Safetensors
Eval Results
Luminex-72B-v0.1 / trainer_log.jsonl
NeuralNovel's picture
Upload folder using huggingface_hub
767248b verified
raw
history blame
19.8 kB
{"current_steps": 5, "total_steps": 396, "loss": 2.8429, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009996066923030483, "epoch": 0.04, "percentage": 1.26, "elapsed_time": "0:00:51", "remaining_time": "1:07:21"}
{"current_steps": 10, "total_steps": 396, "loss": 1.7586, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009984273879759713, "epoch": 0.08, "percentage": 2.53, "elapsed_time": "0:01:40", "remaining_time": "1:04:35"}
{"current_steps": 15, "total_steps": 396, "loss": 1.7084, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009964639423366442, "epoch": 0.11, "percentage": 3.79, "elapsed_time": "0:02:29", "remaining_time": "1:03:07"}
{"current_steps": 20, "total_steps": 396, "loss": 1.7022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009937194443381972, "epoch": 0.15, "percentage": 5.05, "elapsed_time": "0:03:17", "remaining_time": "1:01:57"}
{"current_steps": 25, "total_steps": 396, "loss": 1.436, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009901982117093786, "epoch": 0.19, "percentage": 6.31, "elapsed_time": "0:04:06", "remaining_time": "1:00:55"}
{"current_steps": 30, "total_steps": 396, "loss": 1.5345, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000985905784161771, "epoch": 0.23, "percentage": 7.58, "elapsed_time": "0:04:55", "remaining_time": "1:00:00"}
{"current_steps": 35, "total_steps": 396, "loss": 1.5542, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009808489146745465, "epoch": 0.26, "percentage": 8.84, "elapsed_time": "0:05:43", "remaining_time": "0:59:03"}
{"current_steps": 40, "total_steps": 396, "loss": 1.5173, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009750355588704727, "epoch": 0.3, "percentage": 10.1, "elapsed_time": "0:06:32", "remaining_time": "0:58:08"}
{"current_steps": 45, "total_steps": 396, "loss": 1.4094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000968474862499881, "epoch": 0.34, "percentage": 11.36, "elapsed_time": "0:07:20", "remaining_time": "0:57:18"}
{"current_steps": 50, "total_steps": 396, "loss": 1.6779, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009611771470522907, "epoch": 0.38, "percentage": 12.63, "elapsed_time": "0:08:08", "remaining_time": "0:56:23"}
{"current_steps": 55, "total_steps": 396, "loss": 1.593, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009531538935183251, "epoch": 0.41, "percentage": 13.89, "elapsed_time": "0:08:57", "remaining_time": "0:55:30"}
{"current_steps": 60, "total_steps": 396, "loss": 1.8026, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009444177243274617, "epoch": 0.45, "percentage": 15.15, "elapsed_time": "0:09:45", "remaining_time": "0:54:39"}
{"current_steps": 65, "total_steps": 396, "loss": 1.1646, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009349823834900395, "epoch": 0.49, "percentage": 16.41, "elapsed_time": "0:10:36", "remaining_time": "0:54:00"}
{"current_steps": 70, "total_steps": 396, "loss": 1.4566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009248627149747573, "epoch": 0.53, "percentage": 17.68, "elapsed_time": "0:11:24", "remaining_time": "0:53:08"}
{"current_steps": 75, "total_steps": 396, "loss": 1.3848, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009140746393556853, "epoch": 0.56, "percentage": 18.94, "elapsed_time": "0:12:13", "remaining_time": "0:52:19"}
{"current_steps": 80, "total_steps": 396, "loss": 1.6641, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009026351287655293, "epoch": 0.6, "percentage": 20.2, "elapsed_time": "0:13:01", "remaining_time": "0:51:28"}
{"current_steps": 85, "total_steps": 396, "loss": 1.2664, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008905621801945467, "epoch": 0.64, "percentage": 21.46, "elapsed_time": "0:13:50", "remaining_time": "0:50:40"}
{"current_steps": 90, "total_steps": 396, "loss": 1.4103, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008778747871771292, "epoch": 0.68, "percentage": 22.73, "elapsed_time": "0:14:40", "remaining_time": "0:49:52"}
{"current_steps": 95, "total_steps": 396, "loss": 1.3391, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008645929099105886, "epoch": 0.72, "percentage": 23.99, "elapsed_time": "0:15:28", "remaining_time": "0:49:03"}
{"current_steps": 100, "total_steps": 396, "loss": 1.3329, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008507374438531607, "epoch": 0.75, "percentage": 25.25, "elapsed_time": "0:16:17", "remaining_time": "0:48:13"}
