Training in progress, epoch 6
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:a116c256150362681bcc6bc7d024c964cbbe657cd7340555efa2c6e6b763f947
|
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:b7795304b46230cc55ed4684affaf85dd1acf247ce516dbe5574f58e1ebb685a
|
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 sha256:8475b740151c00a55e477d2f1afb3263f50f8dd64abbccda95206ddbc5ee6204
|
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 sha256:3fedcd86351fe523afcfb358c09773372bfe2e5c4ae5510dec1a85cf0e1ca208
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -294,3 +294,54 @@
|
|
294 |
{"current_steps": 294, "total_steps": 364, "loss": 0.0939, "lr": 2.1774083993013715e-06, "epoch": 5.617834394904459, "percentage": 80.77, "elapsed_time": "0:33:28", "remaining_time": "0:07:58"}
|
295 |
{"current_steps": 295, "total_steps": 364, "loss": 0.0914, "lr": 2.1179212497272582e-06, "epoch": 5.6369426751592355, "percentage": 81.04, "elapsed_time": "0:33:33", "remaining_time": "0:07:51"}
|
296 |
{"current_steps": 296, "total_steps": 364, "loss": 0.0612, "lr": 2.0591616146792705e-06, "epoch": 5.656050955414012, "percentage": 81.32, "elapsed_time": "0:33:37", "remaining_time": "0:07:43"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
294 |
{"current_steps": 294, "total_steps": 364, "loss": 0.0939, "lr": 2.1774083993013715e-06, "epoch": 5.617834394904459, "percentage": 80.77, "elapsed_time": "0:33:28", "remaining_time": "0:07:58"}
|
295 |
{"current_steps": 295, "total_steps": 364, "loss": 0.0914, "lr": 2.1179212497272582e-06, "epoch": 5.6369426751592355, "percentage": 81.04, "elapsed_time": "0:33:33", "remaining_time": "0:07:51"}
|
296 |
{"current_steps": 296, "total_steps": 364, "loss": 0.0612, "lr": 2.0591616146792705e-06, "epoch": 5.656050955414012, "percentage": 81.32, "elapsed_time": "0:33:37", "remaining_time": "0:07:43"}
|
297 |
+
{"current_steps": 297, "total_steps": 364, "loss": 0.0745, "lr": 2.0011349176617133e-06, "epoch": 5.67515923566879, "percentage": 81.59, "elapsed_time": "0:33:42", "remaining_time": "0:07:36"}
|
298 |
+
{"current_steps": 298, "total_steps": 364, "loss": 0.0862, "lr": 1.9438465145288377e-06, "epoch": 5.694267515923567, "percentage": 81.87, "elapsed_time": "0:33:46", "remaining_time": "0:07:28"}
|
299 |
+
{"current_steps": 299, "total_steps": 364, "loss": 0.0902, "lr": 1.8873016929904942e-06, "epoch": 5.713375796178344, "percentage": 82.14, "elapsed_time": "0:33:51", "remaining_time": "0:07:21"}
|
300 |
+
{"current_steps": 300, "total_steps": 364, "loss": 0.0651, "lr": 1.8315056721240831e-06, "epoch": 5.732484076433121, "percentage": 82.42, "elapsed_time": "0:33:54", "remaining_time": "0:07:14"}
|
301 |
+
{"current_steps": 301, "total_steps": 364, "loss": 0.0725, "lr": 1.7764636018928249e-06, "epoch": 5.751592356687898, "percentage": 82.69, "elapsed_time": "0:33:59", "remaining_time": "0:07:06"}
|
302 |
+
{"current_steps": 302, "total_steps": 364, "loss": 0.0805, "lr": 1.722180562670428e-06, "epoch": 5.770700636942675, "percentage": 82.97, "elapsed_time": "0:34:04", "remaining_time": "0:06:59"}
