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 sha256:8bd8aceb9563fc842348d27baac474b5394309c18f2fd7ba5041c8ff805b2cd5
|
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 sha256:35c65ba5d5012d1072d4771fd1f5751c238984e5901435998fd9c17b68fac7af
|
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:c553dfe23ed7f2d25051b4a822b1a6a4d3a4b3f1be83b448fce7e17516e6dfee
|
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 sha256:239e747a56330001f9aa2ace4a96332dee36ff06a86dcbd42598a7dd16fec9c8
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -365,3 +365,78 @@
|
|
365 |
{"current_steps": 304, "total_steps": 380, "loss": 0.452, "lr": 9.358222275240884e-06, "epoch": 3.9878147847278633, "percentage": 80.0, "elapsed_time": "2:09:41", "remaining_time": "0:32:25"}
|
366 |
{"current_steps": 305, "total_steps": 380, "loss": 0.4523, "lr": 9.123333963347166e-06, "epoch": 4.000812347684809, "percentage": 80.26, "elapsed_time": "2:13:16", "remaining_time": "0:32:46"}
|
367 |
{"current_steps": 306, "total_steps": 380, "loss": 0.4304, "lr": 8.89105105427945e-06, "epoch": 4.013809910641755, "percentage": 80.53, "elapsed_time": "2:14:59", "remaining_time": "0:32:38"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
365 |
{"current_steps": 304, "total_steps": 380, "loss": 0.452, "lr": 9.358222275240884e-06, "epoch": 3.9878147847278633, "percentage": 80.0, "elapsed_time": "2:09:41", "remaining_time": "0:32:25"}
|
366 |
{"current_steps": 305, "total_steps": 380, "loss": 0.4523, "lr": 9.123333963347166e-06, "epoch": 4.000812347684809, "percentage": 80.26, "elapsed_time": "2:13:16", "remaining_time": "0:32:46"}
|
367 |
{"current_steps": 306, "total_steps": 380, "loss": 0.4304, "lr": 8.89105105427945e-06, "epoch": 4.013809910641755, "percentage": 80.53, "elapsed_time": "2:14:59", "remaining_time": "0:32:38"}
|
368 |
+
{"current_steps": 307, "total_steps": 380, "loss": 0.4184, "lr": 8.661393148293355e-06, "epoch": 4.0268074735987005, "percentage": 80.79, "elapsed_time": "2:16:44", "remaining_time": "0:32:30"}
|
369 |
+
{"current_steps": 308, "total_steps": 380, "loss": 0.4272, "lr": 8.434379624144261e-06, "epoch": 4.039805036555646, "percentage": 81.05, "elapsed_time": "2:18:29", "remaining_time": "0:32:22"}
|
370 |
+
{"current_steps": 309, "total_steps": 380, "loss": 0.4291, "lr": 8.210029637452016e-06, "epoch": 4.052802599512591, "percentage": 81.32, "elapsed_time": "2:20:14", "remaining_time": "0:32:13"}
|
371 |
+
{"current_steps": 310, "total_steps": 380, "loss": 0.43, "lr": 7.988362119084642e-06, "epoch": 4.065800162469537, "percentage": 81.58, "elapsed_time": "2:21:58", "remaining_time": "0:32:03"}
|
372 |
+
{"current_steps": 311, "total_steps": 380, "loss": 0.4245, "lr": 7.769395773560874e-06, "epoch": 4.078797725426482, "percentage": 81.84, "elapsed_time": "2:23:42", "remaining_time": "0:31:53"}
|
373 |
+
{"current_steps": 312, "total_steps": 380, "loss": 0.4205, "lr": 7.553149077471915e-06, "epoch": 4.0917952883834285, "percentage": 82.11, "elapsed_time": "2:25:27", "remaining_time": "0:31:42"}
|
374 |
+
{"current_steps": 313, "total_steps": 380, "loss": 0.4281, "lr": 7.3396402779222845e-06, "epoch": 4.104792851340374, "percentage": 82.37, "elapsed_time": "2:27:12", "remaining_time": "0:31:30"}
|
375 |
+
{"current_steps": 314, "total_steps": 380, "loss": 0.4361, "lr": 7.128887390990198e-06, "epoch": 4.117790414297319, "percentage": 82.63, "elapsed_time": "2:28:58", "remaining_time": "0:31:18"}
