Training in progress, epoch 7
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:a4dbd112c37729018677b70019136338902f7191913b68a9f92369767635b409
|
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:ec139470237901c0b2dca073b9e1e742038f9795ccca3a309e76ec6191ffb661
|
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 sha256:262427ba221bf1e940f6ab5c0d0f7d07ee04706e7d622b14b8336e563d67866e
|
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:b6a664d3635d9b547e308c7af03828e120594a346f95fde9921b7eea3a5ee608
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -389,3 +389,58 @@
|
|
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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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"}
|
392 |
+
{"current_steps": 3850, "total_steps": 4392, "loss": 0.507, "lr": 5e-06, "epoch": 7.0095584888484295, "percentage": 87.66, "elapsed_time": "1 day, 11:15:43", "remaining_time": "4:57:50"}
|
393 |
+
{"current_steps": 3860, "total_steps": 4392, "loss": 0.4258, "lr": 5e-06, "epoch": 7.02776513427401, "percentage": 87.89, "elapsed_time": "1 day, 11:21:03", "remaining_time": "4:52:19"}
|
394 |
+
{"current_steps": 3870, "total_steps": 4392, "loss": 0.4304, "lr": 5e-06, "epoch": 7.04597177969959, "percentage": 88.11, "elapsed_time": "1 day, 11:26:23", "remaining_time": "4:46:48"}
|
395 |
+
{"current_steps": 3880, "total_steps": 4392, "loss": 0.4315, "lr": 5e-06, "epoch": 7.064178425125171, "percentage": 88.34, "elapsed_time": "1 day, 11:31:42", "remaining_time": "4:41:17"}
|
396 |
+
{"current_steps": 3890, "total_steps": 4392, "loss": 0.4321, "lr": 5e-06, "epoch": 7.082385070550751, "percentage": 88.57, "elapsed_time": "1 day, 11:37:02", "remaining_time": "4:35:46"}
|
397 |
+
{"current_steps": 3900, "total_steps": 4392, "loss": 0.4316, "lr": 5e-06, "epoch": 7.100591715976331, "percentage": 88.8, "elapsed_time": "1 day, 11:42:23", "remaining_time": "4:30:16"}
|
398 |
+
{"current_steps": 3910, "total_steps": 4392, "loss": 0.4352, "lr": 5e-06, "epoch": 7.118798361401912, "percentage": 89.03, "elapsed_time": "1 day, 11:47:44", "remaining_time": "4:24:45"}
|
399 |
+
{"current_steps": 3920, "total_steps": 4392, "loss": 0.4335, "lr": 5e-06, "epoch": 7.137005006827492, "percentage": 89.25, "elapsed_time": "1 day, 11:53:03", "remaining_time": "4:19:14"}
|
400 |
+
{"current_steps": 3930, "total_steps": 4392, "loss": 0.4344, "lr": 5e-06, "epoch": 7.155211652253072, "percentage": 89.48, "elapsed_time": "1 day, 11:58:24", "remaining_time": "4:13:44"}
|
401 |
+
{"current_steps": 3940, "total_steps": 4392, "loss": 0.4354, "lr": 5e-06, "epoch": 7.173418297678653, "percentage": 89.71, "elapsed_time": "1 day, 12:03:46", "remaining_time": "4:08:13"}
|
402 |
+
{"current_steps": 3950, "total_steps": 4392, "loss": 0.4337, "lr": 5e-06, "epoch": 7.191624943104233, "percentage": 89.94, "elapsed_time": "1 day, 12:09:08", "remaining_time": "4:02:43"}