|
303 |
+
{"current_steps": 303, "total_steps": 364, "loss": 0.0774, "lr": 1.6686615647721638e-06, "epoch": 5.789808917197452, "percentage": 83.24, "elapsed_time": "0:34:08", "remaining_time": "0:06:52"}
|
304 |
+
{"current_steps": 304, "total_steps": 364, "loss": 0.0927, "lr": 1.6159115479924259e-06, "epoch": 5.80891719745223, "percentage": 83.52, "elapsed_time": "0:34:15", "remaining_time": "0:06:45"}
|
305 |
+
{"current_steps": 305, "total_steps": 364, "loss": 0.0741, "lr": 1.5639353811487744e-06, "epoch": 5.828025477707007, "percentage": 83.79, "elapsed_time": "0:34:19", "remaining_time": "0:06:38"}
|
306 |
+
{"current_steps": 306, "total_steps": 364, "loss": 0.0744, "lr": 1.5127378616325606e-06, "epoch": 5.8471337579617835, "percentage": 84.07, "elapsed_time": "0:34:25", "remaining_time": "0:06:31"}
|
307 |
+
{"current_steps": 307, "total_steps": 364, "loss": 0.0908, "lr": 1.462323714966114e-06, "epoch": 5.86624203821656, "percentage": 84.34, "elapsed_time": "0:34:29", "remaining_time": "0:06:24"}
|
308 |
+
{"current_steps": 308, "total_steps": 364, "loss": 0.0998, "lr": 1.4126975943665844e-06, "epoch": 5.885350318471337, "percentage": 84.62, "elapsed_time": "0:34:35", "remaining_time": "0:06:17"}
|
309 |
+
{"current_steps": 309, "total_steps": 364, "loss": 0.0911, "lr": 1.3638640803164516e-06, "epoch": 5.904458598726115, "percentage": 84.89, "elapsed_time": "0:34:40", "remaining_time": "0:06:10"}
|
310 |
+
{"current_steps": 310, "total_steps": 364, "loss": 0.0849, "lr": 1.3158276801407432e-06, "epoch": 5.923566878980892, "percentage": 85.16, "elapsed_time": "0:34:45", "remaining_time": "0:06:03"}
|
311 |
+
{"current_steps": 311, "total_steps": 364, "loss": 0.0676, "lr": 1.2685928275910142e-06, "epoch": 5.942675159235669, "percentage": 85.44, "elapsed_time": "0:34:49", "remaining_time": "0:05:56"}
|
312 |
+
{"current_steps": 312, "total_steps": 364, "loss": 0.0509, "lr": 1.222163882436107e-06, "epoch": 5.961783439490446, "percentage": 85.71, "elapsed_time": "0:34:53", "remaining_time": "0:05:48"}
|
313 |
+
{"current_steps": 313, "total_steps": 364, "loss": 0.089, "lr": 1.1765451300597574e-06, "epoch": 5.980891719745223, "percentage": 85.99, "elapsed_time": "0:34:58", "remaining_time": "0:05:41"}
|
314 |
+
{"current_steps": 314, "total_steps": 364, "loss": 0.0544, "lr": 1.1317407810650372e-06, "epoch": 6.0, "percentage": 86.26, "elapsed_time": "0:35:03", "remaining_time": "0:05:34"}
|
315 |
+
{"current_steps": 315, "total_steps": 364, "loss": 0.0603, "lr": 1.0877549708857228e-06, "epoch": 6.019108280254777, "percentage": 86.54, "elapsed_time": "0:36:47", "remaining_time": "0:05:43"}
|
316 |
+
{"current_steps": 316, "total_steps": 364, "loss": 0.0645, "lr": 1.0445917594046073e-06, "epoch": 6.038216560509555, "percentage": 86.81, "elapsed_time": "0:36:51", "remaining_time": "0:05:35"}
|
317 |
+
{"current_steps": 317, "total_steps": 364, "loss": 0.0571, "lr": 1.0022551305787564e-06, "epoch": 6.057324840764331, "percentage": 87.09, "elapsed_time": "0:36:56", "remaining_time": "0:05:28"}
