Training in progress, step 3000
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 sha256:5b6e05e1f5dfdffe008574a2332a84c8985f386b34a1e6155155aaf2ed610205
|
| 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:c2da7e8a6e9cef01ed0577dd39f1704365e3019abc6821d28a5d5247cebdfcfa
|
| 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 sha256:4cc20ccbda2fb63b1840d0f08a59e818f1c96616345a23352fbd6306ae8aebf5
|
| 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 sha256:111f18077843ea7c9758b195cbf45b408fab927d2b85a029b90ff558a84e3e72
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -558,3 +558,43 @@
|
|
| 558 |
{"current_steps": 2790, "total_steps": 3850, "loss": 0.1865, "lr": 8.561916444888618e-06, "epoch": 5.072793448589627, "percentage": 72.47, "elapsed_time": "18:38:58", "remaining_time": "7:05:07"}
|
| 559 |
{"current_steps": 2795, "total_steps": 3850, "loss": 0.194, "lr": 8.487658686286533e-06, "epoch": 5.08189262966333, "percentage": 72.6, "elapsed_time": "18:41:09", "remaining_time": "7:03:11"}
|
| 560 |
{"current_steps": 2800, "total_steps": 3850, "loss": 0.1857, "lr": 8.413637517578246e-06, "epoch": 5.090991810737034, "percentage": 72.73, "elapsed_time": "18:43:13", "remaining_time": "7:01:12"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 558 |
{"current_steps": 2790, "total_steps": 3850, "loss": 0.1865, "lr": 8.561916444888618e-06, "epoch": 5.072793448589627, "percentage": 72.47, "elapsed_time": "18:38:58", "remaining_time": "7:05:07"}
|
| 559 |
{"current_steps": 2795, "total_steps": 3850, "loss": 0.194, "lr": 8.487658686286533e-06, "epoch": 5.08189262966333, "percentage": 72.6, "elapsed_time": "18:41:09", "remaining_time": "7:03:11"}
|
| 560 |
{"current_steps": 2800, "total_steps": 3850, "loss": 0.1857, "lr": 8.413637517578246e-06, "epoch": 5.090991810737034, "percentage": 72.73, "elapsed_time": "18:43:13", "remaining_time": "7:01:12"}
|
| 561 |
+
{"current_steps": 2805, "total_steps": 3850, "loss": 0.1982, "lr": 8.339854459971313e-06, "epoch": 5.100090991810737, "percentage": 72.86, "elapsed_time": "18:46:33", "remaining_time": "6:59:42"}
|
| 562 |
+
{"current_steps": 2810, "total_steps": 3850, "loss": 0.1906, "lr": 8.266311029779843e-06, "epoch": 5.10919017288444, "percentage": 72.99, "elapsed_time": "18:48:34", "remaining_time": "6:57:41"}
|
| 563 |
+
{"current_steps": 2815, "total_steps": 3850, "loss": 0.1926, "lr": 8.193008738393409e-06, "epoch": 5.1182893539581436, "percentage": 73.12, "elapsed_time": "18:50:38", "remaining_time": "6:55:42"}
|
| 564 |
+
{"current_steps": 2820, "total_steps": 3850, "loss": 0.1915, "lr": 8.119949092245893e-06, "epoch": 5.127388535031847, "percentage": 73.25, "elapsed_time": "18:52:34", "remaining_time": "6:53:40"}
|
| 565 |
+
{"current_steps": 2825, "total_steps": 3850, "loss": 0.1777, "lr": 8.047133592784626e-06, "epoch": 5.136487716105551, "percentage": 73.38, "elapsed_time": "18:54:34", "remaining_time": "6:51:39"}
|
| 566 |
+
{"current_steps": 2830, "total_steps": 3850, "loss": 0.1962, "lr": 7.974563736439454e-06, "epoch": 5.145586897179254, "percentage": 73.51, "elapsed_time": "18:56:33", "remaining_time": "6:49:38"}
|
| 567 |
+
{"current_steps": 2835, "total_steps": 3850, "loss": 0.195, "lr": 7.902241014592042e-06, "epoch": 5.154686078252957, "percentage": 73.64, "elapsed_time": "18:58:19", "remaining_time": "6:47:32"}
|
| 568 |
+
