Training in progress, epoch 4
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 sha256:7c0d2cdadf608caf051213b97ed236cb43147450fa6b6d22ef5e25c1967c317a
|
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 sha256:4c65e48f123091f7375a4d6f500a9da3f2669a1f14835175b50a456794749d1d
|
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:eaa188dee364f5962a74ebe63adfcf0de9d253c6e2f33f61686764917f79e3bf
|
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 sha256:88725a48c58a9dea3a6a60568f50128199e25a1263936c76f9e0dc521c50400a
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -240,3 +240,57 @@
|
|
240 |
{"current_steps": 240, "total_steps": 364, "loss": 0.1336, "lr": 6.2955410725937405e-06, "epoch": 4.585987261146497, "percentage": 65.93, "elapsed_time": "0:27:42", "remaining_time": "0:14:18"}
|
241 |
{"current_steps": 241, "total_steps": 364, "loss": 0.1158, "lr": 6.206475453231644e-06, "epoch": 4.6050955414012735, "percentage": 66.21, "elapsed_time": "0:27:48", "remaining_time": "0:14:11"}
|
242 |
{"current_steps": 242, "total_steps": 364, "loss": 0.1252, "lr": 6.117759975539075e-06, "epoch": 4.624203821656051, "percentage": 66.48, "elapsed_time": "0:27:51", "remaining_time": "0:14:02"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
240 |
{"current_steps": 240, "total_steps": 364, "loss": 0.1336, "lr": 6.2955410725937405e-06, "epoch": 4.585987261146497, "percentage": 65.93, "elapsed_time": "0:27:42", "remaining_time": "0:14:18"}
|
241 |
{"current_steps": 241, "total_steps": 364, "loss": 0.1158, "lr": 6.206475453231644e-06, "epoch": 4.6050955414012735, "percentage": 66.21, "elapsed_time": "0:27:48", "remaining_time": "0:14:11"}
|
242 |
{"current_steps": 242, "total_steps": 364, "loss": 0.1252, "lr": 6.117759975539075e-06, "epoch": 4.624203821656051, "percentage": 66.48, "elapsed_time": "0:27:51", "remaining_time": "0:14:02"}
|
243 |
+
{"current_steps": 243, "total_steps": 364, "loss": 0.1481, "lr": 6.029402827939519e-06, "epoch": 4.643312101910828, "percentage": 66.76, "elapsed_time": "0:27:58", "remaining_time": "0:13:55"}
|
244 |
+
{"current_steps": 244, "total_steps": 364, "loss": 0.1233, "lr": 5.941412165782645e-06, "epoch": 4.662420382165605, "percentage": 67.03, "elapsed_time": "0:28:03", "remaining_time": "0:13:47"}
|
245 |
+
{"current_steps": 245, "total_steps": 364, "loss": 0.1145, "lr": 5.853796110591583e-06, "epoch": 4.681528662420382, "percentage": 67.31, "elapsed_time": "0:28:10", "remaining_time": "0:13:41"}
|
246 |
+
{"current_steps": 246, "total_steps": 364, "loss": 0.1095, "lr": 5.766562749313309e-06, "epoch": 4.7006369426751595, "percentage": 67.58, "elapsed_time": "0:28:14", "remaining_time": "0:13:33"}
|
247 |
+
{"current_steps": 247, "total_steps": 364, "loss": 0.1039, "lr": 5.6797201335722064e-06, "epoch": 4.719745222929936, "percentage": 67.86, "elapsed_time": "0:28:18", "remaining_time": "0:13:24"}
|
248 |
+
{"current_steps": 248, "total_steps": 364, "loss": 0.1166, "lr": 5.593276278926912e-06, "epoch": 4.738853503184713, "percentage": 68.13, "elapsed_time": "0:28:28", "remaining_time": "0:13:19"}
