ryanmarten commited on
Commit
332e9d8
·
verified ·
1 Parent(s): ef9047a

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 sha256:29e5fc1de9d81ce2b45a73ed8394a27abcf1139c15b9c86d8ef4ecc85942e8a5
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a929b5a6f074b23b274f07af5f34bf63984a376ff6c4f31fafd9b1e65dc3064d
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:d29e6c5f2fabfe3b6764bbaf6949ce9cae752ce01397444e97322b43d5c8822b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a82f782da7310981851f3416bfd682cad4300c032431b01f3e192fecc767901
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:fb130427b151a5599083c99e7d1ed08955a7262e83c3c40eb088038563e1adf0
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f3e348f851cc12a24a9041913f09444ed491dbad86fa34dbe6962d15088a0c2
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:bf7a7215cfba49d0db824e8adf243cec63e31ca6bf57b625f172317731af74df
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8866bbda9ed0dd8a45fa063d018705f0c803babfa748f92346031c158f61e6b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -313,3 +313,79 @@
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.2832, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "7:46:24", "remaining_time": "1:54:44"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.2363, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "7:47:52", "remaining_time": "1:53:14"}
315
  {"current_steps": 315, "total_steps": 390, "loss": 0.2323, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "7:49:21", "remaining_time": "1:51:45"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.2832, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "7:46:24", "remaining_time": "1:54:44"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.2363, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "7:47:52", "remaining_time": "1:53:14"}
315
  {"current_steps": 315, "total_steps": 390, "loss": 0.2323, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "7:49:21", "remaining_time": "1:51:45"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.221, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "7:50:37", "remaining_time": "1:50:12"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.2398, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "7:52:10", "remaining_time": "1:48:44"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.2433, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "7:53:30", "remaining_time": "1:47:12"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.2273, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "7:54:44", "remaining_time": "1:45:39"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.2617, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "7:56:18", "remaining_time": "1:44:11"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.2428, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "7:57:49", "remaining_time": "1:42:42"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.2578, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "7:59:16", "remaining_time": "1:41:12"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.2279, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "8:00:33", "remaining_time": "1:39:40"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.2049, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "8:01:58", "remaining_time": "1:38:10"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.2199, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "8:03:10", "remaining_time": "1:36:38"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.2506, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "8:04:51", "remaining_time": "1:35:11"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.2542, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "8:06:17", "remaining_time": "1:33:41"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.2612, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "8:08:03", "remaining_time": "1:32:15"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.2271, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "8:09:28", "remaining_time": "1:30:45"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.2137, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "8:10:47", "remaining_time": "1:29:14"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.2183, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "8:12:14", "remaining_time": "1:27:44"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.241, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "8:13:33", "remaining_time": "1:26:13"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.2303, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "8:15:01", "remaining_time": "1:24:44"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.2235, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "8:16:30", "remaining_time": "1:23:14"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.2344, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "8:17:58", "remaining_time": "1:21:45"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.2281, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "8:19:24", "remaining_time": "1:20:15"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.209, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "8:20:43", "remaining_time": "1:18:44"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.2193, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "8:22:09", "remaining_time": "1:17:15"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.2655, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "8:23:57", "remaining_time": "1:15:49"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.2253, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "8:25:19", "remaining_time": "1:14:18"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.2098, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "8:26:42", "remaining_time": "1:12:48"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.267, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "8:28:18", "remaining_time": "1:11:20"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.2232, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "8:29:44", "remaining_time": "1:09:50"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.2414, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "8:31:15", "remaining_time": "1:08:21"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.2045, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "8:32:36", "remaining_time": "1:06:51"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.2335, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "8:34:11", "remaining_time": "1:05:23"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.2209, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "8:35:31", "remaining_time": "1:03:52"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.1864, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "8:36:35", "remaining_time": "1:02:20"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.2314, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "8:37:54", "remaining_time": "1:00:50"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.2092, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "8:39:07", "remaining_time": "0:59:19"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.2363, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "8:40:33", "remaining_time": "0:57:50"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.2397, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "8:42:04", "remaining_time": "0:56:21"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.2287, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "8:43:39", "remaining_time": "0:54:53"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.2352, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "8:45:08", "remaining_time": "0:53:24"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.2277, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "8:46:31", "remaining_time": "0:51:54"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.2554, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "8:48:08", "remaining_time": "0:50:26"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.2334, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "8:49:36", "remaining_time": "0:48:57"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.2399, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "8:51:06", "remaining_time": "0:47:28"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.2449, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "8:52:32", "remaining_time": "0:45:59"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.2417, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "8:54:07", "remaining_time": "0:44:30"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.2259, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "8:55:31", "remaining_time": "0:43:01"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.2594, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "8:57:13", "remaining_time": "0:41:33"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.2081, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "8:58:36", "remaining_time": "0:40:03"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.212, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "8:59:57", "remaining_time": "0:38:34"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.2286, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "9:01:24", "remaining_time": "0:37:04"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.2691, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "9:03:04", "remaining_time": "0:35:36"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.2283, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "9:04:32", "remaining_time": "0:34:07"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.23, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "9:05:58", "remaining_time": "0:32:38"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.2571, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "9:07:48", "remaining_time": "0:31:10"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.2448, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "9:09:40", "remaining_time": "0:29:42"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.2143, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "9:11:14", "remaining_time": "0:28:13"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.2311, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "9:12:38", "remaining_time": "0:26:44"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.2481, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "9:14:04", "remaining_time": "0:25:15"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.2263, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "9:15:41", "remaining_time": "0:23:46"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.2247, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "9:17:17", "remaining_time": "0:22:17"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.2226, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "9:18:46", "remaining_time": "0:20:48"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.2046, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "9:19:58", "remaining_time": "0:19:18"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.2367, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "9:21:31", "remaining_time": "0:17:49"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.2205, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "9:23:03", "remaining_time": "0:16:20"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.2365, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "9:24:28", "remaining_time": "0:14:51"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.2448, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "9:26:00", "remaining_time": "0:13:22"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.2501, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "9:27:39", "remaining_time": "0:11:53"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.2355, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "9:29:10", "remaining_time": "0:10:24"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.2198, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "9:30:39", "remaining_time": "0:08:54"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.264, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "9:32:05", "remaining_time": "0:07:25"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.2275, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "9:33:37", "remaining_time": "0:05:56"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.2035, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "9:34:47", "remaining_time": "0:04:27"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.2154, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "9:36:13", "remaining_time": "0:02:58"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.2351, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "9:37:54", "remaining_time": "0:01:29"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.2106, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "9:39:15", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "9:41:13", "remaining_time": "0:00:00"}