Training in progress, step 2600
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 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41532912a285d0f05a6200f4d8e2bc35f6b8201d7c406947861cd92843140fda
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38780e62367ae3c7a46e6c6a30bc1fdb7aaa07cc9e18c234694bc1bde150e2b0
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:754ae24701ca12e85ce1cc3d66d176e7eb7d708546d64e2643e0794aae968c0b
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:263592d2d3fae66e6158d742e1ba47179b6255f5851bcd490a5908a17918d3ed
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -479,3 +479,43 @@
|
|
| 479 |
{"current_steps": 2395, "total_steps": 9128, "loss": 0.2857, "lr": 3.687712604149662e-05, "epoch": 1.8369773686229383, "percentage": 26.24, "elapsed_time": "14:56:06", "remaining_time": "1 day, 17:59:11"}
|
| 480 |
{"current_steps": 2400, "total_steps": 9128, "loss": 0.2768, "lr": 3.685657564002981e-05, "epoch": 1.840813195243575, "percentage": 26.29, "elapsed_time": "14:57:49", "remaining_time": "1 day, 17:56:54"}
|
| 481 |
{"current_steps": 2405, "total_steps": 9128, "loss": 0.2868, "lr": 3.68359636083257e-05, "epoch": 1.8446490218642118, "percentage": 26.35, "elapsed_time": "15:00:38", "remaining_time": "1 day, 17:57:40"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 479 |
{"current_steps": 2395, "total_steps": 9128, "loss": 0.2857, "lr": 3.687712604149662e-05, "epoch": 1.8369773686229383, "percentage": 26.24, "elapsed_time": "14:56:06", "remaining_time": "1 day, 17:59:11"}
|
| 480 |
{"current_steps": 2400, "total_steps": 9128, "loss": 0.2768, "lr": 3.685657564002981e-05, "epoch": 1.840813195243575, "percentage": 26.29, "elapsed_time": "14:57:49", "remaining_time": "1 day, 17:56:54"}
|
| 481 |
{"current_steps": 2405, "total_steps": 9128, "loss": 0.2868, "lr": 3.68359636083257e-05, "epoch": 1.8446490218642118, "percentage": 26.35, "elapsed_time": "15:00:38", "remaining_time": "1 day, 17:57:40"}
|
| 482 |
+
{"current_steps": 2410, "total_steps": 9128, "loss": 0.2829, "lr": 3.681529002174505e-05, "epoch": 1.8484848484848486, "percentage": 26.4, "elapsed_time": "15:02:23", "remaining_time": "1 day, 17:55:27"}
|
| 483 |
+
{"current_steps": 2415, "total_steps": 9128, "loss": 0.291, "lr": 3.6794554955873695e-05, "epoch": 1.8523206751054853, "percentage": 26.46, "elapsed_time": "15:04:04", "remaining_time": "1 day, 17:53:03"}
|
| 484 |
+
{"current_steps": 2420, "total_steps": 9128, "loss": 0.2976, "lr": 3.6773758486522215e-05, "epoch": 1.856156501726122, "percentage": 26.51, "elapsed_time": "15:05:43", "remaining_time": "1 day, 17:50:34"}
|
| 485 |
+
{"current_steps": 2425, "total_steps": 9128, "loss": 0.292, "lr": 3.6752900689725714e-05, "epoch": 1.8599923283467588, "percentage": 26.57, "elapsed_time": "15:07:23", "remaining_time": "1 day, 17:48:09"}
|
| 486 |
+
{"current_steps": 2430, "total_steps": 9128, "loss": 0.3091, "lr": 3.673198164174351e-05, "epoch": 1.8638281549673956, "percentage": 26.62, "elapsed_time": "15:09:02", "remaining_time": "1 day, 17:45:38"}
|
| 487 |
+
{"current_steps": 2435, "total_steps": 9128, "loss": 0.2826, "lr": 3.6711001419058855e-05, "epoch": 1.8676639815880323, "percentage": 26.68, "elapsed_time": "15:10:38", "remaining_time": "1 day, 17:43:02"}
|
| 488 |
+
{"current_steps": 2440, "total_steps": 9128, "loss": 0.3031, "lr": 3.668996009837868e-05, "epoch": 1.871499808208669, "percentage": 26.73, "elapsed_time": "15:12:24", "remaining_time": "1 day, 17:40:52"}
|
| 489 |
+
