| {"current_steps": 5, "total_steps": 1800, "loss": 4.687, "lr": 2.2222222222222223e-05, "epoch": 0.05555555555555555, "percentage": 0.28, "elapsed_time": "0:00:01", "remaining_time": "0:07:34", "throughput": 1289.59, "total_tokens": 1632} |
| {"current_steps": 10, "total_steps": 1800, "loss": 1.6103, "lr": 5e-05, "epoch": 0.1111111111111111, "percentage": 0.56, "elapsed_time": "0:00:02", "remaining_time": "0:06:07", "throughput": 1572.94, "total_tokens": 3232} |
| {"current_steps": 15, "total_steps": 1800, "loss": 0.3703, "lr": 7.777777777777778e-05, "epoch": 0.16666666666666666, "percentage": 0.83, "elapsed_time": "0:00:02", "remaining_time": "0:05:38", "throughput": 1698.02, "total_tokens": 4832} |
| {"current_steps": 20, "total_steps": 1800, "loss": 0.2378, "lr": 0.00010555555555555555, "epoch": 0.2222222222222222, "percentage": 1.11, "elapsed_time": "0:00:03", "remaining_time": "0:05:23", "throughput": 1768.63, "total_tokens": 6432} |
| {"current_steps": 25, "total_steps": 1800, "loss": 0.2584, "lr": 0.00013333333333333334, "epoch": 0.2777777777777778, "percentage": 1.39, "elapsed_time": "0:00:04", "remaining_time": "0:05:14", "throughput": 1800.94, "total_tokens": 7968} |
| {"current_steps": 30, "total_steps": 1800, "loss": 0.5879, "lr": 0.0001611111111111111, "epoch": 0.3333333333333333, "percentage": 1.67, "elapsed_time": "0:00:05", "remaining_time": "0:05:07", "throughput": 1823.64, "total_tokens": 9504} |
| {"current_steps": 35, "total_steps": 1800, "loss": 0.28, "lr": 0.00018888888888888888, "epoch": 0.3888888888888889, "percentage": 1.94, "elapsed_time": "0:00:06", "remaining_time": "0:05:02", "throughput": 1849.99, "total_tokens": 11104} |
| {"current_steps": 40, "total_steps": 1800, "loss": 0.2908, "lr": 0.00021666666666666668, "epoch": 0.4444444444444444, "percentage": 2.22, "elapsed_time": "0:00:06", "remaining_time": "0:04:58", "throughput": 1870.12, "total_tokens": 12704} |
| {"current_steps": 45, "total_steps": 1800, "loss": 0.2511, "lr": 0.00024444444444444443, "epoch": 0.5, "percentage": 2.5, "elapsed_time": "0:00:07", "remaining_time": "0:04:55", "throughput": 1878.58, "total_tokens": 14240} |
| {"current_steps": 50, "total_steps": 1800, "loss": 0.2512, "lr": 0.0002722222222222222, "epoch": 0.5555555555555556, "percentage": 2.78, "elapsed_time": "0:00:08", "remaining_time": "0:04:52", "throughput": 1888.64, "total_tokens": 15808} |
| {"current_steps": 55, "total_steps": 1800, "loss": 0.4036, "lr": 0.0003, "epoch": 0.6111111111111112, "percentage": 3.06, "elapsed_time": "0:00:09", "remaining_time": "0:04:50", "throughput": 1894.11, "total_tokens": 17344} |
| {"current_steps": 60, "total_steps": 1800, "loss": 0.2508, "lr": 0.0003277777777777778, "epoch": 0.6666666666666666, "percentage": 3.33, "elapsed_time": "0:00:09", "remaining_time": "0:04:48", "throughput": 1901.51, "total_tokens": 18912} |
| {"current_steps": 65, "total_steps": 1800, "loss": 0.2354, "lr": 0.00035555555555555557, "epoch": 0.7222222222222222, "percentage": 3.61, "elapsed_time": "0:00:10", "remaining_time": "0:04:46", "throughput": 1905.17, "total_tokens": 20448} |
| {"current_steps": 70, "total_steps": 1800, "loss": 0.2819, "lr": 0.00038333333333333334, "epoch": 0.7777777777777778, "percentage": 3.89, "elapsed_time": "0:00:11", "remaining_time": "0:04:44", "throughput": 1908.3, "total_tokens": 21984} |
| {"current_steps": 75, "total_steps": 1800, "loss": 0.2688, "lr": 0.0004111111111111111, "epoch": 0.8333333333333334, "percentage": 4.17, "elapsed_time": "0:00:12", "remaining_time": "0:04:43", "throughput": 1913.05, "total_tokens": 23552} |
| {"current_steps": 80, "total_steps": 1800, "loss": 0.2861, "lr": 0.0004388888888888889, "epoch": 0.8888888888888888, "percentage": 4.44, "elapsed_time": "0:00:13", "remaining_time": "0:04:41", "throughput": 1917.37, "total_tokens": 25120} |
| {"current_steps": 85, "total_steps": 1800, "loss": 0.2392, "lr": 0.00046666666666666666, "epoch": 0.9444444444444444, "percentage": 4.72, "elapsed_time": "0:00:13", "remaining_time": "0:04:40", "throughput": 1919.26, "total_tokens": 26656} |
| {"current_steps": 90, "total_steps": 1800, "loss": 0.245, "lr": 0.0004944444444444445, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:00:14", "remaining_time": "0:04:39", "throughput": 1918.05, "total_tokens": 28192} |
| {"current_steps": 90, "total_steps": 1800, "eval_loss": 0.2327098846435547, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:00:15", "remaining_time": "0:05:01", "throughput": 1778.89, "total_tokens": 28192} |
| {"current_steps": 95, "total_steps": 1800, "loss": 0.235, "lr": 0.0005222222222222223, "epoch": 1.0555555555555556, "percentage": 5.28, "elapsed_time": "0:00:17", "remaining_time": "0:05:15", "throughput": 1696.92, "total_tokens": 29792} |
| {"current_steps": 100, "total_steps": 1800, "loss": 0.2347, "lr": 0.00055, "epoch": 1.1111111111111112, "percentage": 5.56, "elapsed_time": "0:00:18", "remaining_time": "0:05:11", "throughput": 1707.08, "total_tokens": 31328} |
| {"current_steps": 105, "total_steps": 1800, "loss": 0.2524, "lr": 0.0005777777777777778, "epoch": 1.1666666666666667, "percentage": 5.83, "elapsed_time": "0:00:19", "remaining_time": "0:05:09", "throughput": 1714.94, "total_tokens": 32832} |
| {"current_steps": 110, "total_steps": 1800, "loss": 0.2344, "lr": 0.0006055555555555556, "epoch": 1.2222222222222223, "percentage": 6.11, "elapsed_time": "0:00:19", "remaining_time": "0:05:06", "throughput": 1720.72, "total_tokens": 34304} |
| {"current_steps": 115, "total_steps": 1800, "loss": 0.2314, "lr": 0.0006333333333333333, "epoch": 1.2777777777777777, "percentage": 6.39, "elapsed_time": "0:00:20", "remaining_time": "0:05:03", "throughput": 1728.55, "total_tokens": 35840} |
| {"current_steps": 120, "total_steps": 1800, "loss": 0.2244, "lr": 0.0006611111111111111, "epoch": 1.3333333333333333, "percentage": 6.67, "elapsed_time": "0:00:21", "remaining_time": "0:05:01", "throughput": 1735.87, "total_tokens": 37376} |
| {"current_steps": 125, "total_steps": 1800, "loss": 0.2462, "lr": 0.000688888888888889, "epoch": 1.3888888888888888, "percentage": 6.94, "elapsed_time": "0:00:22", "remaining_time": "0:04:59", "throughput": 1741.53, "total_tokens": 38944} |
| {"current_steps": 130, "total_steps": 1800, "loss": 0.2241, "lr": 0.0007166666666666667, "epoch": 1.4444444444444444, "percentage": 7.22, "elapsed_time": "0:00:23", "remaining_time": "0:04:57", "throughput": 1747.4, "total_tokens": 40512} |
| {"current_steps": 135, "total_steps": 1800, "loss": 0.2453, "lr": 0.0007444444444444445, "epoch": 1.5, "percentage": 7.5, "elapsed_time": "0:00:23", "remaining_time": "0:04:55", "throughput": 1755.25, "total_tokens": 42080} |
| {"current_steps": 140, "total_steps": 1800, "loss": 0.2264, "lr": 0.0007722222222222223, "epoch": 1.5555555555555556, "percentage": 7.78, "elapsed_time": "0:00:24", "remaining_time": "0:04:53", "throughput": 1763.78, "total_tokens": 43680} |
| {"current_steps": 145, "total_steps": 1800, "loss": 0.2341, "lr": 0.0008, "epoch": 1.6111111111111112, "percentage": 8.06, "elapsed_time": "0:00:25", "remaining_time": "0:04:51", "throughput": 1769.57, "total_tokens": 45216} |
| {"current_steps": 150, "total_steps": 1800, "loss": 0.2343, "lr": 0.0008277777777777778, "epoch": 1.6666666666666665, "percentage": 8.33, "elapsed_time": "0:00:26", "remaining_time": "0:04:49", "throughput": 1773.9, "total_tokens": 46720} |
| {"current_steps": 155, "total_steps": 1800, "loss": 0.2399, "lr": 0.0008555555555555556, "epoch": 1.7222222222222223, "percentage": 8.61, "elapsed_time": "0:00:27", "remaining_time": "0:04:47", "throughput": 1780.14, "total_tokens": 48288} |
| {"current_steps": 160, "total_steps": 1800, "loss": 0.2303, "lr": 0.0008833333333333333, "epoch": 1.7777777777777777, "percentage": 8.89, "elapsed_time": "0:00:27", "remaining_time": "0:04:46", "throughput": 1787.05, "total_tokens": 49888} |
| {"current_steps": 165, "total_steps": 1800, "loss": 0.2393, "lr": 0.0009111111111111111, "epoch": 1.8333333333333335, "percentage": 9.17, "elapsed_time": "0:00:28", "remaining_time": "0:04:44", "throughput": 1791.55, "total_tokens": 51424} |
| {"current_steps": 170, "total_steps": 1800, "loss": 0.2384, "lr": 0.000938888888888889, "epoch": 1.8888888888888888, "percentage": 9.44, "elapsed_time": "0:00:29", "remaining_time": "0:04:42", "throughput": 1796.82, "total_tokens": 52992} |
| {"current_steps": 175, "total_steps": 1800, "loss": 0.228, "lr": 0.0009666666666666667, "epoch": 1.9444444444444444, "percentage": 9.72, "elapsed_time": "0:00:30", "remaining_time": "0:04:41", "throughput": 1802.79, "total_tokens": 54592} |
| {"current_steps": 180, "total_steps": 1800, "loss": 0.2443, "lr": 0.0009944444444444445, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:00:31", "remaining_time": "0:04:39", "throughput": 1806.44, "total_tokens": 56192} |
| {"current_steps": 180, "total_steps": 1800, "eval_loss": 0.22945284843444824, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:00:31", "remaining_time": "0:04:47", "throughput": 1760.44, "total_tokens": 56192} |
| {"current_steps": 185, "total_steps": 1800, "loss": 0.2365, "lr": 0.000999984957239884, "epoch": 2.0555555555555554, "percentage": 10.28, "elapsed_time": "0:00:33", "remaining_time": "0:04:53", "throughput": 1717.18, "total_tokens": 57760} |
| {"current_steps": 190, "total_steps": 1800, "loss": 0.2684, "lr": 0.0009999238475781956, "epoch": 2.111111111111111, "percentage": 10.56, "elapsed_time": "0:00:34", "remaining_time": "0:04:51", "throughput": 1721.67, "total_tokens": 59264} |
| {"current_steps": 195, "total_steps": 1800, "loss": 0.2517, "lr": 0.000999815736583355, "epoch": 2.1666666666666665, "percentage": 10.83, "elapsed_time": "0:00:35", "remaining_time": "0:04:49", "throughput": 1725.98, "total_tokens": 60768} |
| {"current_steps": 200, "total_steps": 1800, "loss": 0.2444, "lr": 0.000999660634419631, "epoch": 2.2222222222222223, "percentage": 11.11, "elapsed_time": "0:00:35", "remaining_time": "0:04:47", "throughput": 1730.05, "total_tokens": 62272} |
| {"current_steps": 205, "total_steps": 1800, "loss": 0.2327, "lr": 0.0009994585556692623, "epoch": 2.2777777777777777, "percentage": 11.39, "elapsed_time": "0:00:36", "remaining_time": "0:04:46", "throughput": 1734.81, "total_tokens": 63808} |
| {"current_steps": 210, "total_steps": 1800, "loss": 0.2406, "lr": 0.0009992095193310836, "epoch": 2.3333333333333335, "percentage": 11.67, "elapsed_time": "0:00:37", "remaining_time": "0:04:44", "throughput": 1739.36, "total_tokens": 65344} |
| {"current_steps": 215, "total_steps": 1800, "loss": 0.2357, "lr": 0.0009989135488187406, "epoch": 2.388888888888889, "percentage": 11.94, "elapsed_time": "0:00:38", "remaining_time": "0:04:42", "throughput": 1744.45, "total_tokens": 66912} |
| {"current_steps": 220, "total_steps": 1800, "loss": 0.2345, "lr": 0.0009985706719584887, "epoch": 2.4444444444444446, "percentage": 12.22, "elapsed_time": "0:00:39", "remaining_time": "0:04:41", "throughput": 1749.35, "total_tokens": 68480} |
| {"current_steps": 225, "total_steps": 1800, "loss": 0.2317, "lr": 0.000998180920986577, "epoch": 2.5, "percentage": 12.5, "elapsed_time": "0:00:39", "remaining_time": "0:04:39", "throughput": 1754.06, "total_tokens": 70048} |
| {"current_steps": 230, "total_steps": 1800, "loss": 0.2303, "lr": 0.0009977443325462165, "epoch": 2.5555555555555554, "percentage": 12.78, "elapsed_time": "0:00:40", "remaining_time": "0:04:38", "throughput": 1759.97, "total_tokens": 71680} |
