neginr commited on
Commit
5f3ed41
·
verified ·
1 Parent(s): 9b6bc0d

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 sha256:8d363db69516d3a73eb162ae54c0d03dce7b60e20d1ed850cf9cb3c6175841f2
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89875c3305eca1f934e2388c50fe87b5e32a51518f1c8be9d60af924d4acb37c
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:ee4338cbfc42f1cd459c58bbdcb79175315c4b74daed71f8c95d48995e8a5bf8
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85db28cddb053b616da8b7d5b7761913303b7328f6c01d7d96a116f1677bdbf8
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fb7074cdda3273945179c0dd283db8e4cf471237a1f5981f7b67b16e0b2c80f
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da9d7d3c5bdf25275efcc151117acb5d52ffe1f0c9a05d4eccefc7063dc61932
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bf17d4a9d6966d5c4ae91119e0e42e4067ddc5c2d80d8ea82eacbe3a60f11be
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a1535d5d3fe62825e3644aa0a59940e6cb7fd3360aec096631c2317ad83015
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -243,3 +243,54 @@
243
  {"current_steps": 243, "total_steps": 364, "loss": 0.1356, "lr": 6.029402827939519e-06, "epoch": 4.643312101910828, "percentage": 66.76, "elapsed_time": "0:27:25", "remaining_time": "0:13:39"}
244
  {"current_steps": 244, "total_steps": 364, "loss": 0.1072, "lr": 5.941412165782645e-06, "epoch": 4.662420382165605, "percentage": 67.03, "elapsed_time": "0:27:29", "remaining_time": "0:13:31"}
245
  {"current_steps": 245, "total_steps": 364, "loss": 0.1199, "lr": 5.853796110591583e-06, "epoch": 4.681528662420382, "percentage": 67.31, "elapsed_time": "0:27:34", "remaining_time": "0:13:23"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
243
  {"current_steps": 243, "total_steps": 364, "loss": 0.1356, "lr": 6.029402827939519e-06, "epoch": 4.643312101910828, "percentage": 66.76, "elapsed_time": "0:27:25", "remaining_time": "0:13:39"}
244
  {"current_steps": 244, "total_steps": 364, "loss": 0.1072, "lr": 5.941412165782645e-06, "epoch": 4.662420382165605, "percentage": 67.03, "elapsed_time": "0:27:29", "remaining_time": "0:13:31"}
245
  {"current_steps": 245, "total_steps": 364, "loss": 0.1199, "lr": 5.853796110591583e-06, "epoch": 4.681528662420382, "percentage": 67.31, "elapsed_time": "0:27:34", "remaining_time": "0:13:23"}
246
+ {"current_steps": 246, "total_steps": 364, "loss": 0.1397, "lr": 5.766562749313309e-06, "epoch": 4.7006369426751595, "percentage": 67.58, "elapsed_time": "0:27:38", "remaining_time": "0:13:15"}
247
+ {"current_steps": 247, "total_steps": 364, "loss": 0.1534, "lr": 5.6797201335722064e-06, "epoch": 4.719745222929936, "percentage": 67.86, "elapsed_time": "0:27:42", "remaining_time": "0:13:07"}
248
+ {"current_steps": 248, "total_steps": 364, "loss": 0.1258, "lr": 5.593276278926912e-06, "epoch": 4.738853503184713, "percentage": 68.13, "elapsed_time": "0:27:49", "remaining_time": "0:13:00"}
249
+ {"current_steps": 249, "total_steps": 364, "loss": 0.1215, "lr": 5.507239164130501e-06, "epoch": 4.757961783439491, "percentage": 68.41, "elapsed_time": "0:27:56", "remaining_time": "0:12:54"}
250
+ {"current_steps": 250, "total_steps": 364, "loss": 0.1421, "lr": 5.421616730394e-06, "epoch": 4.777070063694268, "percentage": 68.68, "elapsed_time": "0:28:01", "remaining_time": "0:12:46"}
251
+ {"current_steps": 251, "total_steps": 364, "loss": 0.1217, "lr": 5.336416880653461e-06, "epoch": 4.796178343949045, "percentage": 68.96, "elapsed_time": "0:28:08", "remaining_time": "0:12:40"}
252
+ {"current_steps": 252, "total_steps": 364, "loss": 0.1253, "lr": 5.251647478840511e-06, "epoch": 4.8152866242038215, "percentage": 69.23, "elapsed_time": "0:28:12", "remaining_time": "0:12:32"}
253
+ {"current_steps": 253, "total_steps": 364, "loss": 0.1049, "lr": 5.167316349156495e-06, "epoch": 4.834394904458598, "percentage": 69.51, "elapsed_time": "0:28:18", "remaining_time": "0:12:25"}
254
