Training in progress, epoch 2
Browse files
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:979a6245b647dee7f4d8da3725b2f82d23b033c9170e33ad7f0ac44b976775d9
|
3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ac9a48bc8259ce0b78f1df2b871c041f18ecc6ab7d170cba4b0f7b0904710d6
|
3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1926986e288d074eb64a38212d0ab4c2c0974f282a4ce9d80ef400ad107d466e
|
3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:867839a7d3a4a2a7895b055085085b8123b7386f61236fbc6673f3fcb7e6f297
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -245,3 +245,244 @@
|
|
245 |
{"current_steps": 245, "total_steps": 1200, "loss": 0.5424, "lr": 3.8692378506979775e-05, "epoch": 1.0208333333333333, "percentage": 20.42, "elapsed_time": "1:36:23", "remaining_time": "6:15:45"}
|
246 |
{"current_steps": 246, "total_steps": 1200, "loss": 0.5459, "lr": 3.8671608529944035e-05, "epoch": 1.025, "percentage": 20.5, "elapsed_time": "1:36:47", "remaining_time": "6:15:20"}
|
247 |
{"current_steps": 247, "total_steps": 1200, "loss": 0.5367, "lr": 3.8650680561430444e-05, "epoch": 1.0291666666666666, "percentage": 20.58, "elapsed_time": "1:37:11", "remaining_time": "6:14:58"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
245 |
{"current_steps": 245, "total_steps": 1200, "loss": 0.5424, "lr": 3.8692378506979775e-05, "epoch": 1.0208333333333333, "percentage": 20.42, "elapsed_time": "1:36:23", "remaining_time": "6:15:45"}
|
246 |
{"current_steps": 246, "total_steps": 1200, "loss": 0.5459, "lr": 3.8671608529944035e-05, "epoch": 1.025, "percentage": 20.5, "elapsed_time": "1:36:47", "remaining_time": "6:15:20"}
|
247 |
{"current_steps": 247, "total_steps": 1200, "loss": 0.5367, "lr": 3.8650680561430444e-05, "epoch": 1.0291666666666666, "percentage": 20.58, "elapsed_time": "1:37:11", "remaining_time": "6:14:58"}
|
248 |
+
{"current_steps": 248, "total_steps": 1200, "loss": 0.5559, "lr": 3.862959477852285e-05, "epoch": 1.0333333333333334, "percentage": 20.67, "elapsed_time": "1:37:33", "remaining_time": "6:14:31"}
|
249 |
+
{"current_steps": 249, "total_steps": 1200, "loss": 0.5328, "lr": 3.860835135964049e-05, "epoch": 1.0375, "percentage": 20.75, "elapsed_time": "1:37:56", "remaining_time": "6:14:04"}
|
250 |
+
{"current_steps": 250, "total_steps": 1200, "loss": 0.5365, "lr": 3.858695048453645e-05, "epoch": 1.0416666666666667, "percentage": 20.83, "elapsed_time": "1:38:20", "remaining_time": "6:13:40"}
|
251 |
+
{"current_steps": 251, "total_steps": 1200, "loss": 0.5463, "lr": 3.8565392334296135e-05, "epoch": 1.0458333333333334, "percentage": 20.92, "elapsed_time": "1:38:41", "remaining_time": "6:13:09"}
|
252 |
+
{"current_steps": 252, "total_steps": 1200, "loss": 0.5442, "lr": 3.854367709133575e-05, "epoch": 1.05, "percentage": 21.0, "elapsed_time": "1:39:05", "remaining_time": "6:12:46"}
|
253 |
+
{"current_steps": 253, "total_steps": 1200, "loss": 0.5323, "lr": 3.852180493940076e-05, "epoch": 1.0541666666666667, "percentage": 21.08, "elapsed_time": "1:39:28", "remaining_time": "6:12:20"}
|
254 |
+
{"current_steps": 254, "total_steps": 1200, "loss": 0.5545, "lr": 3.849977606356432e-05, "epoch": 1.0583333333333333, "percentage": 21.17, "elapsed_time": "1:39:52", "remaining_time": "6:11:58"}
|
255 |
+
{"current_steps": 255, "total_steps": 1200, "loss": 0.5475, "lr": 3.8477590650225735e-05, "epoch": 1.0625, "percentage": 21.25, "elapsed_time": "1:40:15", "remaining_time": "6:11:32"}
|
256 |
+
{"current_steps": 256, "total_steps": 1200, "loss": 0.5305, "lr": 3.845524888710885e-05, "epoch": 1.0666666666666667, "percentage": 21.33, "elapsed_time": "1:40:38", "remaining_time": "6:11:06"}
|
257 |
+
{"current_steps": 257, "total_steps": 1200, "loss": 0.5573, "lr": 3.843275096326048e-05, "epoch": 1.0708333333333333, "percentage": 21.42, "elapsed_time": "1:41:02", "remaining_time": "6:10:43"}
|
258 |
+
{"current_steps": 258, "total_steps": 1200, "loss": 0.5487, "lr": 3.841009706904881e-05, "epoch": 1.075, "percentage": 21.5, "elapsed_time": "1:41:25", "remaining_time": "6:10:20"}
|
259 |
+
{"current_steps": 259, "total_steps": 1200, "loss": 0.5353, "lr": 3.8387287396161784e-05, "epoch": 1.0791666666666666, "percentage": 21.58, "elapsed_time": "1:41:48", "remaining_time": "6:09:52"}
|
260 |
+
{"current_steps": 260, "total_steps": 1200, "loss": 0.5397, "lr": 3.8364322137605484e-05, "epoch": 1.0833333333333333, "percentage": 21.67, "elapsed_time": "1:42:08", "remaining_time": "6:09:16"}
|
261 |
+
{"current_steps": 261, "total_steps": 1200, "loss": 0.532, "lr": 3.834120148770248e-05, "epoch": 1.0875, "percentage": 21.75, "elapsed_time": "1:42:31", "remaining_time": "6:08:50"}
|
262 |
+
{"current_steps": 262, "total_steps": 1200, "loss": 0.5473, "lr": 3.8317925642090225e-05, "epoch": 1.0916666666666666, "percentage": 21.83, "elapsed_time": "1:42:54", "remaining_time": "6:08:24"}
|
263 |
+
{"current_steps": 263, "total_steps": 1200, "loss": 0.5567, "lr": 3.829449479771935e-05, "epoch": 1.0958333333333334, "percentage": 21.92, "elapsed_time": "1:43:17", "remaining_time": "6:08:00"}
|
264 |
+
{"current_steps": 264, "total_steps": 1200, "loss": 0.5544, "lr": 3.827090915285202e-05, "epoch": 1.1, "percentage": 22.0, "elapsed_time": "1:43:41", "remaining_time": "6:07:38"}
|
265 |
+
{"current_steps": 265, "total_steps": 1200, "loss": 0.5444, "lr": 3.824716890706029e-05, "epoch": 1.1041666666666667, "percentage": 22.08, "elapsed_time": "1:44:05", "remaining_time": "6:07:14"}
|
266 |
+
{"current_steps": 266, "total_steps": 1200, "loss": 0.5453, "lr": 3.8223274261224344e-05, "epoch": 1.1083333333333334, "percentage": 22.17, "elapsed_time": "1:44:28", "remaining_time": "6:06:51"}
|
267 |
+
{"current_steps": 267, "total_steps": 1200, "loss": 0.5414, "lr": 3.8199225417530865e-05, "epoch": 1.1125, "percentage": 22.25, "elapsed_time": "1:44:51", "remaining_time": "6:06:26"}
|
268 |
+
{"current_steps": 268, "total_steps": 1200, "loss": 0.556, "lr": 3.817502257947129e-05, "epoch": 1.1166666666666667, "percentage": 22.33, "elapsed_time": "1:45:14", "remaining_time": "6:06:00"}
|
269 |
+
{"current_steps": 269, "total_steps": 1200, "loss": 0.5428, "lr": 3.815066595184007e-05, "epoch": 1.1208333333333333, "percentage": 22.42, "elapsed_time": "1:45:38", "remaining_time": "6:05:36"}
|
270 |
+
