svjack's picture
Upload folder using huggingface_hub
7547e01 verified
raw
history blame
9.12 kB
{"current_steps": 5, "total_steps": 186, "loss": 0.8099, "learning_rate": 4.9910902453260824e-05, "epoch": 0.08, "percentage": 2.69, "elapsed_time": "0:00:44", "remaining_time": "0:27:01", "throughput": "2566.78", "total_tokens": 114944}
{"current_steps": 10, "total_steps": 186, "loss": 0.958, "learning_rate": 4.964424488287009e-05, "epoch": 0.16, "percentage": 5.38, "elapsed_time": "0:01:29", "remaining_time": "0:26:16", "throughput": "2542.66", "total_tokens": 227728}
{"current_steps": 15, "total_steps": 186, "loss": 0.715, "learning_rate": 4.920192797165511e-05, "epoch": 0.24, "percentage": 8.06, "elapsed_time": "0:02:10", "remaining_time": "0:24:46", "throughput": "2505.70", "total_tokens": 326640}
{"current_steps": 20, "total_steps": 186, "loss": 0.7585, "learning_rate": 4.858710446774951e-05, "epoch": 0.32, "percentage": 10.75, "elapsed_time": "0:02:54", "remaining_time": "0:24:05", "throughput": "2511.00", "total_tokens": 437280}
{"current_steps": 25, "total_steps": 186, "loss": 0.7342, "learning_rate": 4.780415671242334e-05, "epoch": 0.4, "percentage": 13.44, "elapsed_time": "0:03:29", "remaining_time": "0:22:27", "throughput": "2533.17", "total_tokens": 530192}
{"current_steps": 30, "total_steps": 186, "loss": 0.6904, "learning_rate": 4.685866540361456e-05, "epoch": 0.48, "percentage": 16.13, "elapsed_time": "0:04:08", "remaining_time": "0:21:30", "throughput": "2557.91", "total_tokens": 634960}
{"current_steps": 35, "total_steps": 186, "loss": 0.8254, "learning_rate": 4.5757369817809415e-05, "epoch": 0.56, "percentage": 18.82, "elapsed_time": "0:04:46", "remaining_time": "0:20:35", "throughput": "2587.35", "total_tokens": 740704}
{"current_steps": 40, "total_steps": 186, "loss": 0.7551, "learning_rate": 4.45081197738023e-05, "epoch": 0.64, "percentage": 21.51, "elapsed_time": "0:05:26", "remaining_time": "0:19:51", "throughput": "2578.43", "total_tokens": 841600}
{"current_steps": 45, "total_steps": 186, "loss": 0.7747, "learning_rate": 4.3119819680728e-05, "epoch": 0.72, "percentage": 24.19, "elapsed_time": "0:06:07", "remaining_time": "0:19:10", "throughput": "2580.98", "total_tokens": 947648}
{"current_steps": 50, "total_steps": 186, "loss": 0.7027, "learning_rate": 4.160236506918098e-05, "epoch": 0.8, "percentage": 26.88, "elapsed_time": "0:06:46", "remaining_time": "0:18:24", "throughput": "2578.88", "total_tokens": 1047520}
{"current_steps": 55, "total_steps": 186, "loss": 0.7581, "learning_rate": 3.9966572057815373e-05, "epoch": 0.88, "percentage": 29.57, "elapsed_time": "0:07:24", "remaining_time": "0:17:39", "throughput": "2580.17", "total_tokens": 1148080}
{"current_steps": 60, "total_steps": 186, "loss": 0.7221, "learning_rate": 3.822410025817406e-05, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "0:08:05", "remaining_time": "0:16:58", "throughput": "2583.14", "total_tokens": 1252880}
{"current_steps": 65, "total_steps": 186, "loss": 0.8214, "learning_rate": 3.638736966726585e-05, "epoch": 1.04, "percentage": 34.95, "elapsed_time": "0:08:47", "remaining_time": "0:16:21", "throughput": "2587.56", "total_tokens": 1364304}
{"current_steps": 70, "total_steps": 186, "loss": 0.6304, "learning_rate": 3.44694721402644e-05, "epoch": 1.12, "percentage": 37.63, "elapsed_time": "0:09:28", "remaining_time": "0:15:41", "throughput": "2580.91", "total_tokens": 1466240}
{"current_steps": 75, "total_steps": 186, "loss": 0.6434, "learning_rate": 3.2484078074333954e-05, "epoch": 1.2, "percentage": 40.32, "elapsed_time": "0:10:04", "remaining_time": "0:14:55", "throughput": "2577.50", "total_tokens": 1558752}
{"current_steps": 80, "total_steps": 186, "loss": 0.6796, "learning_rate": 3.0445338968721287e-05, "epoch": 1.28, "percentage": 43.01, "elapsed_time": "0:10:47", "remaining_time": "0:14:18", "throughput": "2575.34", "total_tokens": 1668480}
{"current_steps": 85, "total_steps": 186, "loss": 0.6651, "learning_rate": 2.836778655564653e-05, "epoch": 1.3599999999999999, "percentage": 45.7, "elapsed_time": "0:11:27", "remaining_time": "0:13:36", "throughput": "2580.63", "total_tokens": 1773264}
{"current_steps": 90, "total_steps": 186, "loss": 0.7844, "learning_rate": 2.6266229220967818e-05, "epoch": 1.44, "percentage": 48.39, "elapsed_time": "0:12:09", "remaining_time": "0:12:57", "throughput": "2586.23", "total_tokens": 1885920}
{"current_steps": 95, "total_steps": 186, "loss": 0.8139, "learning_rate": 2.4155646452913296e-05, "epoch": 1.52, "percentage": 51.08, "elapsed_time": "0:12:53", "remaining_time": "0:12:20", "throughput": "2581.43", "total_tokens": 1996656}
