Training in progress, step 48
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 sha256:1c38008e3916fec8e8f62afa5a3bd98fe7c5d26d66abc6e96d2d4af4fff2c184
|
| 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 sha256:9482d36f512837bb053f4653e6c9613c71d822c8b455d0f012e909689a04544a
|
| 3 |
size 1912795688
|
trainer_log.jsonl
CHANGED
|
@@ -509,3 +509,37 @@
|
|
| 509 |
{"current_steps": 31, "total_steps": 400, "loss": 0.79, "lr": 7.5e-08, "epoch": 7.872727272727273, "percentage": 7.75, "elapsed_time": "0:03:32", "remaining_time": "0:42:06"}
|
| 510 |
{"current_steps": 32, "total_steps": 400, "loss": 0.9105, "lr": 7.75e-08, "epoch": 8.0, "percentage": 8.0, "elapsed_time": "0:03:35", "remaining_time": "0:41:12"}
|
| 511 |
{"current_steps": 32, "total_steps": 400, "eval_loss": 0.7589532136917114, "epoch": 8.0, "percentage": 8.0, "elapsed_time": "0:03:35", "remaining_time": "0:41:21"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 509 |
{"current_steps": 31, "total_steps": 400, "loss": 0.79, "lr": 7.5e-08, "epoch": 7.872727272727273, "percentage": 7.75, "elapsed_time": "0:03:32", "remaining_time": "0:42:06"}
|
| 510 |
{"current_steps": 32, "total_steps": 400, "loss": 0.9105, "lr": 7.75e-08, "epoch": 8.0, "percentage": 8.0, "elapsed_time": "0:03:35", "remaining_time": "0:41:12"}
|
| 511 |
{"current_steps": 32, "total_steps": 400, "eval_loss": 0.7589532136917114, "epoch": 8.0, "percentage": 8.0, "elapsed_time": "0:03:35", "remaining_time": "0:41:21"}
|
| 512 |
+
{"current_steps": 33, "total_steps": 400, "loss": 0.7914, "lr": 8e-08, "epoch": 8.290909090909091, "percentage": 8.25, "elapsed_time": "0:04:00", "remaining_time": "0:44:35"}
|
| 513 |
+
{"current_steps": 34, "total_steps": 400, "loss": 0.8344, "lr": 8.249999999999999e-08, "epoch": 8.581818181818182, "percentage": 8.5, "elapsed_time": "0:04:07", "remaining_time": "0:44:24"}
|
| 514 |
+
{"current_steps": 35, "total_steps": 400, "loss": 0.7419, "lr": 8.5e-08, "epoch": 8.872727272727273, "percentage": 8.75, "elapsed_time": "0:04:13", "remaining_time": "0:44:07"}
|
| 515 |
+
{"current_steps": 36, "total_steps": 400, "loss": 0.8597, "lr": 8.75e-08, "epoch": 9.0, "percentage": 9.0, "elapsed_time": "0:04:16", "remaining_time": "0:43:17"}
|
| 516 |
+
{"current_steps": 37, "total_steps": 400, "loss": 0.7911, "lr": 9e-08, "epoch": 9.290909090909091, "percentage": 9.25, "elapsed_time": "0:04:23", "remaining_time": "0:43:05"}
|
| 517 |
+
{"current_steps": 38, "total_steps": 400, "loss": 0.852, "lr": 9.25e-08, "epoch": 9.581818181818182, "percentage": 9.5, "elapsed_time": "0:04:30", "remaining_time": "0:42:59"}
|
| 518 |
+
{"current_steps": 39, "total_steps": 400, "loss": 0.7942, "lr": 9.499999999999999e-08, "epoch": 9.872727272727273, "percentage": 9.75, "elapsed_time": "0:04:37", "remaining_time": "0:42:48"}
|
| 519 |
+
{"current_steps": 40, "total_steps": 400, "loss": 0.7006, "lr": 9.749999999999999e-08, "epoch": 10.0, "percentage": 10.0, "elapsed_time": "0:04:40", "remaining_time": "0:42:03"}
|
| 520 |
+
{"current_steps": 41, "total_steps": 400, "loss": 0.7496, "lr": 1e-07, "epoch": 10.290909090909091, "percentage": 10.25, "elapsed_time": "0:04:47", "remaining_time": "0:41:54"}
|
| 521 |
+
{"current_steps": 42, "total_steps": 400, "loss": 0.7978, "lr": 9.99982865378877e-08, "epoch": 10.581818181818182, "percentage": 10.5, "elapsed_time": "0:04:54", "remaining_time": "0:41:47"}
|
| 522 |
+
{"current_steps": 43, "total_steps": 400, "loss": 0.8437, "lr": 9.99931462820376e-08, "epoch": 10.872727272727273, "percentage": 10.75, "elapsed_time": "0:05:01", "remaining_time": "0:41:39"}
|
| 523 |
+
{"current_steps": 44, "total_steps": 400, "loss": 0.7926, "lr": 9.998457962390006e-08, "epoch": 11.0, "percentage": 11.0, "elapsed_time": "0:05:03", "remaining_time": "0:40:58"}
|
| 524 |
+
{"current_steps": 45, "total_steps": 400, "loss": 0.7521, "lr": 9.997258721585931e-08, "epoch": 11.290909090909091, "percentage": 11.25, "elapsed_time": "0:05:10", "remaining_time": "0:40:49"}
|
| 525 |
+
