Training in progress, epoch 24
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:efb329d014d296cf38a7163eedb9001c64ed11a23c691c325710aa438def6c93
|
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:eb9acfe584626bbaf81e966c051322ae47dd992a1f9a4244b3ae46aaa123711d
|
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 sha256:409637d443abe5102fb384cddf5ea888b418aa51c71ff8dc40aceeeef2486ca0
|
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:d76ef04580d5cdcad9879dd3fc9c7793e070c789964505a531c7ee10550fc5f3
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -402,3 +402,21 @@
|
|
402 |
{"current_steps": 3800, "total_steps": 4125, "loss": 0.0195, "lr": 5e-06, "epoch": 22.908816880180858, "percentage": 92.12, "elapsed_time": "1 day, 11:44:42", "remaining_time": "3:03:25"}
|
403 |
{"current_steps": 3810, "total_steps": 4125, "loss": 0.0197, "lr": 5e-06, "epoch": 22.96910324039186, "percentage": 92.36, "elapsed_time": "1 day, 11:50:02", "remaining_time": "2:57:45"}
|
404 |
{"current_steps": 3815, "total_steps": 4125, "eval_loss": 2.359902858734131, "epoch": 22.99924642049736, "percentage": 92.48, "elapsed_time": "1 day, 11:54:42", "remaining_time": "2:55:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
402 |
{"current_steps": 3800, "total_steps": 4125, "loss": 0.0195, "lr": 5e-06, "epoch": 22.908816880180858, "percentage": 92.12, "elapsed_time": "1 day, 11:44:42", "remaining_time": "3:03:25"}
|
403 |
{"current_steps": 3810, "total_steps": 4125, "loss": 0.0197, "lr": 5e-06, "epoch": 22.96910324039186, "percentage": 92.36, "elapsed_time": "1 day, 11:50:02", "remaining_time": "2:57:45"}
|
404 |
{"current_steps": 3815, "total_steps": 4125, "eval_loss": 2.359902858734131, "epoch": 22.99924642049736, "percentage": 92.48, "elapsed_time": "1 day, 11:54:42", "remaining_time": "2:55:05"}
|
405 |
+
{"current_steps": 3820, "total_steps": 4125, "loss": 0.0171, "lr": 5e-06, "epoch": 23.029389600602865, "percentage": 92.61, "elapsed_time": "1 day, 11:59:05", "remaining_time": "2:52:23"}
|
406 |
+
{"current_steps": 3830, "total_steps": 4125, "loss": 0.0149, "lr": 5e-06, "epoch": 23.089675960813867, "percentage": 92.85, "elapsed_time": "1 day, 12:04:31", "remaining_time": "2:46:43"}
|
407 |
+
{"current_steps": 3840, "total_steps": 4125, "loss": 0.0152, "lr": 5e-06, "epoch": 23.14996232102487, "percentage": 93.09, "elapsed_time": "1 day, 12:09:56", "remaining_time": "2:41:02"}
|
408 |
+
{"current_steps": 3850, "total_steps": 4125, "loss": 0.0157, "lr": 5e-06, "epoch": 23.21024868123587, "percentage": 93.33, "elapsed_time": "1 day, 12:15:20", "remaining_time": "2:35:22"}
|
409 |
+
{"current_steps": 3860, "total_steps": 4125, "loss": 0.0159, "lr": 5e-06, "epoch": 23.270535041446873, "percentage": 93.58, "elapsed_time": "1 day, 12:20:45", "remaining_time": "2:29:42"}
|
410 |
+
{"current_steps": 3870, "total_steps": 4125, "loss": 0.0163, "lr": 5e-06, "epoch": 23.330821401657875, "percentage": 93.82, "elapsed_time": "1 day, 12:26:09", "remaining_time": "2:24:02"}
|
411 |
+
{"current_steps": 3880, "total_steps": 4125, "loss": 0.0165, "lr": 5e-06, "epoch": 23.391107761868877, "percentage": 94.06, "elapsed_time": "1 day, 12:31:33", "remaining_time": "2:18:23"}
|
412 |
+
{"current_steps": 3890, "total_steps": 4125, "loss": 0.0168, "lr": 5e-06, "epoch": 23.45139412207988, "percentage": 94.3, "elapsed_time": "1 day, 12:36:56", "remaining_time": "2:12:43"}
|
413 |
+
{"current_steps": 3900, "total_steps": 4125, "loss": 0.0174, "lr": 5e-06, "epoch": 23.51168048229088, "percentage": 94.55, "elapsed_time": "1 day, 12:42:21", "remaining_time": "2:07:03"}
|
414 |
+
{"current_steps": 3910, "total_steps": 4125, "loss": 0.0173, "lr": 5e-06, "epoch": 23.571966842501883, "percentage": 94.79, "elapsed_time": "1 day, 12:47:46", "remaining_time": "2:01:23"}
|
415 |
+
{"current_steps": 3920, "total_steps": 4125, "loss": 0.0174, "lr": 5e-06, "epoch": 23.632253202712885, "percentage": 95.03, "elapsed_time": "1 day, 12:53:11", "remaining_time": "1:55:44"}
|
416 |
+
{"current_steps": 3930, "total_steps": 4125, "loss": 0.0174, "lr": 5e-06, "epoch": 23.692539562923887, "percentage": 95.27, "elapsed_time": "1 day, 12:58:35", "remaining_time": "1:50:04"}
|
417 |
+
{"current_steps": 3940, "total_steps": 4125, "loss": 0.018, "lr": 5e-06, "epoch": 23.75282592313489, "percentage": 95.52, "elapsed_time": "1 day, 13:03:58", "remaining_time": "1:44:25"}
|
418 |
+
{"current_steps": 3950, "total_steps": 4125, "loss": 0.0177, "lr": 5e-06, "epoch": 23.813112283345895, "percentage": 95.76, "elapsed_time": "1 day, 13:09:22", "remaining_time": "1:38:46"}
|
419 |
+
{"current_steps": 3960, "total_steps": 4125, "loss": 0.0179, "lr": 5e-06, "epoch": 23.873398643556897, "percentage": 96.0, "elapsed_time": "1 day, 13:14:46", "remaining_time": "1:33:06"}
|
420 |
+
{"current_steps": 3970, "total_steps": 4125, "loss": 0.018, "lr": 5e-06, "epoch": 23.9336850037679, "percentage": 96.24, "elapsed_time": "1 day, 13:20:10", "remaining_time": "1:27:27"}
|
421 |
+
{"current_steps": 3980, "total_steps": 4125, "loss": 0.0186, "lr": 5e-06, "epoch": 23.9939713639789, "percentage": 96.48, "elapsed_time": "1 day, 13:25:32", "remaining_time": "1:21:48"}
|
422 |
+
{"current_steps": 3981, "total_steps": 4125, "eval_loss": 2.3888232707977295, "epoch": 24.0, "percentage": 96.51, "elapsed_time": "1 day, 13:27:59", "remaining_time": "1:21:18"}
|