|
318 |
+
{"current_steps": 318, "total_steps": 364, "loss": 0.0677, "lr": 9.607489920717983e-07, "epoch": 6.076433121019108, "percentage": 87.36, "elapsed_time": "0:37:03", "remaining_time": "0:05:21"}
|
319 |
+
{"current_steps": 319, "total_steps": 364, "loss": 0.0665, "lr": 9.200771748932513e-07, "epoch": 6.095541401273885, "percentage": 87.64, "elapsed_time": "0:37:09", "remaining_time": "0:05:14"}
|
320 |
+
{"current_steps": 320, "total_steps": 364, "loss": 0.0605, "lr": 8.802434330449128e-07, "epoch": 6.114649681528663, "percentage": 87.91, "elapsed_time": "0:37:14", "remaining_time": "0:05:07"}
|
321 |
+
{"current_steps": 321, "total_steps": 364, "loss": 0.0759, "lr": 8.412514431743657e-07, "epoch": 6.13375796178344, "percentage": 88.19, "elapsed_time": "0:37:21", "remaining_time": "0:05:00"}
|
322 |
+
{"current_steps": 322, "total_steps": 364, "loss": 0.0944, "lr": 8.031048042356393e-07, "epoch": 6.1528662420382165, "percentage": 88.46, "elapsed_time": "0:37:27", "remaining_time": "0:04:53"}
|
323 |
+
{"current_steps": 323, "total_steps": 364, "loss": 0.0737, "lr": 7.65807037157007e-07, "epoch": 6.171974522292993, "percentage": 88.74, "elapsed_time": "0:37:32", "remaining_time": "0:04:45"}
|
324 |
+
{"current_steps": 324, "total_steps": 364, "loss": 0.0801, "lr": 7.293615845160196e-07, "epoch": 6.191082802547771, "percentage": 89.01, "elapsed_time": "0:37:37", "remaining_time": "0:04:38"}
|
325 |
+
{"current_steps": 325, "total_steps": 364, "loss": 0.0843, "lr": 6.937718102217461e-07, "epoch": 6.210191082802548, "percentage": 89.29, "elapsed_time": "0:37:45", "remaining_time": "0:04:31"}
|
326 |
+
{"current_steps": 326, "total_steps": 364, "loss": 0.0479, "lr": 6.590409992042957e-07, "epoch": 6.229299363057325, "percentage": 89.56, "elapsed_time": "0:37:50", "remaining_time": "0:04:24"}
|
327 |
+
{"current_steps": 327, "total_steps": 364, "loss": 0.0996, "lr": 6.251723571116031e-07, "epoch": 6.248407643312102, "percentage": 89.84, "elapsed_time": "0:37:54", "remaining_time": "0:04:17"}
|
328 |
+
{"current_steps": 328, "total_steps": 364, "loss": 0.1195, "lr": 5.921690100135713e-07, "epoch": 6.267515923566879, "percentage": 90.11, "elapsed_time": "0:37:59", "remaining_time": "0:04:10"}
|
329 |
+
{"current_steps": 329, "total_steps": 364, "loss": 0.041, "lr": 5.600340041135133e-07, "epoch": 6.286624203821656, "percentage": 90.38, "elapsed_time": "0:38:03", "remaining_time": "0:04:02"}
|
330 |
+
{"current_steps": 330, "total_steps": 364, "loss": 0.0896, "lr": 5.287703054670012e-07, "epoch": 6.305732484076433, "percentage": 90.66, "elapsed_time": "0:38:10", "remaining_time": "0:03:56"}
|
331 |
+
{"current_steps": 331, "total_steps": 364, "loss": 0.0507, "lr": 4.983807997080925e-07, "epoch": 6.32484076433121, "percentage": 90.93, "elapsed_time": "0:38:15", "remaining_time": "0:03:48"}
|
332 |
+
{"current_steps": 332, "total_steps": 364, "loss": 0.0916, "lr": 4.6886829178299676e-07, "epoch": 6.343949044585988, "percentage": 91.21, "elapsed_time": "0:38:20", "remaining_time": "0:03:41"}