{"current_steps": 270, "total_steps": 1200, "loss": 0.5432, "lr": 3.812615574073301e-05, "epoch": 1.125, "percentage": 22.5, "elapsed_time": "1:46:02", "remaining_time": "6:05:13"}
|
271 |
+
{"current_steps": 271, "total_steps": 1200, "loss": 0.5349, "lr": 3.81014921535454e-05, "epoch": 1.1291666666666667, "percentage": 22.58, "elapsed_time": "1:46:25", "remaining_time": "6:04:49"}
|
272 |
+
{"current_steps": 272, "total_steps": 1200, "loss": 0.5453, "lr": 3.807667539897041e-05, "epoch": 1.1333333333333333, "percentage": 22.67, "elapsed_time": "1:46:49", "remaining_time": "6:04:26"}
|
273 |
+
{"current_steps": 273, "total_steps": 1200, "loss": 0.5395, "lr": 3.805170568699722e-05, "epoch": 1.1375, "percentage": 22.75, "elapsed_time": "1:47:13", "remaining_time": "6:04:04"}
|
274 |
+
{"current_steps": 274, "total_steps": 1200, "loss": 0.5534, "lr": 3.8026583228909244e-05, "epoch": 1.1416666666666666, "percentage": 22.83, "elapsed_time": "1:47:36", "remaining_time": "6:03:41"}
|
275 |
+
{"current_steps": 275, "total_steps": 1200, "loss": 0.55, "lr": 3.800130823728242e-05, "epoch": 1.1458333333333333, "percentage": 22.92, "elapsed_time": "1:48:00", "remaining_time": "6:03:18"}
|
276 |
+
{"current_steps": 276, "total_steps": 1200, "loss": 0.5348, "lr": 3.7975880925983345e-05, "epoch": 1.15, "percentage": 23.0, "elapsed_time": "1:48:24", "remaining_time": "6:02:55"}
|
277 |
+
{"current_steps": 277, "total_steps": 1200, "loss": 0.5193, "lr": 3.795030151016746e-05, "epoch": 1.1541666666666668, "percentage": 23.08, "elapsed_time": "1:48:47", "remaining_time": "6:02:31"}
|
278 |
+
{"current_steps": 278, "total_steps": 1200, "loss": 0.54, "lr": 3.7924570206277274e-05, "epoch": 1.1583333333333332, "percentage": 23.17, "elapsed_time": "1:49:11", "remaining_time": "6:02:06"}
|
279 |
+
{"current_steps": 279, "total_steps": 1200, "loss": 0.5562, "lr": 3.78986872320405e-05, "epoch": 1.1625, "percentage": 23.25, "elapsed_time": "1:49:34", "remaining_time": "6:01:42"}
|
280 |
+
{"current_steps": 280, "total_steps": 1200, "loss": 0.5475, "lr": 3.787265280646825e-05, "epoch": 1.1666666666666667, "percentage": 23.33, "elapsed_time": "1:49:57", "remaining_time": "6:01:17"}
|
281 |
+
{"current_steps": 281, "total_steps": 1200, "loss": 0.5446, "lr": 3.784646714985311e-05, "epoch": 1.1708333333333334, "percentage": 23.42, "elapsed_time": "1:50:20", "remaining_time": "6:00:51"}
|
282 |
+
{"current_steps": 282, "total_steps": 1200, "loss": 0.5423, "lr": 3.782013048376736e-05, "epoch": 1.175, "percentage": 23.5, "elapsed_time": "1:50:43", "remaining_time": "6:00:28"}
|
283 |
+
{"current_steps": 283, "total_steps": 1200, "loss": 0.5551, "lr": 3.779364303106104e-05, "epoch": 1.1791666666666667, "percentage": 23.58, "elapsed_time": "1:51:07", "remaining_time": "6:00:05"}
|
284 |
+
{"current_steps": 284, "total_steps": 1200, "loss": 0.5371, "lr": 3.776700501586009e-05, "epoch": 1.1833333333333333, "percentage": 23.67, "elapsed_time": "1:51:31", "remaining_time": "5:59:43"}
|
285 |
+
{"current_steps": 285, "total_steps": 1200, "loss": 0.5441, "lr": 3.774021666356444e-05, "epoch": 1.1875, "percentage": 23.75, "elapsed_time": "1:51:55", "remaining_time": "5:59:20"}
|
286 |
+
{"current_steps": 286, "total_steps": 1200, "loss": 0.553, "lr": 3.7713278200846125e-05, "epoch": 1.1916666666666667, "percentage": 23.83, "elapsed_time": "1:52:18", "remaining_time": "5:58:55"}
|
287 |
+
{"current_steps": 287, "total_steps": 1200, "loss": 0.5364, "lr": 3.768618985564734e-05, "epoch": 1.1958333333333333, "percentage": 23.92, "elapsed_time": "1:52:41", "remaining_time": "5:58:30"}
|
288 |
+
{"current_steps": 288, "total_steps": 1200, "loss": 0.5381, "lr": 3.7658951857178544e-05, "epoch": 1.2, "percentage": 24.0, "elapsed_time": "1:53:04", "remaining_time": "5:58:05"}
|
289 |
+
{"current_steps": 289, "total_steps": 1200, "loss": 0.5526, "lr": 3.763156443591647e-05, "epoch": 1.2041666666666666, "percentage": 24.08, "elapsed_time": "1:53:28", "remaining_time": "5:57:41"}
|
290 |
+
{"current_steps": 290, "total_steps": 1200, "loss": 0.5402, "lr": 3.760402782360222e-05, "epoch": 1.2083333333333333, "percentage": 24.17, "elapsed_time": "1:53:51", "remaining_time": "5:57:15"}
|
291 |
+
{"current_steps": 291, "total_steps": 1200, "loss": 0.5447, "lr": 3.757634225323931e-05, "epoch": 1.2125, "percentage": 24.25, "elapsed_time": "1:54:13", "remaining_time": "5:56:48"}
|
292 |
+
{"current_steps": 292, "total_steps": 1200, "loss": 0.5464, "lr": 3.754850795909164e-05, "epoch": 1.2166666666666668, "percentage": 24.33, "elapsed_time": "1:54:37", "remaining_time": "5:56:25"}
|
293 |
+
{"current_steps": 293, "total_steps": 1200, "loss": 0.5443, "lr": 3.7520525176681575e-05, "epoch": 1.2208333333333332, "percentage": 24.42, "elapsed_time": "1:55:00", "remaining_time": "5:56:01"}
|
294 |
+
{"current_steps": 294, "total_steps": 1200, "loss": 0.5391, "lr": 3.749239414278792e-05, "epoch": 1.225, "percentage": 24.5, "elapsed_time": "1:55:23", "remaining_time": "5:55:36"}
|
295 |
+
{"current_steps": 295, "total_steps": 1200, "loss": 0.5498, "lr": 3.7464115095443924e-05, "epoch": 1.2291666666666667, "percentage": 24.58, "elapsed_time": "1:55:47", "remaining_time": "5:55:12"}
|
296 |
+
{"current_steps": 296, "total_steps": 1200, "loss": 0.5438, "lr": 3.743568827393525e-05, "epoch": 1.2333333333333334, "percentage": 24.67, "elapsed_time": "1:56:10", "remaining_time": "5:54:47"}
|
297 |
+
{"current_steps": 297, "total_steps": 1200, "loss": 0.5554, "lr": 3.7407113918797995e-05, "epoch": 1.2375, "percentage": 24.75, "elapsed_time": "1:56:32", "remaining_time": "5:54:21"}
|
298 |
+
{"current_steps": 298, "total_steps": 1200, "loss": 0.5335, "lr": 3.7378392271816606e-05, "epoch": 1.2416666666666667, "percentage": 24.83, "elapsed_time": "1:56:56", "remaining_time": "5:53:58"}
|
299 |
+
{"current_steps": 299, "total_steps": 1200, "loss": 0.5437, "lr": 3.734952357602185e-05, "epoch": 1.2458333333333333, "percentage": 24.92, "elapsed_time": "1:57:20", "remaining_time": "5:53:35"}
|
300 |
+
{"current_steps": 300, "total_steps": 1200, "loss": 0.5462, "lr": 3.732050807568878e-05, "epoch": 1.25, "percentage": 25.0, "elapsed_time": "1:57:44", "remaining_time": "5:53:12"}
|
301 |
+
