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 sha256:7b2f7ad4ee2f64287e51d5ffa881f55454ea18d9a9747f5c1e5709224d94e546
|
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 sha256:5a4376570e5ae3d01e40889fee4d3ac345ba0e6b6904785b8cbc9be5fb24cd33
|
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 sha256:4b66820e74114d48541e0901924cabe13635f2843695fa3db7559007b4e9a5d7
|
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 sha256:153b9497da6486be5d8d9bdeaa679e3268c56d7d6aa107a5c077d445f56090dc
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -311,3 +311,81 @@
|
|
311 |
{"current_steps": 311, "total_steps": 390, "loss": 0.2938, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "13:53:22", "remaining_time": "3:31:41"}
|
312 |
{"current_steps": 312, "total_steps": 390, "loss": 0.3017, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:56:08", "remaining_time": "3:29:02"}
|
313 |
{"current_steps": 313, "total_steps": 390, "loss": 0.2866, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:59:32", "remaining_time": "3:26:31"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
311 |
{"current_steps": 311, "total_steps": 390, "loss": 0.2938, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "13:53:22", "remaining_time": "3:31:41"}
|
312 |
{"current_steps": 312, "total_steps": 390, "loss": 0.3017, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:56:08", "remaining_time": "3:29:02"}
|
313 |
{"current_steps": 313, "total_steps": 390, "loss": 0.2866, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:59:32", "remaining_time": "3:26:31"}
|
314 |
+
{"current_steps": 314, "total_steps": 390, "loss": 0.2768, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:02:16", "remaining_time": "3:23:51"}
|
315 |
+
{"current_steps": 315, "total_steps": 390, "loss": 0.2752, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "14:05:03", "remaining_time": "3:21:12"}
|
316 |
+
{"current_steps": 316, "total_steps": 390, "loss": 0.2652, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "14:07:49", "remaining_time": "3:18:32"}
|
317 |
+
{"current_steps": 317, "total_steps": 390, "loss": 0.257, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "14:10:22", "remaining_time": "3:15:49"}
|
318 |
+
{"current_steps": 318, "total_steps": 390, "loss": 0.2723, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "14:12:53", "remaining_time": "3:13:06"}
|
319 |
+
{"current_steps": 319, "total_steps": 390, "loss": 0.2646, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "14:15:18", "remaining_time": "3:10:22"}
|
320 |
+
{"current_steps": 320, "total_steps": 390, "loss": 0.2645, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "14:17:52", "remaining_time": "3:07:39"}
|
321 |
+
{"current_steps": 321, "total_steps": 390, "loss": 0.2652, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "14:20:24", "remaining_time": "3:04:56"}
|
322 |
+
{"current_steps": 322, "total_steps": 390, "loss": 0.2661, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "14:23:06", "remaining_time": "3:02:16"}
|
323 |
+
{"current_steps": 323, "total_steps": 390, "loss": 0.2499, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "14:25:42", "remaining_time": "2:59:34"}
|
324 |
+
{"current_steps": 324, "total_steps": 390, "loss": 0.2628, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "14:28:16", "remaining_time": "2:56:52"}
|
325 |
+
{"current_steps": 325, "total_steps": 390, "loss": 0.2687, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "14:30:58", "remaining_time": "2:54:11"}
|
326 |
+
{"current_steps": 326, "total_steps": 390, "loss": 0.2599, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "14:33:34", "remaining_time": "2:51:29"}
|
327 |
+
{"current_steps": 327, "total_steps": 390, "loss": 0.2556, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "14:36:15", "remaining_time": "2:48:49"}
|
328 |
+
{"current_steps": 328, "total_steps": 390, "loss": 0.2608, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "14:38:41", "remaining_time": "2:46:05"}
|
329 |
+
{"current_steps": 329, "total_steps": 390, "loss": 0.2665, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "14:41:24", "remaining_time": "2:43:25"}
|
330 |
+
{"current_steps": 330, "total_steps": 390, "loss": 0.2631, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "14:44:10", "remaining_time": "2:40:45"}
|
331 |
+
{"current_steps": 331, "total_steps": 390, "loss": 0.2622, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "14:46:17", "remaining_time": "2:37:58"}
|
332 |
+
{"current_steps": 332, "total_steps": 390, "loss": 0.2666, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "14:48:57", "remaining_time": "2:35:17"}
|
333 |
+
