htlou's picture
Upload folder using huggingface_hub
3e76b49 verified
{"current_steps": 5, "total_steps": 429, "loss": 1.6833, "learning_rate": 5e-07, "epoch": 0.034782608695652174, "percentage": 1.17, "elapsed_time": "0:01:07", "remaining_time": "1:36:00"}
{"current_steps": 10, "total_steps": 429, "loss": 1.5247, "learning_rate": 1e-06, "epoch": 0.06956521739130435, "percentage": 2.33, "elapsed_time": "0:02:11", "remaining_time": "1:31:47"}
{"current_steps": 15, "total_steps": 429, "loss": 1.2991, "learning_rate": 9.99648681635985e-07, "epoch": 0.10434782608695652, "percentage": 3.5, "elapsed_time": "0:03:13", "remaining_time": "1:29:06"}
{"current_steps": 20, "total_steps": 429, "loss": 1.2447, "learning_rate": 9.985952202423114e-07, "epoch": 0.1391304347826087, "percentage": 4.66, "elapsed_time": "0:04:16", "remaining_time": "1:27:24"}
{"current_steps": 25, "total_steps": 429, "loss": 1.1959, "learning_rate": 9.96841096220313e-07, "epoch": 0.17391304347826086, "percentage": 5.83, "elapsed_time": "0:05:19", "remaining_time": "1:25:56"}
{"current_steps": 30, "total_steps": 429, "loss": 1.1638, "learning_rate": 9.943887745939163e-07, "epoch": 0.20869565217391303, "percentage": 6.99, "elapsed_time": "0:06:21", "remaining_time": "1:24:34"}
{"current_steps": 35, "total_steps": 429, "loss": 1.1559, "learning_rate": 9.912417015456088e-07, "epoch": 0.24347826086956523, "percentage": 8.16, "elapsed_time": "0:07:23", "remaining_time": "1:23:17"}
{"current_steps": 40, "total_steps": 429, "loss": 1.1673, "learning_rate": 9.874042995736093e-07, "epoch": 0.2782608695652174, "percentage": 9.32, "elapsed_time": "0:08:26", "remaining_time": "1:22:07"}
{"current_steps": 45, "total_steps": 429, "loss": 1.1403, "learning_rate": 9.828819612770495e-07, "epoch": 0.3130434782608696, "percentage": 10.49, "elapsed_time": "0:09:29", "remaining_time": "1:21:01"}
{"current_steps": 50, "total_steps": 429, "loss": 1.1387, "learning_rate": 9.77681041777897e-07, "epoch": 0.34782608695652173, "percentage": 11.66, "elapsed_time": "0:10:32", "remaining_time": "1:19:56"}
{"current_steps": 50, "total_steps": 429, "eval_loss": 1.1293702125549316, "epoch": 0.34782608695652173, "percentage": 11.66, "elapsed_time": "0:11:44", "remaining_time": "1:29:00"}
{"current_steps": 55, "total_steps": 429, "loss": 1.1378, "learning_rate": 9.718088497902707e-07, "epoch": 0.3826086956521739, "percentage": 12.82, "elapsed_time": "0:12:47", "remaining_time": "1:26:59"}
{"current_steps": 60, "total_steps": 429, "loss": 1.1359, "learning_rate": 9.652736373497e-07, "epoch": 0.41739130434782606, "percentage": 13.99, "elapsed_time": "0:13:50", "remaining_time": "1:25:08"}
{"current_steps": 65, "total_steps": 429, "loss": 1.1054, "learning_rate": 9.580845882167572e-07, "epoch": 0.45217391304347826, "percentage": 15.15, "elapsed_time": "0:14:54", "remaining_time": "1:23:26"}
{"current_steps": 70, "total_steps": 429, "loss": 1.1003, "learning_rate": 9.502518049713631e-07, "epoch": 0.48695652173913045, "percentage": 16.32, "elapsed_time": "0:15:56", "remaining_time": "1:21:45"}
