Training in progress, step 208
Browse files- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- trainer_log.jsonl +34 -0
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4969539560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50a7626c3332382c720b25d7028428e6e693206a85b1d278123f350e6447c549
|
| 3 |
size 4969539560
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1912795688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:674ac2c674747082527a37e7013363c3374ff004d5b78edf91c3585792370cd4
|
| 3 |
size 1912795688
|
trainer_log.jsonl
CHANGED
|
@@ -679,3 +679,37 @@
|
|
| 679 |
{"current_steps": 191, "total_steps": 400, "loss": 0.7551, "lr": 6.664685702961344e-08, "epoch": 47.872727272727275, "percentage": 47.75, "elapsed_time": "0:23:08", "remaining_time": "0:25:19"}
|
| 680 |
{"current_steps": 192, "total_steps": 400, "loss": 0.6327, "lr": 6.626710018244986e-08, "epoch": 48.0, "percentage": 48.0, "elapsed_time": "0:23:11", "remaining_time": "0:25:07"}
|
| 681 |
{"current_steps": 192, "total_steps": 400, "eval_loss": 0.6752312183380127, "epoch": 48.0, "percentage": 48.0, "elapsed_time": "0:23:12", "remaining_time": "0:25:08"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 679 |
{"current_steps": 191, "total_steps": 400, "loss": 0.7551, "lr": 6.664685702961344e-08, "epoch": 47.872727272727275, "percentage": 47.75, "elapsed_time": "0:23:08", "remaining_time": "0:25:19"}
|
| 680 |
{"current_steps": 192, "total_steps": 400, "loss": 0.6327, "lr": 6.626710018244986e-08, "epoch": 48.0, "percentage": 48.0, "elapsed_time": "0:23:11", "remaining_time": "0:25:07"}
|
| 681 |
{"current_steps": 192, "total_steps": 400, "eval_loss": 0.6752312183380127, "epoch": 48.0, "percentage": 48.0, "elapsed_time": "0:23:12", "remaining_time": "0:25:08"}
|
| 682 |
+
{"current_steps": 193, "total_steps": 400, "loss": 0.7312, "lr": 6.588648530198504e-08, "epoch": 48.29090909090909, "percentage": 48.25, "elapsed_time": "0:23:37", "remaining_time": "0:25:19"}
|
| 683 |
+
{"current_steps": 194, "total_steps": 400, "loss": 0.7467, "lr": 6.550504137351574e-08, "epoch": 48.58181818181818, "percentage": 48.5, "elapsed_time": "0:23:44", "remaining_time": "0:25:12"}
|
| 684 |
+
{"current_steps": 195, "total_steps": 400, "loss": 0.6271, "lr": 6.512279744547392e-08, "epoch": 48.872727272727275, "percentage": 48.75, "elapsed_time": "0:23:51", "remaining_time": "0:25:04"}
|
| 685 |
+
{"current_steps": 196, "total_steps": 400, "loss": 0.7127, "lr": 6.473978262721462e-08, "epoch": 49.0, "percentage": 49.0, "elapsed_time": "0:23:53", "remaining_time": "0:24:52"}
|
| 686 |
+
{"current_steps": 197, "total_steps": 400, "loss": 0.7255, "lr": 6.435602608679917e-08, "epoch": 49.29090909090909, "percentage": 49.25, "elapsed_time": "0:24:00", "remaining_time": "0:24:44"}
|
| 687 |
+
{"current_steps": 198, "total_steps": 400, "loss": 0.6177, "lr": 6.397155704877387e-08, "epoch": 49.58181818181818, "percentage": 49.5, "elapsed_time": "0:24:07", "remaining_time": "0:24:36"}
|
| 688 |
+
{"current_steps": 199, "total_steps": 400, "loss": 0.7295, "lr": 6.358640479194451e-08, "epoch": 49.872727272727275, "percentage": 49.75, "elapsed_time": "0:24:14", "remaining_time": "0:24:28"}
|
| 689 |
+
{"current_steps": 200, "total_steps": 400, "loss": 0.7091, "lr": 6.320059864714664e-08, "epoch": 50.0, "percentage": 50.0, "elapsed_time": "0:24:17", "remaining_time": "0:24:17"}
|
| 690 |
+
{"current_steps": 201, "total_steps": 400, "loss": 0.7432, "lr": 6.281416799501187e-08, "epoch": 50.29090909090909, "percentage": 50.25, "elapsed_time": "0:24:24", "remaining_time": "0:24:09"}
|
| 691 |
+
{"current_steps": 202, "total_steps": 400, "loss": 0.676, "lr": 6.242714226373049e-08, "epoch": 50.58181818181818, "percentage": 50.5, "elapsed_time": "0:24:30", "remaining_time": "0:24:01"}
|
| 692 |
+
{"current_steps": 203, "total_steps": 400, "loss": 0.7086, "lr": 6.203955092681039e-08, "epoch": 50.872727272727275, "percentage": 50.75, "elapsed_time": "0:24:37", "remaining_time": "0:23:53"}
|
| 693 |
+
{"current_steps": 204, "total_steps": 400, "loss": 0.5264, "lr": 6.165142350083249e-08, "epoch": 51.0, "percentage": 51.0, "elapsed_time": "0:24:40", "remaining_time": "0:23:42"}
|
| 694 |
+