+ {"current_steps": 254, "total_steps": 364, "loss": 0.0929, "lr": 5.083431275350312e-06, "epoch": 4.853503184713376, "percentage": 69.78, "elapsed_time": "0:28:23", "remaining_time": "0:12:17"}
255
+ {"current_steps": 255, "total_steps": 364, "loss": 0.1183, "lr": 5.000000000000003e-06, "epoch": 4.872611464968153, "percentage": 70.05, "elapsed_time": "0:28:28", "remaining_time": "0:12:10"}
256
+ {"current_steps": 256, "total_steps": 364, "loss": 0.1385, "lr": 4.917030223798057e-06, "epoch": 4.89171974522293, "percentage": 70.33, "elapsed_time": "0:28:32", "remaining_time": "0:12:02"}
257
+ {"current_steps": 257, "total_steps": 364, "loss": 0.106, "lr": 4.834529604840686e-06, "epoch": 4.9108280254777075, "percentage": 70.6, "elapsed_time": "0:28:36", "remaining_time": "0:11:54"}
258
+ {"current_steps": 258, "total_steps": 364, "loss": 0.096, "lr": 4.7525057579209775e-06, "epoch": 4.929936305732484, "percentage": 70.88, "elapsed_time": "0:28:40", "remaining_time": "0:11:46"}
259
+ {"current_steps": 259, "total_steps": 364, "loss": 0.1009, "lr": 4.670966253826027e-06, "epoch": 4.949044585987261, "percentage": 71.15, "elapsed_time": "0:28:44", "remaining_time": "0:11:39"}
260
+ {"current_steps": 260, "total_steps": 364, "loss": 0.1286, "lr": 4.589918618638173e-06, "epoch": 4.968152866242038, "percentage": 71.43, "elapsed_time": "0:28:48", "remaining_time": "0:11:31"}
261
+ {"current_steps": 261, "total_steps": 364, "loss": 0.1145, "lr": 4.5093703330403385e-06, "epoch": 4.987261146496815, "percentage": 71.7, "elapsed_time": "0:28:53", "remaining_time": "0:11:24"}
262
+ {"current_steps": 262, "total_steps": 364, "loss": 0.1196, "lr": 4.429328831625565e-06, "epoch": 5.006369426751593, "percentage": 71.98, "elapsed_time": "0:30:45", "remaining_time": "0:11:58"}
263
+ {"current_steps": 263, "total_steps": 364, "loss": 0.0876, "lr": 4.349801502210801e-06, "epoch": 5.025477707006369, "percentage": 72.25, "elapsed_time": "0:30:51", "remaining_time": "0:11:50"}
264
+ {"current_steps": 264, "total_steps": 364, "loss": 0.0992, "lr": 4.270795685155001e-06, "epoch": 5.044585987261146, "percentage": 72.53, "elapsed_time": "0:30:56", "remaining_time": "0:11:43"}
265
+ {"current_steps": 265, "total_steps": 364, "loss": 0.0811, "lr": 4.192318672681631e-06, "epoch": 5.063694267515924, "percentage": 72.8, "elapsed_time": "0:31:00", "remaining_time": "0:11:35"}
266
+ {"current_steps": 266, "total_steps": 364, "loss": 0.0765, "lr": 4.1143777082055715e-06, "epoch": 5.082802547770701, "percentage": 73.08, "elapsed_time": "0:31:04", "remaining_time": "0:11:27"}
267
+ {"current_steps": 267, "total_steps": 364, "loss": 0.0993, "lr": 4.036979985664566e-06, "epoch": 5.101910828025478, "percentage": 73.35, "elapsed_time": "0:31:10", "remaining_time": "0:11:19"}
268
+ {"current_steps": 268, "total_steps": 364, "loss": 0.0704, "lr": 3.960132648855226e-06, "epoch": 5.1210191082802545, "percentage": 73.63, "elapsed_time": "0:31:14", "remaining_time": "0:11:11"}
269
+ {"current_steps": 269, "total_steps": 364, "loss": 0.078, "lr": 3.883842790773647e-06, "epoch": 5.140127388535032, "percentage": 73.9, "elapsed_time": "0:31:17", "remaining_time": "0:11:03"}
270
+ {"current_steps": 270, "total_steps": 364, "loss": 0.0901, "lr": 3.8081174529607346e-06, "epoch": 5.159235668789809, "percentage": 74.18, "elapsed_time": "0:31:23", "remaining_time": "0:10:55"}
271
+ {"current_steps": 271, "total_steps": 364, "loss": 0.1005, "lr": 3.732963624852275e-06, "epoch": 5.178343949044586, "percentage": 74.45, "elapsed_time": "0:31:29", "remaining_time": "0:10:48"}
272
+ {"current_steps": 272, "total_steps": 364, "loss": 0.0794, "lr": 3.6583882431338047e-06, "epoch": 5.197452229299363, "percentage": 74.73, "elapsed_time": "0:31:33", "remaining_time": "0:10:40"}
273
+ {"current_steps": 273, "total_steps": 364, "loss": 0.0804, "lr": 3.584398191100341e-06, "epoch": 5.2165605095541405, "percentage": 75.0, "elapsed_time": "0:31:38", "remaining_time": "0:10:32"}
274