{"current_steps": 46, "total_steps": 400, "loss": 0.7497, "lr": 9.99571699711836e-08, "epoch": 11.581818181818182, "percentage": 11.5, "elapsed_time": "0:05:17", "remaining_time": "0:40:42"}
|
| 526 |
+
{"current_steps": 47, "total_steps": 400, "loss": 0.8709, "lr": 9.993832906395581e-08, "epoch": 11.872727272727273, "percentage": 11.75, "elapsed_time": "0:05:24", "remaining_time": "0:40:38"}
|
| 527 |
+
{"current_steps": 48, "total_steps": 400, "loss": 0.8193, "lr": 9.991606592898401e-08, "epoch": 12.0, "percentage": 12.0, "elapsed_time": "0:05:27", "remaining_time": "0:40:00"}
|
| 528 |
+
{"current_steps": 48, "total_steps": 400, "eval_loss": 0.7549822926521301, "epoch": 12.0, "percentage": 12.0, "elapsed_time": "0:05:28", "remaining_time": "0:40:06"}
|
| 529 |
+
{"current_steps": 49, "total_steps": 400, "loss": 0.8488, "lr": 9.989038226169209e-08, "epoch": 12.290909090909091, "percentage": 12.25, "elapsed_time": "0:05:57", "remaining_time": "0:42:40"}
|
| 530 |
+
{"current_steps": 50, "total_steps": 400, "loss": 0.7697, "lr": 9.986128001799076e-08, "epoch": 12.581818181818182, "percentage": 12.5, "elapsed_time": "0:06:04", "remaining_time": "0:42:33"}
|
| 531 |
+
{"current_steps": 51, "total_steps": 400, "loss": 0.769, "lr": 9.982876141412855e-08, "epoch": 12.872727272727273, "percentage": 12.75, "elapsed_time": "0:06:11", "remaining_time": "0:42:22"}
|
| 532 |
+
{"current_steps": 52, "total_steps": 400, "loss": 0.8111, "lr": 9.979282892652304e-08, "epoch": 13.0, "percentage": 13.0, "elapsed_time": "0:06:14", "remaining_time": "0:41:48"}
|
| 533 |
+
{"current_steps": 53, "total_steps": 400, "loss": 0.798, "lr": 9.975348529157229e-08, "epoch": 13.290909090909091, "percentage": 13.25, "elapsed_time": "0:06:21", "remaining_time": "0:41:39"}
|
| 534 |
+
{"current_steps": 54, "total_steps": 400, "loss": 0.8011, "lr": 9.971073350544643e-08, "epoch": 13.581818181818182, "percentage": 13.5, "elapsed_time": "0:06:28", "remaining_time": "0:41:30"}
|
| 535 |
+
{"current_steps": 55, "total_steps": 400, "loss": 0.7109, "lr": 9.966457682385949e-08, "epoch": 13.872727272727273, "percentage": 13.75, "elapsed_time": "0:06:35", "remaining_time": "0:41:23"}
|
| 536 |
+
{"current_steps": 56, "total_steps": 400, "loss": 0.969, "lr": 9.961501876182147e-08, "epoch": 14.0, "percentage": 14.0, "elapsed_time": "0:06:38", "remaining_time": "0:40:50"}
|
| 537 |
+
{"current_steps": 57, "total_steps": 400, "loss": 0.7757, "lr": 9.956206309337066e-08, "epoch": 14.290909090909091, "percentage": 14.25, "elapsed_time": "0:06:46", "remaining_time": "0:40:44"}
|
| 538 |
+
{"current_steps": 58, "total_steps": 400, "loss": 0.7974, "lr": 9.950571385128625e-08, "epoch": 14.581818181818182, "percentage": 14.5, "elapsed_time": "0:06:53", "remaining_time": "0:40:35"}
|
| 539 |
+
{"current_steps": 59, "total_steps": 400, "loss": 0.842, "lr": 9.94459753267812e-08, "epoch": 14.872727272727273, "percentage": 14.75, "elapsed_time": "0:06:59", "remaining_time": "0:40:26"}
|
| 540 |
+
{"current_steps": 60, "total_steps": 400, "loss": 0.7127, "lr": 9.938285206917541e-08, "epoch": 15.0, "percentage": 15.0, "elapsed_time": "0:07:02", "remaining_time": "0:39:55"}
|
| 541 |
+
{"current_steps": 61, "total_steps": 400, "loss": 0.7662, "lr": 9.931634888554937e-08, "epoch": 15.290909090909091, "percentage": 15.25, "elapsed_time": "0:07:10", "remaining_time": "0:39:51"}
|
| 542 |
+
{"current_steps": 62, "total_steps": 400, "loss": 0.7652, "lr": 9.924647084037797e-08, "epoch": 15.581818181818182, "percentage": 15.5, "elapsed_time": "0:07:16", "remaining_time": "0:39:40"}
|
| 543 |
+
{"current_steps": 63, "total_steps": 400, "loss": 0.854, "lr": 9.917322325514488e-08, "epoch": 15.872727272727273, "percentage": 15.75, "elapsed_time": "0:07:23", "remaining_time": "0:39:33"}
|
| 544 |
+
{"current_steps": 64, "total_steps": 400, "loss": 0.6939, "lr": 9.909661170793732e-08, "epoch": 16.0, "percentage": 16.0, "elapsed_time": "0:07:26", "remaining_time": "0:39:04"}
|
| 545 |
+
{"current_steps": 64, "total_steps": 400, "eval_loss": 0.7460314631462097, "epoch": 16.0, "percentage": 16.0, "elapsed_time": "0:07:27", "remaining_time": "0:39:08"}
|