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 sha256:529f36cc6c1a606599df7a9dee164693920856eaa316c55656a78339b5856c05
|
| 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:f298f99cacb499a8c46273b192904cf1394e3a0af2aa61720b5d6ed8ab786d91
|
| 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:f4af57787cb004f70beeaf8e37f003b579dea21cd04bab7e2eb3c5b345c0dde1
|
| 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:d04545968814e02e057dba307678eb50c1a7953abfdac86f70b80117701ddabc
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -294,3 +294,52 @@
|
|
| 294 |
{"current_steps": 294, "total_steps": 364, "loss": 0.0899, "lr": 2.1774083993013715e-06, "epoch": 5.617834394904459, "percentage": 80.77, "elapsed_time": "0:34:03", "remaining_time": "0:08:06"}
|
| 295 |
{"current_steps": 295, "total_steps": 364, "loss": 0.0844, "lr": 2.1179212497272582e-06, "epoch": 5.6369426751592355, "percentage": 81.04, "elapsed_time": "0:34:07", "remaining_time": "0:07:58"}
|
| 296 |
{"current_steps": 296, "total_steps": 364, "loss": 0.0638, "lr": 2.0591616146792705e-06, "epoch": 5.656050955414012, "percentage": 81.32, "elapsed_time": "0:34:11", "remaining_time": "0:07:51"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 294 |
{"current_steps": 294, "total_steps": 364, "loss": 0.0899, "lr": 2.1774083993013715e-06, "epoch": 5.617834394904459, "percentage": 80.77, "elapsed_time": "0:34:03", "remaining_time": "0:08:06"}
|
| 295 |
{"current_steps": 295, "total_steps": 364, "loss": 0.0844, "lr": 2.1179212497272582e-06, "epoch": 5.6369426751592355, "percentage": 81.04, "elapsed_time": "0:34:07", "remaining_time": "0:07:58"}
|
| 296 |
{"current_steps": 296, "total_steps": 364, "loss": 0.0638, "lr": 2.0591616146792705e-06, "epoch": 5.656050955414012, "percentage": 81.32, "elapsed_time": "0:34:11", "remaining_time": "0:07:51"}
|
| 297 |
+
{"current_steps": 297, "total_steps": 364, "loss": 0.0987, "lr": 2.0011349176617133e-06, "epoch": 5.67515923566879, "percentage": 81.59, "elapsed_time": "0:34:17", "remaining_time": "0:07:44"}
|
| 298 |
+
{"current_steps": 298, "total_steps": 364, "loss": 0.0857, "lr": 1.9438465145288377e-06, "epoch": 5.694267515923567, "percentage": 81.87, "elapsed_time": "0:34:24", "remaining_time": "0:07:37"}
|
| 299 |
+
{"current_steps": 299, "total_steps": 364, "loss": 0.0981, "lr": 1.8873016929904942e-06, "epoch": 5.713375796178344, "percentage": 82.14, "elapsed_time": "0:34:28", "remaining_time": "0:07:29"}
|
| 300 |
+
{"current_steps": 300, "total_steps": 364, "loss": 0.0661, "lr": 1.8315056721240831e-06, "epoch": 5.732484076433121, "percentage": 82.42, "elapsed_time": "0:34:33", "remaining_time": "0:07:22"}
|
| 301 |
+
{"current_steps": 301, "total_steps": 364, "loss": 0.0743, "lr": 1.7764636018928249e-06, "epoch": 5.751592356687898, "percentage": 82.69, "elapsed_time": "0:34:37", "remaining_time": "0:07:14"}
|
| 302 |
+
