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 sha256:0497842f9b5648119e3e4d2cb9af2205445df02d30f11d1e409549e1ca41ae34
|
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 sha256:8a366977ddffd3a0a0aed81affcde5868a7efc67890e14f552c2bbf3772fa028
|
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:ca28a14eb22107282935f1022584c11bd16da2b623044a659dd5c495489e6b48
|
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:a4d5f1179a3cfa62c7970b401bfad0ec43170728ef453d79f4daf053e21b329a
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -306,3 +306,76 @@
|
|
306 |
{"current_steps": 306, "total_steps": 380, "loss": 0.4503, "lr": 8.89105105427945e-06, "epoch": 3.9821283509342, "percentage": 80.53, "elapsed_time": "8:34:53", "remaining_time": "2:04:30"}
|
307 |
{"current_steps": 307, "total_steps": 380, "loss": 0.4514, "lr": 8.661393148293355e-06, "epoch": 3.9951259138911457, "percentage": 80.79, "elapsed_time": "8:36:32", "remaining_time": "2:02:49"}
|
308 |
{"current_steps": 308, "total_steps": 380, "loss": 0.4384, "lr": 8.434379624144261e-06, "epoch": 4.0097481722177095, "percentage": 81.05, "elapsed_time": "8:39:55", "remaining_time": "2:01:32"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
306 |
{"current_steps": 306, "total_steps": 380, "loss": 0.4503, "lr": 8.89105105427945e-06, "epoch": 3.9821283509342, "percentage": 80.53, "elapsed_time": "8:34:53", "remaining_time": "2:04:30"}
|
307 |
{"current_steps": 307, "total_steps": 380, "loss": 0.4514, "lr": 8.661393148293355e-06, "epoch": 3.9951259138911457, "percentage": 80.79, "elapsed_time": "8:36:32", "remaining_time": "2:02:49"}
|
308 |
{"current_steps": 308, "total_steps": 380, "loss": 0.4384, "lr": 8.434379624144261e-06, "epoch": 4.0097481722177095, "percentage": 81.05, "elapsed_time": "8:39:55", "remaining_time": "2:01:32"}
|
309 |
+
{"current_steps": 309, "total_steps": 380, "loss": 0.4219, "lr": 8.210029637452016e-06, "epoch": 4.022745735174655, "percentage": 81.32, "elapsed_time": "8:41:34", "remaining_time": "1:59:50"}
|
310 |
+
{"current_steps": 310, "total_steps": 380, "loss": 0.423, "lr": 7.988362119084642e-06, "epoch": 4.0357432981316, "percentage": 81.58, "elapsed_time": "8:43:13", "remaining_time": "1:58:08"}
|
311 |
+
{"current_steps": 311, "total_steps": 380, "loss": 0.4265, "lr": 7.769395773560874e-06, "epoch": 4.048740861088546, "percentage": 81.84, "elapsed_time": "8:44:52", "remaining_time": "1:56:27"}
|
312 |
+
{"current_steps": 312, "total_steps": 380, "loss": 0.4293, "lr": 7.553149077471915e-06, "epoch": 4.061738424045491, "percentage": 82.11, "elapsed_time": "8:46:31", "remaining_time": "1:54:45"}
|
313 |
+
{"current_steps": 313, "total_steps": 380, "loss": 0.4269, "lr": 7.3396402779222845e-06, "epoch": 4.074735987002437, "percentage": 82.37, "elapsed_time": "8:48:11", "remaining_time": "1:53:03"}
|
314 |
+
{"current_steps": 314, "total_steps": 380, "loss": 0.4203, "lr": 7.128887390990198e-06, "epoch": 4.087733549959383, "percentage": 82.63, "elapsed_time": "8:49:50", "remaining_time": "1:51:22"}
|
315 |
+
{"current_steps": 315, "total_steps": 380, "loss": 0.4237, "lr": 6.9209082002072725e-06, "epoch": 4.100731112916328, "percentage": 82.89, "elapsed_time": "8:51:29", "remaining_time": "1:49:40"}
|
316 |
+