|
333 |
+
{"current_steps": 333, "total_steps": 364, "loss": 0.0787, "lr": 4.402355056911656e-07, "epoch": 6.3630573248407645, "percentage": 91.48, "elapsed_time": "0:38:24", "remaining_time": "0:03:34"}
|
334 |
+
{"current_steps": 334, "total_steps": 364, "loss": 0.0898, "lr": 4.124850842338779e-07, "epoch": 6.382165605095541, "percentage": 91.76, "elapsed_time": "0:38:30", "remaining_time": "0:03:27"}
|
335 |
+
{"current_steps": 335, "total_steps": 364, "loss": 0.082, "lr": 3.8561958877030957e-07, "epoch": 6.401273885350318, "percentage": 92.03, "elapsed_time": "0:38:34", "remaining_time": "0:03:20"}
|
336 |
+
{"current_steps": 336, "total_steps": 364, "loss": 0.0537, "lr": 3.5964149898111587e-07, "epoch": 6.420382165605096, "percentage": 92.31, "elapsed_time": "0:38:39", "remaining_time": "0:03:13"}
|
337 |
+
{"current_steps": 337, "total_steps": 364, "loss": 0.0579, "lr": 3.345532126395579e-07, "epoch": 6.439490445859873, "percentage": 92.58, "elapsed_time": "0:38:43", "remaining_time": "0:03:06"}
|
338 |
+
{"current_steps": 338, "total_steps": 364, "loss": 0.0726, "lr": 3.1035704539019384e-07, "epoch": 6.45859872611465, "percentage": 92.86, "elapsed_time": "0:38:47", "remaining_time": "0:02:59"}
|
339 |
+
{"current_steps": 339, "total_steps": 364, "loss": 0.0706, "lr": 2.870552305351382e-07, "epoch": 6.477707006369426, "percentage": 93.13, "elapsed_time": "0:38:52", "remaining_time": "0:02:52"}
|
340 |
+
{"current_steps": 340, "total_steps": 364, "loss": 0.0424, "lr": 2.646499188279328e-07, "epoch": 6.496815286624204, "percentage": 93.41, "elapsed_time": "0:38:58", "remaining_time": "0:02:45"}
|
341 |
+
{"current_steps": 341, "total_steps": 364, "loss": 0.1085, "lr": 2.4314317827503375e-07, "epoch": 6.515923566878981, "percentage": 93.68, "elapsed_time": "0:39:05", "remaining_time": "0:02:38"}
|
342 |
+
{"current_steps": 342, "total_steps": 364, "loss": 0.0576, "lr": 2.2253699394493066e-07, "epoch": 6.535031847133758, "percentage": 93.96, "elapsed_time": "0:39:09", "remaining_time": "0:02:31"}
|
343 |
+
{"current_steps": 343, "total_steps": 364, "loss": 0.0573, "lr": 2.028332677849254e-07, "epoch": 6.554140127388535, "percentage": 94.23, "elapsed_time": "0:39:13", "remaining_time": "0:02:24"}
|
344 |
+
{"current_steps": 344, "total_steps": 364, "loss": 0.059, "lr": 1.840338184455881e-07, "epoch": 6.573248407643312, "percentage": 94.51, "elapsed_time": "0:39:17", "remaining_time": "0:02:17"}
|
345 |
+
{"current_steps": 345, "total_steps": 364, "loss": 0.0611, "lr": 1.6614038111289034e-07, "epoch": 6.592356687898089, "percentage": 94.78, "elapsed_time": "0:39:21", "remaining_time": "0:02:10"}
|
346 |
+
{"current_steps": 346, "total_steps": 364, "loss": 0.0793, "lr": 1.49154607348051e-07, "epoch": 6.611464968152866, "percentage": 95.05, "elapsed_time": "0:39:28", "remaining_time": "0:02:03"}
|
347 |
+
{"current_steps": 347, "total_steps": 364, "loss": 0.0613, "lr": 1.330780649350938e-07, "epoch": 6.630573248407643, "percentage": 95.33, "elapsed_time": "0:39:34", "remaining_time": "0:01:56"}
|