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 sha256:3f6c813ec8b7177224f4d4485ac313bd115b442ecb2fc11702d3f1a26d881ccc
|
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 sha256:0bd5b307204f9c88c4980afa3b0197bf865026429a0b9a33cfc4ff64a6af154c
|
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:a0b35fc27cb7981c3eaa488d2df774ae5dbd56cb547a7ae876a0cda07bb29dfd
|
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:d8f4410f890118518e40691735a930c719307e454b23bd46baf4f4cca7e3dfb0
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -312,3 +312,80 @@
|
|
312 |
{"current_steps": 312, "total_steps": 390, "loss": 0.2589, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "11:43:37", "remaining_time": "2:55:54"}
|
313 |
{"current_steps": 313, "total_steps": 390, "loss": 0.2478, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "11:46:40", "remaining_time": "2:53:50"}
|
314 |
{"current_steps": 314, "total_steps": 390, "loss": 0.2321, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "11:48:46", "remaining_time": "2:51:33"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
312 |
{"current_steps": 312, "total_steps": 390, "loss": 0.2589, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "11:43:37", "remaining_time": "2:55:54"}
|
313 |
{"current_steps": 313, "total_steps": 390, "loss": 0.2478, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "11:46:40", "remaining_time": "2:53:50"}
|
314 |
{"current_steps": 314, "total_steps": 390, "loss": 0.2321, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "11:48:46", "remaining_time": "2:51:33"}
|
315 |
+
{"current_steps": 315, "total_steps": 390, "loss": 0.2214, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "11:51:00", "remaining_time": "2:49:17"}
|
316 |
+
{"current_steps": 316, "total_steps": 390, "loss": 0.2151, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "11:53:21", "remaining_time": "2:47:03"}
|
317 |
+
{"current_steps": 317, "total_steps": 390, "loss": 0.2247, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "11:55:34", "remaining_time": "2:44:47"}
|
318 |
+
{"current_steps": 318, "total_steps": 390, "loss": 0.2277, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "11:57:45", "remaining_time": "2:42:30"}
|
319 |
+
{"current_steps": 319, "total_steps": 390, "loss": 0.2167, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "12:00:05", "remaining_time": "2:40:16"}
|
320 |
+
{"current_steps": 320, "total_steps": 390, "loss": 0.2166, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "12:02:11", "remaining_time": "2:37:58"}
|
321 |
+
{"current_steps": 321, "total_steps": 390, "loss": 0.2107, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "12:04:18", "remaining_time": "2:35:41"}
|
322 |
+
{"current_steps": 322, "total_steps": 390, "loss": 0.2084, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "12:06:16", "remaining_time": "2:33:22"}
|
323 |
+
{"current_steps": 323, "total_steps": 390, "loss": 0.2119, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "12:08:14", "remaining_time": "2:31:03"}
|
324 |
+
{"current_steps": 324, "total_steps": 390, "loss": 0.3212, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "12:10:25", "remaining_time": "2:28:47"}
|
325 |
+
{"current_steps": 325, "total_steps": 390, "loss": 0.2363, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "12:12:42", "remaining_time": "2:26:32"}
|
326 |
+
{"current_steps": 326, "total_steps": 390, "loss": 0.2096, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "12:14:48", "remaining_time": "2:24:15"}
|
327 |
+
{"current_steps": 327, "total_steps": 390, "loss": 0.188, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "12:17:09", "remaining_time": "2:22:01"}
|
328 |
+
{"current_steps": 328, "total_steps": 390, "loss": 0.2302, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "12:19:17", "remaining_time": "2:19:44"}
|
329 |
+
{"current_steps": 329, "total_steps": 390, "loss": 0.2175, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "12:21:17", "remaining_time": "2:17:26"}
|
330 |
+
{"current_steps": 330, "total_steps": 390, "loss": 0.2153, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "12:23:37", "remaining_time": "2:15:12"}
|
331 |
+
{"current_steps": 331, "total_steps": 390, "loss": 0.2093, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "12:25:47", "remaining_time": "2:12:56"}
|
332 |
+
{"current_steps": 332, "total_steps": 390, "loss": 0.2133, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "12:27:53", "remaining_time": "2:10:39"}
|
333 |
+
{"current_steps": 333, "total_steps": 390, "loss": 0.2172, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "12:30:03", "remaining_time": "2:08:23"}
|
334 |
