Training in progress, step 366
Browse files
model-00001-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4986211280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cb4bb9cebc726040540b890e8f7a5bb43a156a267fdbe3c3c537195fa943457
|
3 |
size 4986211280
|
model-00002-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4954847344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d5e2c9e3535152f4f4194a62fa20733934f9b65f14b1e16144733dc04ea9dc5
|
3 |
size 4954847344
|
model-00003-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4954847392
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff2605f70dd92215547d63f5e85ae848ea12e50f3d73b99f132f924bd004d589
|
3 |
size 4954847392
|
model-00004-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4954847392
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99bcf5b75b9c29988a11d20de3624bbf190ac5e85e55f3b37c34699e66417abb
|
3 |
size 4954847392
|
model-00005-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4954847392
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87c5f4a402a858c0eef4ed559532ee7263924e7b9012ebaa4e2696ddd0afba4c
|
3 |
size 4954847392
|
model-00006-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4734533160
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd35a98376c546642ef4873dafedb0e6e91748b9cb7c97e786c73713b92efefb
|
3 |
size 4734533160
|
trainer_log.jsonl
CHANGED
@@ -303,3 +303,66 @@
|
|
303 |
{"current_steps": 302, "total_steps": 366, "loss": 0.3962, "lr": 9.325824311285564e-07, "epoch": 2.4583901773533423, "percentage": 82.51, "elapsed_time": "6:37:09", "remaining_time": "1:24:09"}
|
304 |
{"current_steps": 303, "total_steps": 366, "loss": 0.4263, "lr": 9.050006215123419e-07, "epoch": 2.466575716234652, "percentage": 82.79, "elapsed_time": "6:38:27", "remaining_time": "1:22:50"}
|
305 |
{"current_steps": 304, "total_steps": 366, "loss": 0.4052, "lr": 8.777921982911996e-07, "epoch": 2.4747612551159617, "percentage": 83.06, "elapsed_time": "6:39:33", "remaining_time": "1:21:29"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
303 |
{"current_steps": 302, "total_steps": 366, "loss": 0.3962, "lr": 9.325824311285564e-07, "epoch": 2.4583901773533423, "percentage": 82.51, "elapsed_time": "6:37:09", "remaining_time": "1:24:09"}
|
304 |
{"current_steps": 303, "total_steps": 366, "loss": 0.4263, "lr": 9.050006215123419e-07, "epoch": 2.466575716234652, "percentage": 82.79, "elapsed_time": "6:38:27", "remaining_time": "1:22:50"}
|
305 |
{"current_steps": 304, "total_steps": 366, "loss": 0.4052, "lr": 8.777921982911996e-07, "epoch": 2.4747612551159617, "percentage": 83.06, "elapsed_time": "6:39:33", "remaining_time": "1:21:29"}
|
306 |
+
{"current_steps": 305, "total_steps": 366, "loss": 0.4034, "lr": 8.509596423580712e-07, "epoch": 2.4829467939972716, "percentage": 83.33, "elapsed_time": "6:40:46", "remaining_time": "1:20:09"}
|
307 |
+
{"current_steps": 306, "total_steps": 366, "loss": 0.3882, "lr": 8.245054003339247e-07, "epoch": 2.491132332878581, "percentage": 83.61, "elapsed_time": "6:41:45", "remaining_time": "1:18:46"}
|
308 |
+