{"current_steps": 316, "total_steps": 380, "loss": 0.4323, "lr": 6.715720255058e-06, "epoch": 4.113728675873274, "percentage": 83.16, "elapsed_time": "8:53:08", "remaining_time": "1:47:58"}
|
317 |
+
{"current_steps": 317, "total_steps": 380, "loss": 0.4232, "lr": 6.513340869498859e-06, "epoch": 4.126726238830219, "percentage": 83.42, "elapsed_time": "8:54:47", "remaining_time": "1:46:17"}
|
318 |
+
{"current_steps": 318, "total_steps": 380, "loss": 0.427, "lr": 6.313787120497376e-06, "epoch": 4.139723801787165, "percentage": 83.68, "elapsed_time": "8:56:26", "remaining_time": "1:44:35"}
|
319 |
+
{"current_steps": 319, "total_steps": 380, "loss": 0.422, "lr": 6.117075846591123e-06, "epoch": 4.15272136474411, "percentage": 83.95, "elapsed_time": "8:58:05", "remaining_time": "1:42:53"}
|
320 |
+
{"current_steps": 320, "total_steps": 380, "loss": 0.424, "lr": 5.923223646466923e-06, "epoch": 4.1657189277010565, "percentage": 84.21, "elapsed_time": "8:59:45", "remaining_time": "1:41:12"}
|
321 |
+
{"current_steps": 321, "total_steps": 380, "loss": 0.4239, "lr": 5.732246877560146e-06, "epoch": 4.178716490658002, "percentage": 84.47, "elapsed_time": "9:01:24", "remaining_time": "1:39:30"}
|
322 |
+
{"current_steps": 322, "total_steps": 380, "loss": 0.4247, "lr": 5.5441616546745646e-06, "epoch": 4.191714053614947, "percentage": 84.74, "elapsed_time": "9:03:03", "remaining_time": "1:37:49"}
|
323 |
+
{"current_steps": 323, "total_steps": 380, "loss": 0.423, "lr": 5.358983848622452e-06, "epoch": 4.204711616571893, "percentage": 85.0, "elapsed_time": "9:04:42", "remaining_time": "1:36:07"}
|
324 |
+
{"current_steps": 324, "total_steps": 380, "loss": 0.426, "lr": 5.176729084885508e-06, "epoch": 4.217709179528838, "percentage": 85.26, "elapsed_time": "9:06:21", "remaining_time": "1:34:25"}
|
325 |
+
{"current_steps": 325, "total_steps": 380, "loss": 0.424, "lr": 4.99741274229625e-06, "epoch": 4.230706742485784, "percentage": 85.53, "elapsed_time": "9:08:01", "remaining_time": "1:32:44"}
|
326 |
+
{"current_steps": 326, "total_steps": 380, "loss": 0.4236, "lr": 4.821049951740442e-06, "epoch": 4.24370430544273, "percentage": 85.79, "elapsed_time": "9:09:40", "remaining_time": "1:31:02"}
|
327 |
+
{"current_steps": 327, "total_steps": 380, "loss": 0.4264, "lr": 4.647655594880225e-06, "epoch": 4.256701868399675, "percentage": 86.05, "elapsed_time": "9:11:19", "remaining_time": "1:29:21"}
|
328 |
+
{"current_steps": 328, "total_steps": 380, "loss": 0.4306, "lr": 4.4772443028985004e-06, "epoch": 4.269699431356621, "percentage": 86.32, "elapsed_time": "9:12:58", "remaining_time": "1:27:40"}
|
329 |
+
{"current_steps": 329, "total_steps": 380, "loss": 0.4279, "lr": 4.3098304552642385e-06, "epoch": 4.282696994313566, "percentage": 86.58, "elapsed_time": "9:14:38", "remaining_time": "1:25:58"}
|
330 |
+
{"current_steps": 330, "total_steps": 380, "loss": 0.4219, "lr": 4.1454281785191995e-06, "epoch": 4.295694557270512, "percentage": 86.84, "elapsed_time": "9:16:17", "remaining_time": "1:24:17"}
|
331 |
+
{"current_steps": 331, "total_steps": 380, "loss": 0.4239, "lr": 3.984051345085855e-06, "epoch": 4.308692120227457, "percentage": 87.11, "elapsed_time": "9:17:56", "remaining_time": "1:22:35"}
|
332 |
+
{"current_steps": 332, "total_steps": 380, "loss": 0.4188, "lr": 3.825713572096903e-06, "epoch": 4.3216896831844025, "percentage": 87.37, "elapsed_time": "9:19:35", "remaining_time": "1:20:54"}