+
{"current_steps": 334, "total_steps": 390, "loss": 0.2198, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "12:32:17", "remaining_time": "2:06:07"}
|
335 |
+
{"current_steps": 335, "total_steps": 390, "loss": 0.2197, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "12:34:24", "remaining_time": "2:03:51"}
|
336 |
+
{"current_steps": 336, "total_steps": 390, "loss": 0.1961, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "12:36:31", "remaining_time": "2:01:35"}
|
337 |
+
{"current_steps": 337, "total_steps": 390, "loss": 0.2098, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "12:38:58", "remaining_time": "1:59:21"}
|
338 |
+
{"current_steps": 338, "total_steps": 390, "loss": 0.2042, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "12:41:10", "remaining_time": "1:57:06"}
|
339 |
+
{"current_steps": 339, "total_steps": 390, "loss": 0.2106, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "12:43:14", "remaining_time": "1:54:49"}
|
340 |
+
{"current_steps": 340, "total_steps": 390, "loss": 0.2282, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "12:45:32", "remaining_time": "1:52:34"}
|
341 |
+
{"current_steps": 341, "total_steps": 390, "loss": 0.218, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "12:47:36", "remaining_time": "1:50:18"}
|
342 |
+
{"current_steps": 342, "total_steps": 390, "loss": 0.2287, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "12:49:55", "remaining_time": "1:48:03"}
|
343 |
+
{"current_steps": 343, "total_steps": 390, "loss": 0.2251, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "12:52:08", "remaining_time": "1:45:48"}
|
344 |
+
{"current_steps": 344, "total_steps": 390, "loss": 0.2162, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "12:54:09", "remaining_time": "1:43:31"}
|
345 |
+
{"current_steps": 345, "total_steps": 390, "loss": 0.2224, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "12:56:32", "remaining_time": "1:41:17"}
|
346 |
+
{"current_steps": 346, "total_steps": 390, "loss": 0.2184, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "12:58:41", "remaining_time": "1:39:01"}
|
347 |
+
{"current_steps": 347, "total_steps": 390, "loss": 0.1964, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "13:00:56", "remaining_time": "1:36:46"}
|
348 |
+
{"current_steps": 348, "total_steps": 390, "loss": 0.2135, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "13:03:10", "remaining_time": "1:34:31"}
|
349 |
+
{"current_steps": 349, "total_steps": 390, "loss": 0.2265, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "13:05:38", "remaining_time": "1:32:17"}
|
350 |
+
{"current_steps": 350, "total_steps": 390, "loss": 0.235, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "13:08:03", "remaining_time": "1:30:03"}
|
351 |
+
{"current_steps": 351, "total_steps": 390, "loss": 0.2274, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "13:10:06", "remaining_time": "1:27:47"}
|
352 |
+
{"current_steps": 352, "total_steps": 390, "loss": 0.2011, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "13:12:15", "remaining_time": "1:25:31"}
|
353 |
+
{"current_steps": 353, "total_steps": 390, "loss": 0.2303, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "13:14:17", "remaining_time": "1:23:15"}
|
354 |
+
{"current_steps": 354, "total_steps": 390, "loss": 0.2376, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "13:16:28", "remaining_time": "1:20:59"}
|
355 |
+
{"current_steps": 355, "total_steps": 390, "loss": 0.193, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "13:18:29", "remaining_time": "1:18:43"}
|
356 |
+
{"current_steps": 356, "total_steps": 390, "loss": 0.2199, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "13:20:24", "remaining_time": "1:16:26"}
|
357 |
+
{"current_steps": 357, "total_steps": 390, "loss": 0.2104, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "13:22:22", "remaining_time": "1:14:10"}
|
358 |
+
{"current_steps": 358, "total_steps": 390, "loss": 0.2327, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "13:24:34", "remaining_time": "1:11:55"}
|
359 |
+
{"current_steps": 359, "total_steps": 390, "loss": 0.2152, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "13:26:54", "remaining_time": "1:09:40"}
|
360 |
+
{"current_steps": 360, "total_steps": 390, "loss": 0.2333, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "13:29:26", "remaining_time": "1:07:27"}
|
361 |
+
{"current_steps": 361, "total_steps": 390, "loss": 0.2204, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "13:31:43", "remaining_time": "1:05:12"}
|
362 |
+
{"current_steps": 362, "total_steps": 390, "loss": 0.239, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "13:33:55", "remaining_time": "1:02:57"}
