Training in progress, step 600
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 4998056552
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7800117170cf82b55257c1707adcef8daad710f7cb64de8a9ad8e0e76049a110
|
| 3 |
size 4998056552
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915962464
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d33bdc13a5ab594e1d6d5d1093fd63f65f19a5bb3833eb85415983802d819cc
|
| 3 |
size 4915962464
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915962496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecd844151e6b7f9c65595211ee5132ae0ccdacc12a451cd1dcb4e1f1ea33c3a5
|
| 3 |
size 4915962496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2704357976
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcf99ddf29be9984cb6fe02fbb76153e12808be74b2fb9c543fe45de1e9a0966
|
| 3 |
size 2704357976
|
trainer_log.jsonl
CHANGED
|
@@ -548,3 +548,53 @@
|
|
| 548 |
{"current_steps": 548, "total_steps": 2820, "loss": 0.1214, "lr": 2.833179890384722e-05, "epoch": 0.3887903511883647, "percentage": 19.43, "elapsed_time": "1 day, 12:17:35", "remaining_time": "6 days, 6:28:17"}
|
| 549 |
{"current_steps": 549, "total_steps": 2820, "loss": 0.1173, "lr": 2.832372781990011e-05, "epoch": 0.38949982263213906, "percentage": 19.47, "elapsed_time": "1 day, 12:21:17", "remaining_time": "6 days, 6:23:10"}
|
| 550 |
{"current_steps": 550, "total_steps": 2820, "loss": 0.1077, "lr": 2.831563841365169e-05, "epoch": 0.3902092940759134, "percentage": 19.5, "elapsed_time": "1 day, 12:25:19", "remaining_time": "6 days, 6:19:25"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 548 |
{"current_steps": 548, "total_steps": 2820, "loss": 0.1214, "lr": 2.833179890384722e-05, "epoch": 0.3887903511883647, "percentage": 19.43, "elapsed_time": "1 day, 12:17:35", "remaining_time": "6 days, 6:28:17"}
|
| 549 |
{"current_steps": 549, "total_steps": 2820, "loss": 0.1173, "lr": 2.832372781990011e-05, "epoch": 0.38949982263213906, "percentage": 19.47, "elapsed_time": "1 day, 12:21:17", "remaining_time": "6 days, 6:23:10"}
|
| 550 |
{"current_steps": 550, "total_steps": 2820, "loss": 0.1077, "lr": 2.831563841365169e-05, "epoch": 0.3902092940759134, "percentage": 19.5, "elapsed_time": "1 day, 12:25:19", "remaining_time": "6 days, 6:19:25"}
|
| 551 |
+
{"current_steps": 551, "total_steps": 2820, "loss": 0.0849, "lr": 2.8307530696226224e-05, "epoch": 0.39091876551968785, "percentage": 19.54, "elapsed_time": "1 day, 12:30:15", "remaining_time": "6 days, 6:19:26"}
|
| 552 |
+
{"current_steps": 552, "total_steps": 2820, "loss": 0.1079, "lr": 2.8299404678773145e-05, "epoch": 0.3916282369634622, "percentage": 19.57, "elapsed_time": "1 day, 12:33:53", "remaining_time": "6 days, 6:14:02"}
|
| 553 |
+
{"current_steps": 553, "total_steps": 2820, "loss": 0.1224, "lr": 2.8291260372467064e-05, "epoch": 0.3923377084072366, "percentage": 19.61, "elapsed_time": "1 day, 12:37:40", "remaining_time": "6 days, 6:09:14"}
|
| 554 |
+
{"current_steps": 554, "total_steps": 2820, "loss": 0.0981, "lr": 2.8283097788507713e-05, "epoch": 0.393047179851011, "percentage": 19.65, "elapsed_time": "1 day, 12:41:37", "remaining_time": "6 days, 6:05:13"}
|
| 555 |
+
{"current_steps": 555, "total_steps": 2820, "loss": 0.0984, "lr": 2.8274916938119987e-05, "epoch": 0.3937566512947854, "percentage": 19.68, "elapsed_time": "1 day, 12:45:52", "remaining_time": "6 days, 6:02:20"}