{"current_steps": 307, "total_steps": 366, "loss": 0.4005, "lr": 7.984318843446593e-07, "epoch": 2.499317871759891, "percentage": 83.88, "elapsed_time": "6:43:26", "remaining_time": "1:17:32"}
|
309 |
+
{"current_steps": 308, "total_steps": 366, "loss": 0.4003, "lr": 7.727414718011706e-07, "epoch": 2.5075034106412004, "percentage": 84.15, "elapsed_time": "6:45:04", "remaining_time": "1:16:16"}
|
310 |
+
{"current_steps": 309, "total_steps": 366, "loss": 0.4158, "lr": 7.474365051825749e-07, "epoch": 2.5156889495225103, "percentage": 84.43, "elapsed_time": "6:46:25", "remaining_time": "1:14:58"}
|
311 |
+
{"current_steps": 310, "total_steps": 366, "loss": 0.3879, "lr": 7.225192918226215e-07, "epoch": 2.52387448840382, "percentage": 84.7, "elapsed_time": "6:47:30", "remaining_time": "1:13:36"}
|
312 |
+
{"current_steps": 311, "total_steps": 366, "loss": 0.4158, "lr": 6.979921036993042e-07, "epoch": 2.5320600272851297, "percentage": 84.97, "elapsed_time": "6:48:59", "remaining_time": "1:12:19"}
|
313 |
+
{"current_steps": 312, "total_steps": 366, "loss": 0.415, "lr": 6.738571772276997e-07, "epoch": 2.540245566166439, "percentage": 85.25, "elapsed_time": "6:50:21", "remaining_time": "1:11:01"}
|
314 |
+
{"current_steps": 313, "total_steps": 366, "loss": 0.3929, "lr": 6.501167130560515e-07, "epoch": 2.548431105047749, "percentage": 85.52, "elapsed_time": "6:51:34", "remaining_time": "1:09:41"}
|
315 |
+
{"current_steps": 314, "total_steps": 366, "loss": 0.4123, "lr": 6.267728758651131e-07, "epoch": 2.5566166439290585, "percentage": 85.79, "elapsed_time": "6:52:53", "remaining_time": "1:08:22"}
|
316 |
+
{"current_steps": 315, "total_steps": 366, "loss": 0.3821, "lr": 6.038277941707671e-07, "epoch": 2.5648021828103684, "percentage": 86.07, "elapsed_time": "6:53:55", "remaining_time": "1:07:01"}
|
317 |
+
{"current_steps": 316, "total_steps": 366, "loss": 0.4023, "lr": 5.812835601299438e-07, "epoch": 2.572987721691678, "percentage": 86.34, "elapsed_time": "6:55:06", "remaining_time": "1:05:40"}
|
318 |
+
{"current_steps": 317, "total_steps": 366, "loss": 0.4124, "lr": 5.591422293498633e-07, "epoch": 2.581173260572988, "percentage": 86.61, "elapsed_time": "6:56:27", "remaining_time": "1:04:22"}
|
319 |
+
{"current_steps": 318, "total_steps": 366, "loss": 0.3929, "lr": 5.374058207005945e-07, "epoch": 2.5893587994542973, "percentage": 86.89, "elapsed_time": "6:57:42", "remaining_time": "1:03:02"}
|
320 |
+
{"current_steps": 319, "total_steps": 366, "loss": 0.3859, "lr": 5.160763161309768e-07, "epoch": 2.597544338335607, "percentage": 87.16, "elapsed_time": "6:58:49", "remaining_time": "1:01:42"}
|
321 |
+
{"current_steps": 320, "total_steps": 366, "loss": 0.4166, "lr": 4.951556604879049e-07, "epoch": 2.6057298772169166, "percentage": 87.43, "elapsed_time": "7:00:07", "remaining_time": "1:00:23"}
|
322 |
+
{"current_steps": 321, "total_steps": 366, "loss": 0.3857, "lr": 4.7464576133899043e-07, "epoch": 2.6139154160982265, "percentage": 87.7, "elapsed_time": "7:01:14", "remaining_time": "0:59:03"}
|
323 |
+