|
403 |
+
{"current_steps": 3960, "total_steps": 4392, "loss": 0.4356, "lr": 5e-06, "epoch": 7.209831588529814, "percentage": 90.16, "elapsed_time": "1 day, 12:14:30", "remaining_time": "3:57:13"}
|
404 |
+
{"current_steps": 3970, "total_steps": 4392, "loss": 0.4346, "lr": 5e-06, "epoch": 7.2280382339553935, "percentage": 90.39, "elapsed_time": "1 day, 12:19:52", "remaining_time": "3:51:42"}
|
405 |
+
{"current_steps": 3980, "total_steps": 4392, "loss": 0.437, "lr": 5e-06, "epoch": 7.246244879380974, "percentage": 90.62, "elapsed_time": "1 day, 12:25:13", "remaining_time": "3:46:12"}
|
406 |
+
{"current_steps": 3990, "total_steps": 4392, "loss": 0.4373, "lr": 5e-06, "epoch": 7.264451524806554, "percentage": 90.85, "elapsed_time": "1 day, 12:30:31", "remaining_time": "3:40:41"}
|
407 |
+
{"current_steps": 4000, "total_steps": 4392, "loss": 0.437, "lr": 5e-06, "epoch": 7.282658170232135, "percentage": 91.07, "elapsed_time": "1 day, 12:35:53", "remaining_time": "3:35:11"}
|
408 |
+
{"current_steps": 4010, "total_steps": 4392, "loss": 0.4412, "lr": 5e-06, "epoch": 7.300864815657715, "percentage": 91.3, "elapsed_time": "1 day, 12:41:14", "remaining_time": "3:29:41"}
|
409 |
+
{"current_steps": 4020, "total_steps": 4392, "loss": 0.4404, "lr": 5e-06, "epoch": 7.319071461083295, "percentage": 91.53, "elapsed_time": "1 day, 12:46:35", "remaining_time": "3:24:11"}
|
410 |
+
{"current_steps": 4030, "total_steps": 4392, "loss": 0.4413, "lr": 5e-06, "epoch": 7.337278106508876, "percentage": 91.76, "elapsed_time": "1 day, 12:51:55", "remaining_time": "3:18:41"}
|
411 |
+
{"current_steps": 4040, "total_steps": 4392, "loss": 0.4374, "lr": 5e-06, "epoch": 7.355484751934456, "percentage": 91.99, "elapsed_time": "1 day, 12:57:17", "remaining_time": "3:13:11"}
|
412 |
+
{"current_steps": 4050, "total_steps": 4392, "loss": 0.4427, "lr": 5e-06, "epoch": 7.373691397360036, "percentage": 92.21, "elapsed_time": "1 day, 13:02:39", "remaining_time": "3:07:41"}
|
413 |
+
{"current_steps": 4060, "total_steps": 4392, "loss": 0.4408, "lr": 5e-06, "epoch": 7.391898042785617, "percentage": 92.44, "elapsed_time": "1 day, 13:08:01", "remaining_time": "3:02:11"}
|
414 |
+
{"current_steps": 4070, "total_steps": 4392, "loss": 0.4428, "lr": 5e-06, "epoch": 7.410104688211197, "percentage": 92.67, "elapsed_time": "1 day, 13:13:23", "remaining_time": "2:56:41"}
|
415 |
+
{"current_steps": 4080, "total_steps": 4392, "loss": 0.439, "lr": 5e-06, "epoch": 7.428311333636778, "percentage": 92.9, "elapsed_time": "1 day, 13:18:44", "remaining_time": "2:51:11"}
|
416 |
+
{"current_steps": 4090, "total_steps": 4392, "loss": 0.4408, "lr": 5e-06, "epoch": 7.4465179790623575, "percentage": 93.12, "elapsed_time": "1 day, 13:24:04", "remaining_time": "2:45:41"}
|
417 |
+
{"current_steps": 4100, "total_steps": 4392, "loss": 0.4426, "lr": 5e-06, "epoch": 7.464724624487938, "percentage": 93.35, "elapsed_time": "1 day, 13:29:26", "remaining_time": "2:40:12"}