|
376 |
+
{"current_steps": 315, "total_steps": 380, "loss": 0.4215, "lr": 6.9209082002072725e-06, "epoch": 4.130787977254265, "percentage": 82.89, "elapsed_time": "2:30:43", "remaining_time": "0:31:06"}
|
377 |
+
{"current_steps": 316, "total_steps": 380, "loss": 0.4252, "lr": 6.715720255058e-06, "epoch": 4.14378554021121, "percentage": 83.16, "elapsed_time": "2:32:27", "remaining_time": "0:30:52"}
|
378 |
+
{"current_steps": 317, "total_steps": 380, "loss": 0.4251, "lr": 6.513340869498859e-06, "epoch": 4.156783103168156, "percentage": 83.42, "elapsed_time": "2:34:12", "remaining_time": "0:30:38"}
|
379 |
+
{"current_steps": 318, "total_steps": 380, "loss": 0.4223, "lr": 6.313787120497376e-06, "epoch": 4.169780666125101, "percentage": 83.68, "elapsed_time": "2:35:57", "remaining_time": "0:30:24"}
|
380 |
+
{"current_steps": 319, "total_steps": 380, "loss": 0.4259, "lr": 6.117075846591123e-06, "epoch": 4.182778229082047, "percentage": 83.95, "elapsed_time": "2:37:43", "remaining_time": "0:30:09"}
|
381 |
+
{"current_steps": 320, "total_steps": 380, "loss": 0.4267, "lr": 5.923223646466923e-06, "epoch": 4.195775792038993, "percentage": 84.21, "elapsed_time": "2:39:27", "remaining_time": "0:29:53"}
|
382 |
+
{"current_steps": 321, "total_steps": 380, "loss": 0.4237, "lr": 5.732246877560146e-06, "epoch": 4.208773354995938, "percentage": 84.47, "elapsed_time": "2:41:12", "remaining_time": "0:29:37"}
|
383 |
+
{"current_steps": 322, "total_steps": 380, "loss": 0.4253, "lr": 5.5441616546745646e-06, "epoch": 4.221770917952884, "percentage": 84.74, "elapsed_time": "2:42:56", "remaining_time": "0:29:21"}
|
384 |
+
{"current_steps": 323, "total_steps": 380, "loss": 0.4272, "lr": 5.358983848622452e-06, "epoch": 4.234768480909829, "percentage": 85.0, "elapsed_time": "2:44:41", "remaining_time": "0:29:03"}
|
385 |
+
{"current_steps": 324, "total_steps": 380, "loss": 0.4234, "lr": 5.176729084885508e-06, "epoch": 4.247766043866775, "percentage": 85.26, "elapsed_time": "2:46:25", "remaining_time": "0:28:45"}
|
386 |
+
{"current_steps": 325, "total_steps": 380, "loss": 0.4323, "lr": 4.99741274229625e-06, "epoch": 4.260763606823721, "percentage": 85.53, "elapsed_time": "2:48:09", "remaining_time": "0:28:27"}
|
387 |
+
{"current_steps": 326, "total_steps": 380, "loss": 0.4295, "lr": 4.821049951740442e-06, "epoch": 4.273761169780666, "percentage": 85.79, "elapsed_time": "2:49:53", "remaining_time": "0:28:08"}
|
388 |
+
{"current_steps": 327, "total_steps": 380, "loss": 0.4254, "lr": 4.647655594880225e-06, "epoch": 4.286758732737612, "percentage": 86.05, "elapsed_time": "2:51:37", "remaining_time": "0:27:49"}
|
389 |
+
{"current_steps": 328, "total_steps": 380, "loss": 0.4252, "lr": 4.4772443028985004e-06, "epoch": 4.299756295694557, "percentage": 86.32, "elapsed_time": "2:53:22", "remaining_time": "0:27:29"}
|
390 |
+
{"current_steps": 329, "total_steps": 380, "loss": 0.4242, "lr": 4.3098304552642385e-06, "epoch": 4.312753858651503, "percentage": 86.58, "elapsed_time": "2:55:06", "remaining_time": "0:27:08"}
|
391 |
+
{"current_steps": 330, "total_steps": 380, "loss": 0.4197, "lr": 4.1454281785191995e-06, "epoch": 4.325751421608448, "percentage": 86.84, "elapsed_time": "2:56:51", "remaining_time": "0:26:47"}
|
392 |
+
