fahd-v3-3B-Instruct / trainer_log.jsonl
EbrahemHesham's picture
Training in progress, step 270
1602c96 verified
{"current_steps": 5, "total_steps": 270, "loss": 1.5294, "lr": 1.4814814814814815e-05, "epoch": 0.18691588785046728, "percentage": 1.85, "elapsed_time": "0:00:15", "remaining_time": "0:14:06"}
{"current_steps": 10, "total_steps": 270, "loss": 1.1233, "lr": 3.3333333333333335e-05, "epoch": 0.37383177570093457, "percentage": 3.7, "elapsed_time": "0:00:31", "remaining_time": "0:13:36"}
{"current_steps": 15, "total_steps": 270, "loss": 0.9152, "lr": 5.185185185185185e-05, "epoch": 0.5607476635514018, "percentage": 5.56, "elapsed_time": "0:00:47", "remaining_time": "0:13:24"}
{"current_steps": 20, "total_steps": 270, "loss": 0.7294, "lr": 7.037037037037038e-05, "epoch": 0.7476635514018691, "percentage": 7.41, "elapsed_time": "0:01:03", "remaining_time": "0:13:09"}
{"current_steps": 25, "total_steps": 270, "loss": 0.652, "lr": 8.888888888888889e-05, "epoch": 0.9345794392523364, "percentage": 9.26, "elapsed_time": "0:01:18", "remaining_time": "0:12:51"}
{"current_steps": 30, "total_steps": 270, "loss": 0.5829, "lr": 9.998328666948438e-05, "epoch": 1.1121495327102804, "percentage": 11.11, "elapsed_time": "0:01:32", "remaining_time": "0:12:21"}
{"current_steps": 35, "total_steps": 270, "loss": 0.491, "lr": 9.979538999730047e-05, "epoch": 1.2990654205607477, "percentage": 12.96, "elapsed_time": "0:01:48", "remaining_time": "0:12:07"}
{"current_steps": 40, "total_steps": 270, "loss": 0.4352, "lr": 9.939949247384046e-05, "epoch": 1.485981308411215, "percentage": 14.81, "elapsed_time": "0:02:03", "remaining_time": "0:11:50"}
{"current_steps": 45, "total_steps": 270, "loss": 0.3927, "lr": 9.879724780684519e-05, "epoch": 1.6728971962616823, "percentage": 16.67, "elapsed_time": "0:02:19", "remaining_time": "0:11:38"}
{"current_steps": 50, "total_steps": 270, "loss": 0.368, "lr": 9.799117163889559e-05, "epoch": 1.8598130841121496, "percentage": 18.52, "elapsed_time": "0:02:35", "remaining_time": "0:11:23"}
{"current_steps": 55, "total_steps": 270, "loss": 0.3163, "lr": 9.698463103929542e-05, "epoch": 2.0373831775700935, "percentage": 20.37, "elapsed_time": "0:02:49", "remaining_time": "0:11:02"}
{"current_steps": 60, "total_steps": 270, "loss": 0.2275, "lr": 9.57818304394503e-05, "epoch": 2.2242990654205608, "percentage": 22.22, "elapsed_time": "0:03:05", "remaining_time": "0:10:48"}
{"current_steps": 65, "total_steps": 270, "loss": 0.1946, "lr": 9.438779407049281e-05, "epoch": 2.411214953271028, "percentage": 24.07, "elapsed_time": "0:03:20", "remaining_time": "0:10:33"}
{"current_steps": 70, "total_steps": 270, "loss": 0.1879, "lr": 9.280834497651334e-05, "epoch": 2.5981308411214954, "percentage": 25.93, "elapsed_time": "0:03:36", "remaining_time": "0:10:18"}
{"current_steps": 75, "total_steps": 270, "loss": 0.1602, "lr": 9.105008069106093e-05, "epoch": 2.7850467289719627, "percentage": 27.78, "elapsed_time": "0:03:52", "remaining_time": "0:10:04"}
{"current_steps": 80, "total_steps": 270, "loss": 0.161, "lr": 8.912034567851599e-05, "epoch": 2.97196261682243, "percentage": 29.63, "elapsed_time": "0:04:07", "remaining_time": "0:09:47"}
{"current_steps": 85, "total_steps": 270, "loss": 0.1209, "lr": 8.702720065545024e-05, "epoch": 3.149532710280374, "percentage": 31.48, "elapsed_time": "0:04:21", "remaining_time": "0:09:30"}
{"current_steps": 90, "total_steps": 270, "loss": 0.0991, "lr": 8.47793889201221e-05, "epoch": 3.336448598130841, "percentage": 33.33, "elapsed_time": "0:04:36", "remaining_time": "0:09:13"}