|
| 556 |
+
{"current_steps": 556, "total_steps": 2820, "loss": 0.098, "lr": 2.826671783255389e-05, "epoch": 0.3944661227385598, "percentage": 19.72, "elapsed_time": "1 day, 12:49:25", "remaining_time": "6 days, 5:56:39"}
|
| 557 |
+
{"current_steps": 557, "total_steps": 2820, "loss": 0.1232, "lr": 2.8258500483084534e-05, "epoch": 0.39517559418233417, "percentage": 19.75, "elapsed_time": "1 day, 12:53:36", "remaining_time": "6 days, 5:53:33"}
|
| 558 |
+
{"current_steps": 558, "total_steps": 2820, "loss": 0.1419, "lr": 2.825026490101212e-05, "epoch": 0.39588506562610853, "percentage": 19.79, "elapsed_time": "1 day, 12:58:01", "remaining_time": "6 days, 5:51:19"}
|
| 559 |
+
{"current_steps": 559, "total_steps": 2820, "loss": 0.1186, "lr": 2.8242011097661904e-05, "epoch": 0.39659453706988296, "percentage": 19.82, "elapsed_time": "1 day, 13:01:29", "remaining_time": "6 days, 5:45:19"}
|
| 560 |
+
{"current_steps": 560, "total_steps": 2820, "loss": 0.1373, "lr": 2.8233739084384228e-05, "epoch": 0.3973040085136573, "percentage": 19.86, "elapsed_time": "1 day, 13:06:00", "remaining_time": "6 days, 5:43:33"}
|
| 561 |
+
{"current_steps": 561, "total_steps": 2820, "loss": 0.1317, "lr": 2.8225448872554454e-05, "epoch": 0.3980134799574317, "percentage": 19.89, "elapsed_time": "1 day, 13:09:56", "remaining_time": "6 days, 5:39:23"}
|
| 562 |
+
{"current_steps": 562, "total_steps": 2820, "loss": 0.096, "lr": 2.8217140473572974e-05, "epoch": 0.3987229514012061, "percentage": 19.93, "elapsed_time": "1 day, 13:13:50", "remaining_time": "6 days, 5:35:07"}
|
| 563 |
+
{"current_steps": 563, "total_steps": 2820, "loss": 0.1355, "lr": 2.8208813898865203e-05, "epoch": 0.3994324228449805, "percentage": 19.96, "elapsed_time": "1 day, 13:17:18", "remaining_time": "6 days, 5:29:04"}
|
| 564 |
+
{"current_steps": 564, "total_steps": 2820, "loss": 0.1245, "lr": 2.820046915988153e-05, "epoch": 0.40014189428875485, "percentage": 20.0, "elapsed_time": "1 day, 13:21:00", "remaining_time": "6 days, 5:24:03"}
|
| 565 |
+
{"current_steps": 565, "total_steps": 2820, "loss": 0.116, "lr": 2.8192106268097336e-05, "epoch": 0.4008513657325293, "percentage": 20.04, "elapsed_time": "1 day, 13:25:21", "remaining_time": "6 days, 5:21:31"}
|
| 566 |
+
{"current_steps": 566, "total_steps": 2820, "loss": 0.1156, "lr": 2.818372523501297e-05, "epoch": 0.40156083717630364, "percentage": 20.07, "elapsed_time": "1 day, 13:28:48", "remaining_time": "6 days, 5:15:31"}
|
| 567 |
+
{"current_steps": 567, "total_steps": 2820, "loss": 0.1405, "lr": 2.8175326072153714e-05, "epoch": 0.40227030862007807, "percentage": 20.11, "elapsed_time": "1 day, 13:33:30", "remaining_time": "6 days, 5:14:25"}
|
| 568 |
+
{"current_steps": 568, "total_steps": 2820, "loss": 0.1165, "lr": 2.816690879106979e-05, "epoch": 0.40297978006385243, "percentage": 20.14, "elapsed_time": "1 day, 13:37:33", "remaining_time": "6 days, 5:10:44"}
|
| 569 |
+
{"current_steps": 569, "total_steps": 2820, "loss": 0.163, "lr": 2.8158473403336335e-05, "epoch": 0.4036892515076268, "percentage": 20.18, "elapsed_time": "1 day, 13:41:05", "remaining_time": "6 days, 5:05:02"}
|
| 570 |
+
{"current_steps": 570, "total_steps": 2820, "loss": 0.0983, "lr": 2.8150019920553386e-05, "epoch": 0.4043987229514012, "percentage": 20.21, "elapsed_time": "1 day, 13:45:04", "remaining_time": "6 days, 5:01:04"}
