ryanmarten commited on
Commit
40be4e9
·
verified ·
1 Parent(s): 956274a

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:d1e8da1e3920f11e523f31a4691e383440590eb365f5be6e475538942177bfa6
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a0cee94bbb16110ac8cc12eeab4c0f3af329965d4ef2d7a5e7ea45a6b05cce5
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40c32afcdbbf1e6fa2a375ccd5d7119ef2bf83e4996c3aa92db0eef59c9da5ec
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18d8041c72994d3f03d7c88ad53742e30de790884ba1c7e6e6424bbd164911ca
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09ef38441e8e6e5a6d00e6fb9b05242868c078eedc61cd896abaaff869930666
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f604df9209e2eb968ce0416803aac98650ca6a2a0c1cbb15f1b7c1d8e5f968b
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:213b4807733942ddc8cba5f0fa40e55dc7f1affdcf6a6fdb22fa4a2752760ce7
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1da00387ade7fa3cd36e3ae43054c4f2c9f4fdbc8bbbabb84b26271734cf05
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -311,3 +311,104 @@
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.448, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "13:35:01", "remaining_time": "3:27:02"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4496, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:37:44", "remaining_time": "3:24:26"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4178, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:41:13", "remaining_time": "3:22:01"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
311
  {"current_steps": 311, "total_steps": 390, "loss": 0.448, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "13:35:01", "remaining_time": "3:27:02"}
312
  {"current_steps": 312, "total_steps": 390, "loss": 0.4496, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:37:44", "remaining_time": "3:24:26"}
313
  {"current_steps": 313, "total_steps": 390, "loss": 0.4178, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:41:13", "remaining_time": "3:22:01"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.399, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "13:43:53", "remaining_time": "3:19:24"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.3985, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "13:46:39", "remaining_time": "3:16:49"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.4074, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "13:49:32", "remaining_time": "3:14:15"}
317
+ {"current_steps": 317, "total_steps": 390, "loss": 0.4051, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "13:52:10", "remaining_time": "3:11:38"}
318
+ {"current_steps": 318, "total_steps": 390, "loss": 0.3931, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "13:54:42", "remaining_time": "3:08:59"}
319
+ {"current_steps": 319, "total_steps": 390, "loss": 0.3873, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "13:57:20", "remaining_time": "3:06:22"}
320
+ {"current_steps": 320, "total_steps": 390, "loss": 0.3996, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "13:59:55", "remaining_time": "3:03:43"}
321
+ {"current_steps": 321, "total_steps": 390, "loss": 0.4099, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "14:02:37", "remaining_time": "3:01:07"}
322
+ {"current_steps": 322, "total_steps": 390, "loss": 0.4104, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "14:05:20", "remaining_time": "2:58:31"}
