Training in progress, epoch 6
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 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e960cd5f7b257bd2b920a3e63ba4cb5530feb0065d352176ccb59f586797cfd7
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f34b62975493d7022fb5af99c5c7aa32e34a3f22af30c83c7712a8b13cc44109
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2831c338b02d84f735be92aa5cbd9a2feb74b943b191b0d3c3369e089097eb4
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d851b95326d9d058754c79a6da77fd010f0e13d43e69f1e29998e750d3b9ead
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -333,3 +333,59 @@
|
|
333 |
{"current_steps": 3280, "total_steps": 4392, "loss": 0.5522, "lr": 5e-06, "epoch": 5.971779699590351, "percentage": 74.68, "elapsed_time": "1 day, 5:54:53", "remaining_time": "10:08:30"}
|
334 |
{"current_steps": 3290, "total_steps": 4392, "loss": 0.5504, "lr": 5e-06, "epoch": 5.9899863450159305, "percentage": 74.91, "elapsed_time": "1 day, 6:00:16", "remaining_time": "10:03:00"}
|
335 |
{"current_steps": 3295, "total_steps": 4392, "eval_loss": 0.8121561408042908, "epoch": 5.999089667728721, "percentage": 75.02, "elapsed_time": "1 day, 6:09:36", "remaining_time": "10:02:28"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
333 |
{"current_steps": 3280, "total_steps": 4392, "loss": 0.5522, "lr": 5e-06, "epoch": 5.971779699590351, "percentage": 74.68, "elapsed_time": "1 day, 5:54:53", "remaining_time": "10:08:30"}
|
334 |
{"current_steps": 3290, "total_steps": 4392, "loss": 0.5504, "lr": 5e-06, "epoch": 5.9899863450159305, "percentage": 74.91, "elapsed_time": "1 day, 6:00:16", "remaining_time": "10:03:00"}
|
335 |
{"current_steps": 3295, "total_steps": 4392, "eval_loss": 0.8121561408042908, "epoch": 5.999089667728721, "percentage": 75.02, "elapsed_time": "1 day, 6:09:36", "remaining_time": "10:02:28"}
|
336 |
+
{"current_steps": 3300, "total_steps": 4392, "loss": 0.5616, "lr": 5e-06, "epoch": 6.008192990441511, "percentage": 75.14, "elapsed_time": "1 day, 6:13:22", "remaining_time": "10:00:03"}
|
337 |
+
{"current_steps": 3310, "total_steps": 4392, "loss": 0.4806, "lr": 5e-06, "epoch": 6.026399635867092, "percentage": 75.36, "elapsed_time": "1 day, 6:18:46", "remaining_time": "9:54:32"}
|
338 |
+
{"current_steps": 3320, "total_steps": 4392, "loss": 0.4807, "lr": 5e-06, "epoch": 6.044606281292672, "percentage": 75.59, "elapsed_time": "1 day, 6:24:09", "remaining_time": "9:49:00"}
|
339 |
+
{"current_steps": 3330, "total_steps": 4392, "loss": 0.48, "lr": 5e-06, "epoch": 6.0628129267182524, "percentage": 75.82, "elapsed_time": "1 day, 6:29:29", "remaining_time": "9:43:27"}
|
340 |
+
{"current_steps": 3340, "total_steps": 4392, "loss": 0.4814, "lr": 5e-06, "epoch": 6.081019572143832, "percentage": 76.05, "elapsed_time": "1 day, 6:34:49", "remaining_time": "9:37:54"}
|
341 |
+
{"current_steps": 3350, "total_steps": 4392, "loss": 0.4832, "lr": 5e-06, "epoch": 6.099226217569413, "percentage": 76.28, "elapsed_time": "1 day, 6:40:11", "remaining_time": "9:32:22"}
|
342 |
+
{"current_steps": 3360, "total_steps": 4392, "loss": 0.4836, "lr": 5e-06, "epoch": 6.117432862994993, "percentage": 76.5, "elapsed_time": "1 day, 6:45:33", "remaining_time": "9:26:50"}