{"current_steps": 100, "total_steps": 186, "loss": 0.6717, "learning_rate": 2.2051082071228854e-05, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "0:13:35", "remaining_time": "0:11:41", "throughput": "2578.63", "total_tokens": 2102896}
{"current_steps": 105, "total_steps": 186, "loss": 0.7524, "learning_rate": 1.9967536997783494e-05, "epoch": 1.6800000000000002, "percentage": 56.45, "elapsed_time": "0:14:18", "remaining_time": "0:11:02", "throughput": "2577.77", "total_tokens": 2214272}
{"current_steps": 110, "total_steps": 186, "loss": 0.631, "learning_rate": 1.79198623329424e-05, "epoch": 1.76, "percentage": 59.14, "elapsed_time": "0:14:58", "remaining_time": "0:10:20", "throughput": "2578.49", "total_tokens": 2316448}
{"current_steps": 115, "total_steps": 186, "loss": 0.7462, "learning_rate": 1.5922653499838137e-05, "epoch": 1.8399999999999999, "percentage": 61.83, "elapsed_time": "0:15:40", "remaining_time": "0:09:40", "throughput": "2578.25", "total_tokens": 2425248}
{"current_steps": 120, "total_steps": 186, "loss": 0.6148, "learning_rate": 1.399014621105914e-05, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "0:16:23", "remaining_time": "0:09:01", "throughput": "2578.95", "total_tokens": 2537680}
{"current_steps": 125, "total_steps": 186, "loss": 0.7145, "learning_rate": 1.2136114999284288e-05, "epoch": 2.0, "percentage": 67.2, "elapsed_time": "0:17:02", "remaining_time": "0:08:19", "throughput": "2582.83", "total_tokens": 2642080}
{"current_steps": 130, "total_steps": 186, "loss": 0.6798, "learning_rate": 1.0373775035117305e-05, "epoch": 2.08, "percentage": 69.89, "elapsed_time": "0:17:44", "remaining_time": "0:07:38", "throughput": "2583.35", "total_tokens": 2750752}
{"current_steps": 135, "total_steps": 186, "loss": 0.6754, "learning_rate": 8.715687931944449e-06, "epoch": 2.16, "percentage": 72.58, "elapsed_time": "0:18:23", "remaining_time": "0:06:56", "throughput": "2584.30", "total_tokens": 2852096}
{"current_steps": 140, "total_steps": 186, "loss": 0.6708, "learning_rate": 7.173672209219495e-06, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "0:19:02", "remaining_time": "0:06:15", "throughput": "2584.52", "total_tokens": 2951888}
{"current_steps": 145, "total_steps": 186, "loss": 0.6386, "learning_rate": 5.758719052376693e-06, "epoch": 2.32, "percentage": 77.96, "elapsed_time": "0:19:38", "remaining_time": "0:05:33", "throughput": "2587.95", "total_tokens": 3049616}
{"current_steps": 150, "total_steps": 186, "loss": 0.6995, "learning_rate": 4.480913969818098e-06, "epoch": 2.4, "percentage": 80.65, "elapsed_time": "0:20:16", "remaining_time": "0:04:51", "throughput": "2590.06", "total_tokens": 3150784}
{"current_steps": 155, "total_steps": 186, "loss": 0.6691, "learning_rate": 3.3493649053890326e-06, "epoch": 2.48, "percentage": 83.33, "elapsed_time": "0:20:58", "remaining_time": "0:04:11", "throughput": "2593.15", "total_tokens": 3262992}
{"current_steps": 160, "total_steps": 186, "loss": 0.6024, "learning_rate": 2.372137318741968e-06, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "0:21:42", "remaining_time": "0:03:31", "throughput": "2588.49", "total_tokens": 3371440}
{"current_steps": 165, "total_steps": 186, "loss": 0.6484, "learning_rate": 1.5561966963229924e-06, "epoch": 2.64, "percentage": 88.71, "elapsed_time": "0:22:20", "remaining_time": "0:02:50", "throughput": "2591.26", "total_tokens": 3473680}
{"current_steps": 170, "total_steps": 186, "loss": 0.7137, "learning_rate": 9.073589027514789e-07, "epoch": 2.7199999999999998, "percentage": 91.4, "elapsed_time": "0:23:02", "remaining_time": "0:02:10", "throughput": "2585.69", "total_tokens": 3574736}
{"current_steps": 175, "total_steps": 186, "loss": 0.777, "learning_rate": 4.302487264785521e-07, "epoch": 2.8, "percentage": 94.09, "elapsed_time": "0:23:48", "remaining_time": "0:01:29", "throughput": "2589.29", "total_tokens": 3697920}
{"current_steps": 180, "total_steps": 186, "loss": 0.6529, "learning_rate": 1.2826691520262114e-07, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "0:24:28", "remaining_time": "0:00:48", "throughput": "2590.50", "total_tokens": 3803552}
{"current_steps": 185, "total_steps": 186, "loss": 0.6996, "learning_rate": 3.565936007254855e-09, "epoch": 2.96, "percentage": 99.46, "elapsed_time": "0:25:08", "remaining_time": "0:00:08", "throughput": "2590.41", "total_tokens": 3907456}
{"current_steps": 186, "total_steps": 186, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:25:18", "remaining_time": "0:00:00", "throughput": "2589.06", "total_tokens": 3930992}