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 sha256:474e83fea6ab250e37784d1773bee7531ccd118161b2581bccc662e27b98a07f
|
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 sha256:893ad4c7884a562434494ae4de78f5caf2bb3b6b2922aa97225c7e9e2912b2ee
|
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:c8718e08206908ad7c2ed8fe6c70fa9d3143d11d135d0087e2daa5c43e52ad15
|
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 sha256:95e7df4dd37e92c5d2cea57dfb380263b229cab3d9db30aabc0d162b8f5a6f0b
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -319,3 +319,73 @@
|
|
319 |
{"current_steps": 319, "total_steps": 390, "loss": 0.3477, "lr": 3.904248846874894e-06, "epoch": 4.07667731629393, "percentage": 81.79, "elapsed_time": "2:09:52", "remaining_time": "0:28:54"}
|
320 |
{"current_steps": 320, "total_steps": 390, "loss": 0.3305, "lr": 3.7986423802166705e-06, "epoch": 4.0894568690095845, "percentage": 82.05, "elapsed_time": "2:10:14", "remaining_time": "0:28:29"}
|
321 |
{"current_steps": 321, "total_steps": 390, "loss": 0.3379, "lr": 3.694333792009115e-06, "epoch": 4.102236421725239, "percentage": 82.31, "elapsed_time": "2:10:39", "remaining_time": "0:28:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
319 |
{"current_steps": 319, "total_steps": 390, "loss": 0.3477, "lr": 3.904248846874894e-06, "epoch": 4.07667731629393, "percentage": 81.79, "elapsed_time": "2:09:52", "remaining_time": "0:28:54"}
|
320 |
{"current_steps": 320, "total_steps": 390, "loss": 0.3305, "lr": 3.7986423802166705e-06, "epoch": 4.0894568690095845, "percentage": 82.05, "elapsed_time": "2:10:14", "remaining_time": "0:28:29"}
|
321 |
{"current_steps": 321, "total_steps": 390, "loss": 0.3379, "lr": 3.694333792009115e-06, "epoch": 4.102236421725239, "percentage": 82.31, "elapsed_time": "2:10:39", "remaining_time": "0:28:05"}
|
322 |
+
{"current_steps": 322, "total_steps": 390, "loss": 0.3397, "lr": 3.5913314383339937e-06, "epoch": 4.115015974440895, "percentage": 82.56, "elapsed_time": "2:11:02", "remaining_time": "0:27:40"}
|
323 |
+
{"current_steps": 323, "total_steps": 390, "loss": 0.3538, "lr": 3.4896435706316e-06, "epoch": 4.127795527156549, "percentage": 82.82, "elapsed_time": "2:11:25", "remaining_time": "0:27:15"}
|
324 |
+
{"current_steps": 324, "total_steps": 390, "loss": 0.3396, "lr": 3.3892783350397675e-06, "epoch": 4.140575079872204, "percentage": 83.08, "elapsed_time": "2:11:48", "remaining_time": "0:26:51"}
|
325 |
+
{"current_steps": 325, "total_steps": 390, "loss": 0.3413, "lr": 3.290243771741275e-06, "epoch": 4.15335463258786, "percentage": 83.33, "elapsed_time": "2:12:13", "remaining_time": "0:26:26"}
|
326 |
+
{"current_steps": 326, "total_steps": 390, "loss": 0.3408, "lr": 3.1925478143197418e-06, "epoch": 4.166134185303514, "percentage": 83.59, "elapsed_time": "2:12:35", "remaining_time": "0:26:01"}
|
327 |
+
{"current_steps": 327, "total_steps": 390, "loss": 0.3368, "lr": 3.0961982891241083e-06, "epoch": 4.178913738019169, "percentage": 83.85, "elapsed_time": "2:12:59", "remaining_time": "0:25:37"}
|
328 |
+
{"current_steps": 328, "total_steps": 390, "loss": 0.3354, "lr": 3.001202914641628e-06, "epoch": 4.1916932907348246, "percentage": 84.1, "elapsed_time": "2:13:21", "remaining_time": "0:25:12"}
