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 sha256:4a618fd7df71777db8b30462dee71dda182f9c5d2aa4479e7abc59e1ba2508ff
|
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:ce0ad9fe06eee03492a83bfe5a79b5d7c4f2c5a0530acdaa9594d4be56991f69
|
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 sha256:0043d25a659b9b738fd5e91f956940fae6da582c4af4c8a1371a4efb76f49749
|
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:bc32dbb60aca5efd4c8953f1f0d2c647e4b9f184410ff66d1de9b1e96d6cf46f
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -271,3 +271,55 @@
|
|
271 |
{"current_steps": 271, "total_steps": 364, "loss": 0.2535, "lr": 3.732963624852274e-08, "epoch": 5.178343949044586, "percentage": 74.45, "elapsed_time": "1:09:11", "remaining_time": "0:23:44"}
|
272 |
{"current_steps": 272, "total_steps": 364, "loss": 0.2587, "lr": 3.658388243133804e-08, "epoch": 5.197452229299363, "percentage": 74.73, "elapsed_time": "1:09:22", "remaining_time": "0:23:27"}
|
273 |
{"current_steps": 273, "total_steps": 364, "loss": 0.2452, "lr": 3.584398191100341e-08, "epoch": 5.2165605095541405, "percentage": 75.0, "elapsed_time": "1:09:32", "remaining_time": "0:23:10"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
271 |
{"current_steps": 271, "total_steps": 364, "loss": 0.2535, "lr": 3.732963624852274e-08, "epoch": 5.178343949044586, "percentage": 74.45, "elapsed_time": "1:09:11", "remaining_time": "0:23:44"}
|
272 |
{"current_steps": 272, "total_steps": 364, "loss": 0.2587, "lr": 3.658388243133804e-08, "epoch": 5.197452229299363, "percentage": 74.73, "elapsed_time": "1:09:22", "remaining_time": "0:23:27"}
|
273 |
{"current_steps": 273, "total_steps": 364, "loss": 0.2452, "lr": 3.584398191100341e-08, "epoch": 5.2165605095541405, "percentage": 75.0, "elapsed_time": "1:09:32", "remaining_time": "0:23:10"}
|
274 |
+
{"current_steps": 274, "total_steps": 364, "loss": 0.2432, "lr": 3.5110002980210973e-08, "epoch": 5.235668789808917, "percentage": 75.27, "elapsed_time": "1:09:43", "remaining_time": "0:22:54"}
|
275 |
+
{"current_steps": 275, "total_steps": 364, "loss": 0.2431, "lr": 3.438201338509098e-08, "epoch": 5.254777070063694, "percentage": 75.55, "elapsed_time": "1:09:55", "remaining_time": "0:22:37"}
|
276 |
+
{"current_steps": 276, "total_steps": 364, "loss": 0.2545, "lr": 3.366008031895904e-08, "epoch": 5.273885350318471, "percentage": 75.82, "elapsed_time": "1:10:07", "remaining_time": "0:22:21"}
|
277 |
+
{"current_steps": 277, "total_steps": 364, "loss": 0.2396, "lr": 3.294427041611425e-08, "epoch": 5.292993630573249, "percentage": 76.1, "elapsed_time": "1:10:22", "remaining_time": "0:22:06"}
|
278 |
+
{"current_steps": 278, "total_steps": 364, "loss": 0.2477, "lr": 3.223464974568874e-08, "epoch": 5.312101910828026, "percentage": 76.37, "elapsed_time": "1:10:33", "remaining_time": "0:21:49"}
|
279 |
+
{"current_steps": 279, "total_steps": 364, "loss": 0.2591, "lr": 3.15312838055494e-08, "epoch": 5.3312101910828025, "percentage": 76.65, "elapsed_time": "1:10:47", "remaining_time": "0:21:33"}
|
280 |
+