{"current_steps": 301, "total_steps": 1200, "loss": 0.5418, "lr": 3.7291346016334616e-05, "epoch": 1.2541666666666667, "percentage": 25.08, "elapsed_time": "1:58:07", "remaining_time": "5:52:47"}
|
302 |
+
{"current_steps": 302, "total_steps": 1200, "loss": 0.5476, "lr": 3.726203764471673e-05, "epoch": 1.2583333333333333, "percentage": 25.17, "elapsed_time": "1:58:30", "remaining_time": "5:52:23"}
|
303 |
+
{"current_steps": 303, "total_steps": 1200, "loss": 0.5476, "lr": 3.723258320883052e-05, "epoch": 1.2625, "percentage": 25.25, "elapsed_time": "1:58:53", "remaining_time": "5:51:56"}
|
304 |
+
{"current_steps": 304, "total_steps": 1200, "loss": 0.5369, "lr": 3.720298295790732e-05, "epoch": 1.2666666666666666, "percentage": 25.33, "elapsed_time": "1:59:15", "remaining_time": "5:51:29"}
|
305 |
+
{"current_steps": 305, "total_steps": 1200, "loss": 0.5294, "lr": 3.7173237142412266e-05, "epoch": 1.2708333333333333, "percentage": 25.42, "elapsed_time": "1:59:39", "remaining_time": "5:51:06"}
|
306 |
+
{"current_steps": 306, "total_steps": 1200, "loss": 0.5475, "lr": 3.714334601404225e-05, "epoch": 1.275, "percentage": 25.5, "elapsed_time": "2:00:01", "remaining_time": "5:50:39"}
|
307 |
+
{"current_steps": 307, "total_steps": 1200, "loss": 0.5477, "lr": 3.7113309825723706e-05, "epoch": 1.2791666666666668, "percentage": 25.58, "elapsed_time": "2:00:24", "remaining_time": "5:50:14"}
|
308 |
+
{"current_steps": 308, "total_steps": 1200, "loss": 0.5476, "lr": 3.708312883161052e-05, "epoch": 1.2833333333333332, "percentage": 25.67, "elapsed_time": "2:00:48", "remaining_time": "5:49:51"}
|
309 |
+
{"current_steps": 309, "total_steps": 1200, "loss": 0.5388, "lr": 3.705280328708185e-05, "epoch": 1.2875, "percentage": 25.75, "elapsed_time": "2:01:11", "remaining_time": "5:49:27"}
|
310 |
+
{"current_steps": 310, "total_steps": 1200, "loss": 0.5441, "lr": 3.702233344873999e-05, "epoch": 1.2916666666666667, "percentage": 25.83, "elapsed_time": "2:01:34", "remaining_time": "5:49:02"}
|
311 |
+
{"current_steps": 311, "total_steps": 1200, "loss": 0.5457, "lr": 3.6991719574408216e-05, "epoch": 1.2958333333333334, "percentage": 25.92, "elapsed_time": "2:01:57", "remaining_time": "5:48:37"}
|
312 |
+
{"current_steps": 312, "total_steps": 1200, "loss": 0.5336, "lr": 3.696096192312852e-05, "epoch": 1.3, "percentage": 26.0, "elapsed_time": "2:02:20", "remaining_time": "5:48:12"}
|
313 |
+
{"current_steps": 313, "total_steps": 1200, "loss": 0.5457, "lr": 3.693006075515952e-05, "epoch": 1.3041666666666667, "percentage": 26.08, "elapsed_time": "2:02:43", "remaining_time": "5:47:47"}
|
314 |
+
{"current_steps": 314, "total_steps": 1200, "loss": 0.5425, "lr": 3.689901633197421e-05, "epoch": 1.3083333333333333, "percentage": 26.17, "elapsed_time": "2:03:06", "remaining_time": "5:47:22"}
|
315 |
+
{"current_steps": 315, "total_steps": 1200, "loss": 0.5225, "lr": 3.686782891625772e-05, "epoch": 1.3125, "percentage": 26.25, "elapsed_time": "2:03:30", "remaining_time": "5:46:59"}
|
316 |
+
{"current_steps": 316, "total_steps": 1200, "loss": 0.5501, "lr": 3.683649877190515e-05, "epoch": 1.3166666666666667, "percentage": 26.33, "elapsed_time": "2:03:54", "remaining_time": "5:46:37"}
|
317 |
+
{"current_steps": 317, "total_steps": 1200, "loss": 0.5359, "lr": 3.680502616401932e-05, "epoch": 1.3208333333333333, "percentage": 26.42, "elapsed_time": "2:04:17", "remaining_time": "5:46:12"}
|
318 |
+
{"current_steps": 318, "total_steps": 1200, "loss": 0.5339, "lr": 3.6773411358908486e-05, "epoch": 1.325, "percentage": 26.5, "elapsed_time": "2:04:40", "remaining_time": "5:45:47"}
|
319 |
+
{"current_steps": 319, "total_steps": 1200, "loss": 0.5336, "lr": 3.674165462408415e-05, "epoch": 1.3291666666666666, "percentage": 26.58, "elapsed_time": "2:05:05", "remaining_time": "5:45:27"}
|
320 |
+
{"current_steps": 320, "total_steps": 1200, "loss": 0.5455, "lr": 3.6709756228258735e-05, "epoch": 1.3333333333333333, "percentage": 26.67, "elapsed_time": "2:05:28", "remaining_time": "5:45:02"}
|
321 |
+
{"current_steps": 321, "total_steps": 1200, "loss": 0.5524, "lr": 3.6677716441343366e-05, "epoch": 1.3375, "percentage": 26.75, "elapsed_time": "2:05:52", "remaining_time": "5:44:40"}
|
322 |
+
{"current_steps": 322, "total_steps": 1200, "loss": 0.5413, "lr": 3.664553553444556e-05, "epoch": 1.3416666666666668, "percentage": 26.83, "elapsed_time": "2:06:15", "remaining_time": "5:44:16"}
|
323 |
+
{"current_steps": 323, "total_steps": 1200, "loss": 0.5455, "lr": 3.661321377986691e-05, "epoch": 1.3458333333333332, "percentage": 26.92, "elapsed_time": "2:06:39", "remaining_time": "5:43:54"}
|
324 |
+
{"current_steps": 324, "total_steps": 1200, "loss": 0.5359, "lr": 3.658075145110083e-05, "epoch": 1.35, "percentage": 27.0, "elapsed_time": "2:07:02", "remaining_time": "5:43:29"}
|
325 |
+
{"current_steps": 325, "total_steps": 1200, "loss": 0.5599, "lr": 3.654814882283021e-05, "epoch": 1.3541666666666667, "percentage": 27.08, "elapsed_time": "2:07:25", "remaining_time": "5:43:04"}
|
326 |
+
{"current_steps": 326, "total_steps": 1200, "loss": 0.5451, "lr": 3.6515406170925085e-05, "epoch": 1.3583333333333334, "percentage": 27.17, "elapsed_time": "2:07:51", "remaining_time": "5:42:47"}
|
327 |
+
{"current_steps": 327, "total_steps": 1200, "loss": 0.5511, "lr": 3.648252377244031e-05, "epoch": 1.3625, "percentage": 27.25, "elapsed_time": "2:08:15", "remaining_time": "5:42:25"}
|
328 |
+
{"current_steps": 328, "total_steps": 1200, "loss": 0.5353, "lr": 3.644950190561325e-05, "epoch": 1.3666666666666667, "percentage": 27.33, "elapsed_time": "2:08:38", "remaining_time": "5:41:58"}
|
329 |
+
{"current_steps": 329, "total_steps": 1200, "loss": 0.5363, "lr": 3.641634084986135e-05, "epoch": 1.3708333333333333, "percentage": 27.42, "elapsed_time": "2:09:00", "remaining_time": "5:41:31"}
|
330 |
+
{"current_steps": 330, "total_steps": 1200, "loss": 0.5337, "lr": 3.638304088577984e-05, "epoch": 1.375, "percentage": 27.5, "elapsed_time": "2:09:22", "remaining_time": "5:41:05"}
|
331 |
+
{"current_steps": 331, "total_steps": 1200, "loss": 0.5349, "lr": 3.6349602295139334e-05, "epoch": 1.3791666666666667, "percentage": 27.58, "elapsed_time": "2:09:46", "remaining_time": "5:40:43"}
|
332 |
+
{"current_steps": 332, "total_steps": 1200, "loss": 0.5493, "lr": 3.631602536088345e-05, "epoch": 1.3833333333333333, "percentage": 27.67, "elapsed_time": "2:10:11", "remaining_time": "5:40:22"}