|
363 |
+
{"current_steps": 363, "total_steps": 390, "loss": 0.2311, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "13:36:13", "remaining_time": "1:00:42"}
|
364 |
+
{"current_steps": 364, "total_steps": 390, "loss": 0.256, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "13:38:43", "remaining_time": "0:58:28"}
|
365 |
+
{"current_steps": 365, "total_steps": 390, "loss": 0.2274, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "13:40:54", "remaining_time": "0:56:13"}
|
366 |
+
{"current_steps": 366, "total_steps": 390, "loss": 0.2195, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "13:43:16", "remaining_time": "0:53:59"}
|
367 |
+
{"current_steps": 367, "total_steps": 390, "loss": 0.2064, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "13:45:27", "remaining_time": "0:51:43"}
|
368 |
+
{"current_steps": 368, "total_steps": 390, "loss": 0.2427, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "13:47:42", "remaining_time": "0:49:28"}
|
369 |
+
{"current_steps": 369, "total_steps": 390, "loss": 0.2267, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "13:49:50", "remaining_time": "0:47:13"}
|
370 |
+
{"current_steps": 370, "total_steps": 390, "loss": 0.2233, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "13:52:03", "remaining_time": "0:44:58"}
|
371 |
+
{"current_steps": 371, "total_steps": 390, "loss": 0.2134, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "13:54:13", "remaining_time": "0:42:43"}
|
372 |
+
{"current_steps": 372, "total_steps": 390, "loss": 0.2162, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "13:56:21", "remaining_time": "0:40:28"}
|
373 |
+
{"current_steps": 373, "total_steps": 390, "loss": 0.2057, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "13:58:26", "remaining_time": "0:38:12"}
|
374 |
+
{"current_steps": 374, "total_steps": 390, "loss": 0.2233, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "14:00:43", "remaining_time": "0:35:58"}
|
375 |
+
{"current_steps": 375, "total_steps": 390, "loss": 0.237, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "14:03:03", "remaining_time": "0:33:43"}
|
376 |
+
{"current_steps": 376, "total_steps": 390, "loss": 0.2077, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "14:05:12", "remaining_time": "0:31:28"}
|
377 |
+
{"current_steps": 377, "total_steps": 390, "loss": 0.2136, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "14:07:43", "remaining_time": "0:29:13"}
|
378 |
+
{"current_steps": 378, "total_steps": 390, "loss": 0.2387, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "14:09:59", "remaining_time": "0:26:59"}
|
379 |
+
{"current_steps": 379, "total_steps": 390, "loss": 0.225, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "14:12:09", "remaining_time": "0:24:43"}
|
380 |
+
{"current_steps": 380, "total_steps": 390, "loss": 0.2301, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "14:14:32", "remaining_time": "0:22:29"}
|
381 |
+
{"current_steps": 381, "total_steps": 390, "loss": 0.2351, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "14:16:53", "remaining_time": "0:20:14"}
|
382 |
+
{"current_steps": 382, "total_steps": 390, "loss": 0.2145, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "14:19:07", "remaining_time": "0:17:59"}
|
383 |
+
{"current_steps": 383, "total_steps": 390, "loss": 0.2136, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "14:21:07", "remaining_time": "0:15:44"}
|
384 |
+
{"current_steps": 384, "total_steps": 390, "loss": 0.219, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "14:23:23", "remaining_time": "0:13:29"}
|
385 |
+
{"current_steps": 385, "total_steps": 390, "loss": 0.218, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "14:25:49", "remaining_time": "0:11:14"}
|
386 |
+
{"current_steps": 386, "total_steps": 390, "loss": 0.2368, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "14:28:01", "remaining_time": "0:08:59"}
|
387 |
+
{"current_steps": 387, "total_steps": 390, "loss": 0.2154, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "14:30:18", "remaining_time": "0:06:44"}
|
388 |
+
{"current_steps": 388, "total_steps": 390, "loss": 0.2344, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "14:32:40", "remaining_time": "0:04:29"}
|
389 |
+
{"current_steps": 389, "total_steps": 390, "loss": 0.2147, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "14:34:43", "remaining_time": "0:02:14"}
|
390 |
+
{"current_steps": 390, "total_steps": 390, "loss": 0.2196, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "14:36:53", "remaining_time": "0:00:00"}
|
391 |
+
{"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "14:38:58", "remaining_time": "0:00:00"}
|