323
+ {"current_steps": 323, "total_steps": 390, "loss": 0.4009, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "14:07:48", "remaining_time": "2:55:51"}
324
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3992, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "14:10:28", "remaining_time": "2:53:14"}
325
+ {"current_steps": 325, "total_steps": 390, "loss": 0.4069, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "14:12:55", "remaining_time": "2:50:35"}
326
+ {"current_steps": 326, "total_steps": 390, "loss": 0.404, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "14:15:38", "remaining_time": "2:47:58"}
327
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3919, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "14:18:14", "remaining_time": "2:45:20"}
328
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3983, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "14:20:48", "remaining_time": "2:42:42"}
329
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3876, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "14:23:30", "remaining_time": "2:40:06"}
330
+ {"current_steps": 330, "total_steps": 390, "loss": 0.4083, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "14:26:06", "remaining_time": "2:37:28"}
331
+ {"current_steps": 331, "total_steps": 390, "loss": 0.3925, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "14:28:44", "remaining_time": "2:34:50"}
332
+ {"current_steps": 332, "total_steps": 390, "loss": 0.3897, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "14:31:12", "remaining_time": "2:32:11"}
333
+ {"current_steps": 333, "total_steps": 390, "loss": 0.4029, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "14:33:43", "remaining_time": "2:29:33"}
334
+ {"current_steps": 334, "total_steps": 390, "loss": 0.4152, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "14:36:07", "remaining_time": "2:26:53"}
335
+ {"current_steps": 335, "total_steps": 390, "loss": 0.4129, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "14:38:30", "remaining_time": "2:24:13"}
336
+ {"current_steps": 313, "total_steps": 390, "loss": 0.4032, "lr": 4.5646621393177e-06, "epoch": 4.0128, "percentage": 80.26, "elapsed_time": "0:02:45", "remaining_time": "0:00:40"}
337
+ {"current_steps": 314, "total_steps": 390, "loss": 0.4093, "lr": 4.451449654204685e-06, "epoch": 4.0256, "percentage": 80.51, "elapsed_time": "0:05:26", "remaining_time": "0:01:19"}
338
+ {"current_steps": 315, "total_steps": 390, "loss": 0.3869, "lr": 4.339482751647557e-06, "epoch": 4.0384, "percentage": 80.77, "elapsed_time": "0:08:22", "remaining_time": "0:01:59"}
339
+ {"current_steps": 316, "total_steps": 390, "loss": 0.412, "lr": 4.228770401229824e-06, "epoch": 4.0512, "percentage": 81.03, "elapsed_time": "0:11:07", "remaining_time": "0:02:36"}
340
+ {"current_steps": 317, "total_steps": 390, "loss": 0.4017, "lr": 4.119321472033779e-06, "epoch": 4.064, "percentage": 81.28, "elapsed_time": "0:13:41", "remaining_time": "0:03:09"}
341
+ {"current_steps": 318, "total_steps": 390, "loss": 0.3936, "lr": 4.011144731929981e-06, "epoch": 4.0768, "percentage": 81.54, "elapsed_time": "0:16:13", "remaining_time": "0:03:40"}
342
+ {"current_steps": 319, "total_steps": 390, "loss": 0.3871, "lr": 3.904248846874894e-06, "epoch": 4.0896, "percentage": 81.79, "elapsed_time": "0:18:53", "remaining_time": "0:04:12"}
343