|
329 |
+
{"current_steps": 329, "total_steps": 390, "loss": 0.3674, "lr": 2.907569300879596e-06, "epoch": 4.204472843450479, "percentage": 84.36, "elapsed_time": "2:13:46", "remaining_time": "0:24:48"}
|
330 |
+
{"current_steps": 330, "total_steps": 390, "loss": 0.3281, "lr": 2.815304948755664e-06, "epoch": 4.217252396166134, "percentage": 84.62, "elapsed_time": "2:14:09", "remaining_time": "0:24:23"}
|
331 |
+
{"current_steps": 331, "total_steps": 390, "loss": 0.314, "lr": 2.7244172494969978e-06, "epoch": 4.2300319488817895, "percentage": 84.87, "elapsed_time": "2:14:31", "remaining_time": "0:23:58"}
|
332 |
+
{"current_steps": 332, "total_steps": 390, "loss": 0.345, "lr": 2.6349134840481294e-06, "epoch": 4.242811501597444, "percentage": 85.13, "elapsed_time": "2:14:54", "remaining_time": "0:23:34"}
|
333 |
+
{"current_steps": 333, "total_steps": 390, "loss": 0.3401, "lr": 2.546800822487714e-06, "epoch": 4.255591054313099, "percentage": 85.38, "elapsed_time": "2:15:15", "remaining_time": "0:23:09"}
|
334 |
+
{"current_steps": 334, "total_steps": 390, "loss": 0.3365, "lr": 2.4600863234541338e-06, "epoch": 4.268370607028754, "percentage": 85.64, "elapsed_time": "2:15:39", "remaining_time": "0:22:44"}
|
335 |
+
{"current_steps": 335, "total_steps": 390, "loss": 0.3366, "lr": 2.374776933580025e-06, "epoch": 4.281150159744409, "percentage": 85.9, "elapsed_time": "2:16:02", "remaining_time": "0:22:20"}
|
336 |
+
{"current_steps": 336, "total_steps": 390, "loss": 0.3349, "lr": 2.2908794869358044e-06, "epoch": 4.293929712460064, "percentage": 86.15, "elapsed_time": "2:16:25", "remaining_time": "0:21:55"}
|
337 |
+
{"current_steps": 337, "total_steps": 390, "loss": 0.3404, "lr": 2.2084007044821764e-06, "epoch": 4.306709265175719, "percentage": 86.41, "elapsed_time": "2:16:48", "remaining_time": "0:21:31"}
|
338 |
+
{"current_steps": 338, "total_steps": 390, "loss": 0.3368, "lr": 2.127347193531757e-06, "epoch": 4.319488817891374, "percentage": 86.67, "elapsed_time": "2:17:11", "remaining_time": "0:21:06"}
|
339 |
+
{"current_steps": 339, "total_steps": 390, "loss": 0.3343, "lr": 2.0477254472197237e-06, "epoch": 4.332268370607029, "percentage": 86.92, "elapsed_time": "2:17:35", "remaining_time": "0:20:41"}
|
340 |
+
{"current_steps": 340, "total_steps": 390, "loss": 0.3276, "lr": 1.96954184398368e-06, "epoch": 4.345047923322683, "percentage": 87.18, "elapsed_time": "2:17:59", "remaining_time": "0:20:17"}
|
341 |
+
{"current_steps": 341, "total_steps": 390, "loss": 0.3047, "lr": 1.8928026470526917e-06, "epoch": 4.357827476038339, "percentage": 87.44, "elapsed_time": "2:18:21", "remaining_time": "0:19:52"}
|
342 |
+
{"current_steps": 342, "total_steps": 390, "loss": 0.3552, "lr": 1.817514003945524e-06, "epoch": 4.3706070287539935, "percentage": 87.69, "elapsed_time": "2:18:44", "remaining_time": "0:19:28"}
|
343 |
+
{"current_steps": 343, "total_steps": 390, "loss": 0.3612, "lr": 1.743681945978184e-06, "epoch": 4.383386581469648, "percentage": 87.95, "elapsed_time": "2:19:07", "remaining_time": "0:19:03"}
|
344 |
+