+ {"current_steps": 274, "total_steps": 364, "loss": 0.0746, "lr": 3.511000298021098e-06, "epoch": 5.235668789808917, "percentage": 75.27, "elapsed_time": "0:31:43", "remaining_time": "0:10:25"}
275
+ {"current_steps": 275, "total_steps": 364, "loss": 0.0771, "lr": 3.4382013385090985e-06, "epoch": 5.254777070063694, "percentage": 75.55, "elapsed_time": "0:31:47", "remaining_time": "0:10:17"}
276
+ {"current_steps": 276, "total_steps": 364, "loss": 0.0763, "lr": 3.3660080318959043e-06, "epoch": 5.273885350318471, "percentage": 75.82, "elapsed_time": "0:31:51", "remaining_time": "0:10:09"}
277
+ {"current_steps": 277, "total_steps": 364, "loss": 0.0824, "lr": 3.2944270416114256e-06, "epoch": 5.292993630573249, "percentage": 76.1, "elapsed_time": "0:31:55", "remaining_time": "0:10:01"}
278
+ {"current_steps": 278, "total_steps": 364, "loss": 0.0808, "lr": 3.223464974568874e-06, "epoch": 5.312101910828026, "percentage": 76.37, "elapsed_time": "0:31:59", "remaining_time": "0:09:53"}
279
+ {"current_steps": 279, "total_steps": 364, "loss": 0.0669, "lr": 3.153128380554941e-06, "epoch": 5.3312101910828025, "percentage": 76.65, "elapsed_time": "0:32:05", "remaining_time": "0:09:46"}
280
+ {"current_steps": 280, "total_steps": 364, "loss": 0.078, "lr": 3.0834237516252817e-06, "epoch": 5.350318471337579, "percentage": 76.92, "elapsed_time": "0:32:09", "remaining_time": "0:09:38"}
281
+ {"current_steps": 281, "total_steps": 364, "loss": 0.1098, "lr": 3.0143575215052732e-06, "epoch": 5.369426751592357, "percentage": 77.2, "elapsed_time": "0:32:15", "remaining_time": "0:09:31"}
282
+ {"current_steps": 282, "total_steps": 364, "loss": 0.0736, "lr": 2.94593606499619e-06, "epoch": 5.388535031847134, "percentage": 77.47, "elapsed_time": "0:32:20", "remaining_time": "0:09:24"}
283
+ {"current_steps": 283, "total_steps": 364, "loss": 0.0743, "lr": 2.878165697386812e-06, "epoch": 5.407643312101911, "percentage": 77.75, "elapsed_time": "0:32:24", "remaining_time": "0:09:16"}
284
+ {"current_steps": 284, "total_steps": 364, "loss": 0.0973, "lr": 2.8110526738705345e-06, "epoch": 5.426751592356688, "percentage": 78.02, "elapsed_time": "0:32:30", "remaining_time": "0:09:09"}
285
+ {"current_steps": 285, "total_steps": 364, "loss": 0.0863, "lr": 2.7446031889679893e-06, "epoch": 5.445859872611465, "percentage": 78.3, "elapsed_time": "0:32:36", "remaining_time": "0:09:02"}
286
+ {"current_steps": 286, "total_steps": 364, "loss": 0.0827, "lr": 2.678823375955314e-06, "epoch": 5.464968152866242, "percentage": 78.57, "elapsed_time": "0:32:40", "remaining_time": "0:08:54"}
287
+ {"current_steps": 287, "total_steps": 364, "loss": 0.0927, "lr": 2.6137193062980506e-06, "epoch": 5.484076433121019, "percentage": 78.85, "elapsed_time": "0:32:44", "remaining_time": "0:08:47"}
288
+ {"current_steps": 288, "total_steps": 364, "loss": 0.0862, "lr": 2.5492969890907383e-06, "epoch": 5.503184713375796, "percentage": 79.12, "elapsed_time": "0:32:51", "remaining_time": "0:08:40"}
289
+ {"current_steps": 289, "total_steps": 364, "loss": 0.1076, "lr": 2.485562370502279e-06, "epoch": 5.522292993630574, "percentage": 79.4, "elapsed_time": "0:32:59", "remaining_time": "0:08:33"}
290
+ {"current_steps": 290, "total_steps": 364, "loss": 0.0658, "lr": 2.4225213332271203e-06, "epoch": 5.54140127388535, "percentage": 79.67, "elapsed_time": "0:33:07", "remaining_time": "0:08:27"}
291
+ {"current_steps": 291, "total_steps": 364, "loss": 0.0867, "lr": 2.3601796959422585e-06, "epoch": 5.560509554140127, "percentage": 79.95, "elapsed_time": "0:33:11", "remaining_time": "0:08:19"}
292
+ {"current_steps": 292, "total_steps": 364, "loss": 0.0939, "lr": 2.2985432127701945e-06, "epoch": 5.579617834394904, "percentage": 80.22, "elapsed_time": "0:33:17", "remaining_time": "0:08:12"}
293
+ {"current_steps": 293, "total_steps": 364, "loss": 0.0792, "lr": 2.2376175727478346e-06, "epoch": 5.598726114649682, "percentage": 80.49, "elapsed_time": "0:33:22", "remaining_time": "0:08:05"}
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"}