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:d281ce48449b28b6d4b8ad2e8d8225e9e7a8ff9d4f14704a9bcb6ed42f46c6f6
|
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 sha256:80388ee53553e300357c30f830a8f1abfccdbd279383d99ce712a0720c8b3cc0
|
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 sha256:97af1a55efca56a8747ad610e270129c690ac8b7223d042c2dd8d88596ac322a
|
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:ee785f2efeb6a576b6505d774e3619a49deee90e97f7a385808d255073eb3c09
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -311,3 +311,81 @@
|
|
311 |
{"current_steps": 311, "total_steps": 390, "loss": 0.2622, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "12:59:51", "remaining_time": "3:18:05"}
|
312 |
{"current_steps": 312, "total_steps": 390, "loss": 0.2568, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:02:19", "remaining_time": "3:15:34"}
|
313 |
{"current_steps": 313, "total_steps": 390, "loss": 0.2395, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:05:33", "remaining_time": "3:13:15"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
311 |
{"current_steps": 311, "total_steps": 390, "loss": 0.2622, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "12:59:51", "remaining_time": "3:18:05"}
|
312 |
{"current_steps": 312, "total_steps": 390, "loss": 0.2568, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:02:19", "remaining_time": "3:15:34"}
|
313 |
{"current_steps": 313, "total_steps": 390, "loss": 0.2395, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:05:33", "remaining_time": "3:13:15"}
|
314 |
+
{"current_steps": 314, "total_steps": 390, "loss": 0.216, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "13:07:57", "remaining_time": "3:10:43"}
|
315 |
+
{"current_steps": 315, "total_steps": 390, "loss": 0.2217, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "13:10:32", "remaining_time": "3:08:13"}
|
316 |
+
{"current_steps": 316, "total_steps": 390, "loss": 0.2211, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "13:13:06", "remaining_time": "3:05:43"}
|
317 |
+
{"current_steps": 317, "total_steps": 390, "loss": 0.2184, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "13:15:37", "remaining_time": "3:03:13"}
|
318 |
+
{"current_steps": 318, "total_steps": 390, "loss": 0.2187, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "13:18:05", "remaining_time": "3:00:42"}
|
319 |
+
{"current_steps": 319, "total_steps": 390, "loss": 0.2182, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "13:20:38", "remaining_time": "2:58:11"}
|
320 |
+
{"current_steps": 320, "total_steps": 390, "loss": 0.2176, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "13:23:11", "remaining_time": "2:55:41"}
|
321 |
+
{"current_steps": 321, "total_steps": 390, "loss": 0.2154, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "13:25:49", "remaining_time": "2:53:12"}
|
322 |
+
{"current_steps": 322, "total_steps": 390, "loss": 0.2171, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "13:28:05", "remaining_time": "2:50:39"}
|
323 |
+
{"current_steps": 323, "total_steps": 390, "loss": 0.2175, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "13:30:29", "remaining_time": "2:48:07"}
|
324 |
+
{"current_steps": 324, "total_steps": 390, "loss": 0.228, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "13:33:01", "remaining_time": "2:45:36"}
|
325 |
+
{"current_steps": 325, "total_steps": 390, "loss": 0.2255, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "13:35:24", "remaining_time": "2:43:04"}
|
326 |
+
{"current_steps": 326, "total_steps": 390, "loss": 0.2261, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "13:37:52", "remaining_time": "2:40:33"}
|
327 |
+
{"current_steps": 327, "total_steps": 390, "loss": 0.2166, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "13:40:17", "remaining_time": "2:38:02"}
|
328 |
+
{"current_steps": 328, "total_steps": 390, "loss": 0.2094, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "13:42:44", "remaining_time": "2:35:31"}
|
329 |
+
{"current_steps": 329, "total_steps": 390, "loss": 0.2094, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "13:45:19", "remaining_time": "2:33:01"}
|
330 |
+
{"current_steps": 330, "total_steps": 390, "loss": 0.218, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "13:47:53", "remaining_time": "2:30:31"}
|
331 |
+
{"current_steps": 331, "total_steps": 390, "loss": 0.2282, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "13:50:31", "remaining_time": "2:28:02"}
|
332 |
+
{"current_steps": 332, "total_steps": 390, "loss": 0.2164, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "13:52:50", "remaining_time": "2:25:29"}
|
333 |
+