{"current_steps": 344, "total_steps": 390, "loss": 0.3295, "lr": 1.6713123877807413e-06, "epoch": 4.396166134185304, "percentage": 88.21, "elapsed_time": "2:19:31", "remaining_time": "0:18:39"}
|
345 |
+
{"current_steps": 345, "total_steps": 390, "loss": 0.3414, "lr": 1.6004111268235156e-06, "epoch": 4.4089456869009584, "percentage": 88.46, "elapsed_time": "2:19:54", "remaining_time": "0:18:14"}
|
346 |
+
{"current_steps": 346, "total_steps": 390, "loss": 0.3593, "lr": 1.5309838429526714e-06, "epoch": 4.421725239616613, "percentage": 88.72, "elapsed_time": "2:20:17", "remaining_time": "0:17:50"}
|
347 |
+
{"current_steps": 347, "total_steps": 390, "loss": 0.345, "lr": 1.4630360979351644e-06, "epoch": 4.434504792332269, "percentage": 88.97, "elapsed_time": "2:20:41", "remaining_time": "0:17:26"}
|
348 |
+
{"current_steps": 348, "total_steps": 390, "loss": 0.3197, "lr": 1.396573335013236e-06, "epoch": 4.447284345047923, "percentage": 89.23, "elapsed_time": "2:21:02", "remaining_time": "0:17:01"}
|
349 |
+
{"current_steps": 349, "total_steps": 390, "loss": 0.3189, "lr": 1.3316008784683265e-06, "epoch": 4.460063897763578, "percentage": 89.49, "elapsed_time": "2:21:26", "remaining_time": "0:16:36"}
|
350 |
+
{"current_steps": 350, "total_steps": 390, "loss": 0.3308, "lr": 1.2681239331945695e-06, "epoch": 4.472843450479234, "percentage": 89.74, "elapsed_time": "2:21:48", "remaining_time": "0:16:12"}
|
351 |
+
{"current_steps": 351, "total_steps": 390, "loss": 0.336, "lr": 1.2061475842818337e-06, "epoch": 4.485623003194888, "percentage": 90.0, "elapsed_time": "2:22:12", "remaining_time": "0:15:48"}
|
352 |
+
{"current_steps": 352, "total_steps": 390, "loss": 0.323, "lr": 1.1456767966083393e-06, "epoch": 4.498402555910543, "percentage": 90.26, "elapsed_time": "2:22:36", "remaining_time": "0:15:23"}
|
353 |
+
{"current_steps": 353, "total_steps": 390, "loss": 0.3511, "lr": 1.086716414442952e-06, "epoch": 4.511182108626198, "percentage": 90.51, "elapsed_time": "2:22:59", "remaining_time": "0:14:59"}
|
354 |
+
{"current_steps": 354, "total_steps": 390, "loss": 0.334, "lr": 1.0292711610570904e-06, "epoch": 4.523961661341853, "percentage": 90.77, "elapsed_time": "2:23:21", "remaining_time": "0:14:34"}
|
355 |
+
{"current_steps": 355, "total_steps": 390, "loss": 0.3414, "lr": 9.733456383463658e-07, "epoch": 4.536741214057508, "percentage": 91.03, "elapsed_time": "2:23:43", "remaining_time": "0:14:10"}
|
356 |
+
{"current_steps": 356, "total_steps": 390, "loss": 0.3324, "lr": 9.189443264619102e-07, "epoch": 4.549520766773163, "percentage": 91.28, "elapsed_time": "2:24:06", "remaining_time": "0:13:45"}
|
357 |
+
{"current_steps": 357, "total_steps": 390, "loss": 0.318, "lr": 8.660715834514977e-07, "epoch": 4.562300319488818, "percentage": 91.54, "elapsed_time": "2:24:29", "remaining_time": "0:13:21"}
|
358 |
+
{"current_steps": 358, "total_steps": 390, "loss": 0.348, "lr": 8.147316449103959e-07, "epoch": 4.575079872204473, "percentage": 91.79, "elapsed_time": "2:24:52", "remaining_time": "0:12:56"}
|
359 |
+
{"current_steps": 359, "total_steps": 390, "loss": 0.3462, "lr": 7.649286236420806e-07, "epoch": 4.587859424920127, "percentage": 92.05, "elapsed_time": "2:25:14", "remaining_time": "0:12:32"}
|
360 |
+