| {"current_steps": 235, "total_steps": 1800, "loss": 0.2404, "lr": 0.0009972609476841367, "epoch": 2.611111111111111, "percentage": 13.06, "elapsed_time": "0:00:41", "remaining_time": "0:04:36", "throughput": 1764.98, "total_tokens": 73280} |
| {"current_steps": 240, "total_steps": 1800, "loss": 0.2217, "lr": 0.0009967308118467252, "epoch": 2.6666666666666665, "percentage": 13.33, "elapsed_time": "0:00:42", "remaining_time": "0:04:34", "throughput": 1767.1, "total_tokens": 74752} |
| {"current_steps": 245, "total_steps": 1800, "loss": 0.2598, "lr": 0.0009961539748757548, "epoch": 2.7222222222222223, "percentage": 13.61, "elapsed_time": "0:00:43", "remaining_time": "0:04:33", "throughput": 1770.44, "total_tokens": 76288} |
| {"current_steps": 250, "total_steps": 1800, "loss": 0.2304, "lr": 0.0009955304910036994, "epoch": 2.7777777777777777, "percentage": 13.89, "elapsed_time": "0:00:43", "remaining_time": "0:04:32", "throughput": 1774.99, "total_tokens": 77888} |
| {"current_steps": 255, "total_steps": 1800, "loss": 0.2377, "lr": 0.0009948604188486328, "epoch": 2.8333333333333335, "percentage": 14.17, "elapsed_time": "0:00:44", "remaining_time": "0:04:30", "throughput": 1778.72, "total_tokens": 79456} |
| {"current_steps": 260, "total_steps": 1800, "loss": 0.2363, "lr": 0.000994143821408719, "epoch": 2.888888888888889, "percentage": 14.44, "elapsed_time": "0:00:45", "remaining_time": "0:04:29", "throughput": 1783.61, "total_tokens": 81088} |
| {"current_steps": 265, "total_steps": 1800, "loss": 0.2357, "lr": 0.0009933807660562897, "epoch": 2.9444444444444446, "percentage": 14.72, "elapsed_time": "0:00:46", "remaining_time": "0:04:27", "throughput": 1785.84, "total_tokens": 82592} |
| {"current_steps": 270, "total_steps": 1800, "loss": 0.2401, "lr": 0.0009925713245315083, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "0:00:47", "remaining_time": "0:04:26", "throughput": 1788.55, "total_tokens": 84192} |
| {"current_steps": 270, "total_steps": 1800, "eval_loss": 0.23134836554527283, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "0:00:47", "remaining_time": "0:04:31", "throughput": 1758.08, "total_tokens": 84192} |
| {"current_steps": 275, "total_steps": 1800, "loss": 0.2304, "lr": 0.0009917155729356273, "epoch": 3.0555555555555554, "percentage": 15.28, "elapsed_time": "0:00:49", "remaining_time": "0:04:35", "throughput": 1727.8, "total_tokens": 85696} |
| {"current_steps": 280, "total_steps": 1800, "loss": 0.2375, "lr": 0.000990813591723832, "epoch": 3.111111111111111, "percentage": 15.56, "elapsed_time": "0:00:50", "remaining_time": "0:04:33", "throughput": 1732.38, "total_tokens": 87296} |
| {"current_steps": 285, "total_steps": 1800, "loss": 0.2318, "lr": 0.000989865465697677, "epoch": 3.1666666666666665, "percentage": 15.83, "elapsed_time": "0:00:51", "remaining_time": "0:04:32", "throughput": 1735.73, "total_tokens": 88832} |
| {"current_steps": 290, "total_steps": 1800, "loss": 0.2166, "lr": 0.0009888712839971133, "epoch": 3.2222222222222223, "percentage": 16.11, "elapsed_time": "0:00:51", "remaining_time": "0:04:30", "throughput": 1739.0, "total_tokens": 90368} |
| {"current_steps": 295, "total_steps": 1800, "loss": 0.2354, "lr": 0.0009878311400921072, "epoch": 3.2777777777777777, "percentage": 16.39, "elapsed_time": "0:00:52", "remaining_time": "0:04:29", "throughput": 1743.25, "total_tokens": 91968} |
| {"current_steps": 300, "total_steps": 1800, "loss": 0.2449, "lr": 0.0009867451317738534, "epoch": 3.3333333333333335, "percentage": 16.67, "elapsed_time": "0:00:53", "remaining_time": "0:04:27", "throughput": 1747.34, "total_tokens": 93568} |
| {"current_steps": 305, "total_steps": 1800, "loss": 0.2378, "lr": 0.0009856133611455802, "epoch": 3.388888888888889, "percentage": 16.94, "elapsed_time": "0:00:54", "remaining_time": "0:04:26", "throughput": 1751.31, "total_tokens": 95168} |
| {"current_steps": 310, "total_steps": 1800, "loss": 0.2425, "lr": 0.0009844359346129503, "epoch": 3.4444444444444446, "percentage": 17.22, "elapsed_time": "0:00:55", "remaining_time": "0:04:24", "throughput": 1754.16, "total_tokens": 96704} |
| {"current_steps": 315, "total_steps": 1800, "loss": 0.2357, "lr": 0.0009832129628740574, "epoch": 3.5, "percentage": 17.5, "elapsed_time": "0:00:55", "remaining_time": "0:04:23", "throughput": 1757.96, "total_tokens": 98304} |
| {"current_steps": 320, "total_steps": 1800, "loss": 0.2368, "lr": 0.0009819445609090174, "epoch": 3.5555555555555554, "percentage": 17.78, "elapsed_time": "0:00:56", "remaining_time": "0:04:22", "throughput": 1760.63, "total_tokens": 99840} |
| {"current_steps": 325, "total_steps": 1800, "loss": 0.2315, "lr": 0.0009806308479691594, "epoch": 3.611111111111111, "percentage": 18.06, "elapsed_time": "0:00:57", "remaining_time": "0:04:20", "throughput": 1763.21, "total_tokens": 101376} |
| {"current_steps": 330, "total_steps": 1800, "loss": 0.2294, "lr": 0.0009792719475658143, "epoch": 3.6666666666666665, "percentage": 18.33, "elapsed_time": "0:00:58", "remaining_time": "0:04:19", "throughput": 1766.73, "total_tokens": 102976} |
| {"current_steps": 335, "total_steps": 1800, "loss": 0.2325, "lr": 0.0009778679874587015, "epoch": 3.7222222222222223, "percentage": 18.61, "elapsed_time": "0:00:59", "remaining_time": "0:04:18", "throughput": 1770.14, "total_tokens": 104576} |
| {"current_steps": 340, "total_steps": 1800, "loss": 0.2304, "lr": 0.0009764190996439181, "epoch": 3.7777777777777777, "percentage": 18.89, "elapsed_time": "0:00:59", "remaining_time": "0:04:17", "throughput": 1772.45, "total_tokens": 106112} |
| {"current_steps": 345, "total_steps": 1800, "loss": 0.2314, "lr": 0.0009749254203415288, "epoch": 3.8333333333333335, "percentage": 19.17, "elapsed_time": "0:01:00", "remaining_time": "0:04:15", "throughput": 1775.69, "total_tokens": 107712} |
| {"current_steps": 350, "total_steps": 1800, "loss": 0.234, "lr": 0.000973387089982759, "epoch": 3.888888888888889, "percentage": 19.44, "elapsed_time": "0:01:01", "remaining_time": "0:04:14", "throughput": 1779.34, "total_tokens": 109344} |
| {"current_steps": 355, "total_steps": 1800, "loss": 0.2401, "lr": 0.0009718042531967918, "epoch": 3.9444444444444446, "percentage": 19.72, "elapsed_time": "0:01:02", "remaining_time": "0:04:13", "throughput": 1782.4, "total_tokens": 110944} |
| {"current_steps": 360, "total_steps": 1800, "loss": 0.2337, "lr": 0.0009701770587971706, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:01:03", "remaining_time": "0:04:12", "throughput": 1784.42, "total_tokens": 112544} |
| {"current_steps": 360, "total_steps": 1800, "eval_loss": 0.23112532496452332, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:01:03", "remaining_time": "0:04:15", "throughput": 1761.62, "total_tokens": 112544} |
| {"current_steps": 365, "total_steps": 1800, "loss": 0.2357, "lr": 0.0009685056597678075, "epoch": 4.055555555555555, "percentage": 20.28, "elapsed_time": "0:01:05", "remaining_time": "0:04:17", "throughput": 1740.68, "total_tokens": 114144} |
| {"current_steps": 370, "total_steps": 1800, "loss": 0.2285, "lr": 0.0009667902132486009, "epoch": 4.111111111111111, "percentage": 20.56, "elapsed_time": "0:01:06", "remaining_time": "0:04:16", "throughput": 1743.58, "total_tokens": 115712} |
| {"current_steps": 375, "total_steps": 1800, "loss": 0.2343, "lr": 0.0009650308805206616, "epoch": 4.166666666666667, "percentage": 20.83, "elapsed_time": "0:01:07", "remaining_time": "0:04:15", "throughput": 1746.87, "total_tokens": 117312} |
| {"current_steps": 380, "total_steps": 1800, "loss": 0.2245, "lr": 0.0009632278269911492, "epoch": 4.222222222222222, "percentage": 21.11, "elapsed_time": "0:01:07", "remaining_time": "0:04:13", "throughput": 1749.23, "total_tokens": 118848} |
| {"current_steps": 385, "total_steps": 1800, "loss": 0.2225, "lr": 0.0009613812221777212, "epoch": 4.277777777777778, "percentage": 21.39, "elapsed_time": "0:01:08", "remaining_time": "0:04:12", "throughput": 1751.97, "total_tokens": 120416} |
| {"current_steps": 390, "total_steps": 1800, "loss": 0.2649, "lr": 0.0009594912396925958, "epoch": 4.333333333333333, "percentage": 21.67, "elapsed_time": "0:01:09", "remaining_time": "0:04:11", "throughput": 1755.05, "total_tokens": 122016} |
| {"current_steps": 395, "total_steps": 1800, "loss": 0.2293, "lr": 0.0009575580572262289, "epoch": 4.388888888888889, "percentage": 21.94, "elapsed_time": "0:01:10", "remaining_time": "0:04:10", "throughput": 1757.63, "total_tokens": 123584} |
| {"current_steps": 400, "total_steps": 1800, "loss": 0.2338, "lr": 0.0009555818565306084, "epoch": 4.444444444444445, "percentage": 22.22, "elapsed_time": "0:01:11", "remaining_time": "0:04:08", "throughput": 1760.96, "total_tokens": 125216} |
| {"current_steps": 405, "total_steps": 1800, "loss": 0.2345, "lr": 0.0009535628234021669, "epoch": 4.5, "percentage": 22.5, "elapsed_time": "0:01:11", "remaining_time": "0:04:07", "throughput": 1763.43, "total_tokens": 126784} |
| {"current_steps": 410, "total_steps": 1800, "loss": 0.2291, "lr": 0.0009515011476643126, "epoch": 4.555555555555555, "percentage": 22.78, "elapsed_time": "0:01:12", "remaining_time": "0:04:06", "throughput": 1765.85, "total_tokens": 128352} |
| {"current_steps": 415, "total_steps": 1800, "loss": 0.2256, "lr": 0.0009493970231495835, "epoch": 4.611111111111111, "percentage": 23.06, "elapsed_time": "0:01:13", "remaining_time": "0:04:05", "throughput": 1768.22, "total_tokens": 129920} |
| {"current_steps": 420, "total_steps": 1800, "loss": 0.2505, "lr": 0.0009472506476814238, "epoch": 4.666666666666667, "percentage": 23.33, "elapsed_time": "0:01:14", "remaining_time": "0:04:04", "throughput": 1770.55, "total_tokens": 131488} |
| {"current_steps": 425, "total_steps": 1800, "loss": 0.2353, "lr": 0.0009450622230555847, "epoch": 4.722222222222222, "percentage": 23.61, "elapsed_time": "0:01:15", "remaining_time": "0:04:02", "throughput": 1772.82, "total_tokens": 133056} |
| {"current_steps": 430, "total_steps": 1800, "loss": 0.231, "lr": 0.0009428319550211531, "epoch": 4.777777777777778, "percentage": 23.89, "elapsed_time": "0:01:15", "remaining_time": "0:04:01", "throughput": 1775.04, "total_tokens": 134624} |
| {"current_steps": 435, "total_steps": 1800, "loss": 0.2312, "lr": 0.000940560053261206, "epoch": 4.833333333333333, "percentage": 24.17, "elapsed_time": "0:01:16", "remaining_time": "0:04:00", "throughput": 1777.23, "total_tokens": 136192} |
| {"current_steps": 440, "total_steps": 1800, "loss": 0.2328, "lr": 0.0009382467313730985, "epoch": 4.888888888888889, "percentage": 24.44, "elapsed_time": "0:01:17", "remaining_time": "0:03:59", "throughput": 1780.09, "total_tokens": 137824} |
| {"current_steps": 445, "total_steps": 1800, "loss": 0.2322, "lr": 0.0009358922068483812, "epoch": 4.944444444444445, "percentage": 24.72, "elapsed_time": "0:01:18", "remaining_time": "0:03:58", "throughput": 1782.18, "total_tokens": 139392} |
| {"current_steps": 450, "total_steps": 1800, "loss": 0.2353, "lr": 0.0009334967010523523, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:01:19", "remaining_time": "0:03:57", "throughput": 1783.43, "total_tokens": 140960} |
| {"current_steps": 450, "total_steps": 1800, "eval_loss": 0.233585923910141, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:01:19", "remaining_time": "0:03:59", "throughput": 1765.2, "total_tokens": 140960} |
| {"current_steps": 455, "total_steps": 1800, "loss": 0.2314, "lr": 0.0009310604392032455, "epoch": 5.055555555555555, "percentage": 25.28, "elapsed_time": "0:01:21", "remaining_time": "0:04:01", "throughput": 1747.71, "total_tokens": 142560} |
