llama_8b_lima_11_dpo / trainer_log.jsonl
OpenLeecher's picture
Model save
1a55e37 verified
raw
history blame
14.9 kB
{"current_steps": 5, "total_steps": 302, "loss": 1.0783, "accuracy": 0.30000001192092896, "learning_rate": 5e-07, "epoch": 0.016512549537648614, "percentage": 1.66, "elapsed_time": "0:02:10", "remaining_time": "2:09:36"}
{"current_steps": 10, "total_steps": 302, "loss": 1.0498, "accuracy": 0.5799999833106995, "learning_rate": 1e-06, "epoch": 0.03302509907529723, "percentage": 3.31, "elapsed_time": "0:04:04", "remaining_time": "1:58:58"}
{"current_steps": 15, "total_steps": 302, "loss": 1.0541, "accuracy": 0.7599999904632568, "learning_rate": 1.5e-06, "epoch": 0.04953764861294584, "percentage": 4.97, "elapsed_time": "0:06:19", "remaining_time": "2:01:01"}
{"current_steps": 20, "total_steps": 302, "loss": 0.9858, "accuracy": 0.6800000071525574, "learning_rate": 2e-06, "epoch": 0.06605019815059446, "percentage": 6.62, "elapsed_time": "0:08:26", "remaining_time": "1:58:56"}
{"current_steps": 25, "total_steps": 302, "loss": 0.962, "accuracy": 0.8199999928474426, "learning_rate": 1.933221417433731e-06, "epoch": 0.08256274768824307, "percentage": 8.28, "elapsed_time": "0:10:31", "remaining_time": "1:56:39"}
{"current_steps": 30, "total_steps": 302, "loss": 0.9123, "accuracy": 0.7799999713897705, "learning_rate": 1.8676374427845679e-06, "epoch": 0.09907529722589167, "percentage": 9.93, "elapsed_time": "0:12:33", "remaining_time": "1:53:47"}
{"current_steps": 35, "total_steps": 302, "loss": 0.9206, "accuracy": 0.8999999761581421, "learning_rate": 1.8032480760525125e-06, "epoch": 0.1155878467635403, "percentage": 11.59, "elapsed_time": "0:14:41", "remaining_time": "1:52:06"}
{"current_steps": 40, "total_steps": 302, "loss": 0.8675, "accuracy": 0.8600000143051147, "learning_rate": 1.7400533172375636e-06, "epoch": 0.13210039630118892, "percentage": 13.25, "elapsed_time": "0:16:37", "remaining_time": "1:48:55"}
{"current_steps": 45, "total_steps": 302, "loss": 0.868, "accuracy": 0.8600000143051147, "learning_rate": 1.6780531663397214e-06, "epoch": 0.14861294583883752, "percentage": 14.9, "elapsed_time": "0:18:39", "remaining_time": "1:46:32"}
{"current_steps": 50, "total_steps": 302, "loss": 0.7922, "accuracy": 0.8199999928474426, "learning_rate": 1.6172476233589857e-06, "epoch": 0.16512549537648613, "percentage": 16.56, "elapsed_time": "0:20:43", "remaining_time": "1:44:27"}
{"current_steps": 55, "total_steps": 302, "loss": 0.8404, "accuracy": 0.8199999928474426, "learning_rate": 1.5576366882953572e-06, "epoch": 0.18163804491413474, "percentage": 18.21, "elapsed_time": "0:23:06", "remaining_time": "1:43:45"}
{"current_steps": 60, "total_steps": 302, "loss": 0.7906, "accuracy": 0.8399999737739563, "learning_rate": 1.4992203611488356e-06, "epoch": 0.19815059445178335, "percentage": 19.87, "elapsed_time": "0:25:08", "remaining_time": "1:41:24"}
{"current_steps": 65, "total_steps": 302, "loss": 0.894, "accuracy": 0.8600000143051147, "learning_rate": 1.4419986419194208e-06, "epoch": 0.21466314398943198, "percentage": 21.52, "elapsed_time": "0:27:19", "remaining_time": "1:39:38"}
{"current_steps": 70, "total_steps": 302, "loss": 0.8145, "accuracy": 0.8999999761581421, "learning_rate": 1.385971530607112e-06, "epoch": 0.2311756935270806, "percentage": 23.18, "elapsed_time": "0:29:23", "remaining_time": "1:37:26"}
{"current_steps": 75, "total_steps": 302, "loss": 0.8172, "accuracy": 0.8199999928474426, "learning_rate": 1.3311390272119108e-06, "epoch": 0.2476882430647292, "percentage": 24.83, "elapsed_time": "0:31:22", "remaining_time": "1:34:58"}
{"current_steps": 80, "total_steps": 302, "loss": 0.8404, "accuracy": 0.8399999737739563, "learning_rate": 1.2775011317338164e-06, "epoch": 0.26420079260237783, "percentage": 26.49, "elapsed_time": "0:33:27", "remaining_time": "1:32:51"}