|
333 |
+
{"current_steps": 333, "total_steps": 1200, "loss": 0.551, "lr": 3.628231036712639e-05, "epoch": 1.3875, "percentage": 27.75, "elapsed_time": "2:10:35", "remaining_time": "5:40:01"}
|
334 |
+
{"current_steps": 334, "total_steps": 1200, "loss": 0.5506, "lr": 3.624845759915059e-05, "epoch": 1.3916666666666666, "percentage": 27.83, "elapsed_time": "2:10:58", "remaining_time": "5:39:34"}
|
335 |
+
{"current_steps": 335, "total_steps": 1200, "loss": 0.5492, "lr": 3.6214467343404247e-05, "epoch": 1.3958333333333333, "percentage": 27.92, "elapsed_time": "2:11:20", "remaining_time": "5:39:07"}
|
336 |
+
{"current_steps": 336, "total_steps": 1200, "loss": 0.5508, "lr": 3.6180339887498953e-05, "epoch": 1.4, "percentage": 28.0, "elapsed_time": "2:11:43", "remaining_time": "5:38:42"}
|
337 |
+
{"current_steps": 337, "total_steps": 1200, "loss": 0.5435, "lr": 3.61460755202072e-05, "epoch": 1.4041666666666668, "percentage": 28.08, "elapsed_time": "2:12:07", "remaining_time": "5:38:20"}
|
338 |
+
{"current_steps": 338, "total_steps": 1200, "loss": 0.5515, "lr": 3.611167453145999e-05, "epoch": 1.4083333333333332, "percentage": 28.17, "elapsed_time": "2:12:30", "remaining_time": "5:37:56"}
|
339 |
+
{"current_steps": 339, "total_steps": 1200, "loss": 0.5534, "lr": 3.6077137212344345e-05, "epoch": 1.4125, "percentage": 28.25, "elapsed_time": "2:12:54", "remaining_time": "5:37:33"}
|
340 |
+
{"current_steps": 340, "total_steps": 1200, "loss": 0.5454, "lr": 3.604246385510088e-05, "epoch": 1.4166666666666667, "percentage": 28.33, "elapsed_time": "2:13:16", "remaining_time": "5:37:07"}
|
341 |
+
{"current_steps": 341, "total_steps": 1200, "loss": 0.526, "lr": 3.600765475312128e-05, "epoch": 1.4208333333333334, "percentage": 28.42, "elapsed_time": "2:13:39", "remaining_time": "5:36:42"}
|
342 |
+
{"current_steps": 342, "total_steps": 1200, "loss": 0.5324, "lr": 3.597271020094586e-05, "epoch": 1.425, "percentage": 28.5, "elapsed_time": "2:14:03", "remaining_time": "5:36:19"}
|
343 |
+
{"current_steps": 343, "total_steps": 1200, "loss": 0.5575, "lr": 3.593763049426107e-05, "epoch": 1.4291666666666667, "percentage": 28.58, "elapsed_time": "2:14:27", "remaining_time": "5:35:56"}
|
344 |
+
{"current_steps": 344, "total_steps": 1200, "loss": 0.5503, "lr": 3.590241592989696e-05, "epoch": 1.4333333333333333, "percentage": 28.67, "elapsed_time": "2:14:50", "remaining_time": "5:35:31"}
|
345 |
+
{"current_steps": 345, "total_steps": 1200, "loss": 0.5445, "lr": 3.586706680582471e-05, "epoch": 1.4375, "percentage": 28.75, "elapsed_time": "2:15:12", "remaining_time": "5:35:05"}
|
346 |
+
{"current_steps": 346, "total_steps": 1200, "loss": 0.5406, "lr": 3.583158342115407e-05, "epoch": 1.4416666666666667, "percentage": 28.83, "elapsed_time": "2:15:35", "remaining_time": "5:34:39"}
|
347 |
+
{"current_steps": 347, "total_steps": 1200, "loss": 0.5465, "lr": 3.579596607613087e-05, "epoch": 1.4458333333333333, "percentage": 28.92, "elapsed_time": "2:15:58", "remaining_time": "5:34:15"}
|
348 |
+
{"current_steps": 348, "total_steps": 1200, "loss": 0.553, "lr": 3.576021507213444e-05, "epoch": 1.45, "percentage": 29.0, "elapsed_time": "2:16:21", "remaining_time": "5:33:51"}
|
349 |
+
{"current_steps": 349, "total_steps": 1200, "loss": 0.5349, "lr": 3.5724330711675085e-05, "epoch": 1.4541666666666666, "percentage": 29.08, "elapsed_time": "2:16:45", "remaining_time": "5:33:27"}
|
350 |
+
{"current_steps": 350, "total_steps": 1200, "loss": 0.558, "lr": 3.568831329839152e-05, "epoch": 1.4583333333333333, "percentage": 29.17, "elapsed_time": "2:17:09", "remaining_time": "5:33:04"}
|
351 |
+
{"current_steps": 351, "total_steps": 1200, "loss": 0.5214, "lr": 3.565216313704828e-05, "epoch": 1.4625, "percentage": 29.25, "elapsed_time": "2:17:32", "remaining_time": "5:32:41"}
|
352 |
+
{"current_steps": 352, "total_steps": 1200, "loss": 0.5326, "lr": 3.561588053353319e-05, "epoch": 1.4666666666666668, "percentage": 29.33, "elapsed_time": "2:17:56", "remaining_time": "5:32:18"}
|
353 |
+
{"current_steps": 353, "total_steps": 1200, "loss": 0.5274, "lr": 3.557946579485472e-05, "epoch": 1.4708333333333332, "percentage": 29.42, "elapsed_time": "2:18:18", "remaining_time": "5:31:50"}
|
354 |
+
{"current_steps": 354, "total_steps": 1200, "loss": 0.6153, "lr": 3.554291922913942e-05, "epoch": 1.475, "percentage": 29.5, "elapsed_time": "2:18:41", "remaining_time": "5:31:27"}
|
355 |
+
{"current_steps": 355, "total_steps": 1200, "loss": 0.5439, "lr": 3.550624114562932e-05, "epoch": 1.4791666666666667, "percentage": 29.58, "elapsed_time": "2:19:05", "remaining_time": "5:31:05"}
|
356 |
+
{"current_steps": 356, "total_steps": 1200, "loss": 0.557, "lr": 3.5469431854679284e-05, "epoch": 1.4833333333333334, "percentage": 29.67, "elapsed_time": "2:19:28", "remaining_time": "5:30:40"}
|
357 |
+
{"current_steps": 357, "total_steps": 1200, "loss": 0.5478, "lr": 3.5432491667754404e-05, "epoch": 1.4875, "percentage": 29.75, "elapsed_time": "2:19:53", "remaining_time": "5:30:19"}
|
358 |
+
{"current_steps": 358, "total_steps": 1200, "loss": 0.542, "lr": 3.539542089742736e-05, "epoch": 1.4916666666666667, "percentage": 29.83, "elapsed_time": "2:20:16", "remaining_time": "5:29:56"}
|
359 |
+
{"current_steps": 359, "total_steps": 1200, "loss": 0.5527, "lr": 3.535821985737578e-05, "epoch": 1.4958333333333333, "percentage": 29.92, "elapsed_time": "2:20:40", "remaining_time": "5:29:32"}
|
360 |
+
{"current_steps": 360, "total_steps": 1200, "loss": 0.5531, "lr": 3.532088886237956e-05, "epoch": 1.5, "percentage": 30.0, "elapsed_time": "2:21:03", "remaining_time": "5:29:08"}
|
361 |
+
{"current_steps": 361, "total_steps": 1200, "loss": 0.5491, "lr": 3.5283428228318265e-05, "epoch": 1.5041666666666667, "percentage": 30.08, "elapsed_time": "2:21:26", "remaining_time": "5:28:44"}
|
362 |
+
{"current_steps": 362, "total_steps": 1200, "loss": 0.5466, "lr": 3.524583827216837e-05, "epoch": 1.5083333333333333, "percentage": 30.17, "elapsed_time": "2:21:50", "remaining_time": "5:28:20"}
|
363 |
+
{"current_steps": 363, "total_steps": 1200, "loss": 0.5438, "lr": 3.520811931200063e-05, "epoch": 1.5125, "percentage": 30.25, "elapsed_time": "2:22:14", "remaining_time": "5:27:57"}