+ {"current_steps": 320, "total_steps": 390, "loss": 0.4061, "lr": 3.7986423802166705e-06, "epoch": 4.1024, "percentage": 82.05, "elapsed_time": "0:21:39", "remaining_time": "0:04:44"}
344
+ {"current_steps": 321, "total_steps": 390, "loss": 0.4118, "lr": 3.694333792009115e-06, "epoch": 4.1152, "percentage": 82.31, "elapsed_time": "0:24:22", "remaining_time": "0:05:14"}
345
+ {"current_steps": 322, "total_steps": 390, "loss": 0.399, "lr": 3.5913314383339937e-06, "epoch": 4.128, "percentage": 82.56, "elapsed_time": "0:26:54", "remaining_time": "0:05:40"}
346
+ {"current_steps": 323, "total_steps": 390, "loss": 0.4123, "lr": 3.4896435706316e-06, "epoch": 4.1408, "percentage": 82.82, "elapsed_time": "0:29:28", "remaining_time": "0:06:06"}
347
+ {"current_steps": 324, "total_steps": 390, "loss": 0.3944, "lr": 3.3892783350397675e-06, "epoch": 4.1536, "percentage": 83.08, "elapsed_time": "0:32:02", "remaining_time": "0:06:31"}
348
+ {"current_steps": 325, "total_steps": 390, "loss": 0.4028, "lr": 3.290243771741275e-06, "epoch": 4.1664, "percentage": 83.33, "elapsed_time": "0:34:37", "remaining_time": "0:06:55"}
349
+ {"current_steps": 326, "total_steps": 390, "loss": 0.4085, "lr": 3.1925478143197418e-06, "epoch": 4.1792, "percentage": 83.59, "elapsed_time": "0:37:17", "remaining_time": "0:07:19"}
350
+ {"current_steps": 327, "total_steps": 390, "loss": 0.3944, "lr": 3.0961982891241083e-06, "epoch": 4.192, "percentage": 83.85, "elapsed_time": "0:39:54", "remaining_time": "0:07:41"}
351
+ {"current_steps": 328, "total_steps": 390, "loss": 0.3969, "lr": 3.001202914641628e-06, "epoch": 4.2048, "percentage": 84.1, "elapsed_time": "0:42:26", "remaining_time": "0:08:01"}
352
+ {"current_steps": 329, "total_steps": 390, "loss": 0.3867, "lr": 2.907569300879596e-06, "epoch": 4.2176, "percentage": 84.36, "elapsed_time": "0:45:16", "remaining_time": "0:08:23"}
353
+ {"current_steps": 330, "total_steps": 390, "loss": 0.4033, "lr": 2.815304948755664e-06, "epoch": 4.2304, "percentage": 84.62, "elapsed_time": "0:47:48", "remaining_time": "0:08:41"}
354
+ {"current_steps": 331, "total_steps": 390, "loss": 0.3887, "lr": 2.7244172494969978e-06, "epoch": 4.2432, "percentage": 84.87, "elapsed_time": "0:50:26", "remaining_time": "0:08:59"}
355
+ {"current_steps": 332, "total_steps": 390, "loss": 0.4031, "lr": 2.6349134840481294e-06, "epoch": 4.256, "percentage": 85.13, "elapsed_time": "0:52:51", "remaining_time": "0:09:14"}
356
+ {"current_steps": 333, "total_steps": 390, "loss": 0.4081, "lr": 2.546800822487714e-06, "epoch": 4.2688, "percentage": 85.38, "elapsed_time": "0:55:23", "remaining_time": "0:09:28"}
357
+ {"current_steps": 334, "total_steps": 390, "loss": 0.408, "lr": 2.4600863234541338e-06, "epoch": 4.2816, "percentage": 85.64, "elapsed_time": "0:57:45", "remaining_time": "0:09:41"}
358
+ {"current_steps": 335, "total_steps": 390, "loss": 0.411, "lr": 2.374776933580025e-06, "epoch": 4.2943999999999996, "percentage": 85.9, "elapsed_time": "1:00:09", "remaining_time": "0:09:52"}
359
+ {"current_steps": 336, "total_steps": 390, "loss": 0.3926, "lr": 2.2908794869358044e-06, "epoch": 4.3072, "percentage": 86.15, "elapsed_time": "1:02:45", "remaining_time": "0:10:05"}
360
+ {"current_steps": 337, "total_steps": 390, "loss": 0.407, "lr": 2.2084007044821764e-06, "epoch": 4.32, "percentage": 86.41, "elapsed_time": "1:05:28", "remaining_time": "0:10:17"}
361