|
343 |
+
{"current_steps": 3370, "total_steps": 4392, "loss": 0.4842, "lr": 5e-06, "epoch": 6.1356395084205735, "percentage": 76.73, "elapsed_time": "1 day, 6:50:56", "remaining_time": "9:21:19"}
|
344 |
+
{"current_steps": 3380, "total_steps": 4392, "loss": 0.4871, "lr": 5e-06, "epoch": 6.153846153846154, "percentage": 76.96, "elapsed_time": "1 day, 6:56:19", "remaining_time": "9:15:47"}
|
345 |
+
{"current_steps": 3390, "total_steps": 4392, "loss": 0.4891, "lr": 5e-06, "epoch": 6.172052799271734, "percentage": 77.19, "elapsed_time": "1 day, 7:01:42", "remaining_time": "9:10:16"}
|
346 |
+
{"current_steps": 3400, "total_steps": 4392, "loss": 0.4863, "lr": 5e-06, "epoch": 6.190259444697315, "percentage": 77.41, "elapsed_time": "1 day, 7:07:05", "remaining_time": "9:04:45"}
|
347 |
+
{"current_steps": 3410, "total_steps": 4392, "loss": 0.4847, "lr": 5e-06, "epoch": 6.2084660901228945, "percentage": 77.64, "elapsed_time": "1 day, 7:12:28", "remaining_time": "8:59:13"}
|
348 |
+
{"current_steps": 3420, "total_steps": 4392, "loss": 0.4872, "lr": 5e-06, "epoch": 6.226672735548475, "percentage": 77.87, "elapsed_time": "1 day, 7:17:50", "remaining_time": "8:53:42"}
|
349 |
+
{"current_steps": 3430, "total_steps": 4392, "loss": 0.4893, "lr": 5e-06, "epoch": 6.244879380974056, "percentage": 78.1, "elapsed_time": "1 day, 7:23:12", "remaining_time": "8:48:10"}
|
350 |
+
{"current_steps": 3440, "total_steps": 4392, "loss": 0.488, "lr": 5e-06, "epoch": 6.263086026399636, "percentage": 78.32, "elapsed_time": "1 day, 7:28:33", "remaining_time": "8:42:38"}
|
351 |
+
{"current_steps": 3450, "total_steps": 4392, "loss": 0.4926, "lr": 5e-06, "epoch": 6.2812926718252164, "percentage": 78.55, "elapsed_time": "1 day, 7:33:55", "remaining_time": "8:37:07"}
|
352 |
+
{"current_steps": 3460, "total_steps": 4392, "loss": 0.4903, "lr": 5e-06, "epoch": 6.299499317250796, "percentage": 78.78, "elapsed_time": "1 day, 7:39:16", "remaining_time": "8:31:35"}
|
353 |
+
{"current_steps": 3470, "total_steps": 4392, "loss": 0.4928, "lr": 5e-06, "epoch": 6.317705962676377, "percentage": 79.01, "elapsed_time": "1 day, 7:44:36", "remaining_time": "8:26:04"}
|
354 |
+
{"current_steps": 3480, "total_steps": 4392, "loss": 0.489, "lr": 5e-06, "epoch": 6.335912608101957, "percentage": 79.23, "elapsed_time": "1 day, 7:49:56", "remaining_time": "8:20:32"}
|
355 |
+
{"current_steps": 3490, "total_steps": 4392, "loss": 0.4895, "lr": 5e-06, "epoch": 6.3541192535275375, "percentage": 79.46, "elapsed_time": "1 day, 7:55:15", "remaining_time": "8:15:00"}
|
356 |
+
{"current_steps": 3500, "total_steps": 4392, "loss": 0.4874, "lr": 5e-06, "epoch": 6.372325898953118, "percentage": 79.69, "elapsed_time": "1 day, 8:00:35", "remaining_time": "8:09:28"}
|
357 |
+
{"current_steps": 3510, "total_steps": 4392, "loss": 0.4894, "lr": 5e-06, "epoch": 6.390532544378698, "percentage": 79.92, "elapsed_time": "1 day, 8:05:58", "remaining_time": "8:03:57"}
|
358 |
+
{"current_steps": 3520, "total_steps": 4392, "loss": 0.4924, "lr": 5e-06, "epoch": 6.408739189804279, "percentage": 80.15, "elapsed_time": "1 day, 8:11:20", "remaining_time": "7:58:26"}
|
359 |
+