|
364 |
+
{"current_steps": 364, "total_steps": 1200, "loss": 0.5433, "lr": 3.5170271666977383e-05, "epoch": 1.5166666666666666, "percentage": 30.33, "elapsed_time": "2:22:37", "remaining_time": "5:27:32"}
|
365 |
+
{"current_steps": 365, "total_steps": 1200, "loss": 0.5398, "lr": 3.513229565734986e-05, "epoch": 1.5208333333333335, "percentage": 30.42, "elapsed_time": "2:22:59", "remaining_time": "5:27:07"}
|
366 |
+
{"current_steps": 366, "total_steps": 1200, "loss": 0.5361, "lr": 3.5094191604455446e-05, "epoch": 1.525, "percentage": 30.5, "elapsed_time": "2:23:23", "remaining_time": "5:26:44"}
|
367 |
+
{"current_steps": 367, "total_steps": 1200, "loss": 0.5394, "lr": 3.505595983071497e-05, "epoch": 1.5291666666666668, "percentage": 30.58, "elapsed_time": "2:23:46", "remaining_time": "5:26:19"}
|
368 |
+
{"current_steps": 368, "total_steps": 1200, "loss": 0.5438, "lr": 3.5017600659629986e-05, "epoch": 1.5333333333333332, "percentage": 30.67, "elapsed_time": "2:24:09", "remaining_time": "5:25:54"}
|
369 |
+
{"current_steps": 369, "total_steps": 1200, "loss": 0.5528, "lr": 3.497911441578005e-05, "epoch": 1.5375, "percentage": 30.75, "elapsed_time": "2:24:31", "remaining_time": "5:25:29"}
|
370 |
+
{"current_steps": 370, "total_steps": 1200, "loss": 0.5388, "lr": 3.4940501424819927e-05, "epoch": 1.5416666666666665, "percentage": 30.83, "elapsed_time": "2:24:54", "remaining_time": "5:25:03"}
|
371 |
+
{"current_steps": 371, "total_steps": 1200, "loss": 0.5455, "lr": 3.490176201347688e-05, "epoch": 1.5458333333333334, "percentage": 30.92, "elapsed_time": "2:25:18", "remaining_time": "5:24:41"}
|
372 |
+
{"current_steps": 372, "total_steps": 1200, "loss": 0.5386, "lr": 3.4862896509547886e-05, "epoch": 1.55, "percentage": 31.0, "elapsed_time": "2:25:40", "remaining_time": "5:24:14"}
|
373 |
+
{"current_steps": 373, "total_steps": 1200, "loss": 0.5453, "lr": 3.482390524189687e-05, "epoch": 1.5541666666666667, "percentage": 31.08, "elapsed_time": "2:26:02", "remaining_time": "5:23:48"}
|
374 |
+
{"current_steps": 374, "total_steps": 1200, "loss": 0.5397, "lr": 3.478478854045192e-05, "epoch": 1.5583333333333333, "percentage": 31.17, "elapsed_time": "2:26:26", "remaining_time": "5:23:25"}
|
375 |
+
{"current_steps": 375, "total_steps": 1200, "loss": 0.5374, "lr": 3.474554673620248e-05, "epoch": 1.5625, "percentage": 31.25, "elapsed_time": "2:26:49", "remaining_time": "5:23:00"}
|
376 |
+
{"current_steps": 376, "total_steps": 1200, "loss": 0.5317, "lr": 3.470618016119658e-05, "epoch": 1.5666666666666667, "percentage": 31.33, "elapsed_time": "2:27:12", "remaining_time": "5:22:36"}
|
377 |
+
{"current_steps": 377, "total_steps": 1200, "loss": 0.5447, "lr": 3.4666689148537976e-05, "epoch": 1.5708333333333333, "percentage": 31.42, "elapsed_time": "2:27:35", "remaining_time": "5:22:12"}
|
378 |
+
{"current_steps": 378, "total_steps": 1200, "loss": 0.5486, "lr": 3.462707403238341e-05, "epoch": 1.575, "percentage": 31.5, "elapsed_time": "2:27:59", "remaining_time": "5:21:48"}
|
379 |
+
{"current_steps": 379, "total_steps": 1200, "loss": 0.5387, "lr": 3.458733514793971e-05, "epoch": 1.5791666666666666, "percentage": 31.58, "elapsed_time": "2:28:21", "remaining_time": "5:21:23"}
|
380 |
+
{"current_steps": 380, "total_steps": 1200, "loss": 0.536, "lr": 3.4547472831460976e-05, "epoch": 1.5833333333333335, "percentage": 31.67, "elapsed_time": "2:28:46", "remaining_time": "5:21:01"}
|
381 |
+
{"current_steps": 381, "total_steps": 1200, "loss": 0.5299, "lr": 3.450748742024575e-05, "epoch": 1.5875, "percentage": 31.75, "elapsed_time": "2:29:09", "remaining_time": "5:20:37"}
|
382 |
+
{"current_steps": 382, "total_steps": 1200, "loss": 0.5513, "lr": 3.446737925263416e-05, "epoch": 1.5916666666666668, "percentage": 31.83, "elapsed_time": "2:29:33", "remaining_time": "5:20:14"}
|
383 |
+
{"current_steps": 383, "total_steps": 1200, "loss": 0.5373, "lr": 3.442714866800503e-05, "epoch": 1.5958333333333332, "percentage": 31.92, "elapsed_time": "2:29:57", "remaining_time": "5:19:52"}
|
384 |
+
{"current_steps": 384, "total_steps": 1200, "loss": 0.5573, "lr": 3.438679600677303e-05, "epoch": 1.6, "percentage": 32.0, "elapsed_time": "2:30:20", "remaining_time": "5:19:28"}
|
385 |
+
{"current_steps": 385, "total_steps": 1200, "loss": 0.5476, "lr": 3.434632161038579e-05, "epoch": 1.6041666666666665, "percentage": 32.08, "elapsed_time": "2:30:43", "remaining_time": "5:19:04"}
|
386 |
+
{"current_steps": 386, "total_steps": 1200, "loss": 0.5318, "lr": 3.430572582132103e-05, "epoch": 1.6083333333333334, "percentage": 32.17, "elapsed_time": "2:31:07", "remaining_time": "5:18:41"}
|
387 |
+
{"current_steps": 387, "total_steps": 1200, "loss": 0.546, "lr": 3.426500898308364e-05, "epoch": 1.6125, "percentage": 32.25, "elapsed_time": "2:31:30", "remaining_time": "5:18:16"}
|
388 |
+
{"current_steps": 388, "total_steps": 1200, "loss": 0.5556, "lr": 3.422417144020274e-05, "epoch": 1.6166666666666667, "percentage": 32.33, "elapsed_time": "2:31:52", "remaining_time": "5:17:51"}
|
389 |
+
{"current_steps": 389, "total_steps": 1200, "loss": 0.5369, "lr": 3.4183213538228876e-05, "epoch": 1.6208333333333333, "percentage": 32.42, "elapsed_time": "2:32:15", "remaining_time": "5:17:25"}
|
390 |
+
{"current_steps": 390, "total_steps": 1200, "loss": 0.5333, "lr": 3.4142135623730954e-05, "epoch": 1.625, "percentage": 32.5, "elapsed_time": "2:32:39", "remaining_time": "5:17:02"}
|
391 |
+
{"current_steps": 391, "total_steps": 1200, "loss": 0.6215, "lr": 3.410093804429341e-05, "epoch": 1.6291666666666667, "percentage": 32.58, "elapsed_time": "2:33:02", "remaining_time": "5:16:40"}
|
392 |
+
{"current_steps": 392, "total_steps": 1200, "loss": 0.5418, "lr": 3.405962114851324e-05, "epoch": 1.6333333333333333, "percentage": 32.67, "elapsed_time": "2:33:26", "remaining_time": "5:16:16"}
|
393 |
+
{"current_steps": 393, "total_steps": 1200, "loss": 0.5347, "lr": 3.401818528599702e-05, "epoch": 1.6375, "percentage": 32.75, "elapsed_time": "2:33:48", "remaining_time": "5:15:49"}
|
394 |
+
{"current_steps": 394, "total_steps": 1200, "loss": 0.5541, "lr": 3.3976630807358e-05, "epoch": 1.6416666666666666, "percentage": 32.83, "elapsed_time": "2:34:12", "remaining_time": "5:15:27"}
|
395 |
+