{"current_steps": 85, "total_steps": 302, "loss": 0.7826, "accuracy": 0.9599999785423279, "learning_rate": 1.225057844172828e-06, "epoch": 0.2807133421400264, "percentage": 28.15, "elapsed_time": "0:35:26", "remaining_time": "1:30:29"}
{"current_steps": 90, "total_steps": 302, "loss": 0.7617, "accuracy": 0.8999999761581421, "learning_rate": 1.1738091645289474e-06, "epoch": 0.29722589167767505, "percentage": 29.8, "elapsed_time": "0:37:28", "remaining_time": "1:28:15"}
{"current_steps": 90, "total_steps": 302, "eval_loss": 0.7245407700538635, "epoch": 0.29722589167767505, "percentage": 29.8, "elapsed_time": "0:38:55", "remaining_time": "1:31:41"}
{"current_steps": 95, "total_steps": 302, "loss": 0.8122, "accuracy": 0.8799999952316284, "learning_rate": 1.1237550928021727e-06, "epoch": 0.3137384412153236, "percentage": 31.46, "elapsed_time": "0:40:48", "remaining_time": "1:28:55"}
{"current_steps": 100, "total_steps": 302, "loss": 0.762, "accuracy": 0.9399999976158142, "learning_rate": 1.0748956289925052e-06, "epoch": 0.33025099075297226, "percentage": 33.11, "elapsed_time": "0:42:30", "remaining_time": "1:25:52"}
{"current_steps": 105, "total_steps": 302, "loss": 0.7614, "accuracy": 0.9399999976158142, "learning_rate": 1.0272307730999448e-06, "epoch": 0.3467635402906209, "percentage": 34.77, "elapsed_time": "0:44:23", "remaining_time": "1:23:17"}
{"current_steps": 110, "total_steps": 302, "loss": 0.7581, "accuracy": 0.9399999976158142, "learning_rate": 9.807605251244908e-07, "epoch": 0.3632760898282695, "percentage": 36.42, "elapsed_time": "0:46:16", "remaining_time": "1:20:46"}
{"current_steps": 115, "total_steps": 302, "loss": 0.797, "accuracy": 0.8600000143051147, "learning_rate": 9.354848850661436e-07, "epoch": 0.3797886393659181, "percentage": 38.08, "elapsed_time": "0:48:05", "remaining_time": "1:18:12"}
{"current_steps": 120, "total_steps": 302, "loss": 0.7473, "accuracy": 0.9399999976158142, "learning_rate": 8.91403852924903e-07, "epoch": 0.3963011889035667, "percentage": 39.74, "elapsed_time": "0:49:54", "remaining_time": "1:15:40"}
{"current_steps": 125, "total_steps": 302, "loss": 0.7539, "accuracy": 0.9200000166893005, "learning_rate": 8.485174287007695e-07, "epoch": 0.4128137384412153, "percentage": 41.39, "elapsed_time": "0:51:51", "remaining_time": "1:13:25"}
{"current_steps": 130, "total_steps": 302, "loss": 0.7982, "accuracy": 0.8999999761581421, "learning_rate": 8.068256123937427e-07, "epoch": 0.42932628797886396, "percentage": 43.05, "elapsed_time": "0:53:49", "remaining_time": "1:11:13"}
{"current_steps": 135, "total_steps": 302, "loss": 0.7755, "accuracy": 0.800000011920929, "learning_rate": 7.663284040038229e-07, "epoch": 0.44583883751651254, "percentage": 44.7, "elapsed_time": "0:55:46", "remaining_time": "1:08:59"}
{"current_steps": 140, "total_steps": 302, "loss": 0.75, "accuracy": 0.8999999761581421, "learning_rate": 7.270258035310096e-07, "epoch": 0.4623513870541612, "percentage": 46.36, "elapsed_time": "0:57:39", "remaining_time": "1:06:43"}
{"current_steps": 145, "total_steps": 302, "loss": 0.7353, "accuracy": 0.9399999976158142, "learning_rate": 6.889178109753032e-07, "epoch": 0.47886393659180976, "percentage": 48.01, "elapsed_time": "0:59:25", "remaining_time": "1:04:20"}
{"current_steps": 150, "total_steps": 302, "loss": 0.7746, "accuracy": 0.9399999976158142, "learning_rate": 6.520044263367035e-07, "epoch": 0.4953764861294584, "percentage": 49.67, "elapsed_time": "1:01:10", "remaining_time": "1:01:59"}
{"current_steps": 155, "total_steps": 302, "loss": 0.7189, "accuracy": 0.9599999785423279, "learning_rate": 6.162856496152104e-07, "epoch": 0.511889035667107, "percentage": 51.32, "elapsed_time": "1:02:55", "remaining_time": "0:59:40"}