{"current_steps": 333, "total_steps": 390, "loss": 0.264, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "14:51:37", "remaining_time": "2:32:37"}
|
334 |
+
{"current_steps": 334, "total_steps": 390, "loss": 0.2529, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "14:54:10", "remaining_time": "2:29:55"}
|
335 |
+
{"current_steps": 335, "total_steps": 390, "loss": 0.2674, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "14:56:52", "remaining_time": "2:27:14"}
|
336 |
+
{"current_steps": 336, "total_steps": 390, "loss": 0.2692, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "14:59:12", "remaining_time": "2:24:30"}
|
337 |
+
{"current_steps": 337, "total_steps": 390, "loss": 0.265, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "15:01:59", "remaining_time": "2:21:51"}
|
338 |
+
{"current_steps": 338, "total_steps": 390, "loss": 0.2661, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "15:04:45", "remaining_time": "2:19:11"}
|
339 |
+
{"current_steps": 339, "total_steps": 390, "loss": 0.2606, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "15:07:27", "remaining_time": "2:16:31"}
|
340 |
+
{"current_steps": 340, "total_steps": 390, "loss": 0.2631, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "15:09:59", "remaining_time": "2:13:49"}
|
341 |
+
{"current_steps": 341, "total_steps": 390, "loss": 0.2585, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "15:12:29", "remaining_time": "2:11:07"}
|
342 |
+
{"current_steps": 342, "total_steps": 390, "loss": 0.264, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "15:15:14", "remaining_time": "2:08:27"}
|
343 |
+
{"current_steps": 343, "total_steps": 390, "loss": 0.2684, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "15:17:59", "remaining_time": "2:05:47"}
|
344 |
+
{"current_steps": 344, "total_steps": 390, "loss": 0.2511, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "15:20:46", "remaining_time": "2:03:07"}
|
345 |
+
{"current_steps": 345, "total_steps": 390, "loss": 0.2558, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "15:23:32", "remaining_time": "2:00:27"}
|
346 |
+
{"current_steps": 346, "total_steps": 390, "loss": 0.2605, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "15:26:07", "remaining_time": "1:57:46"}
|
347 |
+
{"current_steps": 347, "total_steps": 390, "loss": 0.2643, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "15:28:54", "remaining_time": "1:55:06"}
|
348 |
+
{"current_steps": 348, "total_steps": 390, "loss": 0.2734, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "15:31:40", "remaining_time": "1:52:26"}
|
349 |
+
{"current_steps": 349, "total_steps": 390, "loss": 0.2709, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "15:34:27", "remaining_time": "1:49:46"}
|
350 |
+
{"current_steps": 350, "total_steps": 390, "loss": 0.2595, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "15:37:02", "remaining_time": "1:47:05"}
|
351 |
+
{"current_steps": 351, "total_steps": 390, "loss": 0.2717, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "15:39:41", "remaining_time": "1:44:24"}
|
352 |
+
{"current_steps": 352, "total_steps": 390, "loss": 0.2694, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "15:42:24", "remaining_time": "1:41:44"}
|
353 |
+
{"current_steps": 353, "total_steps": 390, "loss": 0.2627, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "15:45:06", "remaining_time": "1:39:03"}
|
354 |
+
{"current_steps": 354, "total_steps": 390, "loss": 0.2624, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "15:47:42", "remaining_time": "1:36:22"}
|
355 |
+
{"current_steps": 355, "total_steps": 390, "loss": 0.267, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "15:50:23", "remaining_time": "1:33:42"}
|
356 |
+
{"current_steps": 356, "total_steps": 390, "loss": 0.2624, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "15:53:14", "remaining_time": "1:31:02"}
|
357 |
+
{"current_steps": 357, "total_steps": 390, "loss": 0.2666, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "15:55:53", "remaining_time": "1:28:21"}
|
358 |
+
{"current_steps": 358, "total_steps": 390, "loss": 0.2541, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "15:58:26", "remaining_time": "1:25:40"}
|
359 |
+
{"current_steps": 359, "total_steps": 390, "loss": 0.2647, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "16:00:57", "remaining_time": "1:22:58"}
|
360 |
+
{"current_steps": 360, "total_steps": 390, "loss": 0.2687, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "16:03:50", "remaining_time": "1:20:19"}
|
361 |
+
{"current_steps": 361, "total_steps": 390, "loss": 0.2601, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "16:06:27", "remaining_time": "1:17:38"}
|
362 |
+