+ {"current_steps": 338, "total_steps": 390, "loss": 0.4039, "lr": 2.127347193531757e-06, "epoch": 4.3328, "percentage": 86.67, "elapsed_time": "1:08:12", "remaining_time": "0:10:29"}
362
+ {"current_steps": 339, "total_steps": 390, "loss": 0.4138, "lr": 2.0477254472197237e-06, "epoch": 4.3456, "percentage": 86.92, "elapsed_time": "1:10:46", "remaining_time": "0:10:38"}
363
+ {"current_steps": 340, "total_steps": 390, "loss": 0.4006, "lr": 1.96954184398368e-06, "epoch": 4.3584, "percentage": 87.18, "elapsed_time": "1:13:30", "remaining_time": "0:10:48"}
364
+ {"current_steps": 341, "total_steps": 390, "loss": 0.4149, "lr": 1.8928026470526917e-06, "epoch": 4.3712, "percentage": 87.44, "elapsed_time": "1:16:07", "remaining_time": "0:10:56"}
365
+ {"current_steps": 342, "total_steps": 390, "loss": 0.3935, "lr": 1.817514003945524e-06, "epoch": 4.384, "percentage": 87.69, "elapsed_time": "1:18:47", "remaining_time": "0:11:03"}
366
+ {"current_steps": 343, "total_steps": 390, "loss": 0.3968, "lr": 1.743681945978184e-06, "epoch": 4.3968, "percentage": 87.95, "elapsed_time": "1:21:37", "remaining_time": "0:11:11"}
367
+ {"current_steps": 344, "total_steps": 390, "loss": 0.398, "lr": 1.6713123877807413e-06, "epoch": 4.4096, "percentage": 88.21, "elapsed_time": "1:24:10", "remaining_time": "0:11:15"}
368
+ {"current_steps": 345, "total_steps": 390, "loss": 0.4141, "lr": 1.6004111268235156e-06, "epoch": 4.4224, "percentage": 88.46, "elapsed_time": "1:26:56", "remaining_time": "0:11:20"}
369
+ {"current_steps": 346, "total_steps": 390, "loss": 0.3971, "lr": 1.5309838429526714e-06, "epoch": 4.4352, "percentage": 88.72, "elapsed_time": "1:29:35", "remaining_time": "0:11:23"}
370
+ {"current_steps": 347, "total_steps": 390, "loss": 0.3979, "lr": 1.4630360979351644e-06, "epoch": 4.448, "percentage": 88.97, "elapsed_time": "1:32:28", "remaining_time": "0:11:27"}
371
+ {"current_steps": 348, "total_steps": 390, "loss": 0.3976, "lr": 1.396573335013236e-06, "epoch": 4.4608, "percentage": 89.23, "elapsed_time": "1:35:13", "remaining_time": "0:11:29"}
372
+ {"current_steps": 349, "total_steps": 390, "loss": 0.405, "lr": 1.3316008784683265e-06, "epoch": 4.4736, "percentage": 89.49, "elapsed_time": "1:37:49", "remaining_time": "0:11:29"}
373
+ {"current_steps": 350, "total_steps": 390, "loss": 0.3975, "lr": 1.2681239331945695e-06, "epoch": 4.4864, "percentage": 89.74, "elapsed_time": "1:40:16", "remaining_time": "0:11:27"}
374
+ {"current_steps": 351, "total_steps": 390, "loss": 0.4086, "lr": 1.2061475842818337e-06, "epoch": 4.4992, "percentage": 90.0, "elapsed_time": "1:42:50", "remaining_time": "0:11:25"}
375
+ {"current_steps": 352, "total_steps": 390, "loss": 0.3932, "lr": 1.1456767966083393e-06, "epoch": 4.5120000000000005, "percentage": 90.26, "elapsed_time": "1:45:15", "remaining_time": "0:11:21"}
376
+ {"current_steps": 353, "total_steps": 390, "loss": 0.3999, "lr": 1.086716414442952e-06, "epoch": 4.5248, "percentage": 90.51, "elapsed_time": "1:47:57", "remaining_time": "0:11:18"}
377
+ {"current_steps": 354, "total_steps": 390, "loss": 0.3875, "lr": 1.0292711610570904e-06, "epoch": 4.5376, "percentage": 90.77, "elapsed_time": "1:50:37", "remaining_time": "0:11:14"}
378
+ {"current_steps": 355, "total_steps": 390, "loss": 0.4014, "lr": 9.733456383463658e-07, "epoch": 4.5504, "percentage": 91.03, "elapsed_time": "1:53:07", "remaining_time": "0:11:09"}
379
+ {"current_steps": 356, "total_steps": 390, "loss": 0.4144, "lr": 9.189443264619102e-07, "epoch": 4.5632, "percentage": 91.28, "elapsed_time": "1:55:50", "remaining_time": "0:11:03"}