{"current_steps": 302, "total_steps": 364, "loss": 0.061, "lr": 1.722180562670428e-06, "epoch": 5.770700636942675, "percentage": 82.97, "elapsed_time": "0:34:45", "remaining_time": "0:07:08"}
|
| 303 |
+
{"current_steps": 303, "total_steps": 364, "loss": 0.0812, "lr": 1.6686615647721638e-06, "epoch": 5.789808917197452, "percentage": 83.24, "elapsed_time": "0:34:49", "remaining_time": "0:07:00"}
|
| 304 |
+
{"current_steps": 304, "total_steps": 364, "loss": 0.0918, "lr": 1.6159115479924259e-06, "epoch": 5.80891719745223, "percentage": 83.52, "elapsed_time": "0:34:55", "remaining_time": "0:06:53"}
|
| 305 |
+
{"current_steps": 305, "total_steps": 364, "loss": 0.0825, "lr": 1.5639353811487744e-06, "epoch": 5.828025477707007, "percentage": 83.79, "elapsed_time": "0:34:59", "remaining_time": "0:06:46"}
|
| 306 |
+
{"current_steps": 306, "total_steps": 364, "loss": 0.1, "lr": 1.5127378616325606e-06, "epoch": 5.8471337579617835, "percentage": 84.07, "elapsed_time": "0:35:09", "remaining_time": "0:06:39"}
|
| 307 |
+
{"current_steps": 307, "total_steps": 364, "loss": 0.0974, "lr": 1.462323714966114e-06, "epoch": 5.86624203821656, "percentage": 84.34, "elapsed_time": "0:35:14", "remaining_time": "0:06:32"}
|
| 308 |
+
{"current_steps": 308, "total_steps": 364, "loss": 0.0639, "lr": 1.4126975943665844e-06, "epoch": 5.885350318471337, "percentage": 84.62, "elapsed_time": "0:35:22", "remaining_time": "0:06:25"}
|
| 309 |
+
{"current_steps": 309, "total_steps": 364, "loss": 0.1117, "lr": 1.3638640803164516e-06, "epoch": 5.904458598726115, "percentage": 84.89, "elapsed_time": "0:35:29", "remaining_time": "0:06:18"}
|
| 310 |
+
{"current_steps": 310, "total_steps": 364, "loss": 0.0695, "lr": 1.3158276801407432e-06, "epoch": 5.923566878980892, "percentage": 85.16, "elapsed_time": "0:35:33", "remaining_time": "0:06:11"}
|
| 311 |
+
{"current_steps": 311, "total_steps": 364, "loss": 0.0669, "lr": 1.2685928275910142e-06, "epoch": 5.942675159235669, "percentage": 85.44, "elapsed_time": "0:35:39", "remaining_time": "0:06:04"}
|
| 312 |
+
{"current_steps": 312, "total_steps": 364, "loss": 0.0626, "lr": 1.222163882436107e-06, "epoch": 5.961783439490446, "percentage": 85.71, "elapsed_time": "0:35:44", "remaining_time": "0:05:57"}
|
| 313 |
+
{"current_steps": 313, "total_steps": 364, "loss": 0.0892, "lr": 1.1765451300597574e-06, "epoch": 5.980891719745223, "percentage": 85.99, "elapsed_time": "0:35:48", "remaining_time": "0:05:50"}
|
| 314 |
+
{"current_steps": 314, "total_steps": 364, "loss": 0.0607, "lr": 1.1317407810650372e-06, "epoch": 6.0, "percentage": 86.26, "elapsed_time": "0:35:52", "remaining_time": "0:05:42"}
|
| 315 |
+
{"current_steps": 315, "total_steps": 364, "loss": 0.0678, "lr": 1.0877549708857228e-06, "epoch": 6.019108280254777, "percentage": 86.54, "elapsed_time": "0:37:39", "remaining_time": "0:05:51"}
|
| 316 |
+
{"current_steps": 316, "total_steps": 364, "loss": 0.0627, "lr": 1.0445917594046073e-06, "epoch": 6.038216560509555, "percentage": 86.81, "elapsed_time": "0:37:44", "remaining_time": "0:05:43"}
|