{"current_steps": 322, "total_steps": 366, "loss": 0.4134, "lr": 4.545484887986368e-07, "epoch": 2.622100954979536, "percentage": 87.98, "elapsed_time": "7:02:22", "remaining_time": "0:57:42"}
|
324 |
+
{"current_steps": 323, "total_steps": 366, "loss": 0.4038, "lr": 4.348656753575092e-07, "epoch": 2.630286493860846, "percentage": 88.25, "elapsed_time": "7:03:42", "remaining_time": "0:56:24"}
|
325 |
+
{"current_steps": 324, "total_steps": 366, "loss": 0.4126, "lr": 4.1559911571545544e-07, "epoch": 2.6384720327421554, "percentage": 88.52, "elapsed_time": "7:04:53", "remaining_time": "0:55:04"}
|
326 |
+
{"current_steps": 325, "total_steps": 366, "loss": 0.4049, "lr": 3.9675056661785563e-07, "epoch": 2.6466575716234653, "percentage": 88.8, "elapsed_time": "7:06:11", "remaining_time": "0:53:45"}
|
327 |
+
{"current_steps": 326, "total_steps": 366, "loss": 0.393, "lr": 3.783217466954503e-07, "epoch": 2.6548431105047747, "percentage": 89.07, "elapsed_time": "7:07:26", "remaining_time": "0:52:26"}
|
328 |
+
{"current_steps": 327, "total_steps": 366, "loss": 0.4036, "lr": 3.603143363076217e-07, "epoch": 2.6630286493860846, "percentage": 89.34, "elapsed_time": "7:08:38", "remaining_time": "0:51:07"}
|
329 |
+
{"current_steps": 328, "total_steps": 366, "loss": 0.3863, "lr": 3.427299773891868e-07, "epoch": 2.6712141882673945, "percentage": 89.62, "elapsed_time": "7:09:23", "remaining_time": "0:49:44"}
|
330 |
+
{"current_steps": 329, "total_steps": 366, "loss": 0.3967, "lr": 3.255702733006766e-07, "epoch": 2.679399727148704, "percentage": 89.89, "elapsed_time": "7:10:41", "remaining_time": "0:48:26"}
|
331 |
+
{"current_steps": 330, "total_steps": 366, "loss": 0.3953, "lr": 3.088367886821481e-07, "epoch": 2.6875852660300135, "percentage": 90.16, "elapsed_time": "7:11:59", "remaining_time": "0:47:07"}
|
332 |
+
{"current_steps": 331, "total_steps": 366, "loss": 0.4203, "lr": 2.925310493105099e-07, "epoch": 2.6957708049113234, "percentage": 90.44, "elapsed_time": "7:13:26", "remaining_time": "0:45:49"}
|
333 |
+
{"current_steps": 332, "total_steps": 366, "loss": 0.4053, "lr": 2.7665454196040665e-07, "epoch": 2.7039563437926333, "percentage": 90.71, "elapsed_time": "7:14:36", "remaining_time": "0:44:30"}
|
334 |
+
{"current_steps": 333, "total_steps": 366, "loss": 0.3805, "lr": 2.6120871426864866e-07, "epoch": 2.7121418826739427, "percentage": 90.98, "elapsed_time": "7:15:50", "remaining_time": "0:43:11"}
|
335 |
+
{"current_steps": 334, "total_steps": 366, "loss": 0.4104, "lr": 2.4619497460222184e-07, "epoch": 2.720327421555252, "percentage": 91.26, "elapsed_time": "7:17:03", "remaining_time": "0:41:52"}
|
336 |
+
{"current_steps": 335, "total_steps": 366, "loss": 0.3869, "lr": 2.316146919298623e-07, "epoch": 2.728512960436562, "percentage": 91.53, "elapsed_time": "7:18:25", "remaining_time": "0:40:34"}
|
337 |
+
{"current_steps": 336, "total_steps": 366, "loss": 0.4145, "lr": 2.1746919569723858e-07, "epoch": 2.736698499317872, "percentage": 91.8, "elapsed_time": "7:19:28", "remaining_time": "0:39:14"}
|
338 |
+