{"current_steps": 75, "total_steps": 429, "loss": 1.1012, "learning_rate": 9.417862948158997e-07, "epoch": 0.5217391304347826, "percentage": 17.48, "elapsed_time": "0:16:58", "remaining_time": "1:20:08"}
{"current_steps": 80, "total_steps": 429, "loss": 1.1004, "learning_rate": 9.326999541070803e-07, "epoch": 0.5565217391304348, "percentage": 18.65, "elapsed_time": "0:18:01", "remaining_time": "1:18:38"}
{"current_steps": 85, "total_steps": 429, "loss": 1.1176, "learning_rate": 9.23005551638316e-07, "epoch": 0.591304347826087, "percentage": 19.81, "elapsed_time": "0:19:03", "remaining_time": "1:17:09"}
{"current_steps": 90, "total_steps": 429, "loss": 1.0953, "learning_rate": 9.127167106960681e-07, "epoch": 0.6260869565217392, "percentage": 20.98, "elapsed_time": "0:20:06", "remaining_time": "1:15:43"}
{"current_steps": 95, "total_steps": 429, "loss": 1.0863, "learning_rate": 9.018478899154066e-07, "epoch": 0.6608695652173913, "percentage": 22.14, "elapsed_time": "0:21:09", "remaining_time": "1:14:21"}
{"current_steps": 100, "total_steps": 429, "loss": 1.0986, "learning_rate": 8.904143629616732e-07, "epoch": 0.6956521739130435, "percentage": 23.31, "elapsed_time": "0:22:11", "remaining_time": "1:13:01"}
{"current_steps": 100, "total_steps": 429, "eval_loss": 1.0837830305099487, "epoch": 0.6956521739130435, "percentage": 23.31, "elapsed_time": "0:23:22", "remaining_time": "1:16:53"}
{"current_steps": 105, "total_steps": 429, "loss": 1.0741, "learning_rate": 8.784321970668053e-07, "epoch": 0.7304347826086957, "percentage": 24.48, "elapsed_time": "0:25:56", "remaining_time": "1:20:02"}
{"current_steps": 110, "total_steps": 429, "loss": 1.0891, "learning_rate": 8.659182304504808e-07, "epoch": 0.7652173913043478, "percentage": 25.64, "elapsed_time": "0:26:58", "remaining_time": "1:18:14"}
{"current_steps": 115, "total_steps": 429, "loss": 1.0738, "learning_rate": 8.528900486578158e-07, "epoch": 0.8, "percentage": 26.81, "elapsed_time": "0:28:01", "remaining_time": "1:16:30"}
{"current_steps": 120, "total_steps": 429, "loss": 1.0691, "learning_rate": 8.393659598468642e-07, "epoch": 0.8347826086956521, "percentage": 27.97, "elapsed_time": "0:29:03", "remaining_time": "1:14:50"}
{"current_steps": 125, "total_steps": 429, "loss": 1.0759, "learning_rate": 8.253649690606494e-07, "epoch": 0.8695652173913043, "percentage": 29.14, "elapsed_time": "0:30:06", "remaining_time": "1:13:13"}
{"current_steps": 130, "total_steps": 429, "loss": 1.0619, "learning_rate": 8.10906751519882e-07, "epoch": 0.9043478260869565, "percentage": 30.3, "elapsed_time": "0:31:08", "remaining_time": "1:11:37"}
{"current_steps": 135, "total_steps": 429, "loss": 1.06, "learning_rate": 7.960116249738937e-07, "epoch": 0.9391304347826087, "percentage": 31.47, "elapsed_time": "0:32:11", "remaining_time": "1:10:05"}
{"current_steps": 140, "total_steps": 429, "loss": 1.0632, "learning_rate": 7.807005211486444e-07, "epoch": 0.9739130434782609, "percentage": 32.63, "elapsed_time": "0:33:13", "remaining_time": "1:08:35"}
{"current_steps": 145, "total_steps": 429, "loss": 1.0377, "learning_rate": 7.649949563319227e-07, "epoch": 1.008695652173913, "percentage": 33.8, "elapsed_time": "0:34:16", "remaining_time": "1:07:08"}