{"current_steps": 360, "total_steps": 390, "loss": 0.3117, "lr": 7.166665093287539e-07, "epoch": 4.600638977635783, "percentage": 92.31, "elapsed_time": "2:25:36", "remaining_time": "0:12:08"}
|
361 |
+
{"current_steps": 361, "total_steps": 390, "loss": 0.3299, "lr": 6.69949168211721e-07, "epoch": 4.613418530351438, "percentage": 92.56, "elapsed_time": "2:25:59", "remaining_time": "0:11:43"}
|
362 |
+
{"current_steps": 362, "total_steps": 390, "loss": 0.3311, "lr": 6.247803427816945e-07, "epoch": 4.626198083067092, "percentage": 92.82, "elapsed_time": "2:26:21", "remaining_time": "0:11:19"}
|
363 |
+
{"current_steps": 363, "total_steps": 390, "loss": 0.3232, "lr": 5.811636514789598e-07, "epoch": 4.638977635782748, "percentage": 93.08, "elapsed_time": "2:26:44", "remaining_time": "0:10:54"}
|
364 |
+
{"current_steps": 364, "total_steps": 390, "loss": 0.3418, "lr": 5.391025884035239e-07, "epoch": 4.651757188498403, "percentage": 93.33, "elapsed_time": "2:27:07", "remaining_time": "0:10:30"}
|
365 |
+
{"current_steps": 365, "total_steps": 390, "loss": 0.3373, "lr": 4.986005230351954e-07, "epoch": 4.664536741214057, "percentage": 93.59, "elapsed_time": "2:27:30", "remaining_time": "0:10:06"}
|
366 |
+
{"current_steps": 366, "total_steps": 390, "loss": 0.3199, "lr": 4.5966069996365993e-07, "epoch": 4.677316293929713, "percentage": 93.85, "elapsed_time": "2:27:54", "remaining_time": "0:09:41"}
|
367 |
+
{"current_steps": 367, "total_steps": 390, "loss": 0.3369, "lr": 4.22286238628562e-07, "epoch": 4.6900958466453675, "percentage": 94.1, "elapsed_time": "2:28:17", "remaining_time": "0:09:17"}
|
368 |
+
{"current_steps": 368, "total_steps": 390, "loss": 0.3232, "lr": 3.8648013306960664e-07, "epoch": 4.702875399361022, "percentage": 94.36, "elapsed_time": "2:28:40", "remaining_time": "0:08:53"}
|
369 |
+
{"current_steps": 369, "total_steps": 390, "loss": 0.3234, "lr": 3.522452516867048e-07, "epoch": 4.715654952076678, "percentage": 94.62, "elapsed_time": "2:29:01", "remaining_time": "0:08:28"}
|
370 |
+
{"current_steps": 370, "total_steps": 390, "loss": 0.3481, "lr": 3.1958433701019697e-07, "epoch": 4.728434504792332, "percentage": 94.87, "elapsed_time": "2:29:24", "remaining_time": "0:08:04"}
|
371 |
+
{"current_steps": 371, "total_steps": 390, "loss": 0.3364, "lr": 2.8850000548115155e-07, "epoch": 4.741214057507987, "percentage": 95.13, "elapsed_time": "2:29:47", "remaining_time": "0:07:40"}
|
372 |
+
{"current_steps": 372, "total_steps": 390, "loss": 0.3364, "lr": 2.5899474724174313e-07, "epoch": 4.753993610223642, "percentage": 95.38, "elapsed_time": "2:30:10", "remaining_time": "0:07:16"}
|
373 |
+
{"current_steps": 373, "total_steps": 390, "loss": 0.3263, "lr": 2.3107092593579905e-07, "epoch": 4.766773162939297, "percentage": 95.64, "elapsed_time": "2:30:33", "remaining_time": "0:06:51"}
|
374 |
+
{"current_steps": 374, "total_steps": 390, "loss": 0.3228, "lr": 2.0473077851942858e-07, "epoch": 4.779552715654952, "percentage": 95.9, "elapsed_time": "2:30:56", "remaining_time": "0:06:27"}
|
375 |
+
{"current_steps": 375, "total_steps": 390, "loss": 0.3245, "lr": 1.799764150818306e-07, "epoch": 4.792332268370607, "percentage": 96.15, "elapsed_time": "2:31:19", "remaining_time": "0:06:03"}