| {"current_steps": 460, "total_steps": 1800, "loss": 0.2301, "lr": 0.0009285836503510562, "epoch": 5.111111111111111, "percentage": 25.56, "elapsed_time": "0:01:22", "remaining_time": "0:03:59", "throughput": 1749.63, "total_tokens": 144096} |
| {"current_steps": 465, "total_steps": 1800, "loss": 0.2352, "lr": 0.0009260665673560057, "epoch": 5.166666666666667, "percentage": 25.83, "elapsed_time": "0:01:23", "remaining_time": "0:03:58", "throughput": 1751.51, "total_tokens": 145632} |
| {"current_steps": 470, "total_steps": 1800, "loss": 0.2297, "lr": 0.0009235094268666498, "epoch": 5.222222222222222, "percentage": 26.11, "elapsed_time": "0:01:23", "remaining_time": "0:03:57", "throughput": 1754.07, "total_tokens": 147232} |
| {"current_steps": 475, "total_steps": 1800, "loss": 0.2324, "lr": 0.0009209124692976287, "epoch": 5.277777777777778, "percentage": 26.39, "elapsed_time": "0:01:24", "remaining_time": "0:03:56", "throughput": 1756.92, "total_tokens": 148864} |
| {"current_steps": 480, "total_steps": 1800, "loss": 0.2366, "lr": 0.0009182759388070649, "epoch": 5.333333333333333, "percentage": 26.67, "elapsed_time": "0:01:25", "remaining_time": "0:03:55", "throughput": 1759.04, "total_tokens": 150432} |
| {"current_steps": 485, "total_steps": 1800, "loss": 0.2271, "lr": 0.0009156000832736073, "epoch": 5.388888888888889, "percentage": 26.94, "elapsed_time": "0:01:26", "remaining_time": "0:03:54", "throughput": 1761.46, "total_tokens": 152032} |
| {"current_steps": 490, "total_steps": 1800, "loss": 0.2315, "lr": 0.0009128851542731271, "epoch": 5.444444444444445, "percentage": 27.22, "elapsed_time": "0:01:27", "remaining_time": "0:03:52", "throughput": 1763.52, "total_tokens": 153600} |
| {"current_steps": 495, "total_steps": 1800, "loss": 0.2342, "lr": 0.0009101314070550646, "epoch": 5.5, "percentage": 27.5, "elapsed_time": "0:01:27", "remaining_time": "0:03:51", "throughput": 1765.85, "total_tokens": 155200} |
| {"current_steps": 500, "total_steps": 1800, "loss": 0.2372, "lr": 0.0009073391005184324, "epoch": 5.555555555555555, "percentage": 27.78, "elapsed_time": "0:01:28", "remaining_time": "0:03:50", "throughput": 1768.03, "total_tokens": 156800} |
| {"current_steps": 505, "total_steps": 1800, "loss": 0.229, "lr": 0.0009045084971874737, "epoch": 5.611111111111111, "percentage": 28.06, "elapsed_time": "0:01:29", "remaining_time": "0:03:49", "throughput": 1769.63, "total_tokens": 158336} |
| {"current_steps": 510, "total_steps": 1800, "loss": 0.2347, "lr": 0.0009016398631869811, "epoch": 5.666666666666667, "percentage": 28.33, "elapsed_time": "0:01:30", "remaining_time": "0:03:48", "throughput": 1771.54, "total_tokens": 159904} |
| {"current_steps": 515, "total_steps": 1800, "loss": 0.2299, "lr": 0.0008987334682172759, "epoch": 5.722222222222222, "percentage": 28.61, "elapsed_time": "0:01:31", "remaining_time": "0:03:47", "throughput": 1773.71, "total_tokens": 161504} |
| {"current_steps": 520, "total_steps": 1800, "loss": 0.2309, "lr": 0.0008957895855288517, "epoch": 5.777777777777778, "percentage": 28.89, "elapsed_time": "0:01:31", "remaining_time": "0:03:46", "throughput": 1774.93, "total_tokens": 163008} |
| {"current_steps": 525, "total_steps": 1800, "loss": 0.2309, "lr": 0.000892808491896685, "epoch": 5.833333333333333, "percentage": 29.17, "elapsed_time": "0:01:32", "remaining_time": "0:03:44", "throughput": 1776.12, "total_tokens": 164512} |
| {"current_steps": 530, "total_steps": 1800, "loss": 0.2319, "lr": 0.0008897904675942128, "epoch": 5.888888888888889, "percentage": 29.44, "elapsed_time": "0:01:33", "remaining_time": "0:03:43", "throughput": 1777.89, "total_tokens": 166080} |
| {"current_steps": 535, "total_steps": 1800, "loss": 0.2314, "lr": 0.000886735796366982, "epoch": 5.944444444444445, "percentage": 29.72, "elapsed_time": "0:01:34", "remaining_time": "0:03:42", "throughput": 1779.94, "total_tokens": 167680} |
| {"current_steps": 540, "total_steps": 1800, "loss": 0.2335, "lr": 0.0008836447654059734, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "0:01:35", "remaining_time": "0:03:41", "throughput": 1780.7, "total_tokens": 169216} |
| {"current_steps": 540, "total_steps": 1800, "eval_loss": 0.23072807490825653, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "0:01:35", "remaining_time": "0:03:43", "throughput": 1765.51, "total_tokens": 169216} |
| {"current_steps": 545, "total_steps": 1800, "loss": 0.2326, "lr": 0.0008805176653206003, "epoch": 6.055555555555555, "percentage": 30.28, "elapsed_time": "0:01:37", "remaining_time": "0:03:44", "throughput": 1750.95, "total_tokens": 170784} |
| {"current_steps": 550, "total_steps": 1800, "loss": 0.2273, "lr": 0.000877354790111386, "epoch": 6.111111111111111, "percentage": 30.56, "elapsed_time": "0:01:38", "remaining_time": "0:03:43", "throughput": 1752.82, "total_tokens": 172352} |
| {"current_steps": 555, "total_steps": 1800, "loss": 0.2227, "lr": 0.0008741564371423235, "epoch": 6.166666666666667, "percentage": 30.83, "elapsed_time": "0:01:39", "remaining_time": "0:03:42", "throughput": 1754.68, "total_tokens": 173920} |
| {"current_steps": 560, "total_steps": 1800, "loss": 0.2277, "lr": 0.0008709229071129177, "epoch": 6.222222222222222, "percentage": 31.11, "elapsed_time": "0:01:39", "remaining_time": "0:03:41", "throughput": 1756.52, "total_tokens": 175488} |
| {"current_steps": 565, "total_steps": 1800, "loss": 0.2339, "lr": 0.0008676545040299144, "epoch": 6.277777777777778, "percentage": 31.39, "elapsed_time": "0:01:40", "remaining_time": "0:03:40", "throughput": 1758.04, "total_tokens": 177024} |
| {"current_steps": 570, "total_steps": 1800, "loss": 0.2281, "lr": 0.0008643515351787192, "epoch": 6.333333333333333, "percentage": 31.67, "elapsed_time": "0:01:41", "remaining_time": "0:03:38", "throughput": 1760.11, "total_tokens": 178624} |
| {"current_steps": 575, "total_steps": 1800, "loss": 0.2325, "lr": 0.0008610143110945068, "epoch": 6.388888888888889, "percentage": 31.94, "elapsed_time": "0:01:42", "remaining_time": "0:03:37", "throughput": 1760.93, "total_tokens": 180096} |
| {"current_steps": 580, "total_steps": 1800, "loss": 0.2229, "lr": 0.0008576431455330258, "epoch": 6.444444444444445, "percentage": 32.22, "elapsed_time": "0:01:43", "remaining_time": "0:03:36", "throughput": 1762.11, "total_tokens": 181600} |
| {"current_steps": 585, "total_steps": 1800, "loss": 0.2242, "lr": 0.0008542383554411, "epoch": 6.5, "percentage": 32.5, "elapsed_time": "0:01:43", "remaining_time": "0:03:35", "throughput": 1764.37, "total_tokens": 183232} |
| {"current_steps": 590, "total_steps": 1800, "loss": 0.2356, "lr": 0.0008508002609268301, "epoch": 6.555555555555555, "percentage": 32.78, "elapsed_time": "0:01:44", "remaining_time": "0:03:34", "throughput": 1765.77, "total_tokens": 184768} |
| {"current_steps": 595, "total_steps": 1800, "loss": 0.2313, "lr": 0.0008473291852294987, "epoch": 6.611111111111111, "percentage": 33.06, "elapsed_time": "0:01:45", "remaining_time": "0:03:33", "throughput": 1766.34, "total_tokens": 186208} |
| {"current_steps": 600, "total_steps": 1800, "loss": 0.2385, "lr": 0.0008438254546891792, "epoch": 6.666666666666667, "percentage": 33.33, "elapsed_time": "0:01:46", "remaining_time": "0:03:32", "throughput": 1767.96, "total_tokens": 187776} |
| {"current_steps": 605, "total_steps": 1800, "loss": 0.2202, "lr": 0.0008402893987160552, "epoch": 6.722222222222222, "percentage": 33.61, "elapsed_time": "0:01:46", "remaining_time": "0:03:31", "throughput": 1769.57, "total_tokens": 189344} |
| {"current_steps": 610, "total_steps": 1800, "loss": 0.2342, "lr": 0.0008367213497594501, "epoch": 6.777777777777778, "percentage": 33.89, "elapsed_time": "0:01:47", "remaining_time": "0:03:30", "throughput": 1771.15, "total_tokens": 190912} |
| {"current_steps": 615, "total_steps": 1800, "loss": 0.241, "lr": 0.0008331216432765713, "epoch": 6.833333333333333, "percentage": 34.17, "elapsed_time": "0:01:48", "remaining_time": "0:03:29", "throughput": 1772.98, "total_tokens": 192512} |
| {"current_steps": 620, "total_steps": 1800, "loss": 0.2338, "lr": 0.0008294906177009707, "epoch": 6.888888888888889, "percentage": 34.44, "elapsed_time": "0:01:49", "remaining_time": "0:03:28", "throughput": 1774.78, "total_tokens": 194112} |
| {"current_steps": 625, "total_steps": 1800, "loss": 0.2335, "lr": 0.0008258286144107276, "epoch": 6.944444444444445, "percentage": 34.72, "elapsed_time": "0:01:50", "remaining_time": "0:03:27", "throughput": 1776.55, "total_tokens": 195712} |
| {"current_steps": 630, "total_steps": 1800, "loss": 0.2306, "lr": 0.0008221359776963525, "epoch": 7.0, "percentage": 35.0, "elapsed_time": "0:01:50", "remaining_time": "0:03:26", "throughput": 1777.23, "total_tokens": 197248} |
| {"current_steps": 630, "total_steps": 1800, "eval_loss": 0.23276683688163757, "epoch": 7.0, "percentage": 35.0, "elapsed_time": "0:01:51", "remaining_time": "0:03:27", "throughput": 1764.24, "total_tokens": 197248} |
| {"current_steps": 635, "total_steps": 1800, "loss": 0.2401, "lr": 0.000818413054728418, "epoch": 7.055555555555555, "percentage": 35.28, "elapsed_time": "0:01:53", "remaining_time": "0:03:28", "throughput": 1751.31, "total_tokens": 198784} |
| {"current_steps": 640, "total_steps": 1800, "loss": 0.2324, "lr": 0.0008146601955249188, "epoch": 7.111111111111111, "percentage": 35.56, "elapsed_time": "0:01:54", "remaining_time": "0:03:27", "throughput": 1752.68, "total_tokens": 200352} |
| {"current_steps": 645, "total_steps": 1800, "loss": 0.2297, "lr": 0.0008108777529183644, "epoch": 7.166666666666667, "percentage": 35.83, "elapsed_time": "0:01:55", "remaining_time": "0:03:26", "throughput": 1753.77, "total_tokens": 201856} |
| {"current_steps": 650, "total_steps": 1800, "loss": 0.2299, "lr": 0.000807066082522607, "epoch": 7.222222222222222, "percentage": 36.11, "elapsed_time": "0:01:55", "remaining_time": "0:03:25", "throughput": 1755.86, "total_tokens": 203488} |
| {"current_steps": 655, "total_steps": 1800, "loss": 0.2278, "lr": 0.0008032255426994069, "epoch": 7.277777777777778, "percentage": 36.39, "elapsed_time": "0:01:56", "remaining_time": "0:03:23", "throughput": 1757.4, "total_tokens": 205056} |
| {"current_steps": 660, "total_steps": 1800, "loss": 0.2163, "lr": 0.0007993564945247409, "epoch": 7.333333333333333, "percentage": 36.67, "elapsed_time": "0:01:57", "remaining_time": "0:03:22", "throughput": 1759.19, "total_tokens": 206656} |
| {"current_steps": 665, "total_steps": 1800, "loss": 0.2323, "lr": 0.0007954593017548556, "epoch": 7.388888888888889, "percentage": 36.94, "elapsed_time": "0:01:58", "remaining_time": "0:03:21", "throughput": 1761.2, "total_tokens": 208288} |
| {"current_steps": 670, "total_steps": 1800, "loss": 0.2278, "lr": 0.0007915343307920673, "epoch": 7.444444444444445, "percentage": 37.22, "elapsed_time": "0:01:59", "remaining_time": "0:03:20", "throughput": 1762.69, "total_tokens": 209856} |
| {"current_steps": 675, "total_steps": 1800, "loss": 0.2611, "lr": 0.0007875819506503144, "epoch": 7.5, "percentage": 37.5, "elapsed_time": "0:01:59", "remaining_time": "0:03:19", "throughput": 1764.16, "total_tokens": 211424} |
| {"current_steps": 680, "total_steps": 1800, "loss": 0.2402, "lr": 0.0007836025329204635, "epoch": 7.555555555555555, "percentage": 37.78, "elapsed_time": "0:02:00", "remaining_time": "0:03:18", "throughput": 1765.14, "total_tokens": 212928} |
| {"current_steps": 685, "total_steps": 1800, "loss": 0.2251, "lr": 0.0007795964517353734, "epoch": 7.611111111111111, "percentage": 38.06, "elapsed_time": "0:02:01", "remaining_time": "0:03:17", "throughput": 1766.58, "total_tokens": 214496} |