{"current_steps": 3530, "total_steps": 4392, "loss": 0.4958, "lr": 5e-06, "epoch": 6.4269458352298585, "percentage": 80.37, "elapsed_time": "1 day, 8:16:41", "remaining_time": "7:52:55"}
|
360 |
+
{"current_steps": 3540, "total_steps": 4392, "loss": 0.4936, "lr": 5e-06, "epoch": 6.445152480655439, "percentage": 80.6, "elapsed_time": "1 day, 8:22:04", "remaining_time": "7:47:24"}
|
361 |
+
{"current_steps": 3550, "total_steps": 4392, "loss": 0.4904, "lr": 5e-06, "epoch": 6.46335912608102, "percentage": 80.83, "elapsed_time": "1 day, 8:27:26", "remaining_time": "7:41:53"}
|
362 |
+
{"current_steps": 3560, "total_steps": 4392, "loss": 0.4996, "lr": 5e-06, "epoch": 6.4815657715066, "percentage": 81.06, "elapsed_time": "1 day, 8:32:48", "remaining_time": "7:36:23"}
|
363 |
+
{"current_steps": 3570, "total_steps": 4392, "loss": 0.4958, "lr": 5e-06, "epoch": 6.49977241693218, "percentage": 81.28, "elapsed_time": "1 day, 8:38:10", "remaining_time": "7:30:52"}
|
364 |
+
{"current_steps": 3580, "total_steps": 4392, "loss": 0.4998, "lr": 5e-06, "epoch": 6.51797906235776, "percentage": 81.51, "elapsed_time": "1 day, 8:43:30", "remaining_time": "7:25:21"}
|
365 |
+
{"current_steps": 3590, "total_steps": 4392, "loss": 0.4942, "lr": 5e-06, "epoch": 6.536185707783341, "percentage": 81.74, "elapsed_time": "1 day, 8:48:51", "remaining_time": "7:19:50"}
|
366 |
+
{"current_steps": 3600, "total_steps": 4392, "loss": 0.4927, "lr": 5e-06, "epoch": 6.554392353208922, "percentage": 81.97, "elapsed_time": "1 day, 8:54:12", "remaining_time": "7:14:19"}
|
367 |
+
{"current_steps": 3610, "total_steps": 4392, "loss": 0.5009, "lr": 5e-06, "epoch": 6.5725989986345015, "percentage": 82.19, "elapsed_time": "1 day, 8:59:34", "remaining_time": "7:08:48"}
|
368 |
+
{"current_steps": 3620, "total_steps": 4392, "loss": 0.4902, "lr": 5e-06, "epoch": 6.590805644060082, "percentage": 82.42, "elapsed_time": "1 day, 9:04:57", "remaining_time": "7:03:18"}
|
369 |
+
{"current_steps": 3630, "total_steps": 4392, "loss": 0.5004, "lr": 5e-06, "epoch": 6.609012289485662, "percentage": 82.65, "elapsed_time": "1 day, 9:10:19", "remaining_time": "6:57:48"}
|
370 |
+
{"current_steps": 3640, "total_steps": 4392, "loss": 0.4972, "lr": 5e-06, "epoch": 6.627218934911243, "percentage": 82.88, "elapsed_time": "1 day, 9:15:42", "remaining_time": "6:52:18"}
|
371 |
+
{"current_steps": 3650, "total_steps": 4392, "loss": 0.4978, "lr": 5e-06, "epoch": 6.645425580336823, "percentage": 83.11, "elapsed_time": "1 day, 9:21:04", "remaining_time": "6:46:47"}
|
372 |
+
{"current_steps": 3660, "total_steps": 4392, "loss": 0.4962, "lr": 5e-06, "epoch": 6.663632225762403, "percentage": 83.33, "elapsed_time": "1 day, 9:26:24", "remaining_time": "6:41:16"}
|
373 |
+
{"current_steps": 3670, "total_steps": 4392, "loss": 0.4984, "lr": 5e-06, "epoch": 6.681838871187984, "percentage": 83.56, "elapsed_time": "1 day, 9:31:45", "remaining_time": "6:35:46"}
|
374 |
+
{"current_steps": 3680, "total_steps": 4392, "loss": 0.4995, "lr": 5e-06, "epoch": 6.700045516613564, "percentage": 83.79, "elapsed_time": "1 day, 9:37:08", "remaining_time": "6:30:16"}
|
375 |
+
{"current_steps": 3690, "total_steps": 4392, "loss": 0.5007, "lr": 5e-06, "epoch": 6.718252162039144, "percentage": 84.02, "elapsed_time": "1 day, 9:42:31", "remaining_time": "6:24:46"}