{"current_steps": 395, "total_steps": 1200, "loss": 0.5365, "lr": 3.3934958064213105e-05, "epoch": 1.6458333333333335, "percentage": 32.92, "elapsed_time": "2:34:34", "remaining_time": "5:15:02"}
|
396 |
+
{"current_steps": 396, "total_steps": 1200, "loss": 0.5332, "lr": 3.3893167409179945e-05, "epoch": 1.65, "percentage": 33.0, "elapsed_time": "2:34:57", "remaining_time": "5:14:36"}
|
397 |
+
{"current_steps": 397, "total_steps": 1200, "loss": 0.5256, "lr": 3.385125919587389e-05, "epoch": 1.6541666666666668, "percentage": 33.08, "elapsed_time": "2:35:19", "remaining_time": "5:14:09"}
|
398 |
+
{"current_steps": 398, "total_steps": 1200, "loss": 0.5365, "lr": 3.3809233778904995e-05, "epoch": 1.6583333333333332, "percentage": 33.17, "elapsed_time": "2:35:42", "remaining_time": "5:13:45"}
|
399 |
+
{"current_steps": 399, "total_steps": 1200, "loss": 0.5419, "lr": 3.376709151387508e-05, "epoch": 1.6625, "percentage": 33.25, "elapsed_time": "2:36:06", "remaining_time": "5:13:22"}
|
400 |
+
{"current_steps": 400, "total_steps": 1200, "loss": 0.5355, "lr": 3.372483275737468e-05, "epoch": 1.6666666666666665, "percentage": 33.33, "elapsed_time": "2:36:28", "remaining_time": "5:12:57"}
|
401 |
+
{"current_steps": 401, "total_steps": 1200, "loss": 0.5359, "lr": 3.368245786698e-05, "epoch": 1.6708333333333334, "percentage": 33.42, "elapsed_time": "2:36:52", "remaining_time": "5:12:35"}
|
402 |
+
{"current_steps": 402, "total_steps": 1200, "loss": 0.5468, "lr": 3.363996720124997e-05, "epoch": 1.675, "percentage": 33.5, "elapsed_time": "2:37:16", "remaining_time": "5:12:12"}
|
403 |
+
{"current_steps": 403, "total_steps": 1200, "loss": 0.5351, "lr": 3.3597361119723145e-05, "epoch": 1.6791666666666667, "percentage": 33.58, "elapsed_time": "2:37:40", "remaining_time": "5:11:48"}
|
404 |
+
{"current_steps": 404, "total_steps": 1200, "loss": 0.5348, "lr": 3.355463998291465e-05, "epoch": 1.6833333333333333, "percentage": 33.67, "elapsed_time": "2:38:03", "remaining_time": "5:11:25"}
|
405 |
+
{"current_steps": 405, "total_steps": 1200, "loss": 0.5279, "lr": 3.351180415231321e-05, "epoch": 1.6875, "percentage": 33.75, "elapsed_time": "2:38:25", "remaining_time": "5:10:59"}
|
406 |
+
{"current_steps": 406, "total_steps": 1200, "loss": 0.5285, "lr": 3.3468853990378005e-05, "epoch": 1.6916666666666667, "percentage": 33.83, "elapsed_time": "2:38:48", "remaining_time": "5:10:34"}
|
407 |
+
{"current_steps": 407, "total_steps": 1200, "loss": 0.5277, "lr": 3.342578986053567e-05, "epoch": 1.6958333333333333, "percentage": 33.92, "elapsed_time": "2:39:10", "remaining_time": "5:10:08"}
|
408 |
+
{"current_steps": 408, "total_steps": 1200, "loss": 0.5334, "lr": 3.3382612127177166e-05, "epoch": 1.7, "percentage": 34.0, "elapsed_time": "2:39:34", "remaining_time": "5:09:45"}
|
409 |
+
{"current_steps": 409, "total_steps": 1200, "loss": 0.5315, "lr": 3.3339321155654723e-05, "epoch": 1.7041666666666666, "percentage": 34.08, "elapsed_time": "2:39:57", "remaining_time": "5:09:21"}
|
410 |
+
{"current_steps": 410, "total_steps": 1200, "loss": 0.5582, "lr": 3.3295917312278754e-05, "epoch": 1.7083333333333335, "percentage": 34.17, "elapsed_time": "2:40:21", "remaining_time": "5:08:58"}
|
411 |
+
{"current_steps": 411, "total_steps": 1200, "loss": 0.5497, "lr": 3.3252400964314756e-05, "epoch": 1.7125, "percentage": 34.25, "elapsed_time": "2:40:45", "remaining_time": "5:08:36"}
|
412 |
+
{"current_steps": 412, "total_steps": 1200, "loss": 0.6032, "lr": 3.3208772479980154e-05, "epoch": 1.7166666666666668, "percentage": 34.33, "elapsed_time": "2:41:08", "remaining_time": "5:08:11"}
|
413 |
+
{"current_steps": 413, "total_steps": 1200, "loss": 0.5289, "lr": 3.316503222844128e-05, "epoch": 1.7208333333333332, "percentage": 34.42, "elapsed_time": "2:41:30", "remaining_time": "5:07:46"}
|
414 |
+
{"current_steps": 414, "total_steps": 1200, "loss": 0.5379, "lr": 3.312118057981015e-05, "epoch": 1.725, "percentage": 34.5, "elapsed_time": "2:41:53", "remaining_time": "5:07:21"}
|
415 |
+
{"current_steps": 415, "total_steps": 1200, "loss": 0.532, "lr": 3.3077217905141395e-05, "epoch": 1.7291666666666665, "percentage": 34.58, "elapsed_time": "2:42:16", "remaining_time": "5:06:57"}
|
416 |
+
{"current_steps": 416, "total_steps": 1200, "loss": 0.546, "lr": 3.303314457642911e-05, "epoch": 1.7333333333333334, "percentage": 34.67, "elapsed_time": "2:42:39", "remaining_time": "5:06:32"}
|
417 |
+
{"current_steps": 417, "total_steps": 1200, "loss": 0.5269, "lr": 3.298896096660367e-05, "epoch": 1.7375, "percentage": 34.75, "elapsed_time": "2:43:01", "remaining_time": "5:06:07"}
|
418 |
+
{"current_steps": 418, "total_steps": 1200, "loss": 0.5487, "lr": 3.294466744952865e-05, "epoch": 1.7416666666666667, "percentage": 34.83, "elapsed_time": "2:43:25", "remaining_time": "5:05:43"}
|
419 |
+
{"current_steps": 419, "total_steps": 1200, "loss": 0.5364, "lr": 3.290026439999757e-05, "epoch": 1.7458333333333333, "percentage": 34.92, "elapsed_time": "2:43:47", "remaining_time": "5:05:18"}
|
420 |
+
{"current_steps": 420, "total_steps": 1200, "loss": 0.5351, "lr": 3.285575219373079e-05, "epoch": 1.75, "percentage": 35.0, "elapsed_time": "2:44:11", "remaining_time": "5:04:56"}
|
421 |
+
{"current_steps": 421, "total_steps": 1200, "loss": 0.5316, "lr": 3.281113120737231e-05, "epoch": 1.7541666666666667, "percentage": 35.08, "elapsed_time": "2:44:34", "remaining_time": "5:04:31"}
|
422 |
+
{"current_steps": 422, "total_steps": 1200, "loss": 0.5347, "lr": 3.276640181848657e-05, "epoch": 1.7583333333333333, "percentage": 35.17, "elapsed_time": "2:44:57", "remaining_time": "5:04:07"}
|
423 |
+
{"current_steps": 423, "total_steps": 1200, "loss": 0.533, "lr": 3.272156440555528e-05, "epoch": 1.7625, "percentage": 35.25, "elapsed_time": "2:45:20", "remaining_time": "5:03:43"}
|
424 |
+
{"current_steps": 424, "total_steps": 1200, "loss": 0.5384, "lr": 3.26766193479742e-05, "epoch": 1.7666666666666666, "percentage": 35.33, "elapsed_time": "2:45:43", "remaining_time": "5:03:18"}
|
425 |
+
{"current_steps": 425, "total_steps": 1200, "loss": 0.538, "lr": 3.2631567026049954e-05, "epoch": 1.7708333333333335, "percentage": 35.42, "elapsed_time": "2:46:06", "remaining_time": "5:02:54"}
|
426 |
+