{"current_steps": 337, "total_steps": 366, "loss": 0.4082, "lr": 2.037597757057297e-07, "epoch": 2.7448840381991815, "percentage": 92.08, "elapsed_time": "7:20:37", "remaining_time": "0:37:55"}
|
339 |
+
{"current_steps": 338, "total_steps": 366, "loss": 0.3917, "lr": 1.9048768199481983e-07, "epoch": 2.753069577080491, "percentage": 92.35, "elapsed_time": "7:21:46", "remaining_time": "0:36:35"}
|
340 |
+
{"current_steps": 339, "total_steps": 366, "loss": 0.4099, "lr": 1.776541247281177e-07, "epoch": 2.761255115961801, "percentage": 92.62, "elapsed_time": "7:23:04", "remaining_time": "0:35:17"}
|
341 |
+
{"current_steps": 340, "total_steps": 366, "loss": 0.4033, "lr": 1.6526027408301227e-07, "epoch": 2.7694406548431107, "percentage": 92.9, "elapsed_time": "7:24:07", "remaining_time": "0:33:57"}
|
342 |
+
{"current_steps": 341, "total_steps": 366, "loss": 0.412, "lr": 1.5330726014397668e-07, "epoch": 2.77762619372442, "percentage": 93.17, "elapsed_time": "7:25:27", "remaining_time": "0:32:39"}
|
343 |
+
{"current_steps": 342, "total_steps": 366, "loss": 0.4121, "lr": 1.417961727995254e-07, "epoch": 2.7858117326057297, "percentage": 93.44, "elapsed_time": "7:26:23", "remaining_time": "0:31:19"}
|
344 |
+
{"current_steps": 343, "total_steps": 366, "loss": 0.427, "lr": 1.307280616428336e-07, "epoch": 2.7939972714870396, "percentage": 93.72, "elapsed_time": "7:28:00", "remaining_time": "0:30:02"}
|
345 |
+
{"current_steps": 344, "total_steps": 366, "loss": 0.4314, "lr": 1.2010393587603975e-07, "epoch": 2.8021828103683495, "percentage": 93.99, "elapsed_time": "7:29:24", "remaining_time": "0:28:44"}
|
346 |
+
{"current_steps": 345, "total_steps": 366, "loss": 0.4014, "lr": 1.0992476421822052e-07, "epoch": 2.810368349249659, "percentage": 94.26, "elapsed_time": "7:30:35", "remaining_time": "0:27:25"}
|
347 |
+
{"current_steps": 346, "total_steps": 366, "loss": 0.3793, "lr": 1.0019147481706626e-07, "epoch": 2.8185538881309684, "percentage": 94.54, "elapsed_time": "7:31:39", "remaining_time": "0:26:06"}
|
348 |
+
{"current_steps": 347, "total_steps": 366, "loss": 0.3935, "lr": 9.090495516424713e-08, "epoch": 2.8267394270122783, "percentage": 94.81, "elapsed_time": "7:33:02", "remaining_time": "0:24:48"}
|
349 |
+
{"current_steps": 348, "total_steps": 366, "loss": 0.4103, "lr": 8.206605201449447e-08, "epoch": 2.8349249658935882, "percentage": 95.08, "elapsed_time": "7:34:22", "remaining_time": "0:23:30"}
|
350 |
+
{"current_steps": 349, "total_steps": 366, "loss": 0.4194, "lr": 7.367557130838921e-08, "epoch": 2.8431105047748977, "percentage": 95.36, "elapsed_time": "7:35:39", "remaining_time": "0:22:11"}
|
351 |
+
{"current_steps": 350, "total_steps": 366, "loss": 0.4058, "lr": 6.573427809888067e-08, "epoch": 2.851296043656207, "percentage": 95.63, "elapsed_time": "7:37:11", "remaining_time": "0:20:54"}
|
352 |
+
{"current_steps": 351, "total_steps": 366, "loss": 0.4043, "lr": 5.824289648152126e-08, "epoch": 2.859481582537517, "percentage": 95.9, "elapsed_time": "7:38:12", "remaining_time": "0:19:34"}
|
353 |
+
{"current_steps": 352, "total_steps": 366, "loss": 0.4079, "lr": 5.120210952844873e-08, "epoch": 2.867667121418827, "percentage": 96.17, "elapsed_time": "7:39:32", "remaining_time": "0:18:16"}