| {"current_steps": 690, "total_steps": 1800, "loss": 0.227, "lr": 0.0007755640837347215, "epoch": 7.666666666666667, "percentage": 38.33, "elapsed_time": "0:02:02", "remaining_time": "0:03:16", "throughput": 1767.99, "total_tokens": 216064} |
| {"current_steps": 695, "total_steps": 1800, "loss": 0.2359, "lr": 0.0007715058080295917, "epoch": 7.722222222222222, "percentage": 38.61, "elapsed_time": "0:02:02", "remaining_time": "0:03:15", "throughput": 1769.16, "total_tokens": 217600} |
| {"current_steps": 700, "total_steps": 1800, "loss": 0.2393, "lr": 0.0007674220061668323, "epoch": 7.777777777777778, "percentage": 38.89, "elapsed_time": "0:02:03", "remaining_time": "0:03:14", "throughput": 1770.31, "total_tokens": 219136} |
| {"current_steps": 705, "total_steps": 1800, "loss": 0.2368, "lr": 0.0007633130620931837, "epoch": 7.833333333333333, "percentage": 39.17, "elapsed_time": "0:02:04", "remaining_time": "0:03:13", "throughput": 1771.69, "total_tokens": 220704} |
| {"current_steps": 710, "total_steps": 1800, "loss": 0.2299, "lr": 0.0007591793621191819, "epoch": 7.888888888888889, "percentage": 39.44, "elapsed_time": "0:02:05", "remaining_time": "0:03:12", "throughput": 1773.04, "total_tokens": 222272} |
| {"current_steps": 715, "total_steps": 1800, "loss": 0.2227, "lr": 0.0007550212948828377, "epoch": 7.944444444444445, "percentage": 39.72, "elapsed_time": "0:02:06", "remaining_time": "0:03:11", "throughput": 1774.6, "total_tokens": 223872} |
| {"current_steps": 720, "total_steps": 1800, "loss": 0.2366, "lr": 0.0007508392513130979, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "0:02:06", "remaining_time": "0:03:10", "throughput": 1775.42, "total_tokens": 225440} |
| {"current_steps": 720, "total_steps": 1800, "eval_loss": 0.23274831473827362, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "0:02:07", "remaining_time": "0:03:11", "throughput": 1764.08, "total_tokens": 225440} |
| {"current_steps": 725, "total_steps": 1800, "loss": 0.2335, "lr": 0.0007466336245930927, "epoch": 8.055555555555555, "percentage": 40.28, "elapsed_time": "0:02:09", "remaining_time": "0:03:12", "throughput": 1752.01, "total_tokens": 226912} |
| {"current_steps": 730, "total_steps": 1800, "loss": 0.2378, "lr": 0.0007424048101231686, "epoch": 8.11111111111111, "percentage": 40.56, "elapsed_time": "0:02:10", "remaining_time": "0:03:11", "throughput": 1753.61, "total_tokens": 228512} |
| {"current_steps": 735, "total_steps": 1800, "loss": 0.2351, "lr": 0.0007381532054837144, "epoch": 8.166666666666666, "percentage": 40.83, "elapsed_time": "0:02:11", "remaining_time": "0:03:09", "throughput": 1755.02, "total_tokens": 230080} |
| {"current_steps": 740, "total_steps": 1800, "loss": 0.2347, "lr": 0.0007338792103977821, "epoch": 8.222222222222221, "percentage": 41.11, "elapsed_time": "0:02:11", "remaining_time": "0:03:08", "throughput": 1756.18, "total_tokens": 231616} |
| {"current_steps": 745, "total_steps": 1800, "loss": 0.2294, "lr": 0.0007295832266935059, "epoch": 8.277777777777779, "percentage": 41.39, "elapsed_time": "0:02:12", "remaining_time": "0:03:07", "throughput": 1757.55, "total_tokens": 233184} |
| {"current_steps": 750, "total_steps": 1800, "loss": 0.2356, "lr": 0.0007252656582663236, "epoch": 8.333333333333334, "percentage": 41.67, "elapsed_time": "0:02:13", "remaining_time": "0:03:06", "throughput": 1758.47, "total_tokens": 234688} |
| {"current_steps": 755, "total_steps": 1800, "loss": 0.2282, "lr": 0.0007209269110410039, "epoch": 8.38888888888889, "percentage": 41.94, "elapsed_time": "0:02:14", "remaining_time": "0:03:05", "throughput": 1759.82, "total_tokens": 236256} |
| {"current_steps": 760, "total_steps": 1800, "loss": 0.2304, "lr": 0.0007165673929334815, "epoch": 8.444444444444445, "percentage": 42.22, "elapsed_time": "0:02:15", "remaining_time": "0:03:04", "throughput": 1761.35, "total_tokens": 237856} |
| {"current_steps": 765, "total_steps": 1800, "loss": 0.2314, "lr": 0.0007121875138125077, "epoch": 8.5, "percentage": 42.5, "elapsed_time": "0:02:15", "remaining_time": "0:03:03", "throughput": 1762.45, "total_tokens": 239392} |
| {"current_steps": 770, "total_steps": 1800, "loss": 0.2302, "lr": 0.0007077876854611145, "epoch": 8.555555555555555, "percentage": 42.78, "elapsed_time": "0:02:16", "remaining_time": "0:03:02", "throughput": 1763.75, "total_tokens": 240960} |
| {"current_steps": 775, "total_steps": 1800, "loss": 0.2295, "lr": 0.0007033683215379002, "epoch": 8.61111111111111, "percentage": 43.06, "elapsed_time": "0:02:17", "remaining_time": "0:03:01", "throughput": 1764.81, "total_tokens": 242496} |
| {"current_steps": 780, "total_steps": 1800, "loss": 0.2379, "lr": 0.000698929837538139, "epoch": 8.666666666666666, "percentage": 43.33, "elapsed_time": "0:02:18", "remaining_time": "0:03:00", "throughput": 1766.07, "total_tokens": 244064} |
| {"current_steps": 785, "total_steps": 1800, "loss": 0.2384, "lr": 0.0006944726507547168, "epoch": 8.722222222222221, "percentage": 43.61, "elapsed_time": "0:02:18", "remaining_time": "0:02:59", "throughput": 1767.48, "total_tokens": 245664} |
| {"current_steps": 790, "total_steps": 1800, "loss": 0.2293, "lr": 0.0006899971802388996, "epoch": 8.777777777777779, "percentage": 43.89, "elapsed_time": "0:02:19", "remaining_time": "0:02:58", "throughput": 1768.91, "total_tokens": 247264} |
| {"current_steps": 795, "total_steps": 1800, "loss": 0.2368, "lr": 0.0006855038467609335, "epoch": 8.833333333333334, "percentage": 44.17, "elapsed_time": "0:02:20", "remaining_time": "0:02:57", "throughput": 1770.14, "total_tokens": 248832} |
| {"current_steps": 800, "total_steps": 1800, "loss": 0.2304, "lr": 0.0006809930727704874, "epoch": 8.88888888888889, "percentage": 44.44, "elapsed_time": "0:02:21", "remaining_time": "0:02:56", "throughput": 1771.55, "total_tokens": 250432} |
| {"current_steps": 805, "total_steps": 1800, "loss": 0.2268, "lr": 0.0006764652823569344, "epoch": 8.944444444444445, "percentage": 44.72, "elapsed_time": "0:02:22", "remaining_time": "0:02:55", "throughput": 1773.15, "total_tokens": 252064} |
| {"current_steps": 810, "total_steps": 1800, "loss": 0.2396, "lr": 0.0006719209012094805, "epoch": 9.0, "percentage": 45.0, "elapsed_time": "0:02:22", "remaining_time": "0:02:54", "throughput": 1773.89, "total_tokens": 253632} |
| {"current_steps": 810, "total_steps": 1800, "eval_loss": 0.23413518071174622, "epoch": 9.0, "percentage": 45.0, "elapsed_time": "0:02:23", "remaining_time": "0:02:55", "throughput": 1763.82, "total_tokens": 253632} |
| {"current_steps": 815, "total_steps": 1800, "loss": 0.227, "lr": 0.0006673603565771424, "epoch": 9.055555555555555, "percentage": 45.28, "elapsed_time": "0:02:25", "remaining_time": "0:02:55", "throughput": 1753.46, "total_tokens": 255232} |
| {"current_steps": 820, "total_steps": 1800, "loss": 0.2285, "lr": 0.0006627840772285784, "epoch": 9.11111111111111, "percentage": 45.56, "elapsed_time": "0:02:26", "remaining_time": "0:02:54", "throughput": 1754.52, "total_tokens": 256800} |
| {"current_steps": 825, "total_steps": 1800, "loss": 0.2347, "lr": 0.0006581924934117783, "epoch": 9.166666666666666, "percentage": 45.83, "elapsed_time": "0:02:27", "remaining_time": "0:02:53", "throughput": 1755.77, "total_tokens": 258368} |
| {"current_steps": 830, "total_steps": 1800, "loss": 0.231, "lr": 0.0006535860368136113, "epoch": 9.222222222222221, "percentage": 46.11, "elapsed_time": "0:02:27", "remaining_time": "0:02:52", "throughput": 1756.61, "total_tokens": 259872} |
| {"current_steps": 835, "total_steps": 1800, "loss": 0.2346, "lr": 0.0006489651405192409, "epoch": 9.277777777777779, "percentage": 46.39, "elapsed_time": "0:02:28", "remaining_time": "0:02:51", "throughput": 1757.44, "total_tokens": 261376} |
| {"current_steps": 840, "total_steps": 1800, "loss": 0.2336, "lr": 0.0006443302389714074, "epoch": 9.333333333333334, "percentage": 46.67, "elapsed_time": "0:02:29", "remaining_time": "0:02:50", "throughput": 1758.65, "total_tokens": 262944} |
| {"current_steps": 845, "total_steps": 1800, "loss": 0.2384, "lr": 0.0006396817679295822, "epoch": 9.38888888888889, "percentage": 46.94, "elapsed_time": "0:02:30", "remaining_time": "0:02:49", "throughput": 1760.05, "total_tokens": 264544} |
| {"current_steps": 850, "total_steps": 1800, "loss": 0.2325, "lr": 0.0006350201644290005, "epoch": 9.444444444444445, "percentage": 47.22, "elapsed_time": "0:02:31", "remaining_time": "0:02:48", "throughput": 1761.04, "total_tokens": 266080} |
| {"current_steps": 855, "total_steps": 1800, "loss": 0.2329, "lr": 0.0006303458667395708, "epoch": 9.5, "percentage": 47.5, "elapsed_time": "0:02:31", "remaining_time": "0:02:47", "throughput": 1762.4, "total_tokens": 267680} |
| {"current_steps": 860, "total_steps": 1800, "loss": 0.2303, "lr": 0.0006256593143246718, "epoch": 9.555555555555555, "percentage": 47.78, "elapsed_time": "0:02:32", "remaining_time": "0:02:46", "throughput": 1763.74, "total_tokens": 269280} |
| {"current_steps": 865, "total_steps": 1800, "loss": 0.2318, "lr": 0.0006209609477998338, "epoch": 9.61111111111111, "percentage": 48.06, "elapsed_time": "0:02:33", "remaining_time": "0:02:45", "throughput": 1765.26, "total_tokens": 270912} |
| {"current_steps": 870, "total_steps": 1800, "loss": 0.2273, "lr": 0.0006162512088913149, "epoch": 9.666666666666666, "percentage": 48.33, "elapsed_time": "0:02:34", "remaining_time": "0:02:44", "throughput": 1766.58, "total_tokens": 272512} |
| {"current_steps": 875, "total_steps": 1800, "loss": 0.2331, "lr": 0.0006115305403945697, "epoch": 9.722222222222221, "percentage": 48.61, "elapsed_time": "0:02:35", "remaining_time": "0:02:43", "throughput": 1767.51, "total_tokens": 274048} |
| {"current_steps": 880, "total_steps": 1800, "loss": 0.2304, "lr": 0.0006067993861326201, "epoch": 9.777777777777779, "percentage": 48.89, "elapsed_time": "0:02:35", "remaining_time": "0:02:42", "throughput": 1768.8, "total_tokens": 275648} |
| {"current_steps": 885, "total_steps": 1800, "loss": 0.2346, "lr": 0.0006020581909143279, "epoch": 9.833333333333334, "percentage": 49.17, "elapsed_time": "0:02:36", "remaining_time": "0:02:41", "throughput": 1770.08, "total_tokens": 277248} |
| {"current_steps": 890, "total_steps": 1800, "loss": 0.23, "lr": 0.0005973074004925755, "epoch": 9.88888888888889, "percentage": 49.44, "elapsed_time": "0:02:37", "remaining_time": "0:02:40", "throughput": 1771.17, "total_tokens": 278816} |
| {"current_steps": 895, "total_steps": 1800, "loss": 0.2304, "lr": 0.0005925474615223572, "epoch": 9.944444444444445, "percentage": 49.72, "elapsed_time": "0:02:38", "remaining_time": "0:02:39", "throughput": 1772.42, "total_tokens": 280416} |
| {"current_steps": 900, "total_steps": 1800, "loss": 0.228, "lr": 0.0005877788215187867, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:02:39", "remaining_time": "0:02:39", "throughput": 1773.04, "total_tokens": 281984} |
| {"current_steps": 900, "total_steps": 1800, "eval_loss": 0.23290684819221497, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:02:39", "remaining_time": "0:02:39", "throughput": 1763.97, "total_tokens": 281984} |
| {"current_steps": 905, "total_steps": 1800, "loss": 0.2385, "lr": 0.0005830019288150222, "epoch": 10.055555555555555, "percentage": 50.28, "elapsed_time": "0:02:41", "remaining_time": "0:02:39", "throughput": 1754.44, "total_tokens": 283552} |