{"current_steps": 331, "total_steps": 380, "loss": 0.4258, "lr": 3.984051345085855e-06, "epoch": 4.338748984565394, "percentage": 87.11, "elapsed_time": "2:58:35", "remaining_time": "0:26:26"}
|
393 |
+
{"current_steps": 332, "total_steps": 380, "loss": 0.4184, "lr": 3.825713572096903e-06, "epoch": 4.35174654752234, "percentage": 87.37, "elapsed_time": "3:00:19", "remaining_time": "0:26:04"}
|
394 |
+
{"current_steps": 333, "total_steps": 380, "loss": 0.4281, "lr": 3.6704282202461515e-06, "epoch": 4.364744110479285, "percentage": 87.63, "elapsed_time": "3:02:04", "remaining_time": "0:25:41"}
|
395 |
+
{"current_steps": 334, "total_steps": 380, "loss": 0.4197, "lr": 3.518208392661184e-06, "epoch": 4.377741673436231, "percentage": 87.89, "elapsed_time": "3:03:48", "remaining_time": "0:25:18"}
|
396 |
+
{"current_steps": 335, "total_steps": 380, "loss": 0.4265, "lr": 3.3690669337977e-06, "epoch": 4.390739236393176, "percentage": 88.16, "elapsed_time": "3:05:32", "remaining_time": "0:24:55"}
|
397 |
+
{"current_steps": 336, "total_steps": 380, "loss": 0.4251, "lr": 3.2230164283556918e-06, "epoch": 4.4037367993501215, "percentage": 88.42, "elapsed_time": "3:07:17", "remaining_time": "0:24:31"}
|
398 |
+
{"current_steps": 337, "total_steps": 380, "loss": 0.4345, "lr": 3.080069200217497e-06, "epoch": 4.416734362307068, "percentage": 88.68, "elapsed_time": "3:09:01", "remaining_time": "0:24:07"}
|
399 |
+
{"current_steps": 338, "total_steps": 380, "loss": 0.4285, "lr": 2.9402373114079295e-06, "epoch": 4.429731925264013, "percentage": 88.95, "elapsed_time": "3:10:45", "remaining_time": "0:23:42"}
|
400 |
+
{"current_steps": 339, "total_steps": 380, "loss": 0.4273, "lr": 2.803532561076492e-06, "epoch": 4.442729488220959, "percentage": 89.21, "elapsed_time": "3:12:30", "remaining_time": "0:23:16"}
|
401 |
+
{"current_steps": 340, "total_steps": 380, "loss": 0.4269, "lr": 2.669966484501716e-06, "epoch": 4.455727051177904, "percentage": 89.47, "elapsed_time": "3:14:15", "remaining_time": "0:22:51"}
|
402 |
+
{"current_steps": 341, "total_steps": 380, "loss": 0.4308, "lr": 2.5395503521178143e-06, "epoch": 4.46872461413485, "percentage": 89.74, "elapsed_time": "3:15:59", "remaining_time": "0:22:24"}
|
403 |
+
{"current_steps": 342, "total_steps": 380, "loss": 0.4224, "lr": 2.4122951685636674e-06, "epoch": 4.481722177091795, "percentage": 90.0, "elapsed_time": "3:17:44", "remaining_time": "0:21:58"}
|
404 |
+
{"current_steps": 343, "total_steps": 380, "loss": 0.4228, "lr": 2.2882116717542634e-06, "epoch": 4.49471974004874, "percentage": 90.26, "elapsed_time": "3:19:29", "remaining_time": "0:21:31"}
|
405 |
+
{"current_steps": 344, "total_steps": 380, "loss": 0.4251, "lr": 2.1673103319746146e-06, "epoch": 4.507717303005687, "percentage": 90.53, "elapsed_time": "3:21:13", "remaining_time": "0:21:03"}
|
406 |
+
{"current_steps": 345, "total_steps": 380, "loss": 0.425, "lr": 2.049601350996233e-06, "epoch": 4.520714865962632, "percentage": 90.79, "elapsed_time": "3:22:57", "remaining_time": "0:20:35"}
|
407 |
+
{"current_steps": 346, "total_steps": 380, "loss": 0.4278, "lr": 1.93509466121633e-06, "epoch": 4.533712428919578, "percentage": 91.05, "elapsed_time": "3:24:42", "remaining_time": "0:20:06"}
|
408 |
+
{"current_steps": 347, "total_steps": 380, "loss": 0.4277, "lr": 1.8237999248197002e-06, "epoch": 4.546709991876523, "percentage": 91.32, "elapsed_time": "3:26:26", "remaining_time": "0:19:37"}
|
409 |
+