|
| 571 |
+
{"current_steps": 571, "total_steps": 2820, "loss": 0.1233, "lr": 2.8141548354345855e-05, "epoch": 0.4051081943951756, "percentage": 20.25, "elapsed_time": "1 day, 13:48:16", "remaining_time": "6 days, 4:54:02"}
|
| 572 |
+
{"current_steps": 572, "total_steps": 2820, "loss": 0.1234, "lr": 2.813305871636354e-05, "epoch": 0.40581766583894996, "percentage": 20.28, "elapsed_time": "1 day, 13:52:12", "remaining_time": "6 days, 4:49:56"}
|
| 573 |
+
{"current_steps": 573, "total_steps": 2820, "loss": 0.1377, "lr": 2.812455101828107e-05, "epoch": 0.4065271372827244, "percentage": 20.32, "elapsed_time": "1 day, 13:56:10", "remaining_time": "6 days, 4:45:58"}
|
| 574 |
+
{"current_steps": 574, "total_steps": 2820, "loss": 0.1162, "lr": 2.8116025271797923e-05, "epoch": 0.40723660872649875, "percentage": 20.35, "elapsed_time": "1 day, 13:59:36", "remaining_time": "6 days, 4:39:50"}
|
| 575 |
+
{"current_steps": 575, "total_steps": 2820, "loss": 0.1022, "lr": 2.8107481488638392e-05, "epoch": 0.4079460801702732, "percentage": 20.39, "elapsed_time": "1 day, 14:03:12", "remaining_time": "6 days, 4:34:27"}
|
| 576 |
+
{"current_steps": 576, "total_steps": 2820, "loss": 0.1196, "lr": 2.8098919680551574e-05, "epoch": 0.40865555161404754, "percentage": 20.43, "elapsed_time": "1 day, 14:06:53", "remaining_time": "6 days, 4:29:19"}
|
| 577 |
+
{"current_steps": 577, "total_steps": 2820, "loss": 0.1131, "lr": 2.809033985931135e-05, "epoch": 0.4093650230578219, "percentage": 20.46, "elapsed_time": "1 day, 14:10:49", "remaining_time": "6 days, 4:25:15"}
|
| 578 |
+
{"current_steps": 578, "total_steps": 2820, "loss": 0.1178, "lr": 2.8081742036716385e-05, "epoch": 0.41007449450159633, "percentage": 20.5, "elapsed_time": "1 day, 14:14:49", "remaining_time": "6 days, 4:21:22"}
|
| 579 |
+
{"current_steps": 579, "total_steps": 2820, "loss": 0.1515, "lr": 2.8073126224590073e-05, "epoch": 0.4107839659453707, "percentage": 20.53, "elapsed_time": "1 day, 14:18:49", "remaining_time": "6 days, 4:17:32"}
|
| 580 |
+
{"current_steps": 580, "total_steps": 2820, "loss": 0.1467, "lr": 2.806449243478058e-05, "epoch": 0.41149343738914507, "percentage": 20.57, "elapsed_time": "1 day, 14:22:44", "remaining_time": "6 days, 4:13:19"}
|
| 581 |
+
{"current_steps": 581, "total_steps": 2820, "loss": 0.1382, "lr": 2.805584067916076e-05, "epoch": 0.4122029088329195, "percentage": 20.6, "elapsed_time": "1 day, 14:26:22", "remaining_time": "6 days, 4:08:05"}
|
| 582 |
+
{"current_steps": 582, "total_steps": 2820, "loss": 0.1224, "lr": 2.8047170969628203e-05, "epoch": 0.41291238027669386, "percentage": 20.64, "elapsed_time": "1 day, 14:30:18", "remaining_time": "6 days, 4:03:56"}
|
| 583 |
+
{"current_steps": 583, "total_steps": 2820, "loss": 0.1084, "lr": 2.8038483318105168e-05, "epoch": 0.4136218517204682, "percentage": 20.67, "elapsed_time": "1 day, 14:34:41", "remaining_time": "6 days, 4:01:34"}
|
| 584 |
+
{"current_steps": 584, "total_steps": 2820, "loss": 0.0942, "lr": 2.8029777736538598e-05, "epoch": 0.41433132316424265, "percentage": 20.71, "elapsed_time": "1 day, 14:38:32", "remaining_time": "6 days, 3:57:10"}
|
| 585 |
+
{"current_steps": 585, "total_steps": 2820, "loss": 0.0954, "lr": 2.802105423690009e-05, "epoch": 0.415040794608017, "percentage": 20.74, "elapsed_time": "1 day, 14:42:15", "remaining_time": "6 days, 3:52:14"}