|
249 |
+
{"current_steps": 249, "total_steps": 364, "loss": 0.1434, "lr": 5.507239164130501e-06, "epoch": 4.757961783439491, "percentage": 68.41, "elapsed_time": "0:28:34", "remaining_time": "0:13:11"}
|
250 |
+
{"current_steps": 250, "total_steps": 364, "loss": 0.1203, "lr": 5.421616730394e-06, "epoch": 4.777070063694268, "percentage": 68.68, "elapsed_time": "0:28:39", "remaining_time": "0:13:04"}
|
251 |
+
{"current_steps": 251, "total_steps": 364, "loss": 0.1192, "lr": 5.336416880653461e-06, "epoch": 4.796178343949045, "percentage": 68.96, "elapsed_time": "0:28:44", "remaining_time": "0:12:56"}
|
252 |
+
{"current_steps": 252, "total_steps": 364, "loss": 0.1049, "lr": 5.251647478840511e-06, "epoch": 4.8152866242038215, "percentage": 69.23, "elapsed_time": "0:28:51", "remaining_time": "0:12:49"}
|
253 |
+
{"current_steps": 253, "total_steps": 364, "loss": 0.1067, "lr": 5.167316349156495e-06, "epoch": 4.834394904458598, "percentage": 69.51, "elapsed_time": "0:28:55", "remaining_time": "0:12:41"}
|
254 |
+
{"current_steps": 254, "total_steps": 364, "loss": 0.1324, "lr": 5.083431275350312e-06, "epoch": 4.853503184713376, "percentage": 69.78, "elapsed_time": "0:28:59", "remaining_time": "0:12:33"}
|
255 |
+
{"current_steps": 255, "total_steps": 364, "loss": 0.1016, "lr": 5.000000000000003e-06, "epoch": 4.872611464968153, "percentage": 70.05, "elapsed_time": "0:29:03", "remaining_time": "0:12:25"}
|
256 |
+
{"current_steps": 256, "total_steps": 364, "loss": 0.1238, "lr": 4.917030223798057e-06, "epoch": 4.89171974522293, "percentage": 70.33, "elapsed_time": "0:29:07", "remaining_time": "0:12:17"}
|
257 |
+
{"current_steps": 257, "total_steps": 364, "loss": 0.1068, "lr": 4.834529604840686e-06, "epoch": 4.9108280254777075, "percentage": 70.6, "elapsed_time": "0:29:11", "remaining_time": "0:12:09"}
|
258 |
+
{"current_steps": 258, "total_steps": 364, "loss": 0.1093, "lr": 4.7525057579209775e-06, "epoch": 4.929936305732484, "percentage": 70.88, "elapsed_time": "0:29:15", "remaining_time": "0:12:01"}
|
259 |
+
{"current_steps": 259, "total_steps": 364, "loss": 0.1179, "lr": 4.670966253826027e-06, "epoch": 4.949044585987261, "percentage": 71.15, "elapsed_time": "0:29:19", "remaining_time": "0:11:53"}
|
260 |
+
{"current_steps": 260, "total_steps": 364, "loss": 0.1397, "lr": 4.589918618638173e-06, "epoch": 4.968152866242038, "percentage": 71.43, "elapsed_time": "0:29:24", "remaining_time": "0:11:45"}
|
261 |
+
{"current_steps": 261, "total_steps": 364, "loss": 0.121, "lr": 4.5093703330403385e-06, "epoch": 4.987261146496815, "percentage": 71.7, "elapsed_time": "0:29:28", "remaining_time": "0:11:38"}
|
262 |
+
{"current_steps": 262, "total_steps": 364, "loss": 0.1088, "lr": 4.429328831625565e-06, "epoch": 5.006369426751593, "percentage": 71.98, "elapsed_time": "0:31:24", "remaining_time": "0:12:13"}
|
263 |
+
{"current_steps": 263, "total_steps": 364, "loss": 0.0692, "lr": 4.349801502210801e-06, "epoch": 5.025477707006369, "percentage": 72.25, "elapsed_time": "0:31:28", "remaining_time": "0:12:05"}
|
264 |
+