{"current_steps": 348, "total_steps": 380, "loss": 0.4296, "lr": 1.7157265329634354e-06, "epoch": 4.5597075548334685, "percentage": 91.58, "elapsed_time": "3:28:11", "remaining_time": "0:19:08"}
|
410 |
+
{"current_steps": 349, "total_steps": 380, "loss": 0.4254, "lr": 1.6108836049844434e-06, "epoch": 4.572705117790415, "percentage": 91.84, "elapsed_time": "3:29:56", "remaining_time": "0:18:38"}
|
411 |
+
{"current_steps": 350, "total_steps": 380, "loss": 0.4228, "lr": 1.5092799876299835e-06, "epoch": 4.58570268074736, "percentage": 92.11, "elapsed_time": "3:31:41", "remaining_time": "0:18:08"}
|
412 |
+
{"current_steps": 351, "total_steps": 380, "loss": 0.4224, "lr": 1.4109242543111834e-06, "epoch": 4.598700243704306, "percentage": 92.37, "elapsed_time": "3:33:26", "remaining_time": "0:17:38"}
|
413 |
+
{"current_steps": 352, "total_steps": 380, "loss": 0.425, "lr": 1.3158247043795735e-06, "epoch": 4.611697806661251, "percentage": 92.63, "elapsed_time": "3:35:10", "remaining_time": "0:17:06"}
|
414 |
+
{"current_steps": 353, "total_steps": 380, "loss": 0.4248, "lr": 1.2239893624267852e-06, "epoch": 4.6246953696181965, "percentage": 92.89, "elapsed_time": "3:36:54", "remaining_time": "0:16:35"}
|
415 |
+
{"current_steps": 354, "total_steps": 380, "loss": 0.4235, "lr": 1.1354259776074472e-06, "epoch": 4.637692932575142, "percentage": 93.16, "elapsed_time": "3:38:38", "remaining_time": "0:16:03"}
|
416 |
+
{"current_steps": 355, "total_steps": 380, "loss": 0.4181, "lr": 1.050142022985292e-06, "epoch": 4.650690495532087, "percentage": 93.42, "elapsed_time": "3:40:23", "remaining_time": "0:15:31"}
|
417 |
+
{"current_steps": 356, "total_steps": 380, "loss": 0.4294, "lr": 9.681446949025752e-07, "epoch": 4.663688058489034, "percentage": 93.68, "elapsed_time": "3:42:10", "remaining_time": "0:14:58"}
|
418 |
+
{"current_steps": 357, "total_steps": 380, "loss": 0.4223, "lr": 8.89440912372832e-07, "epoch": 4.676685621445979, "percentage": 93.95, "elapsed_time": "3:43:56", "remaining_time": "0:14:25"}
|
419 |
+
{"current_steps": 358, "total_steps": 380, "loss": 0.4254, "lr": 8.140373164970428e-07, "epoch": 4.6896831844029245, "percentage": 94.21, "elapsed_time": "3:45:40", "remaining_time": "0:13:52"}
|
420 |
+
{"current_steps": 359, "total_steps": 380, "loss": 0.4264, "lr": 7.419402699032852e-07, "epoch": 4.70268074735987, "percentage": 94.47, "elapsed_time": "3:47:24", "remaining_time": "0:13:18"}
|
421 |
+
{"current_steps": 360, "total_steps": 380, "loss": 0.4244, "lr": 6.731558562097995e-07, "epoch": 4.715678310316815, "percentage": 94.74, "elapsed_time": "3:49:08", "remaining_time": "0:12:43"}
|
422 |
+
{"current_steps": 361, "total_steps": 380, "loss": 0.4191, "lr": 6.076898795116792e-07, "epoch": 4.728675873273761, "percentage": 95.0, "elapsed_time": "3:50:53", "remaining_time": "0:12:09"}
|
423 |
+
{"current_steps": 362, "total_steps": 380, "loss": 0.4287, "lr": 5.455478638911071e-07, "epoch": 4.741673436230707, "percentage": 95.26, "elapsed_time": "3:52:37", "remaining_time": "0:11:34"}
|
424 |
+
{"current_steps": 363, "total_steps": 380, "loss": 0.4243, "lr": 4.867350529512261e-07, "epoch": 4.754670999187653, "percentage": 95.53, "elapsed_time": "3:54:21", "remaining_time": "0:10:58"}
|
425 |
+
{"current_steps": 364, "total_steps": 380, "loss": 0.4254, "lr": 4.3125640937368373e-07, "epoch": 4.767668562144598, "percentage": 95.79, "elapsed_time": "3:56:06", "remaining_time": "0:10:22"}