{"current_steps": 205, "total_steps": 400, "loss": 0.7346, "lr": 6.126278954320294e-08, "epoch": 51.29090909090909, "percentage": 51.25, "elapsed_time": "0:24:47", "remaining_time": "0:23:34"}
|
| 695 |
+
{"current_steps": 206, "total_steps": 400, "loss": 0.6239, "lr": 6.087367864990232e-08, "epoch": 51.58181818181818, "percentage": 51.5, "elapsed_time": "0:24:53", "remaining_time": "0:23:26"}
|
| 696 |
+
{"current_steps": 207, "total_steps": 400, "loss": 0.688, "lr": 6.048412045323163e-08, "epoch": 51.872727272727275, "percentage": 51.75, "elapsed_time": "0:25:00", "remaining_time": "0:23:19"}
|
| 697 |
+
{"current_steps": 208, "total_steps": 400, "loss": 0.6903, "lr": 6.00941446195558e-08, "epoch": 52.0, "percentage": 52.0, "elapsed_time": "0:25:03", "remaining_time": "0:23:08"}
|
| 698 |
+
{"current_steps": 208, "total_steps": 400, "eval_loss": 0.6604220271110535, "epoch": 52.0, "percentage": 52.0, "elapsed_time": "0:25:04", "remaining_time": "0:23:08"}
|
| 699 |
+
{"current_steps": 209, "total_steps": 400, "loss": 0.6428, "lr": 5.970378084704441e-08, "epoch": 52.29090909090909, "percentage": 52.25, "elapsed_time": "0:25:34", "remaining_time": "0:23:22"}
|
| 700 |
+
{"current_steps": 210, "total_steps": 400, "loss": 0.7572, "lr": 5.931305886341008e-08, "epoch": 52.58181818181818, "percentage": 52.5, "elapsed_time": "0:25:41", "remaining_time": "0:23:14"}
|
| 701 |
+
{"current_steps": 211, "total_steps": 400, "loss": 0.6545, "lr": 5.892200842364462e-08, "epoch": 52.872727272727275, "percentage": 52.75, "elapsed_time": "0:25:48", "remaining_time": "0:23:07"}
|
| 702 |
+
{"current_steps": 212, "total_steps": 400, "loss": 0.6439, "lr": 5.853065930775303e-08, "epoch": 53.0, "percentage": 53.0, "elapsed_time": "0:25:51", "remaining_time": "0:22:55"}
|
| 703 |
+
{"current_steps": 213, "total_steps": 400, "loss": 0.677, "lr": 5.813904131848564e-08, "epoch": 53.29090909090909, "percentage": 53.25, "elapsed_time": "0:25:58", "remaining_time": "0:22:48"}
|
| 704 |
+
{"current_steps": 214, "total_steps": 400, "loss": 0.6321, "lr": 5.7747184279068564e-08, "epoch": 53.58181818181818, "percentage": 53.5, "elapsed_time": "0:26:05", "remaining_time": "0:22:40"}
|
| 705 |
+
{"current_steps": 215, "total_steps": 400, "loss": 0.7326, "lr": 5.735511803093248e-08, "epoch": 53.872727272727275, "percentage": 53.75, "elapsed_time": "0:26:12", "remaining_time": "0:22:32"}
|
| 706 |
+
{"current_steps": 216, "total_steps": 400, "loss": 0.6819, "lr": 5.696287243144012e-08, "epoch": 54.0, "percentage": 54.0, "elapsed_time": "0:26:15", "remaining_time": "0:22:21"}
|
| 707 |
+
{"current_steps": 217, "total_steps": 400, "loss": 0.6655, "lr": 5.6570477351612554e-08, "epoch": 54.29090909090909, "percentage": 54.25, "elapsed_time": "0:26:22", "remaining_time": "0:22:14"}
|
| 708 |
+
{"current_steps": 218, "total_steps": 400, "loss": 0.6743, "lr": 5.61779626738543e-08, "epoch": 54.58181818181818, "percentage": 54.5, "elapsed_time": "0:26:29", "remaining_time": "0:22:06"}
|
| 709 |
+
{"current_steps": 219, "total_steps": 400, "loss": 0.711, "lr": 5.5785358289677765e-08, "epoch": 54.872727272727275, "percentage": 54.75, "elapsed_time": "0:26:35", "remaining_time": "0:21:58"}
|
| 710 |
+
{"current_steps": 220, "total_steps": 400, "loss": 0.6398, "lr": 5.539269409742683e-08, "epoch": 55.0, "percentage": 55.0, "elapsed_time": "0:26:39", "remaining_time": "0:21:48"}
|
| 711 |
+
{"current_steps": 221, "total_steps": 400, "loss": 0.6885, "lr": 5.5e-08, "epoch": 55.29090909090909, "percentage": 55.25, "elapsed_time": "0:26:45", "remaining_time": "0:21:40"}
|
| 712 |
+
{"current_steps": 222, "total_steps": 400, "loss": 0.6391, "lr": 5.460730590257318e-08, "epoch": 55.58181818181818, "percentage": 55.5, "elapsed_time": "0:26:52", "remaining_time": "0:21:32"}
|
| 713 |
+
{"current_steps": 223, "total_steps": 400, "loss": 0.6684, "lr": 5.421464171032224e-08, "epoch": 55.872727272727275, "percentage": 55.75, "elapsed_time": "0:27:00", "remaining_time": "0:21:25"}
|
| 714 |
+
{"current_steps": 224, "total_steps": 400, "loss": 0.7467, "lr": 5.382203732614572e-08, "epoch": 56.0, "percentage": 56.0, "elapsed_time": "0:27:02", "remaining_time": "0:21:15"}
|
| 715 |
+
{"current_steps": 224, "total_steps": 400, "eval_loss": 0.6532977819442749, "epoch": 56.0, "percentage": 56.0, "elapsed_time": "0:27:03", "remaining_time": "0:21:15"}
|