{"current_steps": 426, "total_steps": 1200, "loss": 0.5377, "lr": 3.258640782099675e-05, "epoch": 1.775, "percentage": 35.5, "elapsed_time": "2:46:28", "remaining_time": "5:02:28"}
|
427 |
+
{"current_steps": 427, "total_steps": 1200, "loss": 0.5312, "lr": 3.254114211493324e-05, "epoch": 1.7791666666666668, "percentage": 35.58, "elapsed_time": "2:46:51", "remaining_time": "5:02:04"}
|
428 |
+
{"current_steps": 428, "total_steps": 1200, "loss": 0.5602, "lr": 3.2495770290879204e-05, "epoch": 1.7833333333333332, "percentage": 35.67, "elapsed_time": "2:47:15", "remaining_time": "5:01:41"}
|
429 |
+
{"current_steps": 429, "total_steps": 1200, "loss": 0.5388, "lr": 3.2450292732752395e-05, "epoch": 1.7875, "percentage": 35.75, "elapsed_time": "2:47:38", "remaining_time": "5:01:17"}
|
430 |
+
{"current_steps": 430, "total_steps": 1200, "loss": 0.5411, "lr": 3.2404709825365204e-05, "epoch": 1.7916666666666665, "percentage": 35.83, "elapsed_time": "2:48:01", "remaining_time": "5:00:52"}
|
431 |
+
{"current_steps": 431, "total_steps": 1200, "loss": 0.5474, "lr": 3.235902195442147e-05, "epoch": 1.7958333333333334, "percentage": 35.92, "elapsed_time": "2:48:24", "remaining_time": "5:00:27"}
|
432 |
+
{"current_steps": 432, "total_steps": 1200, "loss": 0.5382, "lr": 3.2313229506513167e-05, "epoch": 1.8, "percentage": 36.0, "elapsed_time": "2:48:47", "remaining_time": "5:00:05"}
|
433 |
+
{"current_steps": 433, "total_steps": 1200, "loss": 0.5378, "lr": 3.2267332869117186e-05, "epoch": 1.8041666666666667, "percentage": 36.08, "elapsed_time": "2:49:12", "remaining_time": "4:59:43"}
|
434 |
+
{"current_steps": 434, "total_steps": 1200, "loss": 0.5339, "lr": 3.2221332430592e-05, "epoch": 1.8083333333333333, "percentage": 36.17, "elapsed_time": "2:49:35", "remaining_time": "4:59:19"}
|
435 |
+
{"current_steps": 435, "total_steps": 1200, "loss": 0.5321, "lr": 3.217522858017442e-05, "epoch": 1.8125, "percentage": 36.25, "elapsed_time": "2:49:59", "remaining_time": "4:58:56"}
|
436 |
+
{"current_steps": 436, "total_steps": 1200, "loss": 0.5269, "lr": 3.2129021707976274e-05, "epoch": 1.8166666666666667, "percentage": 36.33, "elapsed_time": "2:50:22", "remaining_time": "4:58:32"}
|
437 |
+
{"current_steps": 437, "total_steps": 1200, "loss": 0.5452, "lr": 3.208271220498113e-05, "epoch": 1.8208333333333333, "percentage": 36.42, "elapsed_time": "2:50:45", "remaining_time": "4:58:08"}
|
438 |
+
{"current_steps": 438, "total_steps": 1200, "loss": 0.5413, "lr": 3.203630046304097e-05, "epoch": 1.825, "percentage": 36.5, "elapsed_time": "2:51:09", "remaining_time": "4:57:45"}
|
439 |
+
{"current_steps": 439, "total_steps": 1200, "loss": 0.5401, "lr": 3.198978687487288e-05, "epoch": 1.8291666666666666, "percentage": 36.58, "elapsed_time": "2:51:32", "remaining_time": "4:57:22"}
|
440 |
+
{"current_steps": 440, "total_steps": 1200, "loss": 0.5377, "lr": 3.194317183405573e-05, "epoch": 1.8333333333333335, "percentage": 36.67, "elapsed_time": "2:51:55", "remaining_time": "4:56:57"}
|
441 |
+
{"current_steps": 441, "total_steps": 1200, "loss": 0.523, "lr": 3.189645573502683e-05, "epoch": 1.8375, "percentage": 36.75, "elapsed_time": "2:52:17", "remaining_time": "4:56:32"}
|
442 |
+
{"current_steps": 442, "total_steps": 1200, "loss": 0.5312, "lr": 3.184963897307862e-05, "epoch": 1.8416666666666668, "percentage": 36.83, "elapsed_time": "2:52:41", "remaining_time": "4:56:09"}
|
443 |
+
{"current_steps": 443, "total_steps": 1200, "loss": 0.545, "lr": 3.1802721944355295e-05, "epoch": 1.8458333333333332, "percentage": 36.92, "elapsed_time": "2:53:04", "remaining_time": "4:55:45"}
|
444 |
+
{"current_steps": 444, "total_steps": 1200, "loss": 0.5286, "lr": 3.1755705045849465e-05, "epoch": 1.85, "percentage": 37.0, "elapsed_time": "2:53:27", "remaining_time": "4:55:21"}
|
445 |
+
{"current_steps": 445, "total_steps": 1200, "loss": 0.5209, "lr": 3.1708588675398814e-05, "epoch": 1.8541666666666665, "percentage": 37.08, "elapsed_time": "2:53:51", "remaining_time": "4:54:57"}
|
446 |
+
{"current_steps": 446, "total_steps": 1200, "loss": 0.548, "lr": 3.1661373231682696e-05, "epoch": 1.8583333333333334, "percentage": 37.17, "elapsed_time": "2:54:14", "remaining_time": "4:54:34"}
|
447 |
+
{"current_steps": 447, "total_steps": 1200, "loss": 0.5357, "lr": 3.1614059114218795e-05, "epoch": 1.8625, "percentage": 37.25, "elapsed_time": "2:54:37", "remaining_time": "4:54:10"}
|
448 |
+
{"current_steps": 448, "total_steps": 1200, "loss": 0.5434, "lr": 3.156664672335973e-05, "epoch": 1.8666666666666667, "percentage": 37.33, "elapsed_time": "2:55:00", "remaining_time": "4:53:46"}
|
449 |
+
{"current_steps": 449, "total_steps": 1200, "loss": 0.5379, "lr": 3.151913646028967e-05, "epoch": 1.8708333333333333, "percentage": 37.42, "elapsed_time": "2:55:22", "remaining_time": "4:53:20"}
|
450 |
+
{"current_steps": 450, "total_steps": 1200, "loss": 0.538, "lr": 3.147152872702092e-05, "epoch": 1.875, "percentage": 37.5, "elapsed_time": "2:55:46", "remaining_time": "4:52:57"}
|
451 |
+
{"current_steps": 451, "total_steps": 1200, "loss": 0.5353, "lr": 3.1423823926390575e-05, "epoch": 1.8791666666666667, "percentage": 37.58, "elapsed_time": "2:56:09", "remaining_time": "4:52:33"}
|
452 |
+
{"current_steps": 452, "total_steps": 1200, "loss": 0.5266, "lr": 3.137602246205704e-05, "epoch": 1.8833333333333333, "percentage": 37.67, "elapsed_time": "2:56:33", "remaining_time": "4:52:10"}
|
453 |
+
{"current_steps": 453, "total_steps": 1200, "loss": 0.5366, "lr": 3.132812473849666e-05, "epoch": 1.8875, "percentage": 37.75, "elapsed_time": "2:56:56", "remaining_time": "4:51:47"}
|
454 |
+
{"current_steps": 454, "total_steps": 1200, "loss": 0.5285, "lr": 3.128013116100029e-05, "epoch": 1.8916666666666666, "percentage": 37.83, "elapsed_time": "2:57:20", "remaining_time": "4:51:24"}
|
455 |
+
{"current_steps": 455, "total_steps": 1200, "loss": 0.5426, "lr": 3.123204213566986e-05, "epoch": 1.8958333333333335, "percentage": 37.92, "elapsed_time": "2:57:43", "remaining_time": "4:51:00"}
|
456 |
+
{"current_steps": 456, "total_steps": 1200, "loss": 0.5482, "lr": 3.1183858069414936e-05, "epoch": 1.9, "percentage": 38.0, "elapsed_time": "2:58:07", "remaining_time": "4:50:36"}
|
457 |
+
{"current_steps": 457, "total_steps": 1200, "loss": 0.5349, "lr": 3.113557936994929e-05, "epoch": 1.9041666666666668, "percentage": 38.08, "elapsed_time": "2:58:30", "remaining_time": "4:50:13"}