{"current_steps": 280, "total_steps": 364, "loss": 0.2515, "lr": 3.083423751625281e-08, "epoch": 5.350318471337579, "percentage": 76.92, "elapsed_time": "1:10:59", "remaining_time": "0:21:17"}
|
281 |
+
{"current_steps": 281, "total_steps": 364, "loss": 0.2609, "lr": 3.014357521505273e-08, "epoch": 5.369426751592357, "percentage": 77.2, "elapsed_time": "1:11:12", "remaining_time": "0:21:01"}
|
282 |
+
{"current_steps": 282, "total_steps": 364, "loss": 0.2378, "lr": 2.9459360649961896e-08, "epoch": 5.388535031847134, "percentage": 77.47, "elapsed_time": "1:11:22", "remaining_time": "0:20:45"}
|
283 |
+
{"current_steps": 283, "total_steps": 364, "loss": 0.2542, "lr": 2.878165697386812e-08, "epoch": 5.407643312101911, "percentage": 77.75, "elapsed_time": "1:11:35", "remaining_time": "0:20:29"}
|
284 |
+
{"current_steps": 284, "total_steps": 364, "loss": 0.2411, "lr": 2.811052673870534e-08, "epoch": 5.426751592356688, "percentage": 78.02, "elapsed_time": "1:11:43", "remaining_time": "0:20:12"}
|
285 |
+
{"current_steps": 285, "total_steps": 364, "loss": 0.2483, "lr": 2.7446031889679888e-08, "epoch": 5.445859872611465, "percentage": 78.3, "elapsed_time": "1:11:57", "remaining_time": "0:19:56"}
|
286 |
+
{"current_steps": 286, "total_steps": 364, "loss": 0.2594, "lr": 2.6788233759553138e-08, "epoch": 5.464968152866242, "percentage": 78.57, "elapsed_time": "1:12:09", "remaining_time": "0:19:40"}
|
287 |
+
{"current_steps": 287, "total_steps": 364, "loss": 0.2424, "lr": 2.61371930629805e-08, "epoch": 5.484076433121019, "percentage": 78.85, "elapsed_time": "1:12:18", "remaining_time": "0:19:23"}
|
288 |
+
{"current_steps": 288, "total_steps": 364, "loss": 0.2637, "lr": 2.549296989090738e-08, "epoch": 5.503184713375796, "percentage": 79.12, "elapsed_time": "1:12:33", "remaining_time": "0:19:08"}
|
289 |
+
{"current_steps": 289, "total_steps": 364, "loss": 0.2656, "lr": 2.4855623705022788e-08, "epoch": 5.522292993630574, "percentage": 79.4, "elapsed_time": "1:12:47", "remaining_time": "0:18:53"}
|
290 |
+
{"current_steps": 290, "total_steps": 364, "loss": 0.2625, "lr": 2.4225213332271198e-08, "epoch": 5.54140127388535, "percentage": 79.67, "elapsed_time": "1:13:03", "remaining_time": "0:18:38"}
|
291 |
+
{"current_steps": 291, "total_steps": 364, "loss": 0.2534, "lr": 2.3601796959422582e-08, "epoch": 5.560509554140127, "percentage": 79.95, "elapsed_time": "1:13:18", "remaining_time": "0:18:23"}
|
292 |
+
{"current_steps": 292, "total_steps": 364, "loss": 0.2609, "lr": 2.2985432127701942e-08, "epoch": 5.579617834394904, "percentage": 80.22, "elapsed_time": "1:13:30", "remaining_time": "0:18:07"}
|
293 |
+
{"current_steps": 293, "total_steps": 364, "loss": 0.2586, "lr": 2.237617572747834e-08, "epoch": 5.598726114649682, "percentage": 80.49, "elapsed_time": "1:13:43", "remaining_time": "0:17:51"}
|
294 |
+
{"current_steps": 294, "total_steps": 364, "loss": 0.2514, "lr": 2.1774083993013716e-08, "epoch": 5.617834394904459, "percentage": 80.77, "elapsed_time": "1:13:55", "remaining_time": "0:17:36"}
|
295 |
+