{"current_steps": 160, "total_steps": 302, "loss": 0.7417, "accuracy": 0.8999999761581421, "learning_rate": 5.817614808108243e-07, "epoch": 0.5284015852047557, "percentage": 52.98, "elapsed_time": "1:04:50", "remaining_time": "0:57:32"}
{"current_steps": 165, "total_steps": 302, "loss": 0.7836, "accuracy": 0.8600000143051147, "learning_rate": 5.48431919923545e-07, "epoch": 0.5449141347424042, "percentage": 54.64, "elapsed_time": "1:06:47", "remaining_time": "0:55:27"}
{"current_steps": 170, "total_steps": 302, "loss": 0.7627, "accuracy": 0.8799999952316284, "learning_rate": 5.162969669533726e-07, "epoch": 0.5614266842800528, "percentage": 56.29, "elapsed_time": "1:08:34", "remaining_time": "0:53:14"}
{"current_steps": 175, "total_steps": 302, "loss": 0.7018, "accuracy": 0.8999999761581421, "learning_rate": 4.853566219003069e-07, "epoch": 0.5779392338177014, "percentage": 57.95, "elapsed_time": "1:10:20", "remaining_time": "0:51:03"}
{"current_steps": 180, "total_steps": 302, "loss": 0.7151, "accuracy": 0.8799999952316284, "learning_rate": 4.556108847643478e-07, "epoch": 0.5944517833553501, "percentage": 59.6, "elapsed_time": "1:12:10", "remaining_time": "0:48:55"}
{"current_steps": 180, "total_steps": 302, "eval_loss": 0.6197755336761475, "epoch": 0.5944517833553501, "percentage": 59.6, "elapsed_time": "1:13:38", "remaining_time": "0:49:54"}
{"current_steps": 185, "total_steps": 302, "loss": 0.7518, "accuracy": 0.9800000190734863, "learning_rate": 4.270597555454957e-07, "epoch": 0.6109643328929987, "percentage": 61.26, "elapsed_time": "1:15:34", "remaining_time": "0:47:48"}
{"current_steps": 190, "total_steps": 302, "loss": 0.7339, "accuracy": 0.8199999928474426, "learning_rate": 3.997032342437503e-07, "epoch": 0.6274768824306473, "percentage": 62.91, "elapsed_time": "1:17:13", "remaining_time": "0:45:31"}
{"current_steps": 195, "total_steps": 302, "loss": 0.7328, "accuracy": 0.9200000166893005, "learning_rate": 3.7354132085911176e-07, "epoch": 0.6439894319682959, "percentage": 64.57, "elapsed_time": "1:18:59", "remaining_time": "0:43:20"}
{"current_steps": 200, "total_steps": 302, "loss": 0.719, "accuracy": 0.9599999785423279, "learning_rate": 3.4857401539157985e-07, "epoch": 0.6605019815059445, "percentage": 66.23, "elapsed_time": "1:20:49", "remaining_time": "0:41:13"}
{"current_steps": 205, "total_steps": 302, "loss": 0.6845, "accuracy": 0.9399999976158142, "learning_rate": 3.2480131784115487e-07, "epoch": 0.6770145310435931, "percentage": 67.88, "elapsed_time": "1:22:32", "remaining_time": "0:39:03"}
{"current_steps": 210, "total_steps": 302, "loss": 0.7059, "accuracy": 0.8999999761581421, "learning_rate": 3.0222322820783666e-07, "epoch": 0.6935270805812418, "percentage": 69.54, "elapsed_time": "1:24:29", "remaining_time": "0:37:00"}
{"current_steps": 215, "total_steps": 302, "loss": 0.7038, "accuracy": 0.8600000143051147, "learning_rate": 2.808397464916251e-07, "epoch": 0.7100396301188904, "percentage": 71.19, "elapsed_time": "1:26:19", "remaining_time": "0:34:55"}
{"current_steps": 220, "total_steps": 302, "loss": 0.6877, "accuracy": 0.8799999952316284, "learning_rate": 2.6065087269252046e-07, "epoch": 0.726552179656539, "percentage": 72.85, "elapsed_time": "1:28:12", "remaining_time": "0:32:52"}
{"current_steps": 225, "total_steps": 302, "loss": 0.7041, "accuracy": 0.9800000190734863, "learning_rate": 2.4165660681052263e-07, "epoch": 0.7430647291941875, "percentage": 74.5, "elapsed_time": "1:30:09", "remaining_time": "0:30:51"}
{"current_steps": 230, "total_steps": 302, "loss": 0.6885, "accuracy": 0.9599999785423279, "learning_rate": 2.2385694884563155e-07, "epoch": 0.7595772787318362, "percentage": 76.16, "elapsed_time": "1:31:52", "remaining_time": "0:28:45"}