{"current_steps": 333, "total_steps": 390, "loss": 0.2063, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "13:55:14", "remaining_time": "2:22:58"}
|
334 |
+
{"current_steps": 334, "total_steps": 390, "loss": 0.2105, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "13:57:38", "remaining_time": "2:20:26"}
|
335 |
+
{"current_steps": 335, "total_steps": 390, "loss": 0.2101, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "13:59:57", "remaining_time": "2:17:54"}
|
336 |
+
{"current_steps": 336, "total_steps": 390, "loss": 0.2259, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "14:02:29", "remaining_time": "2:15:24"}
|
337 |
+
{"current_steps": 337, "total_steps": 390, "loss": 0.221, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "14:05:03", "remaining_time": "2:12:54"}
|
338 |
+
{"current_steps": 338, "total_steps": 390, "loss": 0.2306, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "14:07:34", "remaining_time": "2:10:23"}
|
339 |
+
{"current_steps": 339, "total_steps": 390, "loss": 0.2123, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "14:10:09", "remaining_time": "2:07:54"}
|
340 |
+
{"current_steps": 340, "total_steps": 390, "loss": 0.2065, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "14:12:58", "remaining_time": "2:05:26"}
|
341 |
+
{"current_steps": 341, "total_steps": 390, "loss": 0.2242, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "14:15:24", "remaining_time": "2:02:55"}
|
342 |
+
{"current_steps": 342, "total_steps": 390, "loss": 0.2216, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "14:18:02", "remaining_time": "2:00:25"}
|
343 |
+
{"current_steps": 343, "total_steps": 390, "loss": 0.2292, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "14:20:30", "remaining_time": "1:57:54"}
|
344 |
+
{"current_steps": 344, "total_steps": 390, "loss": 0.2176, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "14:22:56", "remaining_time": "1:55:23"}
|
345 |
+
{"current_steps": 345, "total_steps": 390, "loss": 0.2146, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "14:25:23", "remaining_time": "1:52:52"}
|
346 |
+
{"current_steps": 346, "total_steps": 390, "loss": 0.206, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "14:27:33", "remaining_time": "1:50:19"}
|
347 |
+
{"current_steps": 347, "total_steps": 390, "loss": 0.2265, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "14:29:53", "remaining_time": "1:47:47"}
|
348 |
+
{"current_steps": 348, "total_steps": 390, "loss": 0.2205, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "14:32:24", "remaining_time": "1:45:17"}
|
349 |
+
{"current_steps": 349, "total_steps": 390, "loss": 0.2207, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "14:35:03", "remaining_time": "1:42:48"}
|
350 |
+
{"current_steps": 350, "total_steps": 390, "loss": 0.2089, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "14:37:24", "remaining_time": "1:40:16"}
|
351 |
+
{"current_steps": 351, "total_steps": 390, "loss": 0.2173, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "14:39:50", "remaining_time": "1:37:45"}
|
352 |
+
{"current_steps": 352, "total_steps": 390, "loss": 0.2113, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "14:42:16", "remaining_time": "1:35:14"}
|
353 |
+
{"current_steps": 353, "total_steps": 390, "loss": 0.2179, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "14:44:50", "remaining_time": "1:32:44"}
|
354 |
+
{"current_steps": 354, "total_steps": 390, "loss": 0.2138, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "14:47:14", "remaining_time": "1:30:13"}
|
355 |
+
{"current_steps": 355, "total_steps": 390, "loss": 0.2171, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "14:49:37", "remaining_time": "1:27:42"}
|
356 |
+
{"current_steps": 356, "total_steps": 390, "loss": 0.2213, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "14:52:19", "remaining_time": "1:25:13"}
|
357 |
+
{"current_steps": 357, "total_steps": 390, "loss": 0.2206, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "14:54:52", "remaining_time": "1:22:43"}
|
358 |
+
{"current_steps": 358, "total_steps": 390, "loss": 0.2199, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "14:57:34", "remaining_time": "1:20:13"}
|
359 |
+
{"current_steps": 359, "total_steps": 390, "loss": 0.2303, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "14:59:58", "remaining_time": "1:17:42"}
|
360 |
+
{"current_steps": 360, "total_steps": 390, "loss": 0.2046, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "15:02:25", "remaining_time": "1:15:12"}
|
361 |
+
{"current_steps": 361, "total_steps": 390, "loss": 0.2094, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "15:04:52", "remaining_time": "1:12:41"}
|
362 |
+
{"current_steps": 362, "total_steps": 390, "loss": 0.2168, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "15:07:21", "remaining_time": "1:10:10"}