| {"current_steps": 910, "total_steps": 1800, "loss": 0.2296, "lr": 0.0005782172325201155, "epoch": 10.11111111111111, "percentage": 50.56, "elapsed_time": "0:02:42", "remaining_time": "0:02:38", "throughput": 1755.56, "total_tokens": 285120} |
| {"current_steps": 915, "total_steps": 1800, "loss": 0.2321, "lr": 0.0005734251824767894, "epoch": 10.166666666666666, "percentage": 50.83, "elapsed_time": "0:02:43", "remaining_time": "0:02:37", "throughput": 1756.84, "total_tokens": 286720} |
| {"current_steps": 920, "total_steps": 1800, "loss": 0.2324, "lr": 0.0005686262292191438, "epoch": 10.222222222222221, "percentage": 51.11, "elapsed_time": "0:02:43", "remaining_time": "0:02:36", "throughput": 1757.94, "total_tokens": 288288} |
| {"current_steps": 925, "total_steps": 1800, "loss": 0.2286, "lr": 0.0005638208239302974, "epoch": 10.277777777777779, "percentage": 51.39, "elapsed_time": "0:02:44", "remaining_time": "0:02:35", "throughput": 1759.04, "total_tokens": 289856} |
| {"current_steps": 930, "total_steps": 1800, "loss": 0.2289, "lr": 0.0005590094183999698, "epoch": 10.333333333333334, "percentage": 51.67, "elapsed_time": "0:02:45", "remaining_time": "0:02:34", "throughput": 1759.95, "total_tokens": 291392} |
| {"current_steps": 935, "total_steps": 1800, "loss": 0.2294, "lr": 0.0005541924649820054, "epoch": 10.38888888888889, "percentage": 51.94, "elapsed_time": "0:02:46", "remaining_time": "0:02:33", "throughput": 1760.5, "total_tokens": 292864} |
| {"current_steps": 940, "total_steps": 1800, "loss": 0.2315, "lr": 0.000549370416551844, "epoch": 10.444444444444445, "percentage": 52.22, "elapsed_time": "0:02:47", "remaining_time": "0:02:32", "throughput": 1761.92, "total_tokens": 294496} |
| {"current_steps": 945, "total_steps": 1800, "loss": 0.2263, "lr": 0.0005445437264639432, "epoch": 10.5, "percentage": 52.5, "elapsed_time": "0:02:47", "remaining_time": "0:02:31", "throughput": 1763.16, "total_tokens": 296096} |
| {"current_steps": 950, "total_steps": 1800, "loss": 0.2281, "lr": 0.0005397128485091551, "epoch": 10.555555555555555, "percentage": 52.78, "elapsed_time": "0:02:48", "remaining_time": "0:02:30", "throughput": 1764.03, "total_tokens": 297632} |
| {"current_steps": 955, "total_steps": 1800, "loss": 0.2347, "lr": 0.0005348782368720626, "epoch": 10.61111111111111, "percentage": 53.06, "elapsed_time": "0:02:49", "remaining_time": "0:02:29", "throughput": 1764.9, "total_tokens": 299168} |
| {"current_steps": 960, "total_steps": 1800, "loss": 0.231, "lr": 0.0005300403460882783, "epoch": 10.666666666666666, "percentage": 53.33, "elapsed_time": "0:02:50", "remaining_time": "0:02:29", "throughput": 1765.93, "total_tokens": 300736} |
| {"current_steps": 965, "total_steps": 1800, "loss": 0.2333, "lr": 0.00052519963100171, "epoch": 10.722222222222221, "percentage": 53.61, "elapsed_time": "0:02:51", "remaining_time": "0:02:28", "throughput": 1766.95, "total_tokens": 302304} |
| {"current_steps": 970, "total_steps": 1800, "loss": 0.225, "lr": 0.000520356546721798, "epoch": 10.777777777777779, "percentage": 53.89, "elapsed_time": "0:02:51", "remaining_time": "0:02:27", "throughput": 1768.3, "total_tokens": 303936} |
| {"current_steps": 975, "total_steps": 1800, "loss": 0.2315, "lr": 0.0005155115485807269, "epoch": 10.833333333333334, "percentage": 54.17, "elapsed_time": "0:02:52", "remaining_time": "0:02:26", "throughput": 1769.3, "total_tokens": 305504} |
| {"current_steps": 980, "total_steps": 1800, "loss": 0.2336, "lr": 0.0005106650920906171, "epoch": 10.88888888888889, "percentage": 54.44, "elapsed_time": "0:02:53", "remaining_time": "0:02:25", "throughput": 1770.11, "total_tokens": 307040} |
| {"current_steps": 985, "total_steps": 1800, "loss": 0.2247, "lr": 0.0005058176329006986, "epoch": 10.944444444444445, "percentage": 54.72, "elapsed_time": "0:02:54", "remaining_time": "0:02:24", "throughput": 1771.09, "total_tokens": 308608} |
| {"current_steps": 990, "total_steps": 1800, "loss": 0.2447, "lr": 0.0005009696267544715, "epoch": 11.0, "percentage": 55.0, "elapsed_time": "0:02:55", "remaining_time": "0:02:23", "throughput": 1771.7, "total_tokens": 310176} |
| {"current_steps": 990, "total_steps": 1800, "eval_loss": 0.23567497730255127, "epoch": 11.0, "percentage": 55.0, "elapsed_time": "0:02:55", "remaining_time": "0:02:23", "throughput": 1763.46, "total_tokens": 310176} |
| {"current_steps": 995, "total_steps": 1800, "loss": 0.2235, "lr": 0.0004961215294468599, "epoch": 11.055555555555555, "percentage": 55.28, "elapsed_time": "0:02:57", "remaining_time": "0:02:23", "throughput": 1755.17, "total_tokens": 311712} |
| {"current_steps": 1000, "total_steps": 1800, "loss": 0.2318, "lr": 0.0004912737967813582, "epoch": 11.11111111111111, "percentage": 55.56, "elapsed_time": "0:02:58", "remaining_time": "0:02:22", "throughput": 1756.18, "total_tokens": 313280} |
| {"current_steps": 1005, "total_steps": 1800, "loss": 0.2188, "lr": 0.0004864268845271786, "epoch": 11.166666666666666, "percentage": 55.83, "elapsed_time": "0:02:59", "remaining_time": "0:02:21", "throughput": 1757.03, "total_tokens": 314816} |
| {"current_steps": 1010, "total_steps": 1800, "loss": 0.2347, "lr": 0.0004815812483764, "epoch": 11.222222222222221, "percentage": 56.11, "elapsed_time": "0:02:59", "remaining_time": "0:02:20", "throughput": 1758.03, "total_tokens": 316384} |
| {"current_steps": 1015, "total_steps": 1800, "loss": 0.2427, "lr": 0.0004767373439011267, "epoch": 11.277777777777779, "percentage": 56.39, "elapsed_time": "0:03:00", "remaining_time": "0:02:19", "throughput": 1759.19, "total_tokens": 317984} |
| {"current_steps": 1020, "total_steps": 1800, "loss": 0.2307, "lr": 0.00047189562651065565, "epoch": 11.333333333333334, "percentage": 56.67, "elapsed_time": "0:03:01", "remaining_time": "0:02:18", "throughput": 1760.18, "total_tokens": 319552} |
| {"current_steps": 1025, "total_steps": 1800, "loss": 0.2357, "lr": 0.00046705655140866074, "epoch": 11.38888888888889, "percentage": 56.94, "elapsed_time": "0:03:02", "remaining_time": "0:02:17", "throughput": 1761.47, "total_tokens": 321184} |
| {"current_steps": 1030, "total_steps": 1800, "loss": 0.2282, "lr": 0.0004622205735503961, "epoch": 11.444444444444445, "percentage": 57.22, "elapsed_time": "0:03:03", "remaining_time": "0:02:16", "throughput": 1762.13, "total_tokens": 322688} |
| {"current_steps": 1035, "total_steps": 1800, "loss": 0.234, "lr": 0.00045738814759992174, "epoch": 11.5, "percentage": 57.5, "elapsed_time": "0:03:03", "remaining_time": "0:02:15", "throughput": 1762.93, "total_tokens": 324224} |
| {"current_steps": 1040, "total_steps": 1800, "loss": 0.2319, "lr": 0.00045255972788735873, "epoch": 11.555555555555555, "percentage": 57.78, "elapsed_time": "0:03:04", "remaining_time": "0:02:14", "throughput": 1763.72, "total_tokens": 325760} |
| {"current_steps": 1045, "total_steps": 1800, "loss": 0.2318, "lr": 0.00044773576836617336, "epoch": 11.61111111111111, "percentage": 58.06, "elapsed_time": "0:03:05", "remaining_time": "0:02:14", "throughput": 1764.37, "total_tokens": 327264} |
| {"current_steps": 1050, "total_steps": 1800, "loss": 0.2313, "lr": 0.000442916722570498, "epoch": 11.666666666666666, "percentage": 58.33, "elapsed_time": "0:03:06", "remaining_time": "0:02:13", "throughput": 1765.31, "total_tokens": 328832} |
| {"current_steps": 1055, "total_steps": 1800, "loss": 0.2272, "lr": 0.0004381030435724919, "epoch": 11.722222222222221, "percentage": 58.61, "elapsed_time": "0:03:07", "remaining_time": "0:02:12", "throughput": 1766.55, "total_tokens": 330464} |
| {"current_steps": 1060, "total_steps": 1800, "loss": 0.2293, "lr": 0.00043329518393974364, "epoch": 11.777777777777779, "percentage": 58.89, "elapsed_time": "0:03:07", "remaining_time": "0:02:11", "throughput": 1767.62, "total_tokens": 332064} |
| {"current_steps": 1065, "total_steps": 1800, "loss": 0.2299, "lr": 0.0004284935956927229, "epoch": 11.833333333333334, "percentage": 59.17, "elapsed_time": "0:03:08", "remaining_time": "0:02:10", "throughput": 1768.69, "total_tokens": 333664} |
| {"current_steps": 1070, "total_steps": 1800, "loss": 0.2268, "lr": 0.00042369873026228263, "epoch": 11.88888888888889, "percentage": 59.44, "elapsed_time": "0:03:09", "remaining_time": "0:02:09", "throughput": 1769.6, "total_tokens": 335232} |
| {"current_steps": 1075, "total_steps": 1800, "loss": 0.229, "lr": 0.00041891103844721633, "epoch": 11.944444444444445, "percentage": 59.72, "elapsed_time": "0:03:10", "remaining_time": "0:02:08", "throughput": 1770.5, "total_tokens": 336800} |
| {"current_steps": 1080, "total_steps": 1800, "loss": 0.229, "lr": 0.00041413097037187657, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "0:03:11", "remaining_time": "0:02:07", "throughput": 1771.2, "total_tokens": 338400} |
| {"current_steps": 1080, "total_steps": 1800, "eval_loss": 0.23775029182434082, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "0:03:11", "remaining_time": "0:02:07", "throughput": 1763.66, "total_tokens": 338400} |
| {"current_steps": 1085, "total_steps": 1800, "loss": 0.2332, "lr": 0.00040935897544385424, "epoch": 12.055555555555555, "percentage": 60.28, "elapsed_time": "0:03:13", "remaining_time": "0:02:07", "throughput": 1756.86, "total_tokens": 339968} |
| {"current_steps": 1090, "total_steps": 1800, "loss": 0.2273, "lr": 0.0004045955023117276, "epoch": 12.11111111111111, "percentage": 60.56, "elapsed_time": "0:03:14", "remaining_time": "0:02:06", "throughput": 1757.41, "total_tokens": 341536} |
| {"current_steps": 1095, "total_steps": 1800, "loss": 0.2319, "lr": 0.00039984099882288133, "epoch": 12.166666666666666, "percentage": 60.83, "elapsed_time": "0:03:15", "remaining_time": "0:02:05", "throughput": 1758.33, "total_tokens": 343104} |
| {"current_steps": 1100, "total_steps": 1800, "loss": 0.2293, "lr": 0.0003950959119814013, "epoch": 12.222222222222221, "percentage": 61.11, "elapsed_time": "0:03:15", "remaining_time": "0:02:04", "throughput": 1759.1, "total_tokens": 344640} |
| {"current_steps": 1105, "total_steps": 1800, "loss": 0.2314, "lr": 0.0003903606879060483, "epoch": 12.277777777777779, "percentage": 61.39, "elapsed_time": "0:03:16", "remaining_time": "0:02:03", "throughput": 1760.31, "total_tokens": 346272} |
| {"current_steps": 1110, "total_steps": 1800, "loss": 0.2309, "lr": 0.0003856357717883161, "epoch": 12.333333333333334, "percentage": 61.67, "elapsed_time": "0:03:17", "remaining_time": "0:02:02", "throughput": 1761.07, "total_tokens": 347808} |
| {"current_steps": 1115, "total_steps": 1800, "loss": 0.2305, "lr": 0.00038092160785057466, "epoch": 12.38888888888889, "percentage": 61.94, "elapsed_time": "0:03:18", "remaining_time": "0:02:01", "throughput": 1761.82, "total_tokens": 349344} |
| {"current_steps": 1120, "total_steps": 1800, "loss": 0.2288, "lr": 0.00037621863930430713, "epoch": 12.444444444444445, "percentage": 62.22, "elapsed_time": "0:03:19", "remaining_time": "0:02:00", "throughput": 1762.71, "total_tokens": 350912} |
| {"current_steps": 1125, "total_steps": 1800, "loss": 0.2278, "lr": 0.000371527308308439, "epoch": 12.5, "percentage": 62.5, "elapsed_time": "0:03:19", "remaining_time": "0:01:59", "throughput": 1763.6, "total_tokens": 352480} |
| {"current_steps": 1130, "total_steps": 1800, "loss": 0.228, "lr": 0.00036684805592776895, "epoch": 12.555555555555555, "percentage": 62.78, "elapsed_time": "0:03:20", "remaining_time": "0:01:58", "throughput": 1764.47, "total_tokens": 354048} |
| {"current_steps": 1135, "total_steps": 1800, "loss": 0.2243, "lr": 0.00036218132209150044, "epoch": 12.61111111111111, "percentage": 63.06, "elapsed_time": "0:03:21", "remaining_time": "0:01:58", "throughput": 1765.49, "total_tokens": 355648} |