|
418 |
+
{"current_steps": 4110, "total_steps": 4392, "loss": 0.4422, "lr": 5e-06, "epoch": 7.482931269913518, "percentage": 93.58, "elapsed_time": "1 day, 13:34:49", "remaining_time": "2:34:42"}
|
419 |
+
{"current_steps": 4120, "total_steps": 4392, "loss": 0.4433, "lr": 5e-06, "epoch": 7.501137915339099, "percentage": 93.81, "elapsed_time": "1 day, 13:40:11", "remaining_time": "2:29:12"}
|
420 |
+
{"current_steps": 4130, "total_steps": 4392, "loss": 0.4425, "lr": 5e-06, "epoch": 7.519344560764679, "percentage": 94.03, "elapsed_time": "1 day, 13:45:32", "remaining_time": "2:23:43"}
|
421 |
+
{"current_steps": 4140, "total_steps": 4392, "loss": 0.4447, "lr": 5e-06, "epoch": 7.537551206190259, "percentage": 94.26, "elapsed_time": "1 day, 13:50:53", "remaining_time": "2:18:13"}
|
422 |
+
{"current_steps": 4150, "total_steps": 4392, "loss": 0.4414, "lr": 5e-06, "epoch": 7.55575785161584, "percentage": 94.49, "elapsed_time": "1 day, 13:56:15", "remaining_time": "2:12:44"}
|
423 |
+
{"current_steps": 4160, "total_steps": 4392, "loss": 0.4475, "lr": 5e-06, "epoch": 7.57396449704142, "percentage": 94.72, "elapsed_time": "1 day, 14:01:38", "remaining_time": "2:07:14"}
|
424 |
+
{"current_steps": 4170, "total_steps": 4392, "loss": 0.4427, "lr": 5e-06, "epoch": 7.592171142467, "percentage": 94.95, "elapsed_time": "1 day, 14:07:01", "remaining_time": "2:01:45"}
|
425 |
+
{"current_steps": 4180, "total_steps": 4392, "loss": 0.4464, "lr": 5e-06, "epoch": 7.610377787892581, "percentage": 95.17, "elapsed_time": "1 day, 14:12:23", "remaining_time": "1:56:15"}
|
426 |
+
{"current_steps": 4190, "total_steps": 4392, "loss": 0.4459, "lr": 5e-06, "epoch": 7.628584433318161, "percentage": 95.4, "elapsed_time": "1 day, 14:17:47", "remaining_time": "1:50:46"}
|
427 |
+
{"current_steps": 4200, "total_steps": 4392, "loss": 0.4466, "lr": 5e-06, "epoch": 7.646791078743742, "percentage": 95.63, "elapsed_time": "1 day, 14:23:08", "remaining_time": "1:45:17"}
|
428 |
+
{"current_steps": 4210, "total_steps": 4392, "loss": 0.4449, "lr": 5e-06, "epoch": 7.6649977241693215, "percentage": 95.86, "elapsed_time": "1 day, 14:28:29", "remaining_time": "1:39:47"}
|
429 |
+
{"current_steps": 4220, "total_steps": 4392, "loss": 0.4491, "lr": 5e-06, "epoch": 7.683204369594902, "percentage": 96.08, "elapsed_time": "1 day, 14:33:48", "remaining_time": "1:34:18"}
|
430 |
+
{"current_steps": 4230, "total_steps": 4392, "loss": 0.4483, "lr": 5e-06, "epoch": 7.701411015020483, "percentage": 96.31, "elapsed_time": "1 day, 14:39:07", "remaining_time": "1:28:49"}
|
431 |
+
{"current_steps": 4240, "total_steps": 4392, "loss": 0.4475, "lr": 5e-06, "epoch": 7.719617660446063, "percentage": 96.54, "elapsed_time": "1 day, 14:44:28", "remaining_time": "1:23:19"}
|
432 |
+