{"current_steps": 264, "total_steps": 364, "loss": 0.1, "lr": 4.270795685155001e-06, "epoch": 5.044585987261146, "percentage": 72.53, "elapsed_time": "0:31:34", "remaining_time": "0:11:57"}
|
265 |
+
{"current_steps": 265, "total_steps": 364, "loss": 0.088, "lr": 4.192318672681631e-06, "epoch": 5.063694267515924, "percentage": 72.8, "elapsed_time": "0:31:37", "remaining_time": "0:11:49"}
|
266 |
+
{"current_steps": 266, "total_steps": 364, "loss": 0.0632, "lr": 4.1143777082055715e-06, "epoch": 5.082802547770701, "percentage": 73.08, "elapsed_time": "0:31:41", "remaining_time": "0:11:40"}
|
267 |
+
{"current_steps": 267, "total_steps": 364, "loss": 0.0785, "lr": 4.036979985664566e-06, "epoch": 5.101910828025478, "percentage": 73.35, "elapsed_time": "0:31:45", "remaining_time": "0:11:32"}
|
268 |
+
{"current_steps": 268, "total_steps": 364, "loss": 0.0807, "lr": 3.960132648855226e-06, "epoch": 5.1210191082802545, "percentage": 73.63, "elapsed_time": "0:31:49", "remaining_time": "0:11:23"}
|
269 |
+
{"current_steps": 269, "total_steps": 364, "loss": 0.0743, "lr": 3.883842790773647e-06, "epoch": 5.140127388535032, "percentage": 73.9, "elapsed_time": "0:31:52", "remaining_time": "0:11:15"}
|
270 |
+
{"current_steps": 270, "total_steps": 364, "loss": 0.083, "lr": 3.8081174529607346e-06, "epoch": 5.159235668789809, "percentage": 74.18, "elapsed_time": "0:31:58", "remaining_time": "0:11:07"}
|
271 |
+
{"current_steps": 271, "total_steps": 364, "loss": 0.0688, "lr": 3.732963624852275e-06, "epoch": 5.178343949044586, "percentage": 74.45, "elapsed_time": "0:32:01", "remaining_time": "0:10:59"}
|
272 |
+
{"current_steps": 272, "total_steps": 364, "loss": 0.0732, "lr": 3.6583882431338047e-06, "epoch": 5.197452229299363, "percentage": 74.73, "elapsed_time": "0:32:06", "remaining_time": "0:10:51"}
|
273 |
+
{"current_steps": 273, "total_steps": 364, "loss": 0.0794, "lr": 3.584398191100341e-06, "epoch": 5.2165605095541405, "percentage": 75.0, "elapsed_time": "0:32:14", "remaining_time": "0:10:44"}
|
274 |
+
{"current_steps": 274, "total_steps": 364, "loss": 0.0987, "lr": 3.511000298021098e-06, "epoch": 5.235668789808917, "percentage": 75.27, "elapsed_time": "0:32:18", "remaining_time": "0:10:36"}
|
275 |
+
{"current_steps": 275, "total_steps": 364, "loss": 0.0519, "lr": 3.4382013385090985e-06, "epoch": 5.254777070063694, "percentage": 75.55, "elapsed_time": "0:32:21", "remaining_time": "0:10:28"}
|
276 |
+
{"current_steps": 276, "total_steps": 364, "loss": 0.1122, "lr": 3.3660080318959043e-06, "epoch": 5.273885350318471, "percentage": 75.82, "elapsed_time": "0:32:26", "remaining_time": "0:10:20"}
|
277 |
+
{"current_steps": 277, "total_steps": 364, "loss": 0.074, "lr": 3.2944270416114256e-06, "epoch": 5.292993630573249, "percentage": 76.1, "elapsed_time": "0:32:30", "remaining_time": "0:10:12"}
|
278 |
+
{"current_steps": 278, "total_steps": 364, "loss": 0.0714, "lr": 3.223464974568874e-06, "epoch": 5.312101910828026, "percentage": 76.37, "elapsed_time": "0:32:35", "remaining_time": "0:10:04"}
|
279 |
+
