Training in progress, step 80
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:d5696b0909841c30ce657da7fef89d416fda37a2d1d0a8e66831a5ea7676d6e4
|
| 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 sha256:8a7223ea8f99f7b799b24686be78454f9f72e8d03fef9f83c56d83584086be14
|
| 3 |
size 1912795688
|
trainer_log.jsonl
CHANGED
|
@@ -543,3 +543,37 @@
|
|
| 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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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"}
|
| 546 |
+
{"current_steps": 65, "total_steps": 400, "loss": 0.7894, "lr": 9.901664203302125e-08, "epoch": 16.29090909090909, "percentage": 16.25, "elapsed_time": "0:07:53", "remaining_time": "0:40:40"}
|
| 547 |
+
{"current_steps": 66, "total_steps": 400, "loss": 0.7476, "lr": 9.8933320320397e-08, "epoch": 16.581818181818182, "percentage": 16.5, "elapsed_time": "0:07:59", "remaining_time": "0:40:28"}
|
| 548 |
+
{"current_steps": 67, "total_steps": 400, "loss": 0.8294, "lr": 9.884665291533559e-08, "epoch": 16.87272727272727, "percentage": 16.75, "elapsed_time": "0:08:06", "remaining_time": "0:40:20"}
|
| 549 |
+
{"current_steps": 68, "total_steps": 400, "loss": 0.741, "lr": 9.875664641789545e-08, "epoch": 17.0, "percentage": 17.0, "elapsed_time": "0:08:09", "remaining_time": "0:39:51"}
|
| 550 |
+
{"current_steps": 69, "total_steps": 400, "loss": 0.7999, "lr": 9.866330768241983e-08, "epoch": 17.29090909090909, "percentage": 17.25, "elapsed_time": "0:08:16", "remaining_time": "0:39:42"}
|
| 551 |
+
{"current_steps": 70, "total_steps": 400, "loss": 0.8324, "lr": 9.856664381701484e-08, "epoch": 17.581818181818182, "percentage": 17.5, "elapsed_time": "0:08:23", "remaining_time": "0:39:32"}
|
| 552 |
+
{"current_steps": 71, "total_steps": 400, "loss": 0.7308, "lr": 9.846666218300807e-08, "epoch": 17.87272727272727, "percentage": 17.75, "elapsed_time": "0:08:29", "remaining_time": "0:39:22"}
|
| 553 |
+
{"current_steps": 72, "total_steps": 400, "loss": 0.7691, "lr": 9.836337039438803e-08, "epoch": 18.0, "percentage": 18.0, "elapsed_time": "0:08:33", "remaining_time": "0:38:58"}
|
| 554 |
+
{"current_steps": 73, "total_steps": 400, "loss": 0.7804, "lr": 9.825677631722435e-08, "epoch": 18.29090909090909, "percentage": 18.25, "elapsed_time": "0:08:39", "remaining_time": "0:38:49"}
|
| 555 |
+
{"current_steps": 74, "total_steps": 400, "loss": 0.808, "lr": 9.814688806906868e-08, "epoch": 18.581818181818182, "percentage": 18.5, "elapsed_time": "0:08:46", "remaining_time": "0:38:40"}
|
| 556 |
+
{"current_steps": 75, "total_steps": 400, "loss": 0.7593, "lr": 9.80337140183366e-08, "epoch": 18.87272727272727, "percentage": 18.75, "elapsed_time": "0:08:53", "remaining_time": "0:38:32"}
|
| 557 |
+
{"current_steps": 76, "total_steps": 400, "loss": 0.795, "lr": 9.791726278367021e-08, "epoch": 19.0, "percentage": 19.0, "elapsed_time": "0:08:56", "remaining_time": "0:38:07"}
|
| 558 |
+
{"current_steps": 77, "total_steps": 400, "loss": 0.8303, "lr": 9.779754323328191e-08, "epoch": 19.29090909090909, "percentage": 19.25, "elapsed_time": "0:09:03", "remaining_time": "0:37:58"}
|
| 559 |
+
{"current_steps": 78, "total_steps": 400, "loss": 0.7404, "lr": 9.767456448427896e-08, "epoch": 19.581818181818182, "percentage": 19.5, "elapsed_time": "0:09:09", "remaining_time": "0:37:50"}
|
| 560 |
+
{"current_steps": 79, "total_steps": 400, "loss": 0.8152, "lr": 9.754833590196926e-08, "epoch": 19.87272727272727, "percentage": 19.75, "elapsed_time": "0:09:16", "remaining_time": "0:37:43"}
|
| 561 |
+
{"current_steps": 80, "total_steps": 400, "loss": 0.6623, "lr": 9.741886709914803e-08, "epoch": 20.0, "percentage": 20.0, "elapsed_time": "0:09:20", "remaining_time": "0:37:20"}