{"current_steps": 150, "total_steps": 429, "loss": 0.9413, "learning_rate": 7.489170011370779e-07, "epoch": 1.0434782608695652, "percentage": 34.97, "elapsed_time": "0:35:18", "remaining_time": "1:05:41"}
{"current_steps": 150, "total_steps": 429, "eval_loss": 1.0630384683609009, "epoch": 1.0434782608695652, "percentage": 34.97, "elapsed_time": "0:36:29", "remaining_time": "1:07:51"}
{"current_steps": 155, "total_steps": 429, "loss": 0.9337, "learning_rate": 7.324892494877733e-07, "epoch": 1.0782608695652174, "percentage": 36.13, "elapsed_time": "0:37:31", "remaining_time": "1:06:19"}
{"current_steps": 160, "total_steps": 429, "loss": 0.9139, "learning_rate": 7.15734786867344e-07, "epoch": 1.1130434782608696, "percentage": 37.3, "elapsed_time": "0:38:33", "remaining_time": "1:04:50"}
{"current_steps": 165, "total_steps": 429, "loss": 0.9151, "learning_rate": 6.986771578773811e-07, "epoch": 1.1478260869565218, "percentage": 38.46, "elapsed_time": "0:39:36", "remaining_time": "1:03:21"}
{"current_steps": 170, "total_steps": 429, "loss": 0.9238, "learning_rate": 6.81340333151128e-07, "epoch": 1.182608695652174, "percentage": 39.63, "elapsed_time": "0:40:38", "remaining_time": "1:01:54"}
{"current_steps": 175, "total_steps": 429, "loss": 0.9168, "learning_rate": 6.637486756681842e-07, "epoch": 1.2173913043478262, "percentage": 40.79, "elapsed_time": "0:41:40", "remaining_time": "1:00:29"}
{"current_steps": 180, "total_steps": 429, "loss": 0.9171, "learning_rate": 6.459269065178591e-07, "epoch": 1.2521739130434781, "percentage": 41.96, "elapsed_time": "0:42:43", "remaining_time": "0:59:05"}
{"current_steps": 185, "total_steps": 429, "loss": 0.9259, "learning_rate": 6.279000701592794e-07, "epoch": 1.2869565217391306, "percentage": 43.12, "elapsed_time": "0:43:45", "remaining_time": "0:57:43"}
{"current_steps": 190, "total_steps": 429, "loss": 0.9273, "learning_rate": 6.096934992270767e-07, "epoch": 1.3217391304347825, "percentage": 44.29, "elapsed_time": "0:44:48", "remaining_time": "0:56:21"}
{"current_steps": 195, "total_steps": 429, "loss": 0.9145, "learning_rate": 5.913327789321077e-07, "epoch": 1.3565217391304347, "percentage": 45.45, "elapsed_time": "0:45:50", "remaining_time": "0:55:00"}
{"current_steps": 200, "total_steps": 429, "loss": 0.9147, "learning_rate": 5.728437111072375e-07, "epoch": 1.391304347826087, "percentage": 46.62, "elapsed_time": "0:46:53", "remaining_time": "0:53:40"}
{"current_steps": 200, "total_steps": 429, "eval_loss": 1.0509551763534546, "epoch": 1.391304347826087, "percentage": 46.62, "elapsed_time": "0:48:03", "remaining_time": "0:55:01"}
{"current_steps": 205, "total_steps": 429, "loss": 0.9193, "learning_rate": 5.542522779487071e-07, "epoch": 1.4260869565217391, "percentage": 47.79, "elapsed_time": "0:50:38", "remaining_time": "0:55:20"}
{"current_steps": 210, "total_steps": 429, "loss": 0.9067, "learning_rate": 5.355846055040448e-07, "epoch": 1.4608695652173913, "percentage": 48.95, "elapsed_time": "0:51:41", "remaining_time": "0:53:54"}
{"current_steps": 215, "total_steps": 429, "loss": 0.9131, "learning_rate": 5.168669269578232e-07, "epoch": 1.4956521739130435, "percentage": 50.12, "elapsed_time": "0:52:44", "remaining_time": "0:52:29"}