| {"current_steps": 1140, "total_steps": 1800, "loss": 0.2372, "lr": 0.0003575275455518811, "epoch": 12.666666666666666, "percentage": 63.33, "elapsed_time": "0:03:22", "remaining_time": "0:01:57", "throughput": 1766.49, "total_tokens": 357248} |
| {"current_steps": 1145, "total_steps": 1800, "loss": 0.2273, "lr": 0.00035288716384295236, "epoch": 12.722222222222221, "percentage": 63.61, "elapsed_time": "0:03:23", "remaining_time": "0:01:56", "throughput": 1767.07, "total_tokens": 358752} |
| {"current_steps": 1150, "total_steps": 1800, "loss": 0.2411, "lr": 0.00034826061323941484, "epoch": 12.777777777777779, "percentage": 63.89, "elapsed_time": "0:03:23", "remaining_time": "0:01:55", "throughput": 1767.77, "total_tokens": 360288} |
| {"current_steps": 1155, "total_steps": 1800, "loss": 0.2358, "lr": 0.0003436483287156091, "epoch": 12.833333333333334, "percentage": 64.17, "elapsed_time": "0:03:24", "remaining_time": "0:01:54", "throughput": 1768.9, "total_tokens": 361920} |
| {"current_steps": 1160, "total_steps": 1800, "loss": 0.2316, "lr": 0.000339050743904623, "epoch": 12.88888888888889, "percentage": 64.44, "elapsed_time": "0:03:25", "remaining_time": "0:01:53", "throughput": 1769.87, "total_tokens": 363520} |
| {"current_steps": 1165, "total_steps": 1800, "loss": 0.2319, "lr": 0.000334468291057521, "epoch": 12.944444444444445, "percentage": 64.72, "elapsed_time": "0:03:26", "remaining_time": "0:01:52", "throughput": 1770.7, "total_tokens": 365088} |
| {"current_steps": 1170, "total_steps": 1800, "loss": 0.2283, "lr": 0.00032990140100270637, "epoch": 13.0, "percentage": 65.0, "elapsed_time": "0:03:27", "remaining_time": "0:01:51", "throughput": 1771.37, "total_tokens": 366688} |
| {"current_steps": 1170, "total_steps": 1800, "eval_loss": 0.23198899626731873, "epoch": 13.0, "percentage": 65.0, "elapsed_time": "0:03:27", "remaining_time": "0:01:51", "throughput": 1764.4, "total_tokens": 366688} |
| {"current_steps": 1175, "total_steps": 1800, "loss": 0.2336, "lr": 0.0003253505031054155, "epoch": 13.055555555555555, "percentage": 65.28, "elapsed_time": "0:03:29", "remaining_time": "0:01:51", "throughput": 1756.38, "total_tokens": 368192} |
| {"current_steps": 1180, "total_steps": 1800, "loss": 0.2247, "lr": 0.00032081602522734986, "epoch": 13.11111111111111, "percentage": 65.56, "elapsed_time": "0:03:30", "remaining_time": "0:01:50", "throughput": 1757.38, "total_tokens": 369792} |
| {"current_steps": 1185, "total_steps": 1800, "loss": 0.2294, "lr": 0.00031629839368645086, "epoch": 13.166666666666666, "percentage": 65.83, "elapsed_time": "0:03:31", "remaining_time": "0:01:49", "throughput": 1758.2, "total_tokens": 371360} |
| {"current_steps": 1190, "total_steps": 1800, "loss": 0.2288, "lr": 0.0003117980332168179, "epoch": 13.222222222222221, "percentage": 66.11, "elapsed_time": "0:03:32", "remaining_time": "0:01:48", "throughput": 1759.04, "total_tokens": 372928} |
| {"current_steps": 1195, "total_steps": 1800, "loss": 0.2358, "lr": 0.00030731536692877595, "epoch": 13.277777777777779, "percentage": 66.39, "elapsed_time": "0:03:32", "remaining_time": "0:01:47", "throughput": 1760.02, "total_tokens": 374528} |
| {"current_steps": 1200, "total_steps": 1800, "loss": 0.2287, "lr": 0.0003028508162690967, "epoch": 13.333333333333334, "percentage": 66.67, "elapsed_time": "0:03:33", "remaining_time": "0:01:46", "throughput": 1760.45, "total_tokens": 376000} |
| {"current_steps": 1205, "total_steps": 1800, "loss": 0.23, "lr": 0.000298404800981375, "epoch": 13.38888888888889, "percentage": 66.94, "elapsed_time": "0:03:34", "remaining_time": "0:01:45", "throughput": 1761.42, "total_tokens": 377600} |
| {"current_steps": 1210, "total_steps": 1800, "loss": 0.2304, "lr": 0.0002939777390665658, "epoch": 13.444444444444445, "percentage": 67.22, "elapsed_time": "0:03:35", "remaining_time": "0:01:44", "throughput": 1762.38, "total_tokens": 379200} |
| {"current_steps": 1215, "total_steps": 1800, "loss": 0.2258, "lr": 0.0002895700467436855, "epoch": 13.5, "percentage": 67.5, "elapsed_time": "0:03:35", "remaining_time": "0:01:43", "throughput": 1762.93, "total_tokens": 380704} |
| {"current_steps": 1220, "total_steps": 1800, "loss": 0.2228, "lr": 0.00028518213841067906, "epoch": 13.555555555555555, "percentage": 67.78, "elapsed_time": "0:03:36", "remaining_time": "0:01:43", "throughput": 1763.74, "total_tokens": 382272} |
| {"current_steps": 1225, "total_steps": 1800, "loss": 0.2239, "lr": 0.00028081442660546124, "epoch": 13.61111111111111, "percentage": 68.06, "elapsed_time": "0:03:37", "remaining_time": "0:01:42", "throughput": 1764.28, "total_tokens": 383776} |
| {"current_steps": 1230, "total_steps": 1800, "loss": 0.2389, "lr": 0.00027646732196712974, "epoch": 13.666666666666666, "percentage": 68.33, "elapsed_time": "0:03:38", "remaining_time": "0:01:41", "throughput": 1765.08, "total_tokens": 385344} |
| {"current_steps": 1235, "total_steps": 1800, "loss": 0.2284, "lr": 0.00027214123319735785, "epoch": 13.722222222222221, "percentage": 68.61, "elapsed_time": "0:03:39", "remaining_time": "0:01:40", "throughput": 1765.88, "total_tokens": 386912} |
| {"current_steps": 1240, "total_steps": 1800, "loss": 0.2259, "lr": 0.00026783656702197156, "epoch": 13.777777777777779, "percentage": 68.89, "elapsed_time": "0:03:39", "remaining_time": "0:01:39", "throughput": 1766.67, "total_tokens": 388480} |
| {"current_steps": 1245, "total_steps": 1800, "loss": 0.2302, "lr": 0.00026355372815270835, "epoch": 13.833333333333334, "percentage": 69.17, "elapsed_time": "0:03:40", "remaining_time": "0:01:38", "throughput": 1767.46, "total_tokens": 390048} |
| {"current_steps": 1250, "total_steps": 1800, "loss": 0.2346, "lr": 0.000259293119249168, "epoch": 13.88888888888889, "percentage": 69.44, "elapsed_time": "0:03:41", "remaining_time": "0:01:37", "throughput": 1768.1, "total_tokens": 391584} |
| {"current_steps": 1255, "total_steps": 1800, "loss": 0.2374, "lr": 0.00025505514088095655, "epoch": 13.944444444444445, "percentage": 69.72, "elapsed_time": "0:03:42", "remaining_time": "0:01:36", "throughput": 1769.01, "total_tokens": 393184} |
| {"current_steps": 1260, "total_steps": 1800, "loss": 0.2299, "lr": 0.0002508401914900249, "epoch": 14.0, "percentage": 70.0, "elapsed_time": "0:03:43", "remaining_time": "0:01:35", "throughput": 1769.5, "total_tokens": 394752} |
| {"current_steps": 1260, "total_steps": 1800, "eval_loss": 0.23503117263317108, "epoch": 14.0, "percentage": 70.0, "elapsed_time": "0:03:43", "remaining_time": "0:01:35", "throughput": 1763.04, "total_tokens": 394752} |
| {"current_steps": 1265, "total_steps": 1800, "loss": 0.2287, "lr": 0.00024664866735320885, "epoch": 14.055555555555555, "percentage": 70.28, "elapsed_time": "0:03:45", "remaining_time": "0:01:35", "throughput": 1756.69, "total_tokens": 396320} |
| {"current_steps": 1270, "total_steps": 1800, "loss": 0.2307, "lr": 0.00024248096254497287, "epoch": 14.11111111111111, "percentage": 70.56, "elapsed_time": "0:03:46", "remaining_time": "0:01:34", "throughput": 1757.59, "total_tokens": 397920} |
| {"current_steps": 1275, "total_steps": 1800, "loss": 0.2273, "lr": 0.00023833746890035963, "epoch": 14.166666666666666, "percentage": 70.83, "elapsed_time": "0:03:47", "remaining_time": "0:01:33", "throughput": 1758.64, "total_tokens": 399552} |
| {"current_steps": 1280, "total_steps": 1800, "loss": 0.2272, "lr": 0.0002342185759781511, "epoch": 14.222222222222221, "percentage": 71.11, "elapsed_time": "0:03:47", "remaining_time": "0:01:32", "throughput": 1759.43, "total_tokens": 401120} |
| {"current_steps": 1285, "total_steps": 1800, "loss": 0.2273, "lr": 0.00023012467102424372, "epoch": 14.277777777777779, "percentage": 71.39, "elapsed_time": "0:03:48", "remaining_time": "0:01:31", "throughput": 1760.34, "total_tokens": 402720} |
| {"current_steps": 1290, "total_steps": 1800, "loss": 0.2316, "lr": 0.00022605613893524008, "epoch": 14.333333333333334, "percentage": 71.67, "elapsed_time": "0:03:49", "remaining_time": "0:01:30", "throughput": 1761.25, "total_tokens": 404320} |
| {"current_steps": 1295, "total_steps": 1800, "loss": 0.2286, "lr": 0.00022201336222226332, "epoch": 14.38888888888889, "percentage": 71.94, "elapsed_time": "0:03:50", "remaining_time": "0:01:29", "throughput": 1761.77, "total_tokens": 405824} |
| {"current_steps": 1300, "total_steps": 1800, "loss": 0.2324, "lr": 0.0002179967209749929, "epoch": 14.444444444444445, "percentage": 72.22, "elapsed_time": "0:03:51", "remaining_time": "0:01:28", "throughput": 1762.41, "total_tokens": 407360} |
| {"current_steps": 1305, "total_steps": 1800, "loss": 0.2218, "lr": 0.00021400659282593083, "epoch": 14.5, "percentage": 72.5, "elapsed_time": "0:03:51", "remaining_time": "0:01:27", "throughput": 1763.16, "total_tokens": 408928} |
| {"current_steps": 1310, "total_steps": 1800, "loss": 0.2345, "lr": 0.0002100433529148979, "epoch": 14.555555555555555, "percentage": 72.78, "elapsed_time": "0:03:52", "remaining_time": "0:01:27", "throughput": 1763.92, "total_tokens": 410496} |
| {"current_steps": 1315, "total_steps": 1800, "loss": 0.2312, "lr": 0.00020610737385376348, "epoch": 14.61111111111111, "percentage": 73.06, "elapsed_time": "0:03:53", "remaining_time": "0:01:26", "throughput": 1764.54, "total_tokens": 412032} |
| {"current_steps": 1320, "total_steps": 1800, "loss": 0.2198, "lr": 0.00020219902569141402, "epoch": 14.666666666666666, "percentage": 73.33, "elapsed_time": "0:03:54", "remaining_time": "0:01:25", "throughput": 1765.04, "total_tokens": 413536} |
| {"current_steps": 1325, "total_steps": 1800, "loss": 0.2254, "lr": 0.00019831867587896218, "epoch": 14.722222222222221, "percentage": 73.61, "elapsed_time": "0:03:55", "remaining_time": "0:01:24", "throughput": 1765.9, "total_tokens": 415136} |
| {"current_steps": 1330, "total_steps": 1800, "loss": 0.2146, "lr": 0.0001944666892352001, "epoch": 14.777777777777779, "percentage": 73.89, "elapsed_time": "0:03:55", "remaining_time": "0:01:23", "throughput": 1766.64, "total_tokens": 416704} |
| {"current_steps": 1335, "total_steps": 1800, "loss": 0.2589, "lr": 0.00019064342791230072, "epoch": 14.833333333333334, "percentage": 74.17, "elapsed_time": "0:03:56", "remaining_time": "0:01:22", "throughput": 1767.37, "total_tokens": 418272} |
| {"current_steps": 1340, "total_steps": 1800, "loss": 0.2212, "lr": 0.00018684925136176834, "epoch": 14.88888888888889, "percentage": 74.44, "elapsed_time": "0:03:57", "remaining_time": "0:01:21", "throughput": 1767.98, "total_tokens": 419808} |
| {"current_steps": 1345, "total_steps": 1800, "loss": 0.227, "lr": 0.0001830845163006448, "epoch": 14.944444444444445, "percentage": 74.72, "elapsed_time": "0:03:58", "remaining_time": "0:01:20", "throughput": 1768.58, "total_tokens": 421344} |
| {"current_steps": 1350, "total_steps": 1800, "loss": 0.2301, "lr": 0.00017934957667797225, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "0:03:59", "remaining_time": "0:01:19", "throughput": 1769.05, "total_tokens": 422912} |
| {"current_steps": 1350, "total_steps": 1800, "eval_loss": 0.23467722535133362, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "0:03:59", "remaining_time": "0:01:19", "throughput": 1763.02, "total_tokens": 422912} |
| {"current_steps": 1355, "total_steps": 1800, "loss": 0.2299, "lr": 0.000175644783641515, "epoch": 15.055555555555555, "percentage": 75.28, "elapsed_time": "0:04:01", "remaining_time": "0:01:19", "throughput": 1757.09, "total_tokens": 424480} |