|
426 |
+
{"current_steps": 365, "total_steps": 380, "loss": 0.4237, "lr": 3.791166144998704e-07, "epoch": 4.780666125101543, "percentage": 96.05, "elapsed_time": "3:57:50", "remaining_time": "0:09:46"}
|
427 |
+
{"current_steps": 366, "total_steps": 380, "loss": 0.4256, "lr": 3.3032006793590977e-07, "epoch": 4.793663688058489, "percentage": 96.32, "elapsed_time": "3:59:34", "remaining_time": "0:09:09"}
|
428 |
+
{"current_steps": 367, "total_steps": 380, "loss": 0.432, "lr": 2.848708871814054e-07, "epoch": 4.806661251015434, "percentage": 96.58, "elapsed_time": "4:01:18", "remaining_time": "0:08:32"}
|
429 |
+
{"current_steps": 368, "total_steps": 380, "loss": 0.431, "lr": 2.4277290728202063e-07, "epoch": 4.81965881397238, "percentage": 96.84, "elapsed_time": "4:03:02", "remaining_time": "0:07:55"}
|
430 |
+
{"current_steps": 369, "total_steps": 380, "loss": 0.4282, "lr": 2.040296805058528e-07, "epoch": 4.832656376929326, "percentage": 97.11, "elapsed_time": "4:04:46", "remaining_time": "0:07:17"}
|
431 |
+
{"current_steps": 370, "total_steps": 380, "loss": 0.4175, "lr": 1.6864447604370004e-07, "epoch": 4.8456539398862715, "percentage": 97.37, "elapsed_time": "4:06:30", "remaining_time": "0:06:39"}
|
432 |
+
{"current_steps": 371, "total_steps": 380, "loss": 0.4225, "lr": 1.3662027973320614e-07, "epoch": 4.858651502843217, "percentage": 97.63, "elapsed_time": "4:08:14", "remaining_time": "0:06:01"}
|
433 |
+
{"current_steps": 372, "total_steps": 380, "loss": 0.4227, "lr": 1.0795979380690657e-07, "epoch": 4.871649065800162, "percentage": 97.89, "elapsed_time": "4:09:59", "remaining_time": "0:05:22"}
|
434 |
+
{"current_steps": 373, "total_steps": 380, "loss": 0.429, "lr": 8.266543666421544e-08, "epoch": 4.884646628757108, "percentage": 98.16, "elapsed_time": "4:11:43", "remaining_time": "0:04:43"}
|
435 |
+
{"current_steps": 374, "total_steps": 380, "loss": 0.4251, "lr": 6.073934266735303e-08, "epoch": 4.897644191714054, "percentage": 98.42, "elapsed_time": "4:13:27", "remaining_time": "0:04:03"}
|
436 |
+
{"current_steps": 375, "total_steps": 380, "loss": 0.4222, "lr": 4.218336196125439e-08, "epoch": 4.9106417546709995, "percentage": 98.68, "elapsed_time": "4:15:11", "remaining_time": "0:03:24"}
|
437 |
+
{"current_steps": 376, "total_steps": 380, "loss": 0.4263, "lr": 2.699906031745414e-08, "epoch": 4.923639317627945, "percentage": 98.95, "elapsed_time": "4:16:56", "remaining_time": "0:02:44"}
|
438 |
+
{"current_steps": 377, "total_steps": 380, "loss": 0.429, "lr": 1.5187719001943378e-08, "epoch": 4.93663688058489, "percentage": 99.21, "elapsed_time": "4:18:40", "remaining_time": "0:02:03"}
|
439 |
+
{"current_steps": 378, "total_steps": 380, "loss": 0.4241, "lr": 6.750334667091629e-09, "epoch": 4.949634443541836, "percentage": 99.47, "elapsed_time": "4:20:24", "remaining_time": "0:01:22"}
|
440 |
+
{"current_steps": 379, "total_steps": 380, "loss": 0.4205, "lr": 1.6876192675052695e-09, "epoch": 4.962632006498781, "percentage": 99.74, "elapsed_time": "4:22:09", "remaining_time": "0:00:41"}
|
441 |
+
{"current_steps": 380, "total_steps": 380, "loss": 0.4228, "lr": 0.0, "epoch": 4.975629569455727, "percentage": 100.0, "elapsed_time": "4:23:53", "remaining_time": "0:00:00"}
|
442 |
+
{"current_steps": 380, "total_steps": 380, "epoch": 4.975629569455727, "percentage": 100.0, "elapsed_time": "4:26:51", "remaining_time": "0:00:00"}
|