|
333 |
+
{"current_steps": 333, "total_steps": 380, "loss": 0.4243, "lr": 3.6704282202461515e-06, "epoch": 4.334687246141349, "percentage": 87.63, "elapsed_time": "9:21:15", "remaining_time": "1:19:12"}
|
334 |
+
{"current_steps": 334, "total_steps": 380, "loss": 0.4221, "lr": 3.518208392661184e-06, "epoch": 4.347684809098294, "percentage": 87.89, "elapsed_time": "9:22:54", "remaining_time": "1:17:31"}
|
335 |
+
{"current_steps": 335, "total_steps": 380, "loss": 0.4204, "lr": 3.3690669337977e-06, "epoch": 4.36068237205524, "percentage": 88.16, "elapsed_time": "9:24:33", "remaining_time": "1:15:50"}
|
336 |
+
{"current_steps": 336, "total_steps": 380, "loss": 0.4218, "lr": 3.2230164283556918e-06, "epoch": 4.373679935012185, "percentage": 88.42, "elapsed_time": "9:26:12", "remaining_time": "1:14:08"}
|
337 |
+
{"current_steps": 337, "total_steps": 380, "loss": 0.424, "lr": 3.080069200217497e-06, "epoch": 4.3866774979691305, "percentage": 88.68, "elapsed_time": "9:27:52", "remaining_time": "1:12:27"}
|
338 |
+
{"current_steps": 338, "total_steps": 380, "loss": 0.4237, "lr": 2.9402373114079295e-06, "epoch": 4.399675060926076, "percentage": 88.95, "elapsed_time": "9:29:31", "remaining_time": "1:10:46"}
|
339 |
+
{"current_steps": 339, "total_steps": 380, "loss": 0.4294, "lr": 2.803532561076492e-06, "epoch": 4.412672623883022, "percentage": 89.21, "elapsed_time": "9:31:10", "remaining_time": "1:09:04"}
|
340 |
+
{"current_steps": 340, "total_steps": 380, "loss": 0.4291, "lr": 2.669966484501716e-06, "epoch": 4.425670186839968, "percentage": 89.47, "elapsed_time": "9:32:49", "remaining_time": "1:07:23"}
|
341 |
+
{"current_steps": 341, "total_steps": 380, "loss": 0.425, "lr": 2.5395503521178143e-06, "epoch": 4.438667749796913, "percentage": 89.74, "elapsed_time": "9:34:29", "remaining_time": "1:05:42"}
|
342 |
+
{"current_steps": 342, "total_steps": 380, "loss": 0.4287, "lr": 2.4122951685636674e-06, "epoch": 4.451665312753859, "percentage": 90.0, "elapsed_time": "9:36:08", "remaining_time": "1:04:00"}
|
343 |
+
{"current_steps": 343, "total_steps": 380, "loss": 0.4297, "lr": 2.2882116717542634e-06, "epoch": 4.464662875710804, "percentage": 90.26, "elapsed_time": "9:37:47", "remaining_time": "1:02:19"}
|
344 |
+
{"current_steps": 344, "total_steps": 380, "loss": 0.422, "lr": 2.1673103319746146e-06, "epoch": 4.477660438667749, "percentage": 90.53, "elapsed_time": "9:39:26", "remaining_time": "1:00:38"}
|
345 |
+
{"current_steps": 345, "total_steps": 380, "loss": 0.4216, "lr": 2.049601350996233e-06, "epoch": 4.490658001624696, "percentage": 90.79, "elapsed_time": "9:41:05", "remaining_time": "0:58:57"}
|
346 |
+
{"current_steps": 346, "total_steps": 380, "loss": 0.4221, "lr": 1.93509466121633e-06, "epoch": 4.503655564581641, "percentage": 91.05, "elapsed_time": "9:42:44", "remaining_time": "0:57:15"}
|
347 |
+
{"current_steps": 347, "total_steps": 380, "loss": 0.4261, "lr": 1.8237999248197002e-06, "epoch": 4.516653127538587, "percentage": 91.32, "elapsed_time": "9:44:24", "remaining_time": "0:55:34"}
|
348 |
+
{"current_steps": 348, "total_steps": 380, "loss": 0.422, "lr": 1.7157265329634354e-06, "epoch": 4.529650690495532, "percentage": 91.58, "elapsed_time": "9:46:03", "remaining_time": "0:53:53"}
|
349 |
+