{"current_steps": 2445, "total_steps": 9128, "loss": 0.3067, "lr": 3.666885775663331e-05, "epoch": 1.8753356348293058, "percentage": 26.79, "elapsed_time": "15:14:05", "remaining_time": "1 day, 17:38:30"}
|
| 490 |
+
{"current_steps": 2450, "total_steps": 9128, "loss": 0.2869, "lr": 3.664769447097614e-05, "epoch": 1.8791714614499426, "percentage": 26.84, "elapsed_time": "15:15:44", "remaining_time": "1 day, 17:36:01"}
|
| 491 |
+
{"current_steps": 2455, "total_steps": 9128, "loss": 0.2953, "lr": 3.662647031878341e-05, "epoch": 1.883007288070579, "percentage": 26.9, "elapsed_time": "15:17:29", "remaining_time": "1 day, 17:33:52"}
|
| 492 |
+
{"current_steps": 2460, "total_steps": 9128, "loss": 0.2929, "lr": 3.660518537765388e-05, "epoch": 1.886843114691216, "percentage": 26.95, "elapsed_time": "15:19:09", "remaining_time": "1 day, 17:31:27"}
|
| 493 |
+
{"current_steps": 2465, "total_steps": 9128, "loss": 0.2993, "lr": 3.6583839725408584e-05, "epoch": 1.8906789413118528, "percentage": 27.0, "elapsed_time": "15:20:45", "remaining_time": "1 day, 17:28:51"}
|
| 494 |
+
{"current_steps": 2470, "total_steps": 9128, "loss": 0.2976, "lr": 3.6562433440090514e-05, "epoch": 1.8945147679324894, "percentage": 27.06, "elapsed_time": "15:22:25", "remaining_time": "1 day, 17:26:27"}
|
| 495 |
+
{"current_steps": 2475, "total_steps": 9128, "loss": 0.273, "lr": 3.654096659996435e-05, "epoch": 1.898350594553126, "percentage": 27.11, "elapsed_time": "15:24:06", "remaining_time": "1 day, 17:24:05"}
|
| 496 |
+
{"current_steps": 2480, "total_steps": 9128, "loss": 0.2801, "lr": 3.651943928351616e-05, "epoch": 1.902186421173763, "percentage": 27.17, "elapsed_time": "15:25:52", "remaining_time": "1 day, 17:21:56"}
|
| 497 |
+
{"current_steps": 2485, "total_steps": 9128, "loss": 0.2865, "lr": 3.6497851569453116e-05, "epoch": 1.9060222477943998, "percentage": 27.22, "elapsed_time": "15:27:35", "remaining_time": "1 day, 17:19:39"}
|
| 498 |
+
{"current_steps": 2490, "total_steps": 9128, "loss": 0.2916, "lr": 3.647620353670325e-05, "epoch": 1.9098580744150364, "percentage": 27.28, "elapsed_time": "15:29:15", "remaining_time": "1 day, 17:17:17"}
|
| 499 |
+
{"current_steps": 2495, "total_steps": 9128, "loss": 0.2801, "lr": 3.64544952644151e-05, "epoch": 1.913693901035673, "percentage": 27.33, "elapsed_time": "15:30:56", "remaining_time": "1 day, 17:14:54"}
|
| 500 |
+
{"current_steps": 2500, "total_steps": 9128, "loss": 0.2943, "lr": 3.643272683195744e-05, "epoch": 1.91752972765631, "percentage": 27.39, "elapsed_time": "15:32:32", "remaining_time": "1 day, 17:12:21"}
|
| 501 |
+
{"current_steps": 2505, "total_steps": 9128, "loss": 0.2847, "lr": 3.6410898318919026e-05, "epoch": 1.9213655542769468, "percentage": 27.44, "elapsed_time": "15:34:13", "remaining_time": "1 day, 17:10:00"}
|
| 502 |
+
{"current_steps": 2510, "total_steps": 9128, "loss": 0.2908, "lr": 3.6389009805108263e-05, "epoch": 1.9252013808975834, "percentage": 27.5, "elapsed_time": "15:35:47", "remaining_time": "1 day, 17:07:22"}
|
| 503 |
+
{"current_steps": 2515, "total_steps": 9128, "loss": 0.2835, "lr": 3.636706137055292e-05, "epoch": 1.92903720751822, "percentage": 27.55, "elapsed_time": "15:37:35", "remaining_time": "1 day, 17:05:20"}
|
| 504 |
+
{"current_steps": 2520, "total_steps": 9128, "loss": 0.2769, "lr": 3.6345053095499865e-05, "epoch": 1.932873034138857, "percentage": 27.61, "elapsed_time": "15:39:27", "remaining_time": "1 day, 17:03:27"}
|
| 505 |
+
{"current_steps": 2525, "total_steps": 9128, "loss": 0.2694, "lr": 3.632298506041474e-05, "epoch": 1.9367088607594938, "percentage": 27.66, "elapsed_time": "15:41:11", "remaining_time": "1 day, 17:01:16"}