|
354 |
+
{"current_steps": 353, "total_steps": 366, "loss": 0.4114, "lr": 4.461255922609986e-08, "epoch": 2.8758526603001364, "percentage": 96.45, "elapsed_time": "7:40:46", "remaining_time": "0:16:58"}
|
355 |
+
{"current_steps": 354, "total_steps": 366, "loss": 0.3987, "lr": 3.8474846416672874e-08, "epoch": 2.884038199181446, "percentage": 96.72, "elapsed_time": "7:42:00", "remaining_time": "0:15:39"}
|
356 |
+
{"current_steps": 355, "total_steps": 366, "loss": 0.3947, "lr": 3.278953074334512e-08, "epoch": 2.892223738062756, "percentage": 96.99, "elapsed_time": "7:43:15", "remaining_time": "0:14:21"}
|
357 |
+
{"current_steps": 356, "total_steps": 366, "loss": 0.3892, "lr": 2.75571305992417e-08, "epoch": 2.9004092769440657, "percentage": 97.27, "elapsed_time": "7:44:40", "remaining_time": "0:13:03"}
|
358 |
+
{"current_steps": 357, "total_steps": 366, "loss": 0.4151, "lr": 2.2778123080167136e-08, "epoch": 2.908594815825375, "percentage": 97.54, "elapsed_time": "7:46:00", "remaining_time": "0:11:44"}
|
359 |
+
{"current_steps": 358, "total_steps": 366, "loss": 0.3986, "lr": 1.845294394110686e-08, "epoch": 2.9167803547066846, "percentage": 97.81, "elapsed_time": "7:47:03", "remaining_time": "0:10:26"}
|
360 |
+
{"current_steps": 359, "total_steps": 366, "loss": 0.4214, "lr": 1.4581987556490095e-08, "epoch": 2.9249658935879945, "percentage": 98.09, "elapsed_time": "7:48:14", "remaining_time": "0:09:07"}
|
361 |
+
{"current_steps": 360, "total_steps": 366, "loss": 0.4103, "lr": 1.1165606884234182e-08, "epoch": 2.9331514324693044, "percentage": 98.36, "elapsed_time": "7:49:21", "remaining_time": "0:07:49"}
|
362 |
+
{"current_steps": 361, "total_steps": 366, "loss": 0.3706, "lr": 8.204113433559202e-09, "epoch": 2.941336971350614, "percentage": 98.63, "elapsed_time": "7:50:27", "remaining_time": "0:06:30"}
|
363 |
+
{"current_steps": 362, "total_steps": 366, "loss": 0.3931, "lr": 5.6977772365857105e-09, "epoch": 2.9495225102319234, "percentage": 98.91, "elapsed_time": "7:51:53", "remaining_time": "0:05:12"}
|
364 |
+
{"current_steps": 363, "total_steps": 366, "loss": 0.411, "lr": 3.6468268237105364e-09, "epoch": 2.9577080491132333, "percentage": 99.18, "elapsed_time": "7:52:56", "remaining_time": "0:03:54"}
|
365 |
+
{"current_steps": 364, "total_steps": 366, "loss": 0.4077, "lr": 2.0514492027728928e-09, "epoch": 2.965893587994543, "percentage": 99.45, "elapsed_time": "7:54:02", "remaining_time": "0:02:36"}
|
366 |
+
{"current_steps": 365, "total_steps": 366, "loss": 0.3988, "lr": 9.117898419991333e-10, "epoch": 2.9740791268758526, "percentage": 99.73, "elapsed_time": "7:55:24", "remaining_time": "0:01:18"}
|
367 |
+
{"current_steps": 366, "total_steps": 366, "loss": 0.3827, "lr": 2.2795265674113721e-10, "epoch": 2.982264665757162, "percentage": 100.0, "elapsed_time": "7:56:42", "remaining_time": "0:00:00"}
|
368 |
+
{"current_steps": 366, "total_steps": 366, "epoch": 2.982264665757162, "percentage": 100.0, "elapsed_time": "8:01:30", "remaining_time": "0:00:00"}
|