{"current_steps": 105, "total_steps": 396, "loss": 1.4708, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008363301868506264, "epoch": 0.79, "percentage": 26.52, "elapsed_time": "0:17:07", "remaining_time": "0:47:26"}
{"current_steps": 110, "total_steps": 396, "loss": 1.5326, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008213938048432696, "epoch": 0.83, "percentage": 27.78, "elapsed_time": "0:17:56", "remaining_time": "0:46:37"}
{"current_steps": 115, "total_steps": 396, "loss": 1.5317, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008059517962071233, "epoch": 0.87, "percentage": 29.04, "elapsed_time": "0:18:45", "remaining_time": "0:45:49"}
{"current_steps": 120, "total_steps": 396, "loss": 1.2481, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007900284547855992, "epoch": 0.9, "percentage": 30.3, "elapsed_time": "0:19:34", "remaining_time": "0:45:00"}
{"current_steps": 125, "total_steps": 396, "loss": 1.4773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007736488316696662, "epoch": 0.94, "percentage": 31.57, "elapsed_time": "0:20:23", "remaining_time": "0:44:11"}
{"current_steps": 130, "total_steps": 396, "loss": 1.2638, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007568386957867032, "epoch": 0.98, "percentage": 32.83, "elapsed_time": "0:21:11", "remaining_time": "0:43:22"}
{"current_steps": 135, "total_steps": 396, "loss": 1.2867, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007396244933600284, "epoch": 1.02, "percentage": 34.09, "elapsed_time": "0:22:00", "remaining_time": "0:42:32"}
{"current_steps": 140, "total_steps": 396, "loss": 1.0248, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007220333063028871, "epoch": 1.05, "percentage": 35.35, "elapsed_time": "0:22:48", "remaining_time": "0:41:43"}
{"current_steps": 145, "total_steps": 396, "loss": 1.0408, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007040928096123516, "epoch": 1.09, "percentage": 36.62, "elapsed_time": "0:23:37", "remaining_time": "0:40:54"}
{"current_steps": 150, "total_steps": 396, "loss": 1.1847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006858312278301637, "epoch": 1.13, "percentage": 37.88, "elapsed_time": "0:24:26", "remaining_time": "0:40:05"}
{"current_steps": 155, "total_steps": 396, "loss": 0.9884, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006672772906390176, "epoch": 1.17, "percentage": 39.14, "elapsed_time": "0:25:15", "remaining_time": "0:39:15"}
{"current_steps": 160, "total_steps": 396, "loss": 1.0086, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006484601876641375, "epoch": 1.21, "percentage": 40.4, "elapsed_time": "0:26:03", "remaining_time": "0:38:26"}
{"current_steps": 165, "total_steps": 396, "loss": 1.0438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006294095225512603, "epoch": 1.24, "percentage": 41.67, "elapsed_time": "0:26:52", "remaining_time": "0:37:37"}
{"current_steps": 170, "total_steps": 396, "loss": 0.9305, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006101552663932703, "epoch": 1.28, "percentage": 42.93, "elapsed_time": "0:27:40", "remaining_time": "0:36:48"}
{"current_steps": 175, "total_steps": 396, "loss": 1.0619, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005907277105787513, "epoch": 1.32, "percentage": 44.19, "elapsed_time": "0:28:30", "remaining_time": "0:35:59"}
{"current_steps": 180, "total_steps": 396, "loss": 1.5694, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005711574191366427, "epoch": 1.36, "percentage": 45.45, "elapsed_time": "0:29:18", "remaining_time": "0:35:10"}
{"current_steps": 185, "total_steps": 396, "loss": 1.0704, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005514751806519673, "epoch": 1.39, "percentage": 46.72, "elapsed_time": "0:30:07", "remaining_time": "0:34:22"}
{"current_steps": 190, "total_steps": 396, "loss": 1.1666, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005317119598282822, "epoch": 1.43, "percentage": 47.98, "elapsed_time": "0:30:56", "remaining_time": "0:33:33"}
{"current_steps": 195, "total_steps": 396, "loss": 0.9914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005118988487730537, "epoch": 1.47, "percentage": 49.24, "elapsed_time": "0:31:45", "remaining_time": "0:32:44"}
{"current_steps": 200, "total_steps": 396, "loss": 1.0523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000492067018082596, "epoch": 1.51, "percentage": 50.51, "elapsed_time": "0:32:34", "remaining_time": "0:31:55"}