{"current_steps": 2840, "total_steps": 3850, "loss": 0.1921, "lr": 7.830166913545181e-06, "epoch": 5.16378525932666, "percentage": 73.77, "elapsed_time": "19:00:12", "remaining_time": "6:45:29"}
|
| 569 |
+
{"current_steps": 2845, "total_steps": 3850, "loss": 0.1904, "lr": 7.758342914492257e-06, "epoch": 5.172884440400364, "percentage": 73.9, "elapsed_time": "19:02:10", "remaining_time": "6:43:28"}
|
| 570 |
+
{"current_steps": 2850, "total_steps": 3850, "loss": 0.1977, "lr": 7.686770493486835e-06, "epoch": 5.1819836214740675, "percentage": 74.03, "elapsed_time": "19:04:32", "remaining_time": "6:41:35"}
|
| 571 |
+
{"current_steps": 2855, "total_steps": 3850, "loss": 0.2044, "lr": 7.615451121412285e-06, "epoch": 5.191082802547771, "percentage": 74.16, "elapsed_time": "19:06:25", "remaining_time": "6:39:32"}
|
| 572 |
+
{"current_steps": 2860, "total_steps": 3850, "loss": 0.1778, "lr": 7.5443862639516e-06, "epoch": 5.200181983621474, "percentage": 74.29, "elapsed_time": "19:08:21", "remaining_time": "6:37:30"}
|
| 573 |
+
{"current_steps": 2865, "total_steps": 3850, "loss": 0.1996, "lr": 7.4735773815572044e-06, "epoch": 5.209281164695177, "percentage": 74.42, "elapsed_time": "19:10:15", "remaining_time": "6:35:27"}
|
| 574 |
+
{"current_steps": 2870, "total_steps": 3850, "loss": 0.1935, "lr": 7.403025929421026e-06, "epoch": 5.218380345768881, "percentage": 74.55, "elapsed_time": "19:12:14", "remaining_time": "6:33:26"}
|
| 575 |
+
{"current_steps": 2875, "total_steps": 3850, "loss": 0.1915, "lr": 7.332733357444524e-06, "epoch": 5.227479526842584, "percentage": 74.68, "elapsed_time": "19:14:02", "remaining_time": "6:31:22"}
|
| 576 |
+
{"current_steps": 2880, "total_steps": 3850, "loss": 0.1837, "lr": 7.262701110208936e-06, "epoch": 5.236578707916287, "percentage": 74.81, "elapsed_time": "19:16:00", "remaining_time": "6:29:20"}
|
| 577 |
+
{"current_steps": 2885, "total_steps": 3850, "loss": 0.1875, "lr": 7.192930626945556e-06, "epoch": 5.245677888989991, "percentage": 74.94, "elapsed_time": "19:18:03", "remaining_time": "6:27:21"}
|
| 578 |
+
{"current_steps": 2890, "total_steps": 3850, "loss": 0.1843, "lr": 7.123423341506168e-06, "epoch": 5.254777070063694, "percentage": 75.06, "elapsed_time": "19:20:05", "remaining_time": "6:25:21"}
|
| 579 |
+
{"current_steps": 2895, "total_steps": 3850, "loss": 0.2006, "lr": 7.054180682333602e-06, "epoch": 5.263876251137398, "percentage": 75.19, "elapsed_time": "19:22:15", "remaining_time": "6:23:24"}
|
| 580 |
+
{"current_steps": 2900, "total_steps": 3850, "loss": 0.1836, "lr": 6.985204072432348e-06, "epoch": 5.272975432211101, "percentage": 75.32, "elapsed_time": "19:24:34", "remaining_time": "6:21:29"}
|
| 581 |
+
{"current_steps": 2905, "total_steps": 3850, "loss": 0.1856, "lr": 6.916494929339315e-06, "epoch": 5.282074613284804, "percentage": 75.45, "elapsed_time": "19:26:32", "remaining_time": "6:19:28"}
|
| 582 |
+
{"current_steps": 2910, "total_steps": 3850, "loss": 0.1992, "lr": 6.848054665094714e-06, "epoch": 5.2911737943585075, "percentage": 75.58, "elapsed_time": "19:28:26", "remaining_time": "6:17:26"}
|
| 583 |
+
{"current_steps": 2915, "total_steps": 3850, "loss": 0.1842, "lr": 6.779884686213043e-06, "epoch": 5.300272975432211, "percentage": 75.71, "elapsed_time": "19:30:21", "remaining_time": "6:15:23"}
|
| 584 |
+
{"current_steps": 2920, "total_steps": 3850, "loss": 0.1913, "lr": 6.71198639365415e-06, "epoch": 5.309372156505915, "percentage": 75.84, "elapsed_time": "19:32:05", "remaining_time": "6:13:18"}