{"current_steps": 220, "total_steps": 429, "loss": 0.8942, "learning_rate": 4.981255457668624e-07, "epoch": 1.5304347826086957, "percentage": 51.28, "elapsed_time": "0:53:47", "remaining_time": "0:51:06"}
{"current_steps": 225, "total_steps": 429, "loss": 0.9294, "learning_rate": 4.793867986966802e-07, "epoch": 1.5652173913043477, "percentage": 52.45, "elapsed_time": "0:54:50", "remaining_time": "0:49:43"}
{"current_steps": 230, "total_steps": 429, "loss": 0.9111, "learning_rate": 4.606770188111338e-07, "epoch": 1.6, "percentage": 53.61, "elapsed_time": "0:55:52", "remaining_time": "0:48:20"}
{"current_steps": 235, "total_steps": 429, "loss": 0.9099, "learning_rate": 4.420224984672653e-07, "epoch": 1.634782608695652, "percentage": 54.78, "elapsed_time": "0:56:55", "remaining_time": "0:46:59"}
{"current_steps": 240, "total_steps": 429, "loss": 0.9073, "learning_rate": 4.2344945236734963e-07, "epoch": 1.6695652173913045, "percentage": 55.94, "elapsed_time": "0:57:58", "remaining_time": "0:45:39"}
{"current_steps": 245, "total_steps": 429, "loss": 0.908, "learning_rate": 4.049839807200688e-07, "epoch": 1.7043478260869565, "percentage": 57.11, "elapsed_time": "0:59:00", "remaining_time": "0:44:19"}
{"current_steps": 250, "total_steps": 429, "loss": 0.9097, "learning_rate": 3.866520325625825e-07, "epoch": 1.7391304347826086, "percentage": 58.28, "elapsed_time": "1:00:03", "remaining_time": "0:42:59"}
{"current_steps": 250, "total_steps": 429, "eval_loss": 1.0377378463745117, "epoch": 1.7391304347826086, "percentage": 58.28, "elapsed_time": "1:01:14", "remaining_time": "0:43:50"}
{"current_steps": 255, "total_steps": 429, "loss": 0.8975, "learning_rate": 3.684793692950344e-07, "epoch": 1.7739130434782608, "percentage": 59.44, "elapsed_time": "1:02:16", "remaining_time": "0:42:29"}
{"current_steps": 260, "total_steps": 429, "loss": 0.9214, "learning_rate": 3.504915284787405e-07, "epoch": 1.808695652173913, "percentage": 60.61, "elapsed_time": "1:03:18", "remaining_time": "0:41:09"}
{"current_steps": 265, "total_steps": 429, "loss": 0.9069, "learning_rate": 3.327137879489312e-07, "epoch": 1.8434782608695652, "percentage": 61.77, "elapsed_time": "1:04:21", "remaining_time": "0:39:49"}
{"current_steps": 270, "total_steps": 429, "loss": 0.9095, "learning_rate": 3.1517113029248233e-07, "epoch": 1.8782608695652174, "percentage": 62.94, "elapsed_time": "1:05:24", "remaining_time": "0:38:30"}
{"current_steps": 275, "total_steps": 429, "loss": 0.892, "learning_rate": 2.9788820774054697e-07, "epoch": 1.9130434782608696, "percentage": 64.1, "elapsed_time": "1:06:26", "remaining_time": "0:37:12"}
{"current_steps": 280, "total_steps": 429, "loss": 0.8931, "learning_rate": 2.8088930752543063e-07, "epoch": 1.9478260869565216, "percentage": 65.27, "elapsed_time": "1:07:29", "remaining_time": "0:35:54"}
{"current_steps": 285, "total_steps": 429, "loss": 0.9201, "learning_rate": 2.641983177503876e-07, "epoch": 1.982608695652174, "percentage": 66.43, "elapsed_time": "1:08:31", "remaining_time": "0:34:37"}