|
| 562 |
+
{"current_steps": 80, "total_steps": 400, "eval_loss": 0.7418057918548584, "epoch": 20.0, "percentage": 20.0, "elapsed_time": "0:09:20", "remaining_time": "0:37:23"}
|
| 563 |
+
{"current_steps": 81, "total_steps": 400, "loss": 0.726, "lr": 9.728616793536587e-08, "epoch": 20.29090909090909, "percentage": 20.25, "elapsed_time": "0:09:49", "remaining_time": "0:38:43"}
|
| 564 |
+
{"current_steps": 82, "total_steps": 400, "loss": 0.7908, "lr": 9.715024851617789e-08, "epoch": 20.581818181818182, "percentage": 20.5, "elapsed_time": "0:09:56", "remaining_time": "0:38:34"}
|
| 565 |
+
{"current_steps": 83, "total_steps": 400, "loss": 0.8219, "lr": 9.701111919237408e-08, "epoch": 20.87272727272727, "percentage": 20.75, "elapsed_time": "0:10:03", "remaining_time": "0:38:24"}
|
| 566 |
+
{"current_steps": 84, "total_steps": 400, "loss": 0.7955, "lr": 9.68687905591911e-08, "epoch": 21.0, "percentage": 21.0, "elapsed_time": "0:10:06", "remaining_time": "0:38:03"}
|
| 567 |
+
{"current_steps": 85, "total_steps": 400, "loss": 0.8459, "lr": 9.672327345550542e-08, "epoch": 21.29090909090909, "percentage": 21.25, "elapsed_time": "0:10:14", "remaining_time": "0:37:57"}
|
| 568 |
+
{"current_steps": 86, "total_steps": 400, "loss": 0.7952, "lr": 9.65745789630079e-08, "epoch": 21.581818181818182, "percentage": 21.5, "elapsed_time": "0:10:21", "remaining_time": "0:37:47"}
|
| 569 |
+
{"current_steps": 87, "total_steps": 400, "loss": 0.6928, "lr": 9.642271840535982e-08, "epoch": 21.87272727272727, "percentage": 21.75, "elapsed_time": "0:10:28", "remaining_time": "0:37:40"}
|
| 570 |
+
{"current_steps": 88, "total_steps": 400, "loss": 0.7813, "lr": 9.626770334733058e-08, "epoch": 22.0, "percentage": 22.0, "elapsed_time": "0:10:31", "remaining_time": "0:37:17"}
|
| 571 |
+
{"current_steps": 89, "total_steps": 400, "loss": 0.783, "lr": 9.610954559391703e-08, "epoch": 22.29090909090909, "percentage": 22.25, "elapsed_time": "0:10:37", "remaining_time": "0:37:08"}
|
| 572 |
+
{"current_steps": 90, "total_steps": 400, "loss": 0.7859, "lr": 9.594825718944444e-08, "epoch": 22.581818181818182, "percentage": 22.5, "elapsed_time": "0:10:44", "remaining_time": "0:36:58"}
|
| 573 |
+
{"current_steps": 91, "total_steps": 400, "loss": 0.7784, "lr": 9.578385041664925e-08, "epoch": 22.87272727272727, "percentage": 22.75, "elapsed_time": "0:10:51", "remaining_time": "0:36:51"}
|
| 574 |
+
{"current_steps": 92, "total_steps": 400, "loss": 0.7613, "lr": 9.561633779574373e-08, "epoch": 23.0, "percentage": 23.0, "elapsed_time": "0:10:54", "remaining_time": "0:36:31"}
|
| 575 |
+
{"current_steps": 93, "total_steps": 400, "loss": 0.7708, "lr": 9.544573208346251e-08, "epoch": 23.29090909090909, "percentage": 23.25, "elapsed_time": "0:11:01", "remaining_time": "0:36:24"}
|
| 576 |
+
{"current_steps": 94, "total_steps": 400, "loss": 0.7975, "lr": 9.527204627209113e-08, "epoch": 23.581818181818182, "percentage": 23.5, "elapsed_time": "0:11:08", "remaining_time": "0:36:15"}
|
| 577 |
+
{"current_steps": 95, "total_steps": 400, "loss": 0.7533, "lr": 9.509529358847655e-08, "epoch": 23.87272727272727, "percentage": 23.75, "elapsed_time": "0:11:15", "remaining_time": "0:36:07"}
|
| 578 |
+
{"current_steps": 96, "total_steps": 400, "loss": 0.8112, "lr": 9.491548749301997e-08, "epoch": 24.0, "percentage": 24.0, "elapsed_time": "0:11:18", "remaining_time": "0:35:48"}
|
| 579 |
+
{"current_steps": 96, "total_steps": 400, "eval_loss": 0.7388671040534973, "epoch": 24.0, "percentage": 24.0, "elapsed_time": "0:11:19", "remaining_time": "0:35:50"}
|