ryanmarten commited on
Commit
9eb4283
·
verified ·
1 Parent(s): 5bea076

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 sha256:903131e87a8483acf71b18d7cc1f7bcfe585f2daf0eaf8116a24f499d724b51f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4bf381e7c6a551c3a13689c05cf5cad4939c826325ae8f9f99fc10b5668b314
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bdcfad7b5e398e0d03dd0de92c31113ccd8addf88d7723fba8cf5a5eed509f0
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8267d90494c44e22a1a51b07a6cd7f685b99f6154c8c8519210f3a9dbcb8a6d
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ed0005da36cceef0ddbc2885c3d8f8ab2eba6dd2486c08ee3c3889384fb6877
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c037b67790da7fee1f62cebd854554053f298c6e51947216756b035ecfe7bac9
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50194bf964167c433a899a6d09b7c242edcbd78b29ab629c639698186f079e47
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12a9855fb12af0263bbe253d76be8710d63f52f3f36d58db77d6b9acdb4de68
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -312,3 +312,80 @@
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.3415, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "12:49:55", "remaining_time": "3:12:28"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.3231, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "12:53:02", "remaining_time": "3:10:10"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3025, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "12:55:13", "remaining_time": "3:07:38"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.3415, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "12:49:55", "remaining_time": "3:12:28"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.3231, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "12:53:02", "remaining_time": "3:10:10"}
314
  {"current_steps": 314, "total_steps": 390, "loss": 0.3025, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "12:55:13", "remaining_time": "3:07:38"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.3507, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "12:57:29", "remaining_time": "3:05:06"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.3099, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "12:59:53", "remaining_time": "3:02:37"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.317, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "13:02:16", "remaining_time": "3:00:08"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.353, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "13:04:49", "remaining_time": "2:57:41"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.293, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "13:07:02", "remaining_time": "2:55:10"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.2994, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "13:09:24", "remaining_time": "2:52:40"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.288, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "13:11:45", "remaining_time": "2:50:11"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.2945, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "13:14:09", "remaining_time": "2:47:42"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.3367, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "13:16:41", "remaining_time": "2:45:15"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3352, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "13:19:05", "remaining_time": "2:42:46"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.3337, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "13:21:28", "remaining_time": "2:40:17"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.2992, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "13:23:44", "remaining_time": "2:37:47"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3486, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "13:26:24", "remaining_time": "2:35:21"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3206, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "13:28:47", "remaining_time": "2:32:52"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3264, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "13:31:11", "remaining_time": "2:30:24"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.3021, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "13:33:15", "remaining_time": "2:27:51"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.2989, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "13:35:35", "remaining_time": "2:25:22"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.2884, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "13:37:54", "remaining_time": "2:22:53"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.328, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "13:40:23", "remaining_time": "2:20:25"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.3155, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "13:42:41", "remaining_time": "2:17:56"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.3059, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "13:45:16", "remaining_time": "2:15:29"}
336
+ {"current_steps": 336, "total_steps": 390, "loss": 0.3278, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "13:47:42", "remaining_time": "2:13:01"}
337
+ {"current_steps": 337, "total_steps": 390, "loss": 0.3202, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "13:50:03", "remaining_time": "2:10:32"}
338
+ {"current_steps": 338, "total_steps": 390, "loss": 0.3045, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "13:52:37", "remaining_time": "2:08:05"}
339
+ {"current_steps": 339, "total_steps": 390, "loss": 0.3413, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "13:55:12", "remaining_time": "2:05:39"}
340
+ {"current_steps": 340, "total_steps": 390, "loss": 0.3571, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "13:57:52", "remaining_time": "2:03:13"}
341
+ {"current_steps": 341, "total_steps": 390, "loss": 0.3319, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "14:00:26", "remaining_time": "2:00:45"}
342
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3153, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "14:02:48", "remaining_time": "1:58:17"}
343
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3258, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "14:05:22", "remaining_time": "1:55:50"}
344
+ {"current_steps": 344, "total_steps": 390, "loss": 0.3031, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "14:07:44", "remaining_time": "1:53:21"}
345
+ {"current_steps": 345, "total_steps": 390, "loss": 0.3085, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "14:10:12", "remaining_time": "1:50:53"}
346
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3295, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "14:12:39", "remaining_time": "1:48:25"}
347