| 317 |
+
{"current_steps": 317, "total_steps": 364, "loss": 0.0494, "lr": 1.0022551305787564e-06, "epoch": 6.057324840764331, "percentage": 87.09, "elapsed_time": "0:37:47", "remaining_time": "0:05:36"}
|
| 318 |
+
{"current_steps": 318, "total_steps": 364, "loss": 0.0949, "lr": 9.607489920717983e-07, "epoch": 6.076433121019108, "percentage": 87.36, "elapsed_time": "0:37:53", "remaining_time": "0:05:28"}
|
| 319 |
+
{"current_steps": 319, "total_steps": 364, "loss": 0.1041, "lr": 9.200771748932513e-07, "epoch": 6.095541401273885, "percentage": 87.64, "elapsed_time": "0:37:59", "remaining_time": "0:05:21"}
|
| 320 |
+
{"current_steps": 320, "total_steps": 364, "loss": 0.0698, "lr": 8.802434330449128e-07, "epoch": 6.114649681528663, "percentage": 87.91, "elapsed_time": "0:38:03", "remaining_time": "0:05:14"}
|
| 321 |
+
{"current_steps": 321, "total_steps": 364, "loss": 0.0698, "lr": 8.412514431743657e-07, "epoch": 6.13375796178344, "percentage": 88.19, "elapsed_time": "0:38:12", "remaining_time": "0:05:07"}
|
| 322 |
+
{"current_steps": 322, "total_steps": 364, "loss": 0.0846, "lr": 8.031048042356393e-07, "epoch": 6.1528662420382165, "percentage": 88.46, "elapsed_time": "0:38:19", "remaining_time": "0:04:59"}
|
| 323 |
+
{"current_steps": 323, "total_steps": 364, "loss": 0.0708, "lr": 7.65807037157007e-07, "epoch": 6.171974522292993, "percentage": 88.74, "elapsed_time": "0:38:23", "remaining_time": "0:04:52"}
|
| 324 |
+
{"current_steps": 324, "total_steps": 364, "loss": 0.0672, "lr": 7.293615845160196e-07, "epoch": 6.191082802547771, "percentage": 89.01, "elapsed_time": "0:38:27", "remaining_time": "0:04:44"}
|
| 325 |
+
{"current_steps": 325, "total_steps": 364, "loss": 0.0847, "lr": 6.937718102217461e-07, "epoch": 6.210191082802548, "percentage": 89.29, "elapsed_time": "0:38:34", "remaining_time": "0:04:37"}
|
| 326 |
+
{"current_steps": 326, "total_steps": 364, "loss": 0.0586, "lr": 6.590409992042957e-07, "epoch": 6.229299363057325, "percentage": 89.56, "elapsed_time": "0:38:40", "remaining_time": "0:04:30"}
|
| 327 |
+
{"current_steps": 327, "total_steps": 364, "loss": 0.0737, "lr": 6.251723571116031e-07, "epoch": 6.248407643312102, "percentage": 89.84, "elapsed_time": "0:38:45", "remaining_time": "0:04:23"}
|
| 328 |
+
{"current_steps": 328, "total_steps": 364, "loss": 0.061, "lr": 5.921690100135713e-07, "epoch": 6.267515923566879, "percentage": 90.11, "elapsed_time": "0:38:49", "remaining_time": "0:04:15"}
|
| 329 |
+
{"current_steps": 329, "total_steps": 364, "loss": 0.0654, "lr": 5.600340041135133e-07, "epoch": 6.286624203821656, "percentage": 90.38, "elapsed_time": "0:38:57", "remaining_time": "0:04:08"}
|
| 330 |
+
{"current_steps": 330, "total_steps": 364, "loss": 0.115, "lr": 5.287703054670012e-07, "epoch": 6.305732484076433, "percentage": 90.66, "elapsed_time": "0:39:03", "remaining_time": "0:04:01"}
|
| 331 |
+
{"current_steps": 331, "total_steps": 364, "loss": 0.0672, "lr": 4.983807997080925e-07, "epoch": 6.32484076433121, "percentage": 90.93, "elapsed_time": "0:39:07", "remaining_time": "0:03:54"}