{"current_steps": 362, "total_steps": 390, "loss": 0.2665, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "16:09:12", "remaining_time": "1:14:57"}
|
363 |
+
{"current_steps": 363, "total_steps": 390, "loss": 0.2654, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "16:11:49", "remaining_time": "1:12:17"}
|
364 |
+
{"current_steps": 364, "total_steps": 390, "loss": 0.2629, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "16:14:22", "remaining_time": "1:09:35"}
|
365 |
+
{"current_steps": 365, "total_steps": 390, "loss": 0.2525, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "16:16:54", "remaining_time": "1:06:54"}
|
366 |
+
{"current_steps": 366, "total_steps": 390, "loss": 0.254, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "16:19:41", "remaining_time": "1:04:14"}
|
367 |
+
{"current_steps": 367, "total_steps": 390, "loss": 0.2604, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "16:22:15", "remaining_time": "1:01:33"}
|
368 |
+
{"current_steps": 368, "total_steps": 390, "loss": 0.2683, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "16:24:56", "remaining_time": "0:58:52"}
|
369 |
+
{"current_steps": 369, "total_steps": 390, "loss": 0.264, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "16:27:44", "remaining_time": "0:56:12"}
|
370 |
+
{"current_steps": 370, "total_steps": 390, "loss": 0.2657, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "16:30:22", "remaining_time": "0:53:32"}
|
371 |
+
{"current_steps": 371, "total_steps": 390, "loss": 0.2562, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "16:32:51", "remaining_time": "0:50:50"}
|
372 |
+
{"current_steps": 372, "total_steps": 390, "loss": 0.2496, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "16:35:14", "remaining_time": "0:48:09"}
|
373 |
+
{"current_steps": 373, "total_steps": 390, "loss": 0.2595, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "16:37:49", "remaining_time": "0:45:28"}
|
374 |
+
{"current_steps": 374, "total_steps": 390, "loss": 0.2604, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "16:40:25", "remaining_time": "0:42:47"}
|
375 |
+
{"current_steps": 375, "total_steps": 390, "loss": 0.2688, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "16:43:05", "remaining_time": "0:40:07"}
|
376 |
+
{"current_steps": 376, "total_steps": 390, "loss": 0.2679, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "16:45:41", "remaining_time": "0:37:26"}
|
377 |
+
{"current_steps": 377, "total_steps": 390, "loss": 0.2655, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "16:48:16", "remaining_time": "0:34:46"}
|
378 |
+
{"current_steps": 378, "total_steps": 390, "loss": 0.2643, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "16:50:56", "remaining_time": "0:32:05"}
|
379 |
+
{"current_steps": 379, "total_steps": 390, "loss": 0.2574, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "16:53:39", "remaining_time": "0:29:25"}
|
380 |
+
{"current_steps": 380, "total_steps": 390, "loss": 0.27, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "16:56:07", "remaining_time": "0:26:44"}
|
381 |
+
{"current_steps": 381, "total_steps": 390, "loss": 0.2625, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "16:58:51", "remaining_time": "0:24:04"}
|
382 |
+
{"current_steps": 382, "total_steps": 390, "loss": 0.2556, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "17:01:26", "remaining_time": "0:21:23"}
|
383 |
+
{"current_steps": 383, "total_steps": 390, "loss": 0.2733, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "17:04:15", "remaining_time": "0:18:43"}
|
384 |
+
{"current_steps": 384, "total_steps": 390, "loss": 0.2665, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "17:06:45", "remaining_time": "0:16:02"}
|
385 |
+
{"current_steps": 385, "total_steps": 390, "loss": 0.2727, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "17:09:45", "remaining_time": "0:13:22"}
|
386 |
+
{"current_steps": 386, "total_steps": 390, "loss": 0.2577, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "17:12:28", "remaining_time": "0:10:41"}
|
387 |
+
{"current_steps": 387, "total_steps": 390, "loss": 0.2585, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "17:15:06", "remaining_time": "0:08:01"}
|
388 |
+
{"current_steps": 388, "total_steps": 390, "loss": 0.2578, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "17:17:49", "remaining_time": "0:05:20"}
|
389 |
+
{"current_steps": 389, "total_steps": 390, "loss": 0.2544, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "17:20:38", "remaining_time": "0:02:40"}
|
390 |
+
{"current_steps": 390, "total_steps": 390, "loss": 0.2557, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:23:28", "remaining_time": "0:00:00"}
|
391 |
+
{"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "17:25:22", "remaining_time": "0:00:00"}
|