281, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.328297247838241e-05, "epoch": 1.95, "percentage": 65.53, "elapsed_time": "0:28:04", "remaining_time": "0:14:46"}
{"current_steps": 235, "total_steps": 351, "loss": 3.0808, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.230672128668831e-05, "epoch": 2.0, "percentage": 66.95, "elapsed_time": "0:28:40", "remaining_time": "0:14:09"}
{"current_steps": 240, "total_steps": 351, "loss": 3.0843, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1355887245137383e-05, "epoch": 2.04, "percentage": 68.38, "elapsed_time": "0:29:16", "remaining_time": "0:13:32"}
{"current_steps": 245, "total_steps": 351, "loss": 3.263, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.043237431346622e-05, "epoch": 2.08, "percentage": 69.8, "elapsed_time": "0:29:52", "remaining_time": "0:12:55"}
{"current_steps": 250, "total_steps": 351, "loss": 3.0803, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.538031743343628e-06, "epoch": 2.12, "percentage": 71.23, "elapsed_time": "0:30:28", "remaining_time": "0:12:18"}
{"current_steps": 255, "total_steps": 351, "loss": 3.1773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.67465037541038e-06, "epoch": 2.17, "percentage": 72.65, "elapsed_time": "0:31:03", "remaining_time": "0:11:41"}
{"current_steps": 260, "total_steps": 351, "loss": 3.2543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.843959053281663e-06, "epoch": 2.21, "percentage": 74.07, "elapsed_time": "0:31:37", "remaining_time": "0:11:04"}
{"current_steps": 265, "total_steps": 351, "loss": 3.1697, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.047621161693152e-06, "epoch": 2.25, "percentage": 75.5, "elapsed_time": "0:32:13", "remaining_time": "0:10:27"}
{"current_steps": 270, "total_steps": 351, "loss": 3.2204, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.28723129572247e-06, "epoch": 2.29, "percentage": 76.92, "elapsed_time": "0:32:52", "remaining_time": "0:09:51"}
{"current_steps": 275, "total_steps": 351, "loss": 3.1626, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.564312067755856e-06, "epoch": 2.34, "percentage": 78.35, "elapsed_time": "0:33:26", "remaining_time": "0:09:14"}
{"current_steps": 280, "total_steps": 351, "loss": 3.2122, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.880311058593617e-06, "epoch": 2.38, "percentage": 79.77, "elapsed_time": "0:34:02", "remaining_time": "0:08:37"}
{"current_steps": 285, "total_steps": 351, "loss": 3.2038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.236597918799706e-06, "epoch": 2.42, "percentage": 81.2, "elapsed_time": "0:34:39", "remaining_time": "0:08:01"}
{"current_steps": 290, "total_steps": 351, "loss": 3.0183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6344616260994946e-06, "epoch": 2.46, "percentage": 82.62, "elapsed_time": "0:35:16", "remaining_time": "0:07:25"}
{"current_steps": 295, "total_steps": 351, "loss": 3.3333, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.07510790431767e-06, "epoch": 2.51, "percentage": 84.05, "elapsed_time": "0:35:51", "remaining_time": "0:06:48"}
{"current_steps": 300, "total_steps": 351, "loss": 3.1501, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5596568090246548e-06, "epoch": 2.55, "percentage": 85.47, "elapsed_time": "0:36:29", "remaining_time": "0:06:12"}
{"current_steps": 305, "total_steps": 351, "loss": 3.2576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0891404847259267e-06, "epoch": 2.59, "percentage": 86.89, "elapsed_time": "0:37:06", "remaining_time": "0:05:35"}
{"current_steps": 310, "total_steps": 351, "loss": 3.2306, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.664501098085408e-06, "epoch": 2.63, "percentage": 88.32, "elapsed_time": "0:37:41", "remaining_time": "0:04:59"}
{"current_steps": 315, "total_steps": 351, "loss": 2.9963, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.286588951321363e-06, "epoch": 2.68, "percentage": 89.74, "elapsed_time": "0:38:20", "remaining_time": "0:04:22"}
{"current_steps": 320, "total_steps": 351, "loss": 3.2718, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.561607795526007e-07, "epoch": 2.72, "percentage": 91.17, "elapsed_time": "0:38:54", "remaining_time": "0:03:46"}
{"current_steps": 325, "total_steps": 351, "loss": 3.2774, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.738782355044049e-07, "epoch": 2.76, "percentage": 92.59, "elapsed_time": "0:39:26", "remaining_time": "0:03:09"}
{"current_steps": 330, "total_steps": 351, "loss": 3.1737, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.403065646083809e-07, "epoch": 2.8, "percentage": 94.02, "elapsed_time": "0:40:02", "remaining_time": "0:02:32"}
{"current_steps": 335, "total_steps": 351, "loss": 3.2095, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.559134731492857e-07, "epoch": 2.85, "percentage": 95.44, "elapsed_time": "0:40:40", "remaining_time": "0:01:56"}
{"current_steps": 340, "total_steps": 351, "loss": 3.2731, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2106819172520434e-07, "epoch": 2.89, "percentage": 96.87, "elapsed_time": "0:41:16", "remaining_time": "0:01:20"}
{"current_steps": 345, "total_steps": 351, "loss": 3.0926, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.604073589645596e-08, "epoch": 2.93, "percentage": 98.29, "elapsed_time": "0:41:54", "remaining_time": "0:00:43"}
{"current_steps": 350, "total_steps": 351, "loss": 3.0457, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0013655036916759e-09, "epoch": 2.97, "percentage": 99.72, "elapsed_time": "0:42:33", "remaining_time": "0:00:07"}
{"current_steps": 351, "total_steps": 351, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.98, "percentage": 100.0, "elapsed_time": "0:42:40", "remaining_time": "0:00:00"}