{"current_steps": 295, "total_steps": 364, "loss": 0.2517, "lr": 2.117921249727258e-08, "epoch": 5.6369426751592355, "percentage": 81.04, "elapsed_time": "1:14:09", "remaining_time": "0:17:20"}
|
296 |
+
{"current_steps": 296, "total_steps": 364, "loss": 0.2571, "lr": 2.0591616146792702e-08, "epoch": 5.656050955414012, "percentage": 81.32, "elapsed_time": "1:14:23", "remaining_time": "0:17:05"}
|
297 |
+
{"current_steps": 297, "total_steps": 364, "loss": 0.2699, "lr": 2.001134917661713e-08, "epoch": 5.67515923566879, "percentage": 81.59, "elapsed_time": "1:14:36", "remaining_time": "0:16:49"}
|
298 |
+
{"current_steps": 298, "total_steps": 364, "loss": 0.2607, "lr": 1.9438465145288373e-08, "epoch": 5.694267515923567, "percentage": 81.87, "elapsed_time": "1:14:53", "remaining_time": "0:16:35"}
|
299 |
+
{"current_steps": 299, "total_steps": 364, "loss": 0.2545, "lr": 1.8873016929904938e-08, "epoch": 5.713375796178344, "percentage": 82.14, "elapsed_time": "1:15:07", "remaining_time": "0:16:19"}
|
300 |
+
{"current_steps": 300, "total_steps": 364, "loss": 0.2441, "lr": 1.831505672124083e-08, "epoch": 5.732484076433121, "percentage": 82.42, "elapsed_time": "1:15:22", "remaining_time": "0:16:04"}
|
301 |
+
{"current_steps": 301, "total_steps": 364, "loss": 0.2498, "lr": 1.776463601892825e-08, "epoch": 5.751592356687898, "percentage": 82.69, "elapsed_time": "1:15:34", "remaining_time": "0:15:49"}
|
302 |
+
{"current_steps": 302, "total_steps": 364, "loss": 0.2561, "lr": 1.7221805626704277e-08, "epoch": 5.770700636942675, "percentage": 82.97, "elapsed_time": "1:15:49", "remaining_time": "0:15:33"}
|
303 |
+
{"current_steps": 303, "total_steps": 364, "loss": 0.2507, "lr": 1.6686615647721637e-08, "epoch": 5.789808917197452, "percentage": 83.24, "elapsed_time": "1:16:01", "remaining_time": "0:15:18"}
|
304 |
+
{"current_steps": 304, "total_steps": 364, "loss": 0.2591, "lr": 1.615911547992426e-08, "epoch": 5.80891719745223, "percentage": 83.52, "elapsed_time": "1:16:16", "remaining_time": "0:15:03"}
|
305 |
+
{"current_steps": 305, "total_steps": 364, "loss": 0.2487, "lr": 1.5639353811487744e-08, "epoch": 5.828025477707007, "percentage": 83.79, "elapsed_time": "1:16:32", "remaining_time": "0:14:48"}
|
306 |
+
{"current_steps": 306, "total_steps": 364, "loss": 0.2514, "lr": 1.5127378616325602e-08, "epoch": 5.8471337579617835, "percentage": 84.07, "elapsed_time": "1:16:45", "remaining_time": "0:14:32"}
|
307 |
+
{"current_steps": 307, "total_steps": 364, "loss": 0.2629, "lr": 1.4623237149661139e-08, "epoch": 5.86624203821656, "percentage": 84.34, "elapsed_time": "1:17:01", "remaining_time": "0:14:18"}
|
308 |
+
{"current_steps": 308, "total_steps": 364, "loss": 0.2388, "lr": 1.4126975943665842e-08, "epoch": 5.885350318471337, "percentage": 84.62, "elapsed_time": "1:17:17", "remaining_time": "0:14:03"}
|
309 |
+
{"current_steps": 309, "total_steps": 364, "loss": 0.2591, "lr": 1.3638640803164514e-08, "epoch": 5.904458598726115, "percentage": 84.89, "elapsed_time": "1:17:32", "remaining_time": "0:13:48"}
|
310 |
+
{"current_steps": 310, "total_steps": 364, "loss": 0.2549, "lr": 1.3158276801407431e-08, "epoch": 5.923566878980892, "percentage": 85.16, "elapsed_time": "1:17:47", "remaining_time": "0:13:32"}