{"current_steps": 95, "total_steps": 270, "loss": 0.0925, "lr": 8.238629983075294e-05, "epoch": 3.5233644859813085, "percentage": 35.19, "elapsed_time": "0:04:52", "remaining_time": "0:08:59"}
{"current_steps": 100, "total_steps": 270, "loss": 0.0877, "lr": 7.985792958513931e-05, "epoch": 3.710280373831776, "percentage": 37.04, "elapsed_time": "0:05:08", "remaining_time": "0:08:45"}
{"current_steps": 100, "total_steps": 270, "eval_loss": 0.16322962939739227, "epoch": 3.710280373831776, "percentage": 37.04, "elapsed_time": "0:05:16", "remaining_time": "0:08:57"}
{"current_steps": 105, "total_steps": 270, "loss": 0.0923, "lr": 7.720483946542914e-05, "epoch": 3.897196261682243, "percentage": 38.89, "elapsed_time": "0:05:36", "remaining_time": "0:08:49"}
{"current_steps": 110, "total_steps": 270, "loss": 0.0776, "lr": 7.443811172247821e-05, "epoch": 4.074766355140187, "percentage": 40.74, "elapsed_time": "0:05:51", "remaining_time": "0:08:31"}
{"current_steps": 115, "total_steps": 270, "loss": 0.0521, "lr": 7.156930328406268e-05, "epoch": 4.261682242990654, "percentage": 42.59, "elapsed_time": "0:06:06", "remaining_time": "0:08:14"}
{"current_steps": 120, "total_steps": 270, "loss": 0.0468, "lr": 6.861039748031351e-05, "epoch": 4.4485981308411215, "percentage": 44.44, "elapsed_time": "0:06:22", "remaining_time": "0:07:58"}
{"current_steps": 125, "total_steps": 270, "loss": 0.0489, "lr": 6.557375398802123e-05, "epoch": 4.635514018691588, "percentage": 46.3, "elapsed_time": "0:06:37", "remaining_time": "0:07:41"}
{"current_steps": 130, "total_steps": 270, "loss": 0.0546, "lr": 6.247205720289907e-05, "epoch": 4.822429906542056, "percentage": 48.15, "elapsed_time": "0:06:52", "remaining_time": "0:07:24"}
{"current_steps": 135, "total_steps": 270, "loss": 0.0444, "lr": 5.9318263255459116e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:07:07", "remaining_time": "0:07:07"}
{"current_steps": 140, "total_steps": 270, "loss": 0.0272, "lr": 5.6125545891822274e-05, "epoch": 5.186915887850467, "percentage": 51.85, "elapsed_time": "0:07:22", "remaining_time": "0:06:50"}
{"current_steps": 145, "total_steps": 270, "loss": 0.0292, "lr": 5.290724144552379e-05, "epoch": 5.373831775700935, "percentage": 53.7, "elapsed_time": "0:07:37", "remaining_time": "0:06:34"}
{"current_steps": 150, "total_steps": 270, "loss": 0.03, "lr": 4.967679313017303e-05, "epoch": 5.5607476635514015, "percentage": 55.56, "elapsed_time": "0:07:53", "remaining_time": "0:06:19"}
{"current_steps": 155, "total_steps": 270, "loss": 0.0277, "lr": 4.6447694885663514e-05, "epoch": 5.747663551401869, "percentage": 57.41, "elapsed_time": "0:08:09", "remaining_time": "0:06:03"}
{"current_steps": 160, "total_steps": 270, "loss": 0.0296, "lr": 4.323343501249346e-05, "epoch": 5.934579439252336, "percentage": 59.26, "elapsed_time": "0:08:25", "remaining_time": "0:05:47"}
{"current_steps": 165, "total_steps": 270, "loss": 0.0228, "lr": 4.004743982964298e-05, "epoch": 6.11214953271028, "percentage": 61.11, "elapsed_time": "0:08:39", "remaining_time": "0:05:30"}
{"current_steps": 170, "total_steps": 270, "loss": 0.0187, "lr": 3.6903017591354706e-05, "epoch": 6.299065420560748, "percentage": 62.96, "elapsed_time": "0:08:54", "remaining_time": "0:05:14"}
{"current_steps": 175, "total_steps": 270, "loss": 0.017, "lr": 3.381330289708396e-05, "epoch": 6.485981308411215, "percentage": 64.81, "elapsed_time": "0:09:10", "remaining_time": "0:04:58"}
{"current_steps": 180, "total_steps": 270, "loss": 0.0181, "lr": 3.079120182682412e-05, "epoch": 6.672897196261682, "percentage": 66.67, "elapsed_time": "0:09:25", "remaining_time": "0:04:42"}
{"current_steps": 185, "total_steps": 270, "loss": 0.0196, "lr": 2.7849338030983257e-05, "epoch": 6.859813084112149, "percentage": 68.52, "elapsed_time": "0:09:41", "remaining_time": "0:04:27"}