{"current_steps": 290, "total_steps": 429, "loss": 0.8534, "learning_rate": 2.4783869382030424e-07, "epoch": 2.017391304347826, "percentage": 67.6, "elapsed_time": "1:09:33", "remaining_time": "0:33:20"}
{"current_steps": 295, "total_steps": 429, "loss": 0.8189, "learning_rate": 2.3183342548044065e-07, "epoch": 2.0521739130434784, "percentage": 68.76, "elapsed_time": "1:10:36", "remaining_time": "0:32:04"}
{"current_steps": 300, "total_steps": 429, "loss": 0.8125, "learning_rate": 2.1620500450955221e-07, "epoch": 2.0869565217391304, "percentage": 69.93, "elapsed_time": "1:11:39", "remaining_time": "0:30:48"}
{"current_steps": 300, "total_steps": 429, "eval_loss": 1.0442272424697876, "epoch": 2.0869565217391304, "percentage": 69.93, "elapsed_time": "1:12:50", "remaining_time": "0:31:19"}
{"current_steps": 305, "total_steps": 429, "loss": 0.8161, "learning_rate": 2.0097539311278898e-07, "epoch": 2.121739130434783, "percentage": 71.1, "elapsed_time": "1:15:26", "remaining_time": "0:30:40"}
{"current_steps": 310, "total_steps": 429, "loss": 0.8136, "learning_rate": 1.8616599305879333e-07, "epoch": 2.1565217391304348, "percentage": 72.26, "elapsed_time": "1:16:29", "remaining_time": "0:29:21"}
{"current_steps": 315, "total_steps": 429, "loss": 0.8154, "learning_rate": 1.7179761560436097e-07, "epoch": 2.1913043478260867, "percentage": 73.43, "elapsed_time": "1:17:32", "remaining_time": "0:28:03"}
{"current_steps": 320, "total_steps": 429, "loss": 0.8086, "learning_rate": 1.5789045224893538e-07, "epoch": 2.226086956521739, "percentage": 74.59, "elapsed_time": "1:18:34", "remaining_time": "0:26:45"}
{"current_steps": 325, "total_steps": 429, "loss": 0.8099, "learning_rate": 1.444640463600293e-07, "epoch": 2.260869565217391, "percentage": 75.76, "elapsed_time": "1:19:37", "remaining_time": "0:25:28"}
{"current_steps": 330, "total_steps": 429, "loss": 0.7974, "learning_rate": 1.3153726570944828e-07, "epoch": 2.2956521739130435, "percentage": 76.92, "elapsed_time": "1:20:40", "remaining_time": "0:24:12"}
{"current_steps": 335, "total_steps": 429, "loss": 0.8068, "learning_rate": 1.1912827595891312e-07, "epoch": 2.3304347826086955, "percentage": 78.09, "elapsed_time": "1:21:42", "remaining_time": "0:22:55"}
{"current_steps": 340, "total_steps": 429, "loss": 0.8067, "learning_rate": 1.0725451513233674e-07, "epoch": 2.365217391304348, "percentage": 79.25, "elapsed_time": "1:22:45", "remaining_time": "0:21:39"}
{"current_steps": 345, "total_steps": 429, "loss": 0.8124, "learning_rate": 9.593266911063253e-08, "epoch": 2.4, "percentage": 80.42, "elapsed_time": "1:23:48", "remaining_time": "0:20:24"}
{"current_steps": 350, "total_steps": 429, "loss": 0.8092, "learning_rate": 8.517864818348803e-08, "epoch": 2.4347826086956523, "percentage": 81.59, "elapsed_time": "1:24:50", "remaining_time": "0:19:08"}
{"current_steps": 350, "total_steps": 429, "eval_loss": 1.0428001880645752, "epoch": 2.4347826086956523, "percentage": 81.59, "elapsed_time": "1:26:01", "remaining_time": "0:19:24"}
{"current_steps": 355, "total_steps": 429, "loss": 0.8206, "learning_rate": 7.500756469105818e-08, "epoch": 2.4695652173913043, "percentage": 82.75, "elapsed_time": "1:27:03", "remaining_time": "0:18:08"}
