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 sha256:89cf4d47bdc9dcbb3882e8d9a7255577e1578e73c488f8891cf253f4056dffd3
|
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:ae7d34fb1b59a6821c77521d8f2b902103b9cc9acfcc227062c85579bf07cf4e
|
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:a901e913104cc2b3b2e6ee0e9a5688c8a52f9a6dfcb245f4295ead0c88a60fde
|
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 sha256:10e6263b3b1349df4cacbf3cd1e210d2c16b9d811b1160035ea7baea1494e002
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -323,3 +323,69 @@
|
|
323 |
{"current_steps": 323, "total_steps": 390, "loss": 0.0952, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "1:36:48", "remaining_time": "0:20:04"}
|
324 |
{"current_steps": 324, "total_steps": 390, "loss": 0.0889, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "1:37:03", "remaining_time": "0:19:46"}
|
325 |
{"current_steps": 325, "total_steps": 390, "loss": 0.0935, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "1:37:20", "remaining_time": "0:19:28"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
323 |
{"current_steps": 323, "total_steps": 390, "loss": 0.0952, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "1:36:48", "remaining_time": "0:20:04"}
|
324 |
{"current_steps": 324, "total_steps": 390, "loss": 0.0889, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "1:37:03", "remaining_time": "0:19:46"}
|
325 |
{"current_steps": 325, "total_steps": 390, "loss": 0.0935, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "1:37:20", "remaining_time": "0:19:28"}
|
326 |
+
{"current_steps": 326, "total_steps": 390, "loss": 0.0947, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "1:37:41", "remaining_time": "0:19:10"}
|
327 |
+
{"current_steps": 327, "total_steps": 390, "loss": 0.093, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "1:37:59", "remaining_time": "0:18:52"}
|
328 |
+
{"current_steps": 328, "total_steps": 390, "loss": 0.0724, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "1:38:17", "remaining_time": "0:18:34"}
|
329 |
+
{"current_steps": 329, "total_steps": 390, "loss": 0.0908, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "1:38:31", "remaining_time": "0:18:16"}
|
330 |
+
{"current_steps": 330, "total_steps": 390, "loss": 0.078, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "1:38:43", "remaining_time": "0:17:57"}
|
331 |
+
{"current_steps": 331, "total_steps": 390, "loss": 0.072, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "1:38:55", "remaining_time": "0:17:37"}
|
332 |
+
{"current_steps": 332, "total_steps": 390, "loss": 0.0907, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "1:39:12", "remaining_time": "0:17:19"}
|
333 |
+
{"current_steps": 333, "total_steps": 390, "loss": 0.0725, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "1:39:24", "remaining_time": "0:17:00"}
|
334 |
+
{"current_steps": 334, "total_steps": 390, "loss": 0.074, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "1:39:38", "remaining_time": "0:16:42"}
|
335 |
+
{"current_steps": 335, "total_steps": 390, "loss": 0.0958, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "1:39:53", "remaining_time": "0:16:23"}
|
336 |
+
{"current_steps": 336, "total_steps": 390, "loss": 0.0985, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "1:40:14", "remaining_time": "0:16:06"}
|
337 |
+
{"current_steps": 337, "total_steps": 390, "loss": 0.0905, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "1:40:32", "remaining_time": "0:15:48"}
|
338 |
+
{"current_steps": 338, "total_steps": 390, "loss": 0.0915, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "1:40:57", "remaining_time": "0:15:31"}
|
339 |
+
{"current_steps": 339, "total_steps": 390, "loss": 0.0672, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "1:41:09", "remaining_time": "0:15:13"}
|
340 |
+
{"current_steps": 340, "total_steps": 390, "loss": 0.0923, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "1:41:29", "remaining_time": "0:14:55"}
|
341 |
+
{"current_steps": 341, "total_steps": 390, "loss": 0.088, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "1:41:44", "remaining_time": "0:14:37"}
|
342 |
+
{"current_steps": 342, "total_steps": 390, "loss": 0.0699, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "1:41:58", "remaining_time": "0:14:18"}
|
343 |
+
{"current_steps": 343, "total_steps": 390, "loss": 0.0782, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "1:42:14", "remaining_time": "0:14:00"}
|
344 |
+
{"current_steps": 344, "total_steps": 390, "loss": 0.0882, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "1:42:28", "remaining_time": "0:13:42"}
|
345 |
+
{"current_steps": 345, "total_steps": 390, "loss": 0.0849, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "1:42:41", "remaining_time": "0:13:23"}
|
346 |
+
{"current_steps": 346, "total_steps": 390, "loss": 0.082, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "1:42:58", "remaining_time": "0:13:05"}
|
347 |
+
{"current_steps": 347, "total_steps": 390, "loss": 0.0761, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "1:43:16", "remaining_time": "0:12:47"}
|
348 |
+
{"current_steps": 348, "total_steps": 390, "loss": 0.0874, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "1:43:30", "remaining_time": "0:12:29"}
|
349 |
+
{"current_steps": 349, "total_steps": 390, "loss": 0.0902, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "1:43:48", "remaining_time": "0:12:11"}
|
350 |
+
{"current_steps": 350, "total_steps": 390, "loss": 0.114, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "1:44:13", "remaining_time": "0:11:54"}
|
351 |
+
{"current_steps": 351, "total_steps": 390, "loss": 0.1027, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "1:44:32", "remaining_time": "0:11:36"}
|
352 |
+
{"current_steps": 352, "total_steps": 390, "loss": 0.0947, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "1:44:50", "remaining_time": "0:11:19"}
|
353 |
+
{"current_steps": 353, "total_steps": 390, "loss": 0.08, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "1:45:06", "remaining_time": "0:11:00"}