{"current_steps": 349, "total_steps": 380, "loss": 0.4275, "lr": 1.6108836049844434e-06, "epoch": 4.5426482534524775, "percentage": 91.84, "elapsed_time": "9:47:42", "remaining_time": "0:52:12"}
|
350 |
+
{"current_steps": 350, "total_steps": 380, "loss": 0.4318, "lr": 1.5092799876299835e-06, "epoch": 4.555645816409423, "percentage": 92.11, "elapsed_time": "9:49:21", "remaining_time": "0:50:31"}
|
351 |
+
{"current_steps": 351, "total_steps": 380, "loss": 0.4262, "lr": 1.4109242543111834e-06, "epoch": 4.568643379366369, "percentage": 92.37, "elapsed_time": "9:51:01", "remaining_time": "0:48:49"}
|
352 |
+
{"current_steps": 352, "total_steps": 380, "loss": 0.4191, "lr": 1.3158247043795735e-06, "epoch": 4.581640942323315, "percentage": 92.63, "elapsed_time": "9:52:40", "remaining_time": "0:47:08"}
|
353 |
+
{"current_steps": 353, "total_steps": 380, "loss": 0.4249, "lr": 1.2239893624267852e-06, "epoch": 4.59463850528026, "percentage": 92.89, "elapsed_time": "9:54:19", "remaining_time": "0:45:27"}
|
354 |
+
{"current_steps": 354, "total_steps": 380, "loss": 0.421, "lr": 1.1354259776074472e-06, "epoch": 4.6076360682372055, "percentage": 93.16, "elapsed_time": "9:55:59", "remaining_time": "0:43:46"}
|
355 |
+
{"current_steps": 355, "total_steps": 380, "loss": 0.4234, "lr": 1.050142022985292e-06, "epoch": 4.620633631194151, "percentage": 93.42, "elapsed_time": "9:57:38", "remaining_time": "0:42:05"}
|
356 |
+
{"current_steps": 356, "total_steps": 380, "loss": 0.4231, "lr": 9.681446949025752e-07, "epoch": 4.633631194151096, "percentage": 93.68, "elapsed_time": "9:59:17", "remaining_time": "0:40:24"}
|
357 |
+
{"current_steps": 357, "total_steps": 380, "loss": 0.4162, "lr": 8.89440912372832e-07, "epoch": 4.646628757108042, "percentage": 93.95, "elapsed_time": "10:00:57", "remaining_time": "0:38:43"}
|
358 |
+
{"current_steps": 358, "total_steps": 380, "loss": 0.4286, "lr": 8.140373164970428e-07, "epoch": 4.659626320064988, "percentage": 94.21, "elapsed_time": "10:02:36", "remaining_time": "0:37:01"}
|
359 |
+
{"current_steps": 359, "total_steps": 380, "loss": 0.4213, "lr": 7.419402699032852e-07, "epoch": 4.6726238830219335, "percentage": 94.47, "elapsed_time": "10:04:15", "remaining_time": "0:35:20"}
|
360 |
+
{"current_steps": 360, "total_steps": 380, "loss": 0.4247, "lr": 6.731558562097995e-07, "epoch": 4.685621445978879, "percentage": 94.74, "elapsed_time": "10:05:54", "remaining_time": "0:33:39"}
|
361 |
+
{"current_steps": 361, "total_steps": 380, "loss": 0.4253, "lr": 6.076898795116792e-07, "epoch": 4.698619008935824, "percentage": 95.0, "elapsed_time": "10:07:33", "remaining_time": "0:31:58"}
|
362 |
+
{"current_steps": 362, "total_steps": 380, "loss": 0.4251, "lr": 5.455478638911071e-07, "epoch": 4.71161657189277, "percentage": 95.26, "elapsed_time": "10:09:13", "remaining_time": "0:30:17"}
|
363 |
+
{"current_steps": 363, "total_steps": 380, "loss": 0.4187, "lr": 4.867350529512261e-07, "epoch": 4.724614134849716, "percentage": 95.53, "elapsed_time": "10:10:52", "remaining_time": "0:28:36"}
|
364 |
+
{"current_steps": 364, "total_steps": 380, "loss": 0.4254, "lr": 4.3125640937368373e-07, "epoch": 4.737611697806662, "percentage": 95.79, "elapsed_time": "10:12:31", "remaining_time": "0:26:55"}
|
365 |
+