{"current_steps": 235, "total_steps": 302, "loss": 0.7388, "accuracy": 0.8799999952316284, "learning_rate": 2.0725189879784716e-07, "epoch": 0.7760898282694848, "percentage": 77.81, "elapsed_time": "1:33:42", "remaining_time": "0:26:42"}
{"current_steps": 240, "total_steps": 302, "loss": 0.7263, "accuracy": 0.8999999761581421, "learning_rate": 1.9184145666716962e-07, "epoch": 0.7926023778071334, "percentage": 79.47, "elapsed_time": "1:35:20", "remaining_time": "0:24:37"}
{"current_steps": 245, "total_steps": 302, "loss": 0.717, "accuracy": 0.9399999976158142, "learning_rate": 1.7762562245359894e-07, "epoch": 0.8091149273447821, "percentage": 81.13, "elapsed_time": "1:37:16", "remaining_time": "0:22:37"}
{"current_steps": 250, "total_steps": 302, "loss": 0.6991, "accuracy": 0.9200000166893005, "learning_rate": 1.6460439615713498e-07, "epoch": 0.8256274768824307, "percentage": 82.78, "elapsed_time": "1:38:54", "remaining_time": "0:20:34"}
{"current_steps": 255, "total_steps": 302, "loss": 0.6716, "accuracy": 0.9800000190734863, "learning_rate": 1.5277777777777774e-07, "epoch": 0.8421400264200792, "percentage": 84.44, "elapsed_time": "1:40:45", "remaining_time": "0:18:34"}
{"current_steps": 260, "total_steps": 302, "loss": 0.7101, "accuracy": 0.9200000166893005, "learning_rate": 1.4214576731552738e-07, "epoch": 0.8586525759577279, "percentage": 86.09, "elapsed_time": "1:42:22", "remaining_time": "0:16:32"}
{"current_steps": 265, "total_steps": 302, "loss": 0.7335, "accuracy": 0.8999999761581421, "learning_rate": 1.327083647703838e-07, "epoch": 0.8751651254953765, "percentage": 87.75, "elapsed_time": "1:44:11", "remaining_time": "0:14:32"}
{"current_steps": 270, "total_steps": 302, "loss": 0.6943, "accuracy": 0.9399999976158142, "learning_rate": 1.2446557014234698e-07, "epoch": 0.8916776750330251, "percentage": 89.4, "elapsed_time": "1:45:58", "remaining_time": "0:12:33"}
{"current_steps": 270, "total_steps": 302, "eval_loss": 0.5851023197174072, "epoch": 0.8916776750330251, "percentage": 89.4, "elapsed_time": "1:47:24", "remaining_time": "0:12:43"}
{"current_steps": 275, "total_steps": 302, "loss": 0.6891, "accuracy": 0.9200000166893005, "learning_rate": 1.1741738343141692e-07, "epoch": 0.9081902245706737, "percentage": 91.06, "elapsed_time": "1:49:10", "remaining_time": "0:10:43"}
{"current_steps": 280, "total_steps": 302, "loss": 0.7032, "accuracy": 0.8600000143051147, "learning_rate": 1.1156380463759368e-07, "epoch": 0.9247027741083224, "percentage": 92.72, "elapsed_time": "1:50:51", "remaining_time": "0:08:42"}
{"current_steps": 285, "total_steps": 302, "loss": 0.7021, "accuracy": 0.9399999976158142, "learning_rate": 1.0690483376087722e-07, "epoch": 0.9412153236459709, "percentage": 94.37, "elapsed_time": "1:52:31", "remaining_time": "0:06:42"}
{"current_steps": 290, "total_steps": 302, "loss": 0.7545, "accuracy": 0.9800000190734863, "learning_rate": 1.0344047080126753e-07, "epoch": 0.9577278731836195, "percentage": 96.03, "elapsed_time": "1:54:26", "remaining_time": "0:04:44"}
{"current_steps": 295, "total_steps": 302, "loss": 0.7387, "accuracy": 0.8799999952316284, "learning_rate": 1.0117071575876465e-07, "epoch": 0.9742404227212682, "percentage": 97.68, "elapsed_time": "1:56:14", "remaining_time": "0:02:45"}
{"current_steps": 300, "total_steps": 302, "loss": 0.732, "accuracy": 0.8600000143051147, "learning_rate": 1.0009556863336854e-07, "epoch": 0.9907529722589168, "percentage": 99.34, "elapsed_time": "1:57:50", "remaining_time": "0:00:47"}
{"current_steps": 302, "total_steps": 302, "epoch": 0.9973579920739762, "percentage": 100.0, "elapsed_time": "1:59:14", "remaining_time": "0:00:00"}