|
376 |
+
{"current_steps": 376, "total_steps": 390, "loss": 0.3437, "lr": 1.5680981867625566e-07, "epoch": 4.805111821086262, "percentage": 96.41, "elapsed_time": "2:31:42", "remaining_time": "0:05:38"}
|
377 |
+
{"current_steps": 377, "total_steps": 390, "loss": 0.3566, "lr": 1.3523284516113955e-07, "epoch": 4.817891373801917, "percentage": 96.67, "elapsed_time": "2:32:06", "remaining_time": "0:05:14"}
|
378 |
+
{"current_steps": 378, "total_steps": 390, "loss": 0.3433, "lr": 1.1524722305144231e-07, "epoch": 4.830670926517572, "percentage": 96.92, "elapsed_time": "2:32:28", "remaining_time": "0:04:50"}
|
379 |
+
{"current_steps": 379, "total_steps": 390, "loss": 0.3329, "lr": 9.685455338016347e-08, "epoch": 4.843450479233227, "percentage": 97.18, "elapsed_time": "2:32:52", "remaining_time": "0:04:26"}
|
380 |
+
{"current_steps": 380, "total_steps": 390, "loss": 0.3489, "lr": 8.005630957010014e-08, "epoch": 4.856230031948882, "percentage": 97.44, "elapsed_time": "2:33:15", "remaining_time": "0:04:01"}
|
381 |
+
{"current_steps": 381, "total_steps": 390, "loss": 0.3357, "lr": 6.485383731580142e-08, "epoch": 4.8690095846645365, "percentage": 97.69, "elapsed_time": "2:33:38", "remaining_time": "0:03:37"}
|
382 |
+
{"current_steps": 382, "total_steps": 390, "loss": 0.3154, "lr": 5.1248354475768034e-08, "epoch": 4.881789137380192, "percentage": 97.95, "elapsed_time": "2:34:00", "remaining_time": "0:03:13"}
|
383 |
+
{"current_steps": 383, "total_steps": 390, "loss": 0.3221, "lr": 3.924095097489922e-08, "epoch": 4.894568690095847, "percentage": 98.21, "elapsed_time": "2:34:23", "remaining_time": "0:02:49"}
|
384 |
+
{"current_steps": 384, "total_steps": 390, "loss": 0.3369, "lr": 2.8832588717164766e-08, "epoch": 4.907348242811501, "percentage": 98.46, "elapsed_time": "2:34:46", "remaining_time": "0:02:25"}
|
385 |
+
{"current_steps": 385, "total_steps": 390, "loss": 0.3413, "lr": 2.0024101508555604e-08, "epoch": 4.920127795527156, "percentage": 98.72, "elapsed_time": "2:35:09", "remaining_time": "0:02:00"}
|
386 |
+
{"current_steps": 386, "total_steps": 390, "loss": 0.3127, "lr": 1.281619499029274e-08, "epoch": 4.932907348242812, "percentage": 98.97, "elapsed_time": "2:35:32", "remaining_time": "0:01:36"}
|
387 |
+
{"current_steps": 387, "total_steps": 390, "loss": 0.3254, "lr": 7.209446582292501e-09, "epoch": 4.945686900958466, "percentage": 99.23, "elapsed_time": "2:35:55", "remaining_time": "0:01:12"}
|
388 |
+
{"current_steps": 388, "total_steps": 390, "loss": 0.3315, "lr": 3.2043054369057523e-09, "epoch": 4.958466453674122, "percentage": 99.49, "elapsed_time": "2:36:17", "remaining_time": "0:00:48"}
|
389 |
+
{"current_steps": 389, "total_steps": 390, "loss": 0.3561, "lr": 8.010924029533406e-10, "epoch": 4.9712460063897765, "percentage": 99.74, "elapsed_time": "2:36:41", "remaining_time": "0:00:24"}
|
390 |
+
{"current_steps": 390, "total_steps": 390, "loss": 0.3372, "lr": 0.0, "epoch": 4.984025559105431, "percentage": 100.0, "elapsed_time": "2:37:04", "remaining_time": "0:00:00"}
|
391 |
+
{"current_steps": 390, "total_steps": 390, "epoch": 4.984025559105431, "percentage": 100.0, "elapsed_time": "2:40:19", "remaining_time": "0:00:00"}
|