380
+ {"current_steps": 357, "total_steps": 390, "loss": 0.3973, "lr": 8.660715834514977e-07, "epoch": 4.576, "percentage": 91.54, "elapsed_time": "1:58:29", "remaining_time": "0:10:57"}
381
+ {"current_steps": 358, "total_steps": 390, "loss": 0.412, "lr": 8.147316449103959e-07, "epoch": 4.5888, "percentage": 91.79, "elapsed_time": "2:01:00", "remaining_time": "0:10:48"}
382
+ {"current_steps": 359, "total_steps": 390, "loss": 0.4181, "lr": 7.649286236420806e-07, "epoch": 4.6016, "percentage": 92.05, "elapsed_time": "2:03:37", "remaining_time": "0:10:40"}
383
+ {"current_steps": 360, "total_steps": 390, "loss": 0.4033, "lr": 7.166665093287539e-07, "epoch": 4.6144, "percentage": 92.31, "elapsed_time": "2:06:24", "remaining_time": "0:10:32"}
384
+ {"current_steps": 361, "total_steps": 390, "loss": 0.3985, "lr": 6.69949168211721e-07, "epoch": 4.6272, "percentage": 92.56, "elapsed_time": "2:09:03", "remaining_time": "0:10:22"}
385
+ {"current_steps": 362, "total_steps": 390, "loss": 0.3949, "lr": 6.247803427816945e-07, "epoch": 4.64, "percentage": 92.82, "elapsed_time": "2:11:44", "remaining_time": "0:10:11"}
386
+ {"current_steps": 363, "total_steps": 390, "loss": 0.3987, "lr": 5.811636514789598e-07, "epoch": 4.6528, "percentage": 93.08, "elapsed_time": "2:14:26", "remaining_time": "0:09:59"}
387
+ {"current_steps": 364, "total_steps": 390, "loss": 0.3987, "lr": 5.391025884035239e-07, "epoch": 4.6655999999999995, "percentage": 93.33, "elapsed_time": "2:16:55", "remaining_time": "0:09:46"}
388
+ {"current_steps": 365, "total_steps": 390, "loss": 0.4017, "lr": 4.986005230351954e-07, "epoch": 4.6784, "percentage": 93.59, "elapsed_time": "2:19:30", "remaining_time": "0:09:33"}
389
+ {"current_steps": 366, "total_steps": 390, "loss": 0.3932, "lr": 4.5966069996365993e-07, "epoch": 4.6912, "percentage": 93.85, "elapsed_time": "2:22:08", "remaining_time": "0:09:19"}
390
+ {"current_steps": 367, "total_steps": 390, "loss": 0.3837, "lr": 4.22286238628562e-07, "epoch": 4.704, "percentage": 94.1, "elapsed_time": "2:24:38", "remaining_time": "0:09:03"}
391
+ {"current_steps": 368, "total_steps": 390, "loss": 0.3947, "lr": 3.8648013306960664e-07, "epoch": 4.7168, "percentage": 94.36, "elapsed_time": "2:27:06", "remaining_time": "0:08:47"}
392
+ {"current_steps": 369, "total_steps": 390, "loss": 0.4044, "lr": 3.522452516867048e-07, "epoch": 4.7296, "percentage": 94.62, "elapsed_time": "2:29:42", "remaining_time": "0:08:31"}
393
+ {"current_steps": 370, "total_steps": 390, "loss": 0.4047, "lr": 3.1958433701019697e-07, "epoch": 4.7424, "percentage": 94.87, "elapsed_time": "2:32:19", "remaining_time": "0:08:14"}
394
+ {"current_steps": 371, "total_steps": 390, "loss": 0.4089, "lr": 2.8850000548115155e-07, "epoch": 4.7552, "percentage": 95.13, "elapsed_time": "2:35:07", "remaining_time": "0:07:56"}
395
+ {"current_steps": 372, "total_steps": 390, "loss": 0.3882, "lr": 2.5899474724174313e-07, "epoch": 4.768, "percentage": 95.38, "elapsed_time": "2:37:45", "remaining_time": "0:07:38"}
396
+ {"current_steps": 373, "total_steps": 390, "loss": 0.3876, "lr": 2.3107092593579905e-07, "epoch": 4.7808, "percentage": 95.64, "elapsed_time": "2:40:15", "remaining_time": "0:07:18"}
397
+ {"current_steps": 374, "total_steps": 390, "loss": 0.397, "lr": 2.0473077851942858e-07, "epoch": 4.7936, "percentage": 95.9, "elapsed_time": "2:43:00", "remaining_time": "0:06:58"}