{"current_steps": 205, "total_steps": 396, "loss": 0.9491, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00047224766780353, "epoch": 1.54, "percentage": 51.77, "elapsed_time": "0:33:23", "remaining_time": "0:31:06"}
{"current_steps": 210, "total_steps": 396, "loss": 1.041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004524719783479088, "epoch": 1.58, "percentage": 53.03, "elapsed_time": "0:34:12", "remaining_time": "0:30:17"}
{"current_steps": 215, "total_steps": 396, "loss": 1.237, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004327710614392341, "epoch": 1.62, "percentage": 54.29, "elapsed_time": "0:35:02", "remaining_time": "0:29:29"}
{"current_steps": 220, "total_steps": 396, "loss": 1.0301, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00041317591116653486, "epoch": 1.66, "percentage": 55.56, "elapsed_time": "0:35:51", "remaining_time": "0:28:41"}
{"current_steps": 225, "total_steps": 396, "loss": 1.0687, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00039371735522351166, "epoch": 1.69, "percentage": 56.82, "elapsed_time": "0:36:40", "remaining_time": "0:27:52"}
{"current_steps": 230, "total_steps": 396, "loss": 0.9959, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00037442600640946044, "epoch": 1.73, "percentage": 58.08, "elapsed_time": "0:37:29", "remaining_time": "0:27:03"}
{"current_steps": 235, "total_steps": 396, "loss": 0.9951, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003553322144682737, "epoch": 1.77, "percentage": 59.34, "elapsed_time": "0:38:18", "remaining_time": "0:26:14"}
{"current_steps": 240, "total_steps": 396, "loss": 1.1158, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003364660183412892, "epoch": 1.81, "percentage": 60.61, "elapsed_time": "0:39:06", "remaining_time": "0:25:25"}
{"current_steps": 245, "total_steps": 396, "loss": 1.2224, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003178570989091028, "epoch": 1.85, "percentage": 61.87, "elapsed_time": "0:39:55", "remaining_time": "0:24:36"}
{"current_steps": 250, "total_steps": 396, "loss": 1.0617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029953473229669324, "epoch": 1.88, "percentage": 63.13, "elapsed_time": "0:40:43", "remaining_time": "0:23:47"}
{"current_steps": 255, "total_steps": 396, "loss": 0.9955, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002815277438153203, "epoch": 1.92, "percentage": 64.39, "elapsed_time": "0:41:32", "remaining_time": "0:22:58"}
{"current_steps": 260, "total_steps": 396, "loss": 0.9129, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002638644626136587, "epoch": 1.96, "percentage": 65.66, "elapsed_time": "0:42:21", "remaining_time": "0:22:09"}
{"current_steps": 265, "total_steps": 396, "loss": 1.0105, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00024657267710950857, "epoch": 2.0, "percentage": 66.92, "elapsed_time": "0:43:10", "remaining_time": "0:21:20"}
{"current_steps": 270, "total_steps": 396, "loss": 0.7617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002296795912722014, "epoch": 2.03, "percentage": 68.18, "elapsed_time": "0:43:59", "remaining_time": "0:20:31"}
{"current_steps": 275, "total_steps": 396, "loss": 0.629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021321178182447708, "epoch": 2.07, "percentage": 69.44, "elapsed_time": "0:44:48", "remaining_time": "0:19:42"}
{"current_steps": 280, "total_steps": 396, "loss": 0.7202, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019719515643116677, "epoch": 2.11, "percentage": 70.71, "elapsed_time": "0:45:37", "remaining_time": "0:18:54"}
{"current_steps": 285, "total_steps": 396, "loss": 0.7211, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018165491294045593, "epoch": 2.15, "percentage": 71.97, "elapsed_time": "0:46:26", "remaining_time": "0:18:05"}
{"current_steps": 290, "total_steps": 396, "loss": 0.6464, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016661549974185424, "epoch": 2.18, "percentage": 73.23, "elapsed_time": "0:47:15", "remaining_time": "0:17:16"}
{"current_steps": 295, "total_steps": 396, "loss": 0.6799, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015210057730323618, "epoch": 2.22, "percentage": 74.49, "elapsed_time": "0:48:05", "remaining_time": "0:16:27"}
{"current_steps": 300, "total_steps": 396, "loss": 0.6218, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001381329809474649, "epoch": 2.26, "percentage": 75.76, "elapsed_time": "0:48:54", "remaining_time": "0:15:38"}