{"current_steps": 360, "total_steps": 429, "loss": 0.8063, "learning_rate": 6.543371178699442e-08, "epoch": 2.5043478260869563, "percentage": 83.92, "elapsed_time": "1:28:05", "remaining_time": "0:16:53"}
{"current_steps": 365, "total_steps": 429, "loss": 0.812, "learning_rate": 5.647054335265489e-08, "epoch": 2.5391304347826087, "percentage": 85.08, "elapsed_time": "1:29:07", "remaining_time": "0:15:37"}
{"current_steps": 370, "total_steps": 429, "loss": 0.8124, "learning_rate": 4.813065509072278e-08, "epoch": 2.573913043478261, "percentage": 86.25, "elapsed_time": "1:30:10", "remaining_time": "0:14:22"}
{"current_steps": 375, "total_steps": 429, "loss": 0.8066, "learning_rate": 4.0425766824798814e-08, "epoch": 2.608695652173913, "percentage": 87.41, "elapsed_time": "1:31:12", "remaining_time": "0:13:08"}
{"current_steps": 380, "total_steps": 429, "loss": 0.8046, "learning_rate": 3.3366706029845096e-08, "epoch": 2.643478260869565, "percentage": 88.58, "elapsed_time": "1:32:15", "remaining_time": "0:11:53"}
{"current_steps": 385, "total_steps": 429, "loss": 0.8165, "learning_rate": 2.696339261662156e-08, "epoch": 2.6782608695652175, "percentage": 89.74, "elapsed_time": "1:33:18", "remaining_time": "0:10:39"}
{"current_steps": 390, "total_steps": 429, "loss": 0.8057, "learning_rate": 2.122482499149869e-08, "epoch": 2.7130434782608694, "percentage": 90.91, "elapsed_time": "1:34:20", "remaining_time": "0:09:26"}
{"current_steps": 395, "total_steps": 429, "loss": 0.7964, "learning_rate": 1.6159067411235737e-08, "epoch": 2.747826086956522, "percentage": 92.07, "elapsed_time": "1:35:22", "remaining_time": "0:08:12"}
{"current_steps": 400, "total_steps": 429, "loss": 0.8049, "learning_rate": 1.177323865049512e-08, "epoch": 2.782608695652174, "percentage": 93.24, "elapsed_time": "1:36:25", "remaining_time": "0:06:59"}
{"current_steps": 400, "total_steps": 429, "eval_loss": 1.0423126220703125, "epoch": 2.782608695652174, "percentage": 93.24, "elapsed_time": "1:37:36", "remaining_time": "0:07:04"}
{"current_steps": 405, "total_steps": 429, "loss": 0.8146, "learning_rate": 8.073501998017152e-09, "epoch": 2.8173913043478263, "percentage": 94.41, "elapsed_time": "1:42:47", "remaining_time": "0:06:05"}
{"current_steps": 410, "total_steps": 429, "loss": 0.7988, "learning_rate": 5.065056595513984e-09, "epoch": 2.8521739130434782, "percentage": 95.57, "elapsed_time": "1:43:50", "remaining_time": "0:04:48"}
{"current_steps": 415, "total_steps": 429, "loss": 0.7937, "learning_rate": 2.752130131453756e-09, "epoch": 2.8869565217391306, "percentage": 96.74, "elapsed_time": "1:44:53", "remaining_time": "0:03:32"}
{"current_steps": 420, "total_steps": 429, "loss": 0.813, "learning_rate": 1.137972900002171e-09, "epoch": 2.9217391304347826, "percentage": 97.9, "elapsed_time": "1:45:55", "remaining_time": "0:02:16"}
{"current_steps": 425, "total_steps": 429, "loss": 0.7961, "learning_rate": 2.2485323347054552e-10, "epoch": 2.9565217391304346, "percentage": 99.07, "elapsed_time": "1:46:58", "remaining_time": "0:01:00"}
{"current_steps": 429, "total_steps": 429, "epoch": 2.9843478260869567, "percentage": 100.0, "elapsed_time": "1:50:11", "remaining_time": "0:00:00"}