398
+ {"current_steps": 375, "total_steps": 390, "loss": 0.4015, "lr": 1.799764150818306e-07, "epoch": 4.8064, "percentage": 96.15, "elapsed_time": "2:45:50", "remaining_time": "0:06:38"}
399
+ {"current_steps": 376, "total_steps": 390, "loss": 0.3901, "lr": 1.5680981867625566e-07, "epoch": 4.8192, "percentage": 96.41, "elapsed_time": "2:48:21", "remaining_time": "0:06:16"}
400
+ {"current_steps": 377, "total_steps": 390, "loss": 0.4175, "lr": 1.3523284516113955e-07, "epoch": 4.832, "percentage": 96.67, "elapsed_time": "2:50:56", "remaining_time": "0:05:53"}
401
+ {"current_steps": 378, "total_steps": 390, "loss": 0.3884, "lr": 1.1524722305144231e-07, "epoch": 4.8448, "percentage": 96.92, "elapsed_time": "2:53:36", "remaining_time": "0:05:30"}
402
+ {"current_steps": 379, "total_steps": 390, "loss": 0.4095, "lr": 9.685455338016347e-08, "epoch": 4.8576, "percentage": 97.18, "elapsed_time": "2:56:04", "remaining_time": "0:05:06"}
403
+ {"current_steps": 380, "total_steps": 390, "loss": 0.4089, "lr": 8.005630957010014e-08, "epoch": 4.8704, "percentage": 97.44, "elapsed_time": "2:58:50", "remaining_time": "0:04:42"}
404
+ {"current_steps": 381, "total_steps": 390, "loss": 0.4035, "lr": 6.485383731580142e-08, "epoch": 4.8832, "percentage": 97.69, "elapsed_time": "3:01:33", "remaining_time": "0:04:17"}
405
+ {"current_steps": 382, "total_steps": 390, "loss": 0.3995, "lr": 5.1248354475768034e-08, "epoch": 4.896, "percentage": 97.95, "elapsed_time": "3:04:07", "remaining_time": "0:03:51"}
406
+ {"current_steps": 383, "total_steps": 390, "loss": 0.4114, "lr": 3.924095097489922e-08, "epoch": 4.9088, "percentage": 98.21, "elapsed_time": "3:06:42", "remaining_time": "0:03:24"}
407
+ {"current_steps": 384, "total_steps": 390, "loss": 0.3931, "lr": 2.8832588717164766e-08, "epoch": 4.9216, "percentage": 98.46, "elapsed_time": "3:09:23", "remaining_time": "0:02:57"}
408
+ {"current_steps": 385, "total_steps": 390, "loss": 0.3886, "lr": 2.0024101508555604e-08, "epoch": 4.9344, "percentage": 98.72, "elapsed_time": "3:11:50", "remaining_time": "0:02:29"}
409
+ {"current_steps": 386, "total_steps": 390, "loss": 0.4167, "lr": 1.281619499029274e-08, "epoch": 4.9472000000000005, "percentage": 98.97, "elapsed_time": "3:14:40", "remaining_time": "0:02:01"}
410
+ {"current_steps": 387, "total_steps": 390, "loss": 0.4058, "lr": 7.209446582292501e-09, "epoch": 4.96, "percentage": 99.23, "elapsed_time": "3:16:59", "remaining_time": "0:01:31"}
411
+ {"current_steps": 388, "total_steps": 390, "loss": 0.3945, "lr": 3.2043054369057523e-09, "epoch": 4.9728, "percentage": 99.49, "elapsed_time": "3:19:39", "remaining_time": "0:01:01"}
412
+ {"current_steps": 389, "total_steps": 390, "loss": 0.3881, "lr": 8.010924029533406e-10, "epoch": 4.9856, "percentage": 99.74, "elapsed_time": "3:22:11", "remaining_time": "0:00:31"}
413
+ {"current_steps": 390, "total_steps": 390, "loss": 0.4067, "lr": 0.0, "epoch": 4.9984, "percentage": 100.0, "elapsed_time": "3:24:38", "remaining_time": "0:00:00"}
414
+ {"current_steps": 390, "total_steps": 390, "epoch": 4.9984, "percentage": 100.0, "elapsed_time": "3:26:02", "remaining_time": "0:00:00"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ad9625d327151c7375e3ff5654061d8943cf0eaa872ccff170eb71676263db9
3
- size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:828cc34765f3ca051d10457733c61edfeebe070c86ae7faff92608d4f33bb649
3
+ size 7352