{"current_steps": 305, "total_steps": 396, "loss": 0.7277, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012473468492715895, "epoch": 2.3, "percentage": 77.02, "elapsed_time": "0:49:43", "remaining_time": "0:14:50"}
{"current_steps": 310, "total_steps": 396, "loss": 0.6244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011192676785412154, "epoch": 2.34, "percentage": 78.28, "elapsed_time": "0:50:32", "remaining_time": "0:14:01"}
{"current_steps": 315, "total_steps": 396, "loss": 0.6352, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.972937953781985e-05, "epoch": 2.37, "percentage": 79.55, "elapsed_time": "0:51:21", "remaining_time": "0:13:12"}
{"current_steps": 320, "total_steps": 396, "loss": 0.6462, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.816170928508365e-05, "epoch": 2.41, "percentage": 80.81, "elapsed_time": "0:52:09", "remaining_time": "0:12:23"}
{"current_steps": 325, "total_steps": 396, "loss": 0.6377, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.724195571089787e-05, "epoch": 2.45, "percentage": 82.07, "elapsed_time": "0:52:58", "remaining_time": "0:11:34"}
{"current_steps": 330, "total_steps": 396, "loss": 0.7165, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.698729810778065e-05, "epoch": 2.49, "percentage": 83.33, "elapsed_time": "0:53:46", "remaining_time": "0:10:45"}
{"current_steps": 335, "total_steps": 396, "loss": 0.6948, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.741386941879179e-05, "epoch": 2.52, "percentage": 84.6, "elapsed_time": "0:54:34", "remaining_time": "0:09:56"}
{"current_steps": 340, "total_steps": 396, "loss": 0.6849, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.853673085668947e-05, "epoch": 2.56, "percentage": 85.86, "elapsed_time": "0:55:22", "remaining_time": "0:09:07"}
{"current_steps": 345, "total_steps": 396, "loss": 0.6742, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.036984820916722e-05, "epoch": 2.6, "percentage": 87.12, "elapsed_time": "0:56:11", "remaining_time": "0:08:18"}
{"current_steps": 350, "total_steps": 396, "loss": 0.7078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.292606986744667e-05, "epoch": 2.64, "percentage": 88.38, "elapsed_time": "0:57:00", "remaining_time": "0:07:29"}
{"current_steps": 355, "total_steps": 396, "loss": 0.6499, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6217106612792528e-05, "epoch": 2.67, "percentage": 89.65, "elapsed_time": "0:57:49", "remaining_time": "0:06:40"}
{"current_steps": 360, "total_steps": 396, "loss": 0.6878, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.025351319275137e-05, "epoch": 2.71, "percentage": 90.91, "elapsed_time": "0:58:37", "remaining_time": "0:05:51"}
{"current_steps": 365, "total_steps": 396, "loss": 0.5469, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5044671716097413e-05, "epoch": 2.75, "percentage": 92.17, "elapsed_time": "0:59:26", "remaining_time": "0:05:02"}
{"current_steps": 370, "total_steps": 396, "loss": 0.7233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0598776892610684e-05, "epoch": 2.79, "percentage": 93.43, "elapsed_time": "1:00:15", "remaining_time": "0:04:14"}
{"current_steps": 375, "total_steps": 396, "loss": 0.7482, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.9228231409067535e-06, "epoch": 2.82, "percentage": 94.7, "elapsed_time": "1:01:03", "remaining_time": "0:03:25"}
{"current_steps": 380, "total_steps": 396, "loss": 0.6865, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.02259358460233e-06, "epoch": 2.86, "percentage": 95.96, "elapsed_time": "1:01:52", "remaining_time": "0:02:36"}
{"current_steps": 385, "total_steps": 396, "loss": 0.6953, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9026509541272275e-06, "epoch": 2.9, "percentage": 97.22, "elapsed_time": "1:02:41", "remaining_time": "0:01:47"}
{"current_steps": 390, "total_steps": 396, "loss": 0.671, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.663304084960185e-07, "epoch": 2.94, "percentage": 98.48, "elapsed_time": "1:03:30", "remaining_time": "0:00:58"}
{"current_steps": 395, "total_steps": 396, "loss": 0.6152, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.573428833345769e-08, "epoch": 2.98, "percentage": 99.75, "elapsed_time": "1:04:19", "remaining_time": "0:00:09"}
{"current_steps": 396, "total_steps": 396, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.98, "percentage": 100.0, "elapsed_time": "1:04:28", "remaining_time": "0:00:00"}