|
311 |
+
{"current_steps": 311, "total_steps": 364, "loss": 0.2552, "lr": 1.268592827591014e-08, "epoch": 5.942675159235669, "percentage": 85.44, "elapsed_time": "1:17:59", "remaining_time": "0:13:17"}
|
312 |
+
{"current_steps": 312, "total_steps": 364, "loss": 0.2561, "lr": 1.2221638824361069e-08, "epoch": 5.961783439490446, "percentage": 85.71, "elapsed_time": "1:18:14", "remaining_time": "0:13:02"}
|
313 |
+
{"current_steps": 313, "total_steps": 364, "loss": 0.2494, "lr": 1.1765451300597573e-08, "epoch": 5.980891719745223, "percentage": 85.99, "elapsed_time": "1:18:26", "remaining_time": "0:12:46"}
|
314 |
+
{"current_steps": 314, "total_steps": 364, "loss": 0.2677, "lr": 1.131740781065037e-08, "epoch": 6.0, "percentage": 86.26, "elapsed_time": "1:18:38", "remaining_time": "0:12:31"}
|
315 |
+
{"current_steps": 315, "total_steps": 364, "loss": 0.2492, "lr": 1.0877549708857225e-08, "epoch": 6.019108280254777, "percentage": 86.54, "elapsed_time": "1:20:33", "remaining_time": "0:12:31"}
|
316 |
+
{"current_steps": 316, "total_steps": 364, "loss": 0.2573, "lr": 1.0445917594046071e-08, "epoch": 6.038216560509555, "percentage": 86.81, "elapsed_time": "1:20:46", "remaining_time": "0:12:16"}
|
317 |
+
{"current_steps": 317, "total_steps": 364, "loss": 0.2478, "lr": 1.0022551305787563e-08, "epoch": 6.057324840764331, "percentage": 87.09, "elapsed_time": "1:21:00", "remaining_time": "0:12:00"}
|
318 |
+
{"current_steps": 318, "total_steps": 364, "loss": 0.2616, "lr": 9.607489920717981e-09, "epoch": 6.076433121019108, "percentage": 87.36, "elapsed_time": "1:21:14", "remaining_time": "0:11:45"}
|
319 |
+
{"current_steps": 319, "total_steps": 364, "loss": 0.23, "lr": 9.200771748932512e-09, "epoch": 6.095541401273885, "percentage": 87.64, "elapsed_time": "1:21:31", "remaining_time": "0:11:30"}
|
320 |
+
{"current_steps": 320, "total_steps": 364, "loss": 0.2423, "lr": 8.802434330449127e-09, "epoch": 6.114649681528663, "percentage": 87.91, "elapsed_time": "1:21:46", "remaining_time": "0:11:14"}
|
321 |
+
{"current_steps": 321, "total_steps": 364, "loss": 0.2506, "lr": 8.412514431743656e-09, "epoch": 6.13375796178344, "percentage": 88.19, "elapsed_time": "1:22:00", "remaining_time": "0:10:59"}
|
322 |
+
{"current_steps": 322, "total_steps": 364, "loss": 0.2518, "lr": 8.031048042356392e-09, "epoch": 6.1528662420382165, "percentage": 88.46, "elapsed_time": "1:22:12", "remaining_time": "0:10:43"}
|
323 |
+
{"current_steps": 323, "total_steps": 364, "loss": 0.2571, "lr": 7.65807037157007e-09, "epoch": 6.171974522292993, "percentage": 88.74, "elapsed_time": "1:22:27", "remaining_time": "0:10:28"}
|
324 |
+
{"current_steps": 324, "total_steps": 364, "loss": 0.2492, "lr": 7.293615845160195e-09, "epoch": 6.191082802547771, "percentage": 89.01, "elapsed_time": "1:22:41", "remaining_time": "0:10:12"}
|
325 |
+
{"current_steps": 325, "total_steps": 364, "loss": 0.2486, "lr": 6.9377181022174604e-09, "epoch": 6.210191082802548, "percentage": 89.29, "elapsed_time": "1:22:56", "remaining_time": "0:09:57"}
|