|
458 |
+
{"current_steps": 458, "total_steps": 1200, "loss": 0.5321, "lr": 3.1087206445787436e-05, "epoch": 1.9083333333333332, "percentage": 38.17, "elapsed_time": "2:58:53", "remaining_time": "4:49:48"}
|
459 |
+
{"current_steps": 459, "total_steps": 1200, "loss": 0.5452, "lr": 3.103873970624117e-05, "epoch": 1.9125, "percentage": 38.25, "elapsed_time": "2:59:15", "remaining_time": "4:49:23"}
|
460 |
+
{"current_steps": 460, "total_steps": 1200, "loss": 0.5328, "lr": 3.0990179561416124e-05, "epoch": 1.9166666666666665, "percentage": 38.33, "elapsed_time": "2:59:37", "remaining_time": "4:48:58"}
|
461 |
+
{"current_steps": 461, "total_steps": 1200, "loss": 0.5389, "lr": 3.094152642220829e-05, "epoch": 1.9208333333333334, "percentage": 38.42, "elapsed_time": "3:00:01", "remaining_time": "4:48:35"}
|
462 |
+
{"current_steps": 462, "total_steps": 1200, "loss": 0.541, "lr": 3.0892780700300544e-05, "epoch": 1.925, "percentage": 38.5, "elapsed_time": "3:00:25", "remaining_time": "4:48:13"}
|
463 |
+
{"current_steps": 463, "total_steps": 1200, "loss": 0.5755, "lr": 3.084394280815914e-05, "epoch": 1.9291666666666667, "percentage": 38.58, "elapsed_time": "3:00:48", "remaining_time": "4:47:48"}
|
464 |
+
{"current_steps": 464, "total_steps": 1200, "loss": 0.53, "lr": 3.079501315903026e-05, "epoch": 1.9333333333333333, "percentage": 38.67, "elapsed_time": "3:01:11", "remaining_time": "4:47:24"}
|
465 |
+
{"current_steps": 465, "total_steps": 1200, "loss": 0.5321, "lr": 3.0745992166936484e-05, "epoch": 1.9375, "percentage": 38.75, "elapsed_time": "3:01:33", "remaining_time": "4:46:58"}
|
466 |
+
{"current_steps": 466, "total_steps": 1200, "loss": 0.5313, "lr": 3.0696880246673293e-05, "epoch": 1.9416666666666667, "percentage": 38.83, "elapsed_time": "3:01:56", "remaining_time": "4:46:35"}
|
467 |
+
{"current_steps": 467, "total_steps": 1200, "loss": 0.5345, "lr": 3.064767781380558e-05, "epoch": 1.9458333333333333, "percentage": 38.92, "elapsed_time": "3:02:18", "remaining_time": "4:46:09"}
|
468 |
+
{"current_steps": 468, "total_steps": 1200, "loss": 0.5341, "lr": 3.05983852846641e-05, "epoch": 1.95, "percentage": 39.0, "elapsed_time": "3:02:41", "remaining_time": "4:45:44"}
|
469 |
+
{"current_steps": 469, "total_steps": 1200, "loss": 0.526, "lr": 3.0549003076342e-05, "epoch": 1.9541666666666666, "percentage": 39.08, "elapsed_time": "3:03:02", "remaining_time": "4:45:18"}
|
470 |
+
{"current_steps": 470, "total_steps": 1200, "loss": 0.5382, "lr": 3.0499531606691204e-05, "epoch": 1.9583333333333335, "percentage": 39.17, "elapsed_time": "3:03:25", "remaining_time": "4:44:53"}
|
471 |
+
{"current_steps": 471, "total_steps": 1200, "loss": 0.5321, "lr": 3.0449971294318977e-05, "epoch": 1.9625, "percentage": 39.25, "elapsed_time": "3:03:48", "remaining_time": "4:44:29"}
|
472 |
+
{"current_steps": 472, "total_steps": 1200, "loss": 0.5437, "lr": 3.0400322558584308e-05, "epoch": 1.9666666666666668, "percentage": 39.33, "elapsed_time": "3:04:11", "remaining_time": "4:44:05"}
|
473 |
+
{"current_steps": 473, "total_steps": 1200, "loss": 0.526, "lr": 3.0350585819594402e-05, "epoch": 1.9708333333333332, "percentage": 39.42, "elapsed_time": "3:04:34", "remaining_time": "4:43:42"}
|
474 |
+
{"current_steps": 474, "total_steps": 1200, "loss": 0.5261, "lr": 3.030076149820109e-05, "epoch": 1.975, "percentage": 39.5, "elapsed_time": "3:04:58", "remaining_time": "4:43:18"}
|
475 |
+
{"current_steps": 475, "total_steps": 1200, "loss": 0.5229, "lr": 3.0250850015997307e-05, "epoch": 1.9791666666666665, "percentage": 39.58, "elapsed_time": "3:05:20", "remaining_time": "4:42:53"}
|
476 |
+
{"current_steps": 476, "total_steps": 1200, "loss": 0.5239, "lr": 3.020085179531351e-05, "epoch": 1.9833333333333334, "percentage": 39.67, "elapsed_time": "3:05:42", "remaining_time": "4:42:28"}
|
477 |
+
{"current_steps": 477, "total_steps": 1200, "loss": 0.5388, "lr": 3.0150767259214087e-05, "epoch": 1.9875, "percentage": 39.75, "elapsed_time": "3:06:05", "remaining_time": "4:42:03"}
|
478 |
+
{"current_steps": 478, "total_steps": 1200, "loss": 0.5253, "lr": 3.0100596831493806e-05, "epoch": 1.9916666666666667, "percentage": 39.83, "elapsed_time": "3:06:29", "remaining_time": "4:41:41"}
|
479 |
+
{"current_steps": 479, "total_steps": 1200, "loss": 0.5383, "lr": 3.0050340936674202e-05, "epoch": 1.9958333333333333, "percentage": 39.92, "elapsed_time": "3:06:53", "remaining_time": "4:41:18"}
|
480 |
+
{"current_steps": 480, "total_steps": 1200, "loss": 0.5302, "lr": 3.0000000000000004e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "3:07:16", "remaining_time": "4:40:54"}
|
481 |
+
{"current_steps": 481, "total_steps": 1200, "loss": 0.4922, "lr": 2.9949574447435533e-05, "epoch": 2.004166666666667, "percentage": 40.08, "elapsed_time": "3:10:21", "remaining_time": "4:44:33"}
|
482 |
+
{"current_steps": 482, "total_steps": 1200, "loss": 0.4804, "lr": 2.9899064705661086e-05, "epoch": 2.0083333333333333, "percentage": 40.17, "elapsed_time": "3:10:44", "remaining_time": "4:44:08"}
|
483 |
+
{"current_steps": 483, "total_steps": 1200, "loss": 0.4851, "lr": 2.9848471202069347e-05, "epoch": 2.0125, "percentage": 40.25, "elapsed_time": "3:11:08", "remaining_time": "4:43:44"}
|
484 |
+
{"current_steps": 484, "total_steps": 1200, "loss": 0.4761, "lr": 2.9797794364761743e-05, "epoch": 2.0166666666666666, "percentage": 40.33, "elapsed_time": "3:11:31", "remaining_time": "4:43:20"}
|
485 |
+
{"current_steps": 485, "total_steps": 1200, "loss": 0.4931, "lr": 2.974703462254485e-05, "epoch": 2.0208333333333335, "percentage": 40.42, "elapsed_time": "3:11:55", "remaining_time": "4:42:55"}
|
486 |
+
{"current_steps": 486, "total_steps": 1200, "loss": 0.484, "lr": 2.9696192404926747e-05, "epoch": 2.025, "percentage": 40.5, "elapsed_time": "3:12:18", "remaining_time": "4:42:32"}
|
487 |
+
{"current_steps": 487, "total_steps": 1200, "loss": 0.485, "lr": 2.964526814211338e-05, "epoch": 2.029166666666667, "percentage": 40.58, "elapsed_time": "3:12:42", "remaining_time": "4:42:08"}
|
488 |
+
{"current_steps": 488, "total_steps": 1200, "loss": 0.4809, "lr": 2.959426226500493e-05, "epoch": 2.033333333333333, "percentage": 40.67, "elapsed_time": "3:13:07", "remaining_time": "4:41:46"}
|