|
| 586 |
+
{"current_steps": 586, "total_steps": 2820, "loss": 0.1028, "lr": 2.8012312831185875e-05, "epoch": 0.41575026605179144, "percentage": 20.78, "elapsed_time": "1 day, 14:46:19", "remaining_time": "6 days, 3:48:36"}
|
| 587 |
+
{"current_steps": 587, "total_steps": 2820, "loss": 0.14, "lr": 2.8003553531416818e-05, "epoch": 0.4164597374955658, "percentage": 20.82, "elapsed_time": "1 day, 14:50:17", "remaining_time": "6 days, 3:44:37"}
|
| 588 |
+
{"current_steps": 588, "total_steps": 2820, "loss": 0.0995, "lr": 2.799477634963838e-05, "epoch": 0.4171692089393402, "percentage": 20.85, "elapsed_time": "1 day, 14:53:47", "remaining_time": "6 days, 3:38:52"}
|
| 589 |
+
{"current_steps": 589, "total_steps": 2820, "loss": 0.1044, "lr": 2.798598129792063e-05, "epoch": 0.4178786803831146, "percentage": 20.89, "elapsed_time": "1 day, 14:57:15", "remaining_time": "6 days, 3:32:59"}
|
| 590 |
+
{"current_steps": 590, "total_steps": 2820, "loss": 0.0943, "lr": 2.797716838835819e-05, "epoch": 0.41858815182688897, "percentage": 20.92, "elapsed_time": "1 day, 15:00:38", "remaining_time": "6 days, 3:26:51"}
|
| 591 |
+
{"current_steps": 591, "total_steps": 2820, "loss": 0.1404, "lr": 2.7968337633070252e-05, "epoch": 0.41929762327066333, "percentage": 20.96, "elapsed_time": "1 day, 15:04:14", "remaining_time": "6 days, 3:21:29"}
|
| 592 |
+
{"current_steps": 592, "total_steps": 2820, "loss": 0.1078, "lr": 2.7959489044200553e-05, "epoch": 0.42000709471443776, "percentage": 20.99, "elapsed_time": "1 day, 15:07:52", "remaining_time": "6 days, 3:16:15"}
|
| 593 |
+
{"current_steps": 593, "total_steps": 2820, "loss": 0.1174, "lr": 2.795062263391734e-05, "epoch": 0.4207165661582121, "percentage": 21.03, "elapsed_time": "1 day, 15:11:39", "remaining_time": "6 days, 3:11:38"}
|
| 594 |
+
{"current_steps": 594, "total_steps": 2820, "loss": 0.1252, "lr": 2.7941738414413374e-05, "epoch": 0.42142603760198655, "percentage": 21.06, "elapsed_time": "1 day, 15:15:29", "remaining_time": "6 days, 3:07:08"}
|
| 595 |
+
{"current_steps": 595, "total_steps": 2820, "loss": 0.1609, "lr": 2.793283639790592e-05, "epoch": 0.4221355090457609, "percentage": 21.1, "elapsed_time": "1 day, 15:18:59", "remaining_time": "6 days, 3:01:26"}
|
| 596 |
+
{"current_steps": 596, "total_steps": 2820, "loss": 0.1041, "lr": 2.7923916596636692e-05, "epoch": 0.4228449804895353, "percentage": 21.13, "elapsed_time": "1 day, 15:22:38", "remaining_time": "6 days, 2:56:17"}
|
| 597 |
+
{"current_steps": 597, "total_steps": 2820, "loss": 0.0839, "lr": 2.7914979022871874e-05, "epoch": 0.4235544519333097, "percentage": 21.17, "elapsed_time": "1 day, 15:26:30", "remaining_time": "6 days, 2:52:00"}
|
| 598 |
+
{"current_steps": 598, "total_steps": 2820, "loss": 0.1249, "lr": 2.790602368890209e-05, "epoch": 0.4242639233770841, "percentage": 21.21, "elapsed_time": "1 day, 15:30:32", "remaining_time": "6 days, 2:48:15"}
|
| 599 |
+
{"current_steps": 599, "total_steps": 2820, "loss": 0.0968, "lr": 2.789705060704239e-05, "epoch": 0.42497339482085844, "percentage": 21.24, "elapsed_time": "1 day, 15:35:04", "remaining_time": "6 days, 2:46:26"}
|
| 600 |
+
{"current_steps": 600, "total_steps": 2820, "loss": 0.1286, "lr": 2.7888059789632228e-05, "epoch": 0.42568286626463286, "percentage": 21.28, "elapsed_time": "1 day, 15:39:16", "remaining_time": "6 days, 2:43:17"}
|