|
| 506 |
+
{"current_steps": 2530, "total_steps": 9128, "loss": 0.2781, "lr": 3.630085734598167e-05, "epoch": 1.9405446873801304, "percentage": 27.72, "elapsed_time": "15:42:54", "remaining_time": "1 day, 16:58:59"}
|
| 507 |
+
{"current_steps": 2535, "total_steps": 9128, "loss": 0.2793, "lr": 3.6278670033103e-05, "epoch": 1.944380514000767, "percentage": 27.77, "elapsed_time": "15:44:34", "remaining_time": "1 day, 16:56:38"}
|
| 508 |
+
{"current_steps": 2540, "total_steps": 9128, "loss": 0.2751, "lr": 3.6256423202898974e-05, "epoch": 1.948216340621404, "percentage": 27.83, "elapsed_time": "15:46:17", "remaining_time": "1 day, 16:54:23"}
|
| 509 |
+
{"current_steps": 2545, "total_steps": 9128, "loss": 0.2711, "lr": 3.62341169367074e-05, "epoch": 1.9520521672420408, "percentage": 27.88, "elapsed_time": "15:47:57", "remaining_time": "1 day, 16:52:00"}
|
| 510 |
+
{"current_steps": 2550, "total_steps": 9128, "loss": 0.2798, "lr": 3.6211751316083447e-05, "epoch": 1.9558879938626774, "percentage": 27.94, "elapsed_time": "15:49:33", "remaining_time": "1 day, 16:49:30"}
|
| 511 |
+
{"current_steps": 2555, "total_steps": 9128, "loss": 0.2773, "lr": 3.6189326422799254e-05, "epoch": 1.959723820483314, "percentage": 27.99, "elapsed_time": "15:51:14", "remaining_time": "1 day, 16:47:10"}
|
| 512 |
+
{"current_steps": 2560, "total_steps": 9128, "loss": 0.2977, "lr": 3.616684233884371e-05, "epoch": 1.963559647103951, "percentage": 28.05, "elapsed_time": "15:52:53", "remaining_time": "1 day, 16:44:46"}
|
| 513 |
+
{"current_steps": 2565, "total_steps": 9128, "loss": 0.2841, "lr": 3.614429914642206e-05, "epoch": 1.9673954737245878, "percentage": 28.1, "elapsed_time": "15:54:26", "remaining_time": "1 day, 16:42:05"}
|
| 514 |
+
{"current_steps": 2570, "total_steps": 9128, "loss": 0.2801, "lr": 3.612169692795571e-05, "epoch": 1.9712313003452244, "percentage": 28.16, "elapsed_time": "15:56:09", "remaining_time": "1 day, 16:39:53"}
|
| 515 |
+
{"current_steps": 2575, "total_steps": 9128, "loss": 0.2725, "lr": 3.6099035766081836e-05, "epoch": 1.975067126965861, "percentage": 28.21, "elapsed_time": "15:57:47", "remaining_time": "1 day, 16:37:25"}
|
| 516 |
+
{"current_steps": 2580, "total_steps": 9128, "loss": 0.2806, "lr": 3.607631574365316e-05, "epoch": 1.978902953586498, "percentage": 28.26, "elapsed_time": "15:59:24", "remaining_time": "1 day, 16:34:58"}
|
| 517 |
+
{"current_steps": 2585, "total_steps": 9128, "loss": 0.2871, "lr": 3.6053536943737555e-05, "epoch": 1.9827387802071348, "percentage": 28.32, "elapsed_time": "16:01:03", "remaining_time": "1 day, 16:32:35"}
|
| 518 |
+
{"current_steps": 2590, "total_steps": 9128, "loss": 0.2904, "lr": 3.6030699449617846e-05, "epoch": 1.9865746068277714, "percentage": 28.37, "elapsed_time": "16:02:42", "remaining_time": "1 day, 16:30:12"}
|
| 519 |
+
{"current_steps": 2595, "total_steps": 9128, "loss": 0.2816, "lr": 3.6007803344791415e-05, "epoch": 1.990410433448408, "percentage": 28.43, "elapsed_time": "16:04:23", "remaining_time": "1 day, 16:27:54"}
|
| 520 |
+
{"current_steps": 2600, "total_steps": 9128, "loss": 0.2836, "lr": 3.598484871296996e-05, "epoch": 1.994246260069045, "percentage": 28.48, "elapsed_time": "16:06:01", "remaining_time": "1 day, 16:25:27"}
|
| 521 |
+
{"current_steps": 2605, "total_steps": 9128, "loss": 0.2784, "lr": 3.5961835638079136e-05, "epoch": 1.9980820866896818, "percentage": 28.54, "elapsed_time": "16:09:04", "remaining_time": "1 day, 16:26:34"}
|