|
354 |
+
{"current_steps": 354, "total_steps": 390, "loss": 0.1075, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "1:45:21", "remaining_time": "0:10:42"}
|
355 |
+
{"current_steps": 355, "total_steps": 390, "loss": 0.0815, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "1:45:40", "remaining_time": "0:10:25"}
|
356 |
+
{"current_steps": 356, "total_steps": 390, "loss": 0.0751, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "1:45:55", "remaining_time": "0:10:07"}
|
357 |
+
{"current_steps": 357, "total_steps": 390, "loss": 0.0948, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "1:46:13", "remaining_time": "0:09:49"}
|
358 |
+
{"current_steps": 358, "total_steps": 390, "loss": 0.1034, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "1:46:27", "remaining_time": "0:09:30"}
|
359 |
+
{"current_steps": 359, "total_steps": 390, "loss": 0.1001, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "1:46:44", "remaining_time": "0:09:13"}
|
360 |
+
{"current_steps": 360, "total_steps": 390, "loss": 0.0859, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "1:46:56", "remaining_time": "0:08:54"}
|
361 |
+
{"current_steps": 361, "total_steps": 390, "loss": 0.0844, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "1:47:10", "remaining_time": "0:08:36"}
|
362 |
+
{"current_steps": 362, "total_steps": 390, "loss": 0.0838, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "1:47:23", "remaining_time": "0:08:18"}
|
363 |
+
{"current_steps": 363, "total_steps": 390, "loss": 0.1056, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "1:47:42", "remaining_time": "0:08:00"}
|
364 |
+
{"current_steps": 364, "total_steps": 390, "loss": 0.0731, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "1:47:54", "remaining_time": "0:07:42"}
|
365 |
+
{"current_steps": 365, "total_steps": 390, "loss": 0.1029, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "1:48:15", "remaining_time": "0:07:24"}
|
366 |
+
{"current_steps": 366, "total_steps": 390, "loss": 0.0935, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "1:48:28", "remaining_time": "0:07:06"}
|
367 |
+
{"current_steps": 367, "total_steps": 390, "loss": 0.0747, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "1:48:40", "remaining_time": "0:06:48"}
|
368 |
+
{"current_steps": 368, "total_steps": 390, "loss": 0.1067, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "1:49:01", "remaining_time": "0:06:31"}
|
369 |
+
{"current_steps": 369, "total_steps": 390, "loss": 0.0864, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "1:49:16", "remaining_time": "0:06:13"}
|
370 |
+
{"current_steps": 370, "total_steps": 390, "loss": 0.0894, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "1:49:33", "remaining_time": "0:05:55"}
|
371 |
+
{"current_steps": 371, "total_steps": 390, "loss": 0.0843, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "1:49:54", "remaining_time": "0:05:37"}
|
372 |
+
{"current_steps": 372, "total_steps": 390, "loss": 0.0933, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "1:50:15", "remaining_time": "0:05:20"}
|
373 |
+
{"current_steps": 373, "total_steps": 390, "loss": 0.0947, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "1:50:34", "remaining_time": "0:05:02"}
|
374 |
+
{"current_steps": 374, "total_steps": 390, "loss": 0.0815, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "1:50:54", "remaining_time": "0:04:44"}
|
375 |
+
{"current_steps": 375, "total_steps": 390, "loss": 0.1057, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "1:51:11", "remaining_time": "0:04:26"}
|
376 |
+
{"current_steps": 376, "total_steps": 390, "loss": 0.0958, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "1:51:32", "remaining_time": "0:04:09"}
|
377 |
+
{"current_steps": 377, "total_steps": 390, "loss": 0.077, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "1:51:51", "remaining_time": "0:03:51"}
|
378 |
+
{"current_steps": 378, "total_steps": 390, "loss": 0.0762, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "1:52:14", "remaining_time": "0:03:33"}
|
379 |
+
{"current_steps": 379, "total_steps": 390, "loss": 0.0752, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "1:52:29", "remaining_time": "0:03:15"}
|
380 |
+
{"current_steps": 380, "total_steps": 390, "loss": 0.0906, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "1:52:42", "remaining_time": "0:02:57"}
|
381 |
+
{"current_steps": 381, "total_steps": 390, "loss": 0.096, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "1:52:58", "remaining_time": "0:02:40"}
|
382 |
+
{"current_steps": 382, "total_steps": 390, "loss": 0.0738, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "1:53:10", "remaining_time": "0:02:22"}
|
383 |
+
{"current_steps": 383, "total_steps": 390, "loss": 0.0896, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "1:53:29", "remaining_time": "0:02:04"}
|
384 |
+
{"current_steps": 384, "total_steps": 390, "loss": 0.0878, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "1:53:47", "remaining_time": "0:01:46"}
|
385 |
+
{"current_steps": 385, "total_steps": 390, "loss": 0.0959, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "1:54:05", "remaining_time": "0:01:28"}
|
386 |
+
{"current_steps": 386, "total_steps": 390, "loss": 0.0961, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "1:54:19", "remaining_time": "0:01:11"}
|
387 |
+
{"current_steps": 387, "total_steps": 390, "loss": 0.0833, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "1:54:33", "remaining_time": "0:00:53"}
|
388 |
+
{"current_steps": 388, "total_steps": 390, "loss": 0.0955, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "1:54:49", "remaining_time": "0:00:35"}
|
389 |
+
{"current_steps": 389, "total_steps": 390, "loss": 0.1059, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "1:55:07", "remaining_time": "0:00:17"}
|
390 |
+
{"current_steps": 390, "total_steps": 390, "loss": 0.0854, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "1:55:21", "remaining_time": "0:00:00"}
|
391 |
+
{"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "1:58:47", "remaining_time": "0:00:00"}
|