|
| 585 |
+
{"current_steps": 2925, "total_steps": 3850, "loss": 0.2024, "lr": 6.644361182794494e-06, "epoch": 5.318471337579618, "percentage": 75.97, "elapsed_time": "19:34:02", "remaining_time": "6:11:16"}
|
| 586 |
+
{"current_steps": 2930, "total_steps": 3850, "loss": 0.1906, "lr": 6.577010443398388e-06, "epoch": 5.327570518653321, "percentage": 76.1, "elapsed_time": "19:35:58", "remaining_time": "6:09:14"}
|
| 587 |
+
{"current_steps": 2935, "total_steps": 3850, "loss": 0.2053, "lr": 6.50993555958954e-06, "epoch": 5.336669699727024, "percentage": 76.23, "elapsed_time": "19:37:52", "remaining_time": "6:07:12"}
|
| 588 |
+
{"current_steps": 2940, "total_steps": 3850, "loss": 0.1951, "lr": 6.4431379098225185e-06, "epoch": 5.345768880800728, "percentage": 76.36, "elapsed_time": "19:39:39", "remaining_time": "6:05:07"}
|
| 589 |
+
{"current_steps": 2945, "total_steps": 3850, "loss": 0.1958, "lr": 6.376618866854485e-06, "epoch": 5.3548680618744315, "percentage": 76.49, "elapsed_time": "19:41:45", "remaining_time": "6:03:09"}
|
| 590 |
+
{"current_steps": 2950, "total_steps": 3850, "loss": 0.1772, "lr": 6.310379797716946e-06, "epoch": 5.363967242948135, "percentage": 76.62, "elapsed_time": "19:43:40", "remaining_time": "6:01:07"}
|
| 591 |
+
{"current_steps": 2955, "total_steps": 3850, "loss": 0.1811, "lr": 6.24442206368766e-06, "epoch": 5.373066424021838, "percentage": 76.75, "elapsed_time": "19:45:45", "remaining_time": "5:59:08"}
|
| 592 |
+
{"current_steps": 2960, "total_steps": 3850, "loss": 0.1905, "lr": 6.178747020262708e-06, "epoch": 5.382165605095541, "percentage": 76.88, "elapsed_time": "19:47:47", "remaining_time": "5:57:08"}
|
| 593 |
+
{"current_steps": 2965, "total_steps": 3850, "loss": 0.1891, "lr": 6.1133560171285625e-06, "epoch": 5.391264786169245, "percentage": 77.01, "elapsed_time": "19:49:33", "remaining_time": "5:55:03"}
|
| 594 |
+
{"current_steps": 2970, "total_steps": 3850, "loss": 0.197, "lr": 6.04825039813443e-06, "epoch": 5.400363967242948, "percentage": 77.14, "elapsed_time": "19:51:35", "remaining_time": "5:53:03"}
|
| 595 |
+
{"current_steps": 2975, "total_steps": 3850, "loss": 0.1966, "lr": 5.983431501264545e-06, "epoch": 5.409463148316651, "percentage": 77.27, "elapsed_time": "19:53:41", "remaining_time": "5:51:05"}
|
| 596 |
+
{"current_steps": 2980, "total_steps": 3850, "loss": 0.1897, "lr": 5.918900658610765e-06, "epoch": 5.418562329390355, "percentage": 77.4, "elapsed_time": "19:55:33", "remaining_time": "5:49:02"}
|
| 597 |
+
{"current_steps": 2985, "total_steps": 3850, "loss": 0.1961, "lr": 5.8546591963451226e-06, "epoch": 5.427661510464058, "percentage": 77.53, "elapsed_time": "19:57:35", "remaining_time": "5:47:02"}
|
| 598 |
+
{"current_steps": 2990, "total_steps": 3850, "loss": 0.2182, "lr": 5.790708434692627e-06, "epoch": 5.436760691537762, "percentage": 77.66, "elapsed_time": "19:59:14", "remaining_time": "5:44:56"}
|
| 599 |
+
{"current_steps": 2995, "total_steps": 3850, "loss": 0.1952, "lr": 5.727049687904076e-06, "epoch": 5.445859872611465, "percentage": 77.79, "elapsed_time": "20:01:15", "remaining_time": "5:42:55"}
|
| 600 |
+
{"current_steps": 3000, "total_steps": 3850, "loss": 0.1847, "lr": 5.66368426422909e-06, "epoch": 5.454959053685168, "percentage": 77.92, "elapsed_time": "20:03:20", "remaining_time": "5:40:56"}
|