{"current_steps": 365, "total_steps": 380, "loss": 0.423, "lr": 3.791166144998704e-07, "epoch": 4.750609260763607, "percentage": 96.05, "elapsed_time": "10:14:10", "remaining_time": "0:25:14"}
|
366 |
+
{"current_steps": 366, "total_steps": 380, "loss": 0.4224, "lr": 3.3032006793590977e-07, "epoch": 4.763606823720552, "percentage": 96.32, "elapsed_time": "10:15:49", "remaining_time": "0:23:33"}
|
367 |
+
{"current_steps": 367, "total_steps": 380, "loss": 0.4255, "lr": 2.848708871814054e-07, "epoch": 4.776604386677498, "percentage": 96.58, "elapsed_time": "10:17:29", "remaining_time": "0:21:52"}
|
368 |
+
{"current_steps": 368, "total_steps": 380, "loss": 0.4202, "lr": 2.4277290728202063e-07, "epoch": 4.789601949634443, "percentage": 96.84, "elapsed_time": "10:19:08", "remaining_time": "0:20:11"}
|
369 |
+
{"current_steps": 369, "total_steps": 380, "loss": 0.4316, "lr": 2.040296805058528e-07, "epoch": 4.802599512591389, "percentage": 97.11, "elapsed_time": "10:20:47", "remaining_time": "0:18:30"}
|
370 |
+
{"current_steps": 370, "total_steps": 380, "loss": 0.43, "lr": 1.6864447604370004e-07, "epoch": 4.815597075548335, "percentage": 97.37, "elapsed_time": "10:22:26", "remaining_time": "0:16:49"}
|
371 |
+
{"current_steps": 371, "total_steps": 380, "loss": 0.4311, "lr": 1.3662027973320614e-07, "epoch": 4.8285946385052805, "percentage": 97.63, "elapsed_time": "10:24:05", "remaining_time": "0:15:08"}
|
372 |
+
{"current_steps": 372, "total_steps": 380, "loss": 0.4182, "lr": 1.0795979380690657e-07, "epoch": 4.841592201462226, "percentage": 97.89, "elapsed_time": "10:25:44", "remaining_time": "0:13:27"}
|
373 |
+
{"current_steps": 373, "total_steps": 380, "loss": 0.4172, "lr": 8.266543666421544e-08, "epoch": 4.854589764419171, "percentage": 98.16, "elapsed_time": "10:27:24", "remaining_time": "0:11:46"}
|
374 |
+
{"current_steps": 374, "total_steps": 380, "loss": 0.4234, "lr": 6.073934266735303e-08, "epoch": 4.867587327376117, "percentage": 98.42, "elapsed_time": "10:29:03", "remaining_time": "0:10:05"}
|
375 |
+
{"current_steps": 375, "total_steps": 380, "loss": 0.4268, "lr": 4.218336196125439e-08, "epoch": 4.880584890333062, "percentage": 98.68, "elapsed_time": "10:30:42", "remaining_time": "0:08:24"}
|
376 |
+
{"current_steps": 376, "total_steps": 380, "loss": 0.4234, "lr": 2.699906031745414e-08, "epoch": 4.8935824532900085, "percentage": 98.95, "elapsed_time": "10:32:21", "remaining_time": "0:06:43"}
|
377 |
+
{"current_steps": 377, "total_steps": 380, "loss": 0.4217, "lr": 1.5187719001943378e-08, "epoch": 4.906580016246954, "percentage": 99.21, "elapsed_time": "10:34:01", "remaining_time": "0:05:02"}
|
378 |
+
{"current_steps": 378, "total_steps": 380, "loss": 0.4235, "lr": 6.750334667091629e-09, "epoch": 4.919577579203899, "percentage": 99.47, "elapsed_time": "10:35:40", "remaining_time": "0:03:21"}
|
379 |
+
{"current_steps": 379, "total_steps": 380, "loss": 0.4274, "lr": 1.6876192675052695e-09, "epoch": 4.932575142160845, "percentage": 99.74, "elapsed_time": "10:37:19", "remaining_time": "0:01:40"}
|
380 |
+
{"current_steps": 380, "total_steps": 380, "loss": 0.4228, "lr": 0.0, "epoch": 4.94557270511779, "percentage": 100.0, "elapsed_time": "10:38:59", "remaining_time": "0:00:00"}
|
381 |
+
{"current_steps": 380, "total_steps": 380, "epoch": 4.94557270511779, "percentage": 100.0, "elapsed_time": "10:41:45", "remaining_time": "0:00:00"}
|