{"current_steps": 190, "total_steps": 270, "loss": 0.0158, "lr": 2.500000000000001e-05, "epoch": 7.037383177570093, "percentage": 70.37, "elapsed_time": "0:09:56", "remaining_time": "0:04:11"}
{"current_steps": 195, "total_steps": 270, "loss": 0.0138, "lr": 2.225508973396016e-05, "epoch": 7.224299065420561, "percentage": 72.22, "elapsed_time": "0:10:11", "remaining_time": "0:03:55"}
{"current_steps": 200, "total_steps": 270, "loss": 0.012, "lr": 1.9626073026625818e-05, "epoch": 7.411214953271028, "percentage": 74.07, "elapsed_time": "0:10:27", "remaining_time": "0:03:39"}
{"current_steps": 200, "total_steps": 270, "eval_loss": 0.17594270408153534, "epoch": 7.411214953271028, "percentage": 74.07, "elapsed_time": "0:10:34", "remaining_time": "0:03:42"}
{"current_steps": 205, "total_steps": 270, "loss": 0.0116, "lr": 1.7123931571546827e-05, "epoch": 7.598130841121495, "percentage": 75.93, "elapsed_time": "0:10:55", "remaining_time": "0:03:27"}
{"current_steps": 210, "total_steps": 270, "loss": 0.0122, "lr": 1.4759117090312197e-05, "epoch": 7.785046728971962, "percentage": 77.78, "elapsed_time": "0:11:11", "remaining_time": "0:03:11"}
{"current_steps": 215, "total_steps": 270, "loss": 0.0128, "lr": 1.25415076745532e-05, "epoch": 7.97196261682243, "percentage": 79.63, "elapsed_time": "0:11:26", "remaining_time": "0:02:55"}
{"current_steps": 220, "total_steps": 270, "loss": 0.0104, "lr": 1.0480366524062042e-05, "epoch": 8.149532710280374, "percentage": 81.48, "elapsed_time": "0:11:41", "remaining_time": "0:02:39"}
{"current_steps": 225, "total_steps": 270, "loss": 0.0096, "lr": 8.584303253381847e-06, "epoch": 8.336448598130842, "percentage": 83.33, "elapsed_time": "0:11:55", "remaining_time": "0:02:23"}
{"current_steps": 230, "total_steps": 270, "loss": 0.0087, "lr": 6.861237928494579e-06, "epoch": 8.523364485981308, "percentage": 85.19, "elapsed_time": "0:12:11", "remaining_time": "0:02:07"}
{"current_steps": 235, "total_steps": 270, "loss": 0.0091, "lr": 5.318367983829392e-06, "epoch": 8.710280373831775, "percentage": 87.04, "elapsed_time": "0:12:27", "remaining_time": "0:01:51"}
{"current_steps": 240, "total_steps": 270, "loss": 0.0093, "lr": 3.962138157783085e-06, "epoch": 8.897196261682243, "percentage": 88.89, "elapsed_time": "0:12:42", "remaining_time": "0:01:35"}
{"current_steps": 245, "total_steps": 270, "loss": 0.0082, "lr": 2.798213572335001e-06, "epoch": 9.074766355140186, "percentage": 90.74, "elapsed_time": "0:12:56", "remaining_time": "0:01:19"}
{"current_steps": 250, "total_steps": 270, "loss": 0.0088, "lr": 1.8314560692059835e-06, "epoch": 9.261682242990654, "percentage": 92.59, "elapsed_time": "0:13:12", "remaining_time": "0:01:03"}
{"current_steps": 255, "total_steps": 270, "loss": 0.0078, "lr": 1.0659039014077944e-06, "epoch": 9.448598130841122, "percentage": 94.44, "elapsed_time": "0:13:27", "remaining_time": "0:00:47"}
{"current_steps": 260, "total_steps": 270, "loss": 0.0093, "lr": 5.047548650136513e-07, "epoch": 9.63551401869159, "percentage": 96.3, "elapsed_time": "0:13:43", "remaining_time": "0:00:31"}
{"current_steps": 265, "total_steps": 270, "loss": 0.0082, "lr": 1.503529416103988e-07, "epoch": 9.822429906542055, "percentage": 98.15, "elapsed_time": "0:13:59", "remaining_time": "0:00:15"}
{"current_steps": 270, "total_steps": 270, "loss": 0.0076, "lr": 4.178507228136397e-09, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:14:13", "remaining_time": "0:00:00"}
{"current_steps": 270, "total_steps": 270, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:14:19", "remaining_time": "0:00:00"}