| {"current_steps": 1360, "total_steps": 1800, "loss": 0.2289, "lr": 0.00017197048550474643, "epoch": 15.11111111111111, "percentage": 75.56, "elapsed_time": "0:04:02", "remaining_time": "0:01:18", "throughput": 1757.83, "total_tokens": 426048} |
| {"current_steps": 1365, "total_steps": 1800, "loss": 0.2294, "lr": 0.0001683270277141014, "epoch": 15.166666666666666, "percentage": 75.83, "elapsed_time": "0:04:03", "remaining_time": "0:01:17", "throughput": 1758.69, "total_tokens": 427648} |
| {"current_steps": 1370, "total_steps": 1800, "loss": 0.2284, "lr": 0.00016471475281649818, "epoch": 15.222222222222221, "percentage": 76.11, "elapsed_time": "0:04:03", "remaining_time": "0:01:16", "throughput": 1759.42, "total_tokens": 429216} |
| {"current_steps": 1375, "total_steps": 1800, "loss": 0.2362, "lr": 0.0001611340004271339, "epoch": 15.277777777777779, "percentage": 76.39, "elapsed_time": "0:04:04", "remaining_time": "0:01:15", "throughput": 1759.91, "total_tokens": 430720} |
| {"current_steps": 1380, "total_steps": 1800, "loss": 0.2274, "lr": 0.0001575851071975541, "epoch": 15.333333333333334, "percentage": 76.67, "elapsed_time": "0:04:05", "remaining_time": "0:01:14", "throughput": 1760.76, "total_tokens": 432320} |
| {"current_steps": 1385, "total_steps": 1800, "loss": 0.2222, "lr": 0.00015406840678400203, "epoch": 15.38888888888889, "percentage": 76.94, "elapsed_time": "0:04:06", "remaining_time": "0:01:13", "throughput": 1761.48, "total_tokens": 433888} |
| {"current_steps": 1390, "total_steps": 1800, "loss": 0.2184, "lr": 0.00015058422981604997, "epoch": 15.444444444444445, "percentage": 77.22, "elapsed_time": "0:04:07", "remaining_time": "0:01:12", "throughput": 1762.2, "total_tokens": 435456} |
| {"current_steps": 1395, "total_steps": 1800, "loss": 0.22, "lr": 0.00014713290386551348, "epoch": 15.5, "percentage": 77.5, "elapsed_time": "0:04:07", "remaining_time": "0:01:11", "throughput": 1762.91, "total_tokens": 437024} |
| {"current_steps": 1400, "total_steps": 1800, "loss": 0.2566, "lr": 0.00014371475341565454, "epoch": 15.555555555555555, "percentage": 77.78, "elapsed_time": "0:04:08", "remaining_time": "0:01:11", "throughput": 1763.39, "total_tokens": 438528} |
| {"current_steps": 1405, "total_steps": 1800, "loss": 0.2336, "lr": 0.00014033009983067452, "epoch": 15.61111111111111, "percentage": 78.06, "elapsed_time": "0:04:09", "remaining_time": "0:01:10", "throughput": 1764.09, "total_tokens": 440096} |
| {"current_steps": 1410, "total_steps": 1800, "loss": 0.2329, "lr": 0.00013697926132550054, "epoch": 15.666666666666666, "percentage": 78.33, "elapsed_time": "0:04:10", "remaining_time": "0:01:09", "throughput": 1764.68, "total_tokens": 441632} |
| {"current_steps": 1415, "total_steps": 1800, "loss": 0.2294, "lr": 0.0001336625529358682, "epoch": 15.722222222222221, "percentage": 78.61, "elapsed_time": "0:04:11", "remaining_time": "0:01:08", "throughput": 1765.11, "total_tokens": 443136} |
| {"current_steps": 1420, "total_steps": 1800, "loss": 0.2289, "lr": 0.00013038028648870205, "epoch": 15.777777777777779, "percentage": 78.89, "elapsed_time": "0:04:11", "remaining_time": "0:01:07", "throughput": 1765.92, "total_tokens": 444736} |
| {"current_steps": 1425, "total_steps": 1800, "loss": 0.2307, "lr": 0.0001271327705727991, "epoch": 15.833333333333334, "percentage": 79.17, "elapsed_time": "0:04:12", "remaining_time": "0:01:06", "throughput": 1766.72, "total_tokens": 446336} |
| {"current_steps": 1430, "total_steps": 1800, "loss": 0.2248, "lr": 0.0001239203105098165, "epoch": 15.88888888888889, "percentage": 79.44, "elapsed_time": "0:04:13", "remaining_time": "0:01:05", "throughput": 1767.52, "total_tokens": 447936} |
| {"current_steps": 1435, "total_steps": 1800, "loss": 0.2271, "lr": 0.00012074320832556557, "epoch": 15.944444444444445, "percentage": 79.72, "elapsed_time": "0:04:14", "remaining_time": "0:01:04", "throughput": 1767.97, "total_tokens": 449440} |
| {"current_steps": 1440, "total_steps": 1800, "loss": 0.2232, "lr": 0.00011760176272161627, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "0:04:15", "remaining_time": "0:01:03", "throughput": 1768.4, "total_tokens": 451008} |
| {"current_steps": 1440, "total_steps": 1800, "eval_loss": 0.23479977250099182, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "0:04:15", "remaining_time": "0:01:03", "throughput": 1762.76, "total_tokens": 451008} |
| {"current_steps": 1445, "total_steps": 1800, "loss": 0.2316, "lr": 0.00011449626904721472, "epoch": 16.055555555555557, "percentage": 80.28, "elapsed_time": "0:04:17", "remaining_time": "0:01:03", "throughput": 1757.13, "total_tokens": 452576} |
| {"current_steps": 1450, "total_steps": 1800, "loss": 0.2261, "lr": 0.00011142701927151455, "epoch": 16.11111111111111, "percentage": 80.56, "elapsed_time": "0:04:18", "remaining_time": "0:01:02", "throughput": 1757.67, "total_tokens": 454112} |
| {"current_steps": 1455, "total_steps": 1800, "loss": 0.2259, "lr": 0.00010839430195612793, "epoch": 16.166666666666668, "percentage": 80.83, "elapsed_time": "0:04:19", "remaining_time": "0:01:01", "throughput": 1758.36, "total_tokens": 455680} |
| {"current_steps": 1460, "total_steps": 1800, "loss": 0.2243, "lr": 0.00010539840222799463, "epoch": 16.22222222222222, "percentage": 81.11, "elapsed_time": "0:04:19", "remaining_time": "0:01:00", "throughput": 1759.16, "total_tokens": 457280} |
| {"current_steps": 1465, "total_steps": 1800, "loss": 0.2255, "lr": 0.00010243960175257604, "epoch": 16.27777777777778, "percentage": 81.39, "elapsed_time": "0:04:20", "remaining_time": "0:00:59", "throughput": 1759.85, "total_tokens": 458848} |
| {"current_steps": 1470, "total_steps": 1800, "loss": 0.2238, "lr": 9.9518178707374e-05, "epoch": 16.333333333333332, "percentage": 81.67, "elapsed_time": "0:04:21", "remaining_time": "0:00:58", "throughput": 1760.53, "total_tokens": 460416} |
| {"current_steps": 1475, "total_steps": 1800, "loss": 0.2266, "lr": 9.663440775577653e-05, "epoch": 16.38888888888889, "percentage": 81.94, "elapsed_time": "0:04:22", "remaining_time": "0:00:57", "throughput": 1761.43, "total_tokens": 462048} |
| {"current_steps": 1480, "total_steps": 1800, "loss": 0.218, "lr": 9.378856002123548e-05, "epoch": 16.444444444444443, "percentage": 82.22, "elapsed_time": "0:04:23", "remaining_time": "0:00:56", "throughput": 1762.0, "total_tokens": 463584} |
| {"current_steps": 1485, "total_steps": 1800, "loss": 0.2233, "lr": 9.098090306177625e-05, "epoch": 16.5, "percentage": 82.5, "elapsed_time": "0:04:23", "remaining_time": "0:00:55", "throughput": 1762.66, "total_tokens": 465152} |
| {"current_steps": 1490, "total_steps": 1800, "loss": 0.2287, "lr": 8.821170084484247e-05, "epoch": 16.555555555555557, "percentage": 82.78, "elapsed_time": "0:04:24", "remaining_time": "0:00:55", "throughput": 1763.33, "total_tokens": 466720} |
| {"current_steps": 1495, "total_steps": 1800, "loss": 0.2262, "lr": 8.548121372247918e-05, "epoch": 16.61111111111111, "percentage": 83.06, "elapsed_time": "0:04:25", "remaining_time": "0:00:54", "throughput": 1763.89, "total_tokens": 468256} |
| {"current_steps": 1500, "total_steps": 1800, "loss": 0.2108, "lr": 8.278969840685458e-05, "epoch": 16.666666666666668, "percentage": 83.33, "elapsed_time": "0:04:26", "remaining_time": "0:00:53", "throughput": 1764.44, "total_tokens": 469792} |
| {"current_steps": 1505, "total_steps": 1800, "loss": 0.2431, "lr": 8.013740794612512e-05, "epoch": 16.72222222222222, "percentage": 83.61, "elapsed_time": "0:04:27", "remaining_time": "0:00:52", "throughput": 1765.09, "total_tokens": 471360} |
| {"current_steps": 1510, "total_steps": 1800, "loss": 0.2221, "lr": 7.752459170064491e-05, "epoch": 16.77777777777778, "percentage": 83.89, "elapsed_time": "0:04:27", "remaining_time": "0:00:51", "throughput": 1765.63, "total_tokens": 472896} |
| {"current_steps": 1515, "total_steps": 1800, "loss": 0.2229, "lr": 7.4951495319521e-05, "epoch": 16.833333333333332, "percentage": 84.17, "elapsed_time": "0:04:28", "remaining_time": "0:00:50", "throughput": 1766.38, "total_tokens": 474496} |
| {"current_steps": 1520, "total_steps": 1800, "loss": 0.2221, "lr": 7.241836071751879e-05, "epoch": 16.88888888888889, "percentage": 84.44, "elapsed_time": "0:04:29", "remaining_time": "0:00:49", "throughput": 1766.99, "total_tokens": 476064} |
| {"current_steps": 1525, "total_steps": 1800, "loss": 0.2251, "lr": 6.992542605231739e-05, "epoch": 16.944444444444443, "percentage": 84.72, "elapsed_time": "0:04:30", "remaining_time": "0:00:48", "throughput": 1767.52, "total_tokens": 477600} |
| {"current_steps": 1530, "total_steps": 1800, "loss": 0.2318, "lr": 6.747292570211916e-05, "epoch": 17.0, "percentage": 85.0, "elapsed_time": "0:04:31", "remaining_time": "0:00:47", "throughput": 1767.72, "total_tokens": 479104} |
| {"current_steps": 1530, "total_steps": 1800, "eval_loss": 0.24350161850452423, "epoch": 17.0, "percentage": 85.0, "elapsed_time": "0:04:31", "remaining_time": "0:00:47", "throughput": 1762.41, "total_tokens": 479104} |
| {"current_steps": 1535, "total_steps": 1800, "loss": 0.2191, "lr": 6.506109024361429e-05, "epoch": 17.055555555555557, "percentage": 85.28, "elapsed_time": "0:04:33", "remaining_time": "0:00:47", "throughput": 1757.3, "total_tokens": 480736} |
| {"current_steps": 1540, "total_steps": 1800, "loss": 0.2099, "lr": 6.269014643030213e-05, "epoch": 17.11111111111111, "percentage": 85.56, "elapsed_time": "0:04:34", "remaining_time": "0:00:46", "throughput": 1757.95, "total_tokens": 482304} |
| {"current_steps": 1545, "total_steps": 1800, "loss": 0.2332, "lr": 6.0360317171172794e-05, "epoch": 17.166666666666668, "percentage": 85.83, "elapsed_time": "0:04:35", "remaining_time": "0:00:45", "throughput": 1758.6, "total_tokens": 483872} |
| {"current_steps": 1550, "total_steps": 1800, "loss": 0.2026, "lr": 5.807182150975027e-05, "epoch": 17.22222222222222, "percentage": 86.11, "elapsed_time": "0:04:35", "remaining_time": "0:00:44", "throughput": 1759.15, "total_tokens": 485408} |
| {"current_steps": 1555, "total_steps": 1800, "loss": 0.2208, "lr": 5.5824874603498056e-05, "epoch": 17.27777777777778, "percentage": 86.39, "elapsed_time": "0:04:36", "remaining_time": "0:00:43", "throughput": 1759.69, "total_tokens": 486944} |
| {"current_steps": 1560, "total_steps": 1800, "loss": 0.2278, "lr": 5.361968770359071e-05, "epoch": 17.333333333333332, "percentage": 86.67, "elapsed_time": "0:04:37", "remaining_time": "0:00:42", "throughput": 1760.44, "total_tokens": 488544} |
| {"current_steps": 1565, "total_steps": 1800, "loss": 0.2334, "lr": 5.145646813505339e-05, "epoch": 17.38888888888889, "percentage": 86.94, "elapsed_time": "0:04:38", "remaining_time": "0:00:41", "throughput": 1761.18, "total_tokens": 490144} |
| {"current_steps": 1570, "total_steps": 1800, "loss": 0.2179, "lr": 4.933541927726887e-05, "epoch": 17.444444444444443, "percentage": 87.22, "elapsed_time": "0:04:39", "remaining_time": "0:00:40", "throughput": 1761.72, "total_tokens": 491680} |
| {"current_steps": 1575, "total_steps": 1800, "loss": 0.2309, "lr": 4.725674054485712e-05, "epoch": 17.5, "percentage": 87.5, "elapsed_time": "0:04:39", "remaining_time": "0:00:39", "throughput": 1762.35, "total_tokens": 493248} |
| {"current_steps": 1580, "total_steps": 1800, "loss": 0.2227, "lr": 4.522062736892635e-05, "epoch": 17.555555555555557, "percentage": 87.78, "elapsed_time": "0:04:40", "remaining_time": "0:00:39", "throughput": 1762.98, "total_tokens": 494816} |