{"current_steps": 279, "total_steps": 364, "loss": 0.0709, "lr": 3.153128380554941e-06, "epoch": 5.3312101910828025, "percentage": 76.65, "elapsed_time": "0:32:42", "remaining_time": "0:09:57"}
|
280 |
+
{"current_steps": 280, "total_steps": 364, "loss": 0.0888, "lr": 3.0834237516252817e-06, "epoch": 5.350318471337579, "percentage": 76.92, "elapsed_time": "0:32:47", "remaining_time": "0:09:50"}
|
281 |
+
{"current_steps": 281, "total_steps": 364, "loss": 0.0738, "lr": 3.0143575215052732e-06, "epoch": 5.369426751592357, "percentage": 77.2, "elapsed_time": "0:32:50", "remaining_time": "0:09:42"}
|
282 |
+
{"current_steps": 282, "total_steps": 364, "loss": 0.1008, "lr": 2.94593606499619e-06, "epoch": 5.388535031847134, "percentage": 77.47, "elapsed_time": "0:32:57", "remaining_time": "0:09:35"}
|
283 |
+
{"current_steps": 283, "total_steps": 364, "loss": 0.0812, "lr": 2.878165697386812e-06, "epoch": 5.407643312101911, "percentage": 77.75, "elapsed_time": "0:33:02", "remaining_time": "0:09:27"}
|
284 |
+
{"current_steps": 284, "total_steps": 364, "loss": 0.0869, "lr": 2.8110526738705345e-06, "epoch": 5.426751592356688, "percentage": 78.02, "elapsed_time": "0:33:06", "remaining_time": "0:09:19"}
|
285 |
+
{"current_steps": 285, "total_steps": 364, "loss": 0.0931, "lr": 2.7446031889679893e-06, "epoch": 5.445859872611465, "percentage": 78.3, "elapsed_time": "0:33:14", "remaining_time": "0:09:12"}
|
286 |
+
{"current_steps": 286, "total_steps": 364, "loss": 0.0656, "lr": 2.678823375955314e-06, "epoch": 5.464968152866242, "percentage": 78.57, "elapsed_time": "0:33:19", "remaining_time": "0:09:05"}
|
287 |
+
{"current_steps": 287, "total_steps": 364, "loss": 0.0954, "lr": 2.6137193062980506e-06, "epoch": 5.484076433121019, "percentage": 78.85, "elapsed_time": "0:33:23", "remaining_time": "0:08:57"}
|
288 |
+
{"current_steps": 288, "total_steps": 364, "loss": 0.0701, "lr": 2.5492969890907383e-06, "epoch": 5.503184713375796, "percentage": 79.12, "elapsed_time": "0:33:28", "remaining_time": "0:08:50"}
|
289 |
+
{"current_steps": 289, "total_steps": 364, "loss": 0.1008, "lr": 2.485562370502279e-06, "epoch": 5.522292993630574, "percentage": 79.4, "elapsed_time": "0:33:34", "remaining_time": "0:08:42"}
|
290 |
+
{"current_steps": 290, "total_steps": 364, "loss": 0.0752, "lr": 2.4225213332271203e-06, "epoch": 5.54140127388535, "percentage": 79.67, "elapsed_time": "0:33:40", "remaining_time": "0:08:35"}
|
291 |
+
{"current_steps": 291, "total_steps": 364, "loss": 0.09, "lr": 2.3601796959422585e-06, "epoch": 5.560509554140127, "percentage": 79.95, "elapsed_time": "0:33:47", "remaining_time": "0:08:28"}
|
292 |
+
{"current_steps": 292, "total_steps": 364, "loss": 0.1096, "lr": 2.2985432127701945e-06, "epoch": 5.579617834394904, "percentage": 80.22, "elapsed_time": "0:33:53", "remaining_time": "0:08:21"}
|
293 |
+
{"current_steps": 293, "total_steps": 364, "loss": 0.0831, "lr": 2.2376175727478346e-06, "epoch": 5.598726114649682, "percentage": 80.49, "elapsed_time": "0:33:57", "remaining_time": "0:08:13"}
|
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"}
|