+ {"current_steps": 347, "total_steps": 390, "loss": 0.2994, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "14:14:57", "remaining_time": "1:45:56"}
348
+ {"current_steps": 348, "total_steps": 390, "loss": 0.3105, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "14:17:20", "remaining_time": "1:43:28"}
349
+ {"current_steps": 349, "total_steps": 390, "loss": 0.3173, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "14:19:48", "remaining_time": "1:41:00"}
350
+ {"current_steps": 350, "total_steps": 390, "loss": 0.3235, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "14:22:21", "remaining_time": "1:38:33"}
351
+ {"current_steps": 351, "total_steps": 390, "loss": 0.3042, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "14:24:48", "remaining_time": "1:36:05"}
352
+ {"current_steps": 352, "total_steps": 390, "loss": 0.3204, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "14:27:24", "remaining_time": "1:33:38"}
353
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3411, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "14:29:57", "remaining_time": "1:31:11"}
354
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3319, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "14:32:29", "remaining_time": "1:28:43"}
355
+ {"current_steps": 355, "total_steps": 390, "loss": 0.3234, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "14:34:57", "remaining_time": "1:26:15"}
356
+ {"current_steps": 356, "total_steps": 390, "loss": 0.3401, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "14:37:22", "remaining_time": "1:23:47"}
357
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3088, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "14:39:40", "remaining_time": "1:21:18"}
358
+ {"current_steps": 358, "total_steps": 390, "loss": 0.3153, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "14:42:08", "remaining_time": "1:18:51"}
359
+ {"current_steps": 359, "total_steps": 390, "loss": 0.3216, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "14:44:26", "remaining_time": "1:16:22"}
360
+ {"current_steps": 360, "total_steps": 390, "loss": 0.3093, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "14:46:38", "remaining_time": "1:13:53"}
361
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3091, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "14:48:54", "remaining_time": "1:11:24"}
362
+ {"current_steps": 362, "total_steps": 390, "loss": 0.2905, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "14:51:10", "remaining_time": "1:08:55"}
363
+ {"current_steps": 363, "total_steps": 390, "loss": 0.2995, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "14:53:13", "remaining_time": "1:06:26"}
364
+ {"current_steps": 364, "total_steps": 390, "loss": 0.2783, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "14:55:21", "remaining_time": "1:03:57"}
365
+ {"current_steps": 365, "total_steps": 390, "loss": 0.3508, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "14:57:52", "remaining_time": "1:01:29"}
366
+ {"current_steps": 366, "total_steps": 390, "loss": 0.3058, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "15:00:17", "remaining_time": "0:59:02"}
367
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3228, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "15:02:47", "remaining_time": "0:56:34"}
368
+ {"current_steps": 368, "total_steps": 390, "loss": 0.3045, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "15:05:03", "remaining_time": "0:54:06"}
369
+ {"current_steps": 369, "total_steps": 390, "loss": 0.308, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "15:07:18", "remaining_time": "0:51:38"}
370
+ {"current_steps": 370, "total_steps": 390, "loss": 0.3214, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "15:09:55", "remaining_time": "0:49:11"}
371
+ {"current_steps": 371, "total_steps": 390, "loss": 0.3227, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "15:12:11", "remaining_time": "0:46:42"}
372
+ {"current_steps": 372, "total_steps": 390, "loss": 0.3052, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "15:14:28", "remaining_time": "0:44:14"}
373
+ {"current_steps": 373, "total_steps": 390, "loss": 0.3402, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "15:16:59", "remaining_time": "0:41:47"}
374
+ {"current_steps": 374, "total_steps": 390, "loss": 0.325, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "15:19:20", "remaining_time": "0:39:19"}
375
+ {"current_steps": 375, "total_steps": 390, "loss": 0.3366, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "15:21:50", "remaining_time": "0:36:52"}
376
+ {"current_steps": 376, "total_steps": 390, "loss": 0.3392, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "15:24:17", "remaining_time": "0:34:24"}
377
+ {"current_steps": 377, "total_steps": 390, "loss": 0.2974, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "15:26:43", "remaining_time": "0:31:57"}
378
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3141, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "15:28:52", "remaining_time": "0:29:29"}
379
+ {"current_steps": 379, "total_steps": 390, "loss": 0.3358, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "15:31:29", "remaining_time": "0:27:02"}
380
+ {"current_steps": 380, "total_steps": 390, "loss": 0.3114, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "15:33:56", "remaining_time": "0:24:34"}
381
+ {"current_steps": 381, "total_steps": 390, "loss": 0.3149, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "15:36:21", "remaining_time": "0:22:07"}
382
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3388, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "15:38:54", "remaining_time": "0:19:39"}
383
+ {"current_steps": 383, "total_steps": 390, "loss": 0.3179, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "15:41:28", "remaining_time": "0:17:12"}
384
+ {"current_steps": 384, "total_steps": 390, "loss": 0.2996, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "15:44:01", "remaining_time": "0:14:45"}
385
+ {"current_steps": 385, "total_steps": 390, "loss": 0.295, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "15:46:14", "remaining_time": "0:12:17"}
386
+ {"current_steps": 386, "total_steps": 390, "loss": 0.3035, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "15:48:35", "remaining_time": "0:09:49"}
387
+ {"current_steps": 387, "total_steps": 390, "loss": 0.2965, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "15:50:55", "remaining_time": "0:07:22"}
388
+ {"current_steps": 388, "total_steps": 390, "loss": 0.34, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "15:53:26", "remaining_time": "0:04:54"}
389
+ {"current_steps": 389, "total_steps": 390, "loss": 0.2919, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "15:55:44", "remaining_time": "0:02:27"}
390
+ {"current_steps": 390, "total_steps": 390, "loss": 0.3017, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "15:58:09", "remaining_time": "0:00:00"}
391
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "16:00:07", "remaining_time": "0:00:00"}