|
376 |
+
{"current_steps": 3700, "total_steps": 4392, "loss": 0.5, "lr": 5e-06, "epoch": 6.736458807464724, "percentage": 84.24, "elapsed_time": "1 day, 9:47:53", "remaining_time": "6:19:16"}
|
377 |
+
{"current_steps": 3710, "total_steps": 4392, "loss": 0.5003, "lr": 5e-06, "epoch": 6.754665452890305, "percentage": 84.47, "elapsed_time": "1 day, 9:53:13", "remaining_time": "6:13:45"}
|
378 |
+
{"current_steps": 3720, "total_steps": 4392, "loss": 0.498, "lr": 5e-06, "epoch": 6.772872098315886, "percentage": 84.7, "elapsed_time": "1 day, 9:58:36", "remaining_time": "6:08:15"}
|
379 |
+
{"current_steps": 3730, "total_steps": 4392, "loss": 0.4994, "lr": 5e-06, "epoch": 6.7910787437414655, "percentage": 84.93, "elapsed_time": "1 day, 10:03:56", "remaining_time": "6:02:45"}
|
380 |
+
{"current_steps": 3740, "total_steps": 4392, "loss": 0.4997, "lr": 5e-06, "epoch": 6.809285389167046, "percentage": 85.15, "elapsed_time": "1 day, 10:09:15", "remaining_time": "5:57:15"}
|
381 |
+
{"current_steps": 3750, "total_steps": 4392, "loss": 0.4982, "lr": 5e-06, "epoch": 6.827492034592626, "percentage": 85.38, "elapsed_time": "1 day, 10:14:34", "remaining_time": "5:51:44"}
|
382 |
+
{"current_steps": 3760, "total_steps": 4392, "loss": 0.5008, "lr": 5e-06, "epoch": 6.845698680018207, "percentage": 85.61, "elapsed_time": "1 day, 10:19:52", "remaining_time": "5:46:14"}
|
383 |
+
{"current_steps": 3770, "total_steps": 4392, "loss": 0.4983, "lr": 5e-06, "epoch": 6.8639053254437865, "percentage": 85.84, "elapsed_time": "1 day, 10:25:13", "remaining_time": "5:40:44"}
|
384 |
+
{"current_steps": 3780, "total_steps": 4392, "loss": 0.5012, "lr": 5e-06, "epoch": 6.882111970869367, "percentage": 86.07, "elapsed_time": "1 day, 10:30:34", "remaining_time": "5:35:14"}
|
385 |
+
{"current_steps": 3790, "total_steps": 4392, "loss": 0.4993, "lr": 5e-06, "epoch": 6.900318616294948, "percentage": 86.29, "elapsed_time": "1 day, 10:35:57", "remaining_time": "5:29:44"}
|
386 |
+
{"current_steps": 3800, "total_steps": 4392, "loss": 0.4969, "lr": 5e-06, "epoch": 6.918525261720528, "percentage": 86.52, "elapsed_time": "1 day, 10:41:19", "remaining_time": "5:24:14"}
|
387 |
+
{"current_steps": 3810, "total_steps": 4392, "loss": 0.4997, "lr": 5e-06, "epoch": 6.936731907146108, "percentage": 86.75, "elapsed_time": "1 day, 10:46:41", "remaining_time": "5:18:45"}
|
388 |
+
{"current_steps": 3820, "total_steps": 4392, "loss": 0.4995, "lr": 5e-06, "epoch": 6.954938552571688, "percentage": 86.98, "elapsed_time": "1 day, 10:52:01", "remaining_time": "5:13:15"}
|
389 |
+
{"current_steps": 3830, "total_steps": 4392, "loss": 0.5045, "lr": 5e-06, "epoch": 6.973145197997269, "percentage": 87.2, "elapsed_time": "1 day, 10:57:20", "remaining_time": "5:07:45"}
|
390 |
+
{"current_steps": 3840, "total_steps": 4392, "loss": 0.5002, "lr": 5e-06, "epoch": 6.99135184342285, "percentage": 87.43, "elapsed_time": "1 day, 11:02:40", "remaining_time": "5:02:15"}
|
391 |
+
{"current_steps": 3844, "total_steps": 4392, "eval_loss": 0.8599892854690552, "epoch": 6.998634501593082, "percentage": 87.52, "elapsed_time": "1 day, 11:11:30", "remaining_time": "5:01:01"}
|