|
| 332 |
+
{"current_steps": 332, "total_steps": 364, "loss": 0.0755, "lr": 4.6886829178299676e-07, "epoch": 6.343949044585988, "percentage": 91.21, "elapsed_time": "0:39:12", "remaining_time": "0:03:46"}
|
| 333 |
+
{"current_steps": 333, "total_steps": 364, "loss": 0.0634, "lr": 4.402355056911656e-07, "epoch": 6.3630573248407645, "percentage": 91.48, "elapsed_time": "0:39:17", "remaining_time": "0:03:39"}
|
| 334 |
+
{"current_steps": 334, "total_steps": 364, "loss": 0.0652, "lr": 4.124850842338779e-07, "epoch": 6.382165605095541, "percentage": 91.76, "elapsed_time": "0:39:21", "remaining_time": "0:03:32"}
|
| 335 |
+
{"current_steps": 335, "total_steps": 364, "loss": 0.0532, "lr": 3.8561958877030957e-07, "epoch": 6.401273885350318, "percentage": 92.03, "elapsed_time": "0:39:29", "remaining_time": "0:03:25"}
|
| 336 |
+
{"current_steps": 336, "total_steps": 364, "loss": 0.0426, "lr": 3.5964149898111587e-07, "epoch": 6.420382165605096, "percentage": 92.31, "elapsed_time": "0:39:33", "remaining_time": "0:03:17"}
|
| 337 |
+
{"current_steps": 337, "total_steps": 364, "loss": 0.0932, "lr": 3.345532126395579e-07, "epoch": 6.439490445859873, "percentage": 92.58, "elapsed_time": "0:39:39", "remaining_time": "0:03:10"}
|
| 338 |
+
{"current_steps": 338, "total_steps": 364, "loss": 0.0595, "lr": 3.1035704539019384e-07, "epoch": 6.45859872611465, "percentage": 92.86, "elapsed_time": "0:39:43", "remaining_time": "0:03:03"}
|
| 339 |
+
{"current_steps": 339, "total_steps": 364, "loss": 0.0758, "lr": 2.870552305351382e-07, "epoch": 6.477707006369426, "percentage": 93.13, "elapsed_time": "0:39:51", "remaining_time": "0:02:56"}
|
| 340 |
+
{"current_steps": 340, "total_steps": 364, "loss": 0.0668, "lr": 2.646499188279328e-07, "epoch": 6.496815286624204, "percentage": 93.41, "elapsed_time": "0:39:55", "remaining_time": "0:02:49"}
|
| 341 |
+
{"current_steps": 341, "total_steps": 364, "loss": 0.0743, "lr": 2.4314317827503375e-07, "epoch": 6.515923566878981, "percentage": 93.68, "elapsed_time": "0:40:02", "remaining_time": "0:02:42"}
|
| 342 |
+
{"current_steps": 342, "total_steps": 364, "loss": 0.0449, "lr": 2.2253699394493066e-07, "epoch": 6.535031847133758, "percentage": 93.96, "elapsed_time": "0:40:06", "remaining_time": "0:02:34"}
|
| 343 |
+
{"current_steps": 343, "total_steps": 364, "loss": 0.077, "lr": 2.028332677849254e-07, "epoch": 6.554140127388535, "percentage": 94.23, "elapsed_time": "0:40:11", "remaining_time": "0:02:27"}
|
| 344 |
+
{"current_steps": 344, "total_steps": 364, "loss": 0.0824, "lr": 1.840338184455881e-07, "epoch": 6.573248407643312, "percentage": 94.51, "elapsed_time": "0:40:18", "remaining_time": "0:02:20"}
|
| 345 |
+
{"current_steps": 345, "total_steps": 364, "loss": 0.0461, "lr": 1.6614038111289034e-07, "epoch": 6.592356687898089, "percentage": 94.78, "elapsed_time": "0:40:21", "remaining_time": "0:02:13"}
|