{"current_steps": 4250, "total_steps": 4392, "loss": 0.451, "lr": 5e-06, "epoch": 7.737824305871643, "percentage": 96.77, "elapsed_time": "1 day, 14:49:49", "remaining_time": "1:17:50"}
|
433 |
+
{"current_steps": 4260, "total_steps": 4392, "loss": 0.448, "lr": 5e-06, "epoch": 7.756030951297223, "percentage": 96.99, "elapsed_time": "1 day, 14:55:10", "remaining_time": "1:12:21"}
|
434 |
+
{"current_steps": 4270, "total_steps": 4392, "loss": 0.4523, "lr": 5e-06, "epoch": 7.774237596722804, "percentage": 97.22, "elapsed_time": "1 day, 15:00:30", "remaining_time": "1:06:52"}
|
435 |
+
{"current_steps": 4280, "total_steps": 4392, "loss": 0.4515, "lr": 5e-06, "epoch": 7.792444242148385, "percentage": 97.45, "elapsed_time": "1 day, 15:05:52", "remaining_time": "1:01:23"}
|
436 |
+
{"current_steps": 4290, "total_steps": 4392, "loss": 0.448, "lr": 5e-06, "epoch": 7.810650887573964, "percentage": 97.68, "elapsed_time": "1 day, 15:11:12", "remaining_time": "0:55:54"}
|
437 |
+
{"current_steps": 4300, "total_steps": 4392, "loss": 0.452, "lr": 5e-06, "epoch": 7.828857532999545, "percentage": 97.91, "elapsed_time": "1 day, 15:16:31", "remaining_time": "0:50:25"}
|
438 |
+
{"current_steps": 4310, "total_steps": 4392, "loss": 0.4502, "lr": 5e-06, "epoch": 7.847064178425125, "percentage": 98.13, "elapsed_time": "1 day, 15:21:52", "remaining_time": "0:44:56"}
|
439 |
+
{"current_steps": 4320, "total_steps": 4392, "loss": 0.4508, "lr": 5e-06, "epoch": 7.865270823850706, "percentage": 98.36, "elapsed_time": "1 day, 15:27:12", "remaining_time": "0:39:27"}
|
440 |
+
{"current_steps": 4330, "total_steps": 4392, "loss": 0.4481, "lr": 5e-06, "epoch": 7.883477469276286, "percentage": 98.59, "elapsed_time": "1 day, 15:32:35", "remaining_time": "0:33:58"}
|
441 |
+
{"current_steps": 4340, "total_steps": 4392, "loss": 0.4508, "lr": 5e-06, "epoch": 7.901684114701866, "percentage": 98.82, "elapsed_time": "1 day, 15:37:57", "remaining_time": "0:28:29"}
|
442 |
+
{"current_steps": 4350, "total_steps": 4392, "loss": 0.4488, "lr": 5e-06, "epoch": 7.919890760127447, "percentage": 99.04, "elapsed_time": "1 day, 15:43:19", "remaining_time": "0:23:00"}
|
443 |
+
{"current_steps": 4360, "total_steps": 4392, "loss": 0.453, "lr": 5e-06, "epoch": 7.938097405553027, "percentage": 99.27, "elapsed_time": "1 day, 15:48:41", "remaining_time": "0:17:31"}
|
444 |
+
{"current_steps": 4370, "total_steps": 4392, "loss": 0.4519, "lr": 5e-06, "epoch": 7.956304050978607, "percentage": 99.5, "elapsed_time": "1 day, 15:54:03", "remaining_time": "0:12:03"}
|
445 |
+
{"current_steps": 4380, "total_steps": 4392, "loss": 0.4542, "lr": 5e-06, "epoch": 7.974510696404187, "percentage": 99.73, "elapsed_time": "1 day, 15:59:25", "remaining_time": "0:06:34"}
|
446 |
+
{"current_steps": 4390, "total_steps": 4392, "loss": 0.4505, "lr": 5e-06, "epoch": 7.992717341829768, "percentage": 99.95, "elapsed_time": "1 day, 16:04:44", "remaining_time": "0:01:05"}
|