|
363 |
+
{"current_steps": 363, "total_steps": 390, "loss": 0.2317, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "15:09:43", "remaining_time": "1:07:39"}
|
364 |
+
{"current_steps": 364, "total_steps": 390, "loss": 0.2074, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "15:11:56", "remaining_time": "1:05:08"}
|
365 |
+
{"current_steps": 365, "total_steps": 390, "loss": 0.2184, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "15:14:18", "remaining_time": "1:02:37"}
|
366 |
+
{"current_steps": 366, "total_steps": 390, "loss": 0.2091, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "15:16:52", "remaining_time": "1:00:07"}
|
367 |
+
{"current_steps": 367, "total_steps": 390, "loss": 0.2055, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "15:19:15", "remaining_time": "0:57:36"}
|
368 |
+
{"current_steps": 368, "total_steps": 390, "loss": 0.2252, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "15:21:36", "remaining_time": "0:55:05"}
|
369 |
+
{"current_steps": 369, "total_steps": 390, "loss": 0.2239, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "15:24:07", "remaining_time": "0:52:35"}
|
370 |
+
{"current_steps": 370, "total_steps": 390, "loss": 0.2163, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "15:26:40", "remaining_time": "0:50:05"}
|
371 |
+
{"current_steps": 371, "total_steps": 390, "loss": 0.2211, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "15:29:25", "remaining_time": "0:47:35"}
|
372 |
+
{"current_steps": 372, "total_steps": 390, "loss": 0.2167, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "15:32:06", "remaining_time": "0:45:06"}
|
373 |
+
{"current_steps": 373, "total_steps": 390, "loss": 0.2197, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "15:34:34", "remaining_time": "0:42:35"}
|
374 |
+
{"current_steps": 374, "total_steps": 390, "loss": 0.2027, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "15:36:58", "remaining_time": "0:40:05"}
|
375 |
+
{"current_steps": 375, "total_steps": 390, "loss": 0.2164, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "15:39:21", "remaining_time": "0:37:34"}
|
376 |
+
{"current_steps": 376, "total_steps": 390, "loss": 0.2227, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "15:41:44", "remaining_time": "0:35:03"}
|
377 |
+
{"current_steps": 377, "total_steps": 390, "loss": 0.2238, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "15:44:18", "remaining_time": "0:32:33"}
|
378 |
+
{"current_steps": 378, "total_steps": 390, "loss": 0.2196, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "15:46:47", "remaining_time": "0:30:03"}
|
379 |
+
{"current_steps": 379, "total_steps": 390, "loss": 0.2204, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "15:49:17", "remaining_time": "0:27:33"}
|
380 |
+
{"current_steps": 380, "total_steps": 390, "loss": 0.2168, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "15:51:46", "remaining_time": "0:25:02"}
|
381 |
+
{"current_steps": 381, "total_steps": 390, "loss": 0.2157, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "15:54:22", "remaining_time": "0:22:32"}
|
382 |
+
{"current_steps": 382, "total_steps": 390, "loss": 0.2235, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "15:57:01", "remaining_time": "0:20:02"}
|
383 |
+
{"current_steps": 383, "total_steps": 390, "loss": 0.2191, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "15:59:27", "remaining_time": "0:17:32"}
|
384 |
+
{"current_steps": 384, "total_steps": 390, "loss": 0.2104, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "16:01:54", "remaining_time": "0:15:01"}
|
385 |
+
{"current_steps": 385, "total_steps": 390, "loss": 0.2135, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "16:04:31", "remaining_time": "0:12:31"}
|
386 |
+
{"current_steps": 386, "total_steps": 390, "loss": 0.2079, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "16:06:53", "remaining_time": "0:10:01"}
|
387 |
+
{"current_steps": 387, "total_steps": 390, "loss": 0.2137, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "16:09:23", "remaining_time": "0:07:30"}
|
388 |
+
{"current_steps": 388, "total_steps": 390, "loss": 0.2064, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "16:11:50", "remaining_time": "0:05:00"}
|
389 |
+
{"current_steps": 389, "total_steps": 390, "loss": 0.2166, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "16:14:23", "remaining_time": "0:02:30"}
|
390 |
+
{"current_steps": 390, "total_steps": 390, "loss": 0.2166, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "16:16:51", "remaining_time": "0:00:00"}
|
391 |
+
{"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "16:18:38", "remaining_time": "0:00:00"}
|