| {"current_steps": 1585, "total_steps": 1800, "loss": 0.2249, "lr": 4.322727117869951e-05, "epoch": 17.61111111111111, "percentage": 88.06, "elapsed_time": "0:04:41", "remaining_time": "0:00:38", "throughput": 1763.7, "total_tokens": 496416} |
| {"current_steps": 1590, "total_steps": 1800, "loss": 0.2353, "lr": 4.127685938351694e-05, "epoch": 17.666666666666668, "percentage": 88.33, "elapsed_time": "0:04:42", "remaining_time": "0:00:37", "throughput": 1764.22, "total_tokens": 497952} |
| {"current_steps": 1595, "total_steps": 1800, "loss": 0.2128, "lr": 3.936957535521624e-05, "epoch": 17.72222222222222, "percentage": 88.61, "elapsed_time": "0:04:43", "remaining_time": "0:00:36", "throughput": 1764.84, "total_tokens": 499520} |
| {"current_steps": 1600, "total_steps": 1800, "loss": 0.2246, "lr": 3.750559841089196e-05, "epoch": 17.77777777777778, "percentage": 88.89, "elapsed_time": "0:04:43", "remaining_time": "0:00:35", "throughput": 1765.56, "total_tokens": 501120} |
| {"current_steps": 1605, "total_steps": 1800, "loss": 0.2251, "lr": 3.56851037960379e-05, "epoch": 17.833333333333332, "percentage": 89.17, "elapsed_time": "0:04:44", "remaining_time": "0:00:34", "throughput": 1766.17, "total_tokens": 502688} |
| {"current_steps": 1610, "total_steps": 1800, "loss": 0.219, "lr": 3.3908262668069845e-05, "epoch": 17.88888888888889, "percentage": 89.44, "elapsed_time": "0:04:45", "remaining_time": "0:00:33", "throughput": 1766.68, "total_tokens": 504224} |
| {"current_steps": 1615, "total_steps": 1800, "loss": 0.2137, "lr": 3.217524208023431e-05, "epoch": 17.944444444444443, "percentage": 89.72, "elapsed_time": "0:04:46", "remaining_time": "0:00:32", "throughput": 1767.39, "total_tokens": 505824} |
| {"current_steps": 1620, "total_steps": 1800, "loss": 0.2203, "lr": 3.048620496590304e-05, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "0:04:47", "remaining_time": "0:00:31", "throughput": 1767.79, "total_tokens": 507392} |
| {"current_steps": 1620, "total_steps": 1800, "eval_loss": 0.24611559510231018, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "0:04:47", "remaining_time": "0:00:31", "throughput": 1762.74, "total_tokens": 507392} |
| {"current_steps": 1625, "total_steps": 1800, "loss": 0.2125, "lr": 2.884131012325386e-05, "epoch": 18.055555555555557, "percentage": 90.28, "elapsed_time": "0:04:49", "remaining_time": "0:00:31", "throughput": 1756.51, "total_tokens": 508928} |
| {"current_steps": 1630, "total_steps": 1800, "loss": 0.2346, "lr": 2.724071220034158e-05, "epoch": 18.11111111111111, "percentage": 90.56, "elapsed_time": "0:04:50", "remaining_time": "0:00:30", "throughput": 1757.13, "total_tokens": 510496} |
| {"current_steps": 1635, "total_steps": 1800, "loss": 0.2089, "lr": 2.5684561680557994e-05, "epoch": 18.166666666666668, "percentage": 90.83, "elapsed_time": "0:04:51", "remaining_time": "0:00:29", "throughput": 1757.65, "total_tokens": 512032} |
| {"current_steps": 1640, "total_steps": 1800, "loss": 0.2317, "lr": 2.417300486848373e-05, "epoch": 18.22222222222222, "percentage": 91.11, "elapsed_time": "0:04:52", "remaining_time": "0:00:28", "throughput": 1757.98, "total_tokens": 513504} |
| {"current_steps": 1645, "total_steps": 1800, "loss": 0.2126, "lr": 2.2706183876134045e-05, "epoch": 18.27777777777778, "percentage": 91.39, "elapsed_time": "0:04:52", "remaining_time": "0:00:27", "throughput": 1758.49, "total_tokens": 515040} |
| {"current_steps": 1650, "total_steps": 1800, "loss": 0.2101, "lr": 2.1284236609596887e-05, "epoch": 18.333333333333332, "percentage": 91.67, "elapsed_time": "0:04:53", "remaining_time": "0:00:26", "throughput": 1759.2, "total_tokens": 516640} |
| {"current_steps": 1655, "total_steps": 1800, "loss": 0.209, "lr": 1.990729675606784e-05, "epoch": 18.38888888888889, "percentage": 91.94, "elapsed_time": "0:04:54", "remaining_time": "0:00:25", "throughput": 1759.81, "total_tokens": 518208} |
| {"current_steps": 1660, "total_steps": 1800, "loss": 0.2161, "lr": 1.8575493771281205e-05, "epoch": 18.444444444444443, "percentage": 92.22, "elapsed_time": "0:04:55", "remaining_time": "0:00:24", "throughput": 1760.42, "total_tokens": 519776} |
| {"current_steps": 1665, "total_steps": 1800, "loss": 0.2034, "lr": 1.728895286733906e-05, "epoch": 18.5, "percentage": 92.5, "elapsed_time": "0:04:56", "remaining_time": "0:00:24", "throughput": 1761.02, "total_tokens": 521344} |
| {"current_steps": 1670, "total_steps": 1800, "loss": 0.2009, "lr": 1.6047795000938782e-05, "epoch": 18.555555555555557, "percentage": 92.78, "elapsed_time": "0:04:56", "remaining_time": "0:00:23", "throughput": 1761.82, "total_tokens": 522976} |
| {"current_steps": 1675, "total_steps": 1800, "loss": 0.2189, "lr": 1.4852136862001764e-05, "epoch": 18.61111111111111, "percentage": 93.06, "elapsed_time": "0:04:57", "remaining_time": "0:00:22", "throughput": 1762.42, "total_tokens": 524544} |
| {"current_steps": 1680, "total_steps": 1800, "loss": 0.209, "lr": 1.3702090862701855e-05, "epoch": 18.666666666666668, "percentage": 93.33, "elapsed_time": "0:04:58", "remaining_time": "0:00:21", "throughput": 1763.01, "total_tokens": 526112} |
| {"current_steps": 1685, "total_steps": 1800, "loss": 0.2027, "lr": 1.2597765126897198e-05, "epoch": 18.72222222222222, "percentage": 93.61, "elapsed_time": "0:04:59", "remaining_time": "0:00:20", "throughput": 1763.69, "total_tokens": 527712} |
| {"current_steps": 1690, "total_steps": 1800, "loss": 0.1916, "lr": 1.1539263479964535e-05, "epoch": 18.77777777777778, "percentage": 93.89, "elapsed_time": "0:04:59", "remaining_time": "0:00:19", "throughput": 1764.27, "total_tokens": 529280} |
| {"current_steps": 1695, "total_steps": 1800, "loss": 0.2805, "lr": 1.0526685439037842e-05, "epoch": 18.833333333333332, "percentage": 94.17, "elapsed_time": "0:05:00", "remaining_time": "0:00:18", "throughput": 1764.77, "total_tokens": 530816} |
| {"current_steps": 1700, "total_steps": 1800, "loss": 0.196, "lr": 9.560126203652263e-06, "epoch": 18.88888888888889, "percentage": 94.44, "elapsed_time": "0:05:01", "remaining_time": "0:00:17", "throughput": 1765.54, "total_tokens": 532448} |
| {"current_steps": 1705, "total_steps": 1800, "loss": 0.2193, "lr": 8.639676646793382e-06, "epoch": 18.944444444444443, "percentage": 94.72, "elapsed_time": "0:05:02", "remaining_time": "0:00:16", "throughput": 1766.11, "total_tokens": 534016} |
| {"current_steps": 1710, "total_steps": 1800, "loss": 0.2287, "lr": 7.76542330635388e-06, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "0:05:03", "remaining_time": "0:00:15", "throughput": 1766.48, "total_tokens": 535584} |
| {"current_steps": 1710, "total_steps": 1800, "eval_loss": 0.26315268874168396, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "0:05:04", "remaining_time": "0:00:16", "throughput": 1761.7, "total_tokens": 535584} |
| {"current_steps": 1715, "total_steps": 1800, "loss": 0.2139, "lr": 6.9374483769975016e-06, "epoch": 19.055555555555557, "percentage": 95.28, "elapsed_time": "0:05:05", "remaining_time": "0:00:15", "throughput": 1756.96, "total_tokens": 537152} |
| {"current_steps": 1720, "total_steps": 1800, "loss": 0.2267, "lr": 6.15582970243117e-06, "epoch": 19.11111111111111, "percentage": 95.56, "elapsed_time": "0:05:06", "remaining_time": "0:00:14", "throughput": 1757.54, "total_tokens": 538720} |
| {"current_steps": 1725, "total_steps": 1800, "loss": 0.1985, "lr": 5.42064076808646e-06, "epoch": 19.166666666666668, "percentage": 95.83, "elapsed_time": "0:05:07", "remaining_time": "0:00:13", "throughput": 1758.03, "total_tokens": 540256} |
| {"current_steps": 1730, "total_steps": 1800, "loss": 0.2141, "lr": 4.731950694210896e-06, "epoch": 19.22222222222222, "percentage": 96.11, "elapsed_time": "0:05:08", "remaining_time": "0:00:12", "throughput": 1758.61, "total_tokens": 541824} |
| {"current_steps": 1735, "total_steps": 1800, "loss": 0.2031, "lr": 4.089824229369155e-06, "epoch": 19.27777777777778, "percentage": 96.39, "elapsed_time": "0:05:08", "remaining_time": "0:00:11", "throughput": 1759.28, "total_tokens": 543424} |
| {"current_steps": 1740, "total_steps": 1800, "loss": 0.2143, "lr": 3.4943217443557664e-06, "epoch": 19.333333333333332, "percentage": 96.67, "elapsed_time": "0:05:09", "remaining_time": "0:00:10", "throughput": 1759.96, "total_tokens": 545024} |
| {"current_steps": 1745, "total_steps": 1800, "loss": 0.2094, "lr": 2.9454992265193214e-06, "epoch": 19.38888888888889, "percentage": 96.94, "elapsed_time": "0:05:10", "remaining_time": "0:00:09", "throughput": 1760.44, "total_tokens": 546560} |
| {"current_steps": 1750, "total_steps": 1800, "loss": 0.2101, "lr": 2.4434082744984598e-06, "epoch": 19.444444444444443, "percentage": 97.22, "elapsed_time": "0:05:11", "remaining_time": "0:00:08", "throughput": 1760.92, "total_tokens": 548096} |
| {"current_steps": 1755, "total_steps": 1800, "loss": 0.1968, "lr": 1.9880960933710836e-06, "epoch": 19.5, "percentage": 97.5, "elapsed_time": "0:05:12", "remaining_time": "0:00:08", "throughput": 1761.49, "total_tokens": 549664} |
| {"current_steps": 1760, "total_steps": 1800, "loss": 0.2048, "lr": 1.5796054902157964e-06, "epoch": 19.555555555555557, "percentage": 97.78, "elapsed_time": "0:05:12", "remaining_time": "0:00:07", "throughput": 1762.15, "total_tokens": 551264} |
| {"current_steps": 1765, "total_steps": 1800, "loss": 0.2301, "lr": 1.2179748700879012e-06, "epoch": 19.61111111111111, "percentage": 98.06, "elapsed_time": "0:05:13", "remaining_time": "0:00:06", "throughput": 1762.62, "total_tokens": 552800} |
| {"current_steps": 1770, "total_steps": 1800, "loss": 0.1973, "lr": 9.032382324080101e-07, "epoch": 19.666666666666668, "percentage": 98.33, "elapsed_time": "0:05:14", "remaining_time": "0:00:05", "throughput": 1763.09, "total_tokens": 554336} |
| {"current_steps": 1775, "total_steps": 1800, "loss": 0.2249, "lr": 6.354251677661571e-07, "epoch": 19.72222222222222, "percentage": 98.61, "elapsed_time": "0:05:15", "remaining_time": "0:00:04", "throughput": 1763.56, "total_tokens": 555872} |
| {"current_steps": 1780, "total_steps": 1800, "loss": 0.1961, "lr": 4.1456085513935646e-07, "epoch": 19.77777777777778, "percentage": 98.89, "elapsed_time": "0:05:15", "remaining_time": "0:00:03", "throughput": 1764.29, "total_tokens": 557504} |
| {"current_steps": 1785, "total_steps": 1800, "loss": 0.2223, "lr": 2.4066605952444145e-07, "epoch": 19.833333333333332, "percentage": 99.17, "elapsed_time": "0:05:16", "remaining_time": "0:00:02", "throughput": 1764.75, "total_tokens": 559040} |
| {"current_steps": 1790, "total_steps": 1800, "loss": 0.2048, "lr": 1.1375712998595855e-07, "epoch": 19.88888888888889, "percentage": 99.44, "elapsed_time": "0:05:17", "remaining_time": "0:00:01", "throughput": 1765.4, "total_tokens": 560640} |
| {"current_steps": 1795, "total_steps": 1800, "loss": 0.2315, "lr": 3.384599811889766e-08, "epoch": 19.944444444444443, "percentage": 99.72, "elapsed_time": "0:05:18", "remaining_time": "0:00:00", "throughput": 1765.85, "total_tokens": 562176} |
| {"current_steps": 1800, "total_steps": 1800, "loss": 0.1829, "lr": 9.40176926922387e-10, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:05:19", "remaining_time": "0:00:00", "throughput": 1766.19, "total_tokens": 563744} |
| {"current_steps": 1800, "total_steps": 1800, "eval_loss": 0.25516048073768616, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:05:20", "remaining_time": "0:00:00", "throughput": 1761.68, "total_tokens": 563744} |
| {"current_steps": 1800, "total_steps": 1800, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:05:21", "remaining_time": "0:00:00", "throughput": 1755.37, "total_tokens": 563744} |
|
|