Training in progress, step 3200
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:a02300f8019471869e147f450f702634c0344f2a3e11f2d9545eb2001f8719fa
|
| 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 sha256:0d5e90f77d729eeb022da3a53678b9135fde10a295a882b7d3f69101d347f81e
|
| 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:a9281b8e620e615a5b43608f5ae41fdb547e3387af76909a46e772754c459ee4
|
| 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 sha256:9a7758b0027e5118ca0cb40ad2d5e2b6881fb484922b13b1446212e2889127d4
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -600,3 +600,43 @@
|
|
| 600 |
{"current_steps": 3000, "total_steps": 9128, "loss": 0.1856, "lr": 3.3966648231888726e-05, "epoch": 2.300728807057921, "percentage": 32.87, "elapsed_time": "19:17:31", "remaining_time": "1 day, 15:24:26"}
|
| 601 |
{"current_steps": 3005, "total_steps": 9128, "loss": 0.1825, "lr": 3.393924999490624e-05, "epoch": 2.3045646336785577, "percentage": 32.92, "elapsed_time": "19:20:03", "remaining_time": "1 day, 15:23:45"}
|
| 602 |
{"current_steps": 3010, "total_steps": 9128, "loss": 0.1856, "lr": 3.3911800793878434e-05, "epoch": 2.3084004602991945, "percentage": 32.98, "elapsed_time": "19:21:21", "remaining_time": "1 day, 15:20:31"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 600 |
{"current_steps": 3000, "total_steps": 9128, "loss": 0.1856, "lr": 3.3966648231888726e-05, "epoch": 2.300728807057921, "percentage": 32.87, "elapsed_time": "19:17:31", "remaining_time": "1 day, 15:24:26"}
|
| 601 |
{"current_steps": 3005, "total_steps": 9128, "loss": 0.1825, "lr": 3.393924999490624e-05, "epoch": 2.3045646336785577, "percentage": 32.92, "elapsed_time": "19:20:03", "remaining_time": "1 day, 15:23:45"}
|
| 602 |
{"current_steps": 3010, "total_steps": 9128, "loss": 0.1856, "lr": 3.3911800793878434e-05, "epoch": 2.3084004602991945, "percentage": 32.98, "elapsed_time": "19:21:21", "remaining_time": "1 day, 15:20:31"}
|
| 603 |
+
{"current_steps": 3015, "total_steps": 9128, "loss": 0.1847, "lr": 3.388430072916381e-05, "epoch": 2.3122362869198314, "percentage": 33.03, "elapsed_time": "19:22:38", "remaining_time": "1 day, 15:17:18"}
|
| 604 |
+
{"current_steps": 3020, "total_steps": 9128, "loss": 0.1897, "lr": 3.385674990130685e-05, "epoch": 2.316072113540468, "percentage": 33.09, "elapsed_time": "19:23:54", "remaining_time": "1 day, 15:14:02"}
|
| 605 |
+
{"current_steps": 3025, "total_steps": 9128, "loss": 0.1883, "lr": 3.3829148411037614e-05, "epoch": 2.3199079401611047, "percentage": 33.14, "elapsed_time": "19:25:14", "remaining_time": "1 day, 15:10:53"}
|
| 606 |
+
{"current_steps": 3030, "total_steps": 9128, "loss": 0.1828, "lr": 3.380149635927141e-05, "epoch": 2.3237437667817415, "percentage": 33.19, "elapsed_time": "19:26:29", "remaining_time": "1 day, 15:07:36"}
|
| 607 |
+
{"current_steps": 3035, "total_steps": 9128, "loss": 0.191, "lr": 3.37737938471084e-05, "epoch": 2.327579593402378, "percentage": 33.25, "elapsed_time": "19:27:45", "remaining_time": "1 day, 15:04:21"}
|
| 608 |
+
{"current_steps": 3040, "total_steps": 9128, "loss": 0.1877, "lr": 3.3746040975833226e-05, "epoch": 2.331415420023015, "percentage": 33.3, "elapsed_time": "19:29:01", "remaining_time": "1 day, 15:01:06"}
|
| 609 |
+
{"current_steps": 3045, "total_steps": 9128, "loss": 0.1807, "lr": 3.371823784691467e-05, "epoch": 2.3352512466436517, "percentage": 33.36, "elapsed_time": "19:30:15", "remaining_time": "1 day, 14:57:48"}
|
| 610 |
+
{"current_steps": 3050, "total_steps": 9128, "loss": 0.1807, "lr": 3.369038456200525e-05, "epoch": 2.3390870732642886, "percentage": 33.41, "elapsed_time": "19:31:29", "remaining_time": "1 day, 14:54:31"}
|
| 611 |
+
{"current_steps": 3055, "total_steps": 9128, "loss": 0.1779, "lr": 3.366248122294087e-05, "epoch": 2.3429228998849254, "percentage": 33.47, "elapsed_time": "19:32:43", "remaining_time": "1 day, 14:51:14"}
|
| 612 |
+
{"current_steps": 3060, "total_steps": 9128, "loss": 0.182, "lr": 3.3634527931740435e-05, "epoch": 2.346758726505562, "percentage": 33.52, "elapsed_time": "19:33:57", "remaining_time": "1 day, 14:47:58"}
|
| 613 |
+
{"current_steps": 3065, "total_steps": 9128, "loss": 0.1837, "lr": 3.360652479060548e-05, "epoch": 2.3505945531261987, "percentage": 33.58, "elapsed_time": "19:35:12", "remaining_time": "1 day, 14:44:44"}
|
| 614 |
+
{"current_steps": 3070, "total_steps": 9128, "loss": 0.1782, "lr": 3.357847190191981e-05, "epoch": 2.3544303797468356, "percentage": 33.63, "elapsed_time": "19:36:26", "remaining_time": "1 day, 14:41:27"}
|
| 615 |
+
{"current_steps": 3075, "total_steps": 9128, "loss": 0.185, "lr": 3.35503693682491e-05, "epoch": 2.358266206367472, "percentage": 33.69, "elapsed_time": "19:37:41", "remaining_time": "1 day, 14:38:13"}
|
| 616 |
+
{"current_steps": 3080, "total_steps": 9128, "loss": 0.1824, "lr": 3.352221729234054e-05, "epoch": 2.362102032988109, "percentage": 33.74, "elapsed_time": "19:38:56", "remaining_time": "1 day, 14:34:59"}
|
| 617 |
+
{"current_steps": 3085, "total_steps": 9128, "loss": 0.1869, "lr": 3.3494015777122476e-05, "epoch": 2.3659378596087457, "percentage": 33.8, "elapsed_time": "19:40:10", "remaining_time": "1 day, 14:31:46"}
|
| 618 |
+
{"current_steps": 3090, "total_steps": 9128, "loss": 0.1796, "lr": 3.346576492570397e-05, "epoch": 2.3697736862293826, "percentage": 33.85, "elapsed_time": "19:41:27", "remaining_time": "1 day, 14:28:37"}
|
| 619 |
+
{"current_steps": 3095, "total_steps": 9128, "loss": 0.1933, "lr": 3.34374648413745e-05, "epoch": 2.3736095128500194, "percentage": 33.91, "elapsed_time": "19:42:44", "remaining_time": "1 day, 14:25:28"}
|
| 620 |
+
{"current_steps": 3100, "total_steps": 9128, "loss": 0.1846, "lr": 3.340911562760352e-05, "epoch": 2.377445339470656, "percentage": 33.96, "elapsed_time": "19:44:02", "remaining_time": "1 day, 14:22:23"}
|
| 621 |
+
{"current_steps": 3105, "total_steps": 9128, "loss": 0.1915, "lr": 3.338071738804014e-05, "epoch": 2.3812811660912927, "percentage": 34.02, "elapsed_time": "19:45:17", "remaining_time": "1 day, 14:19:11"}
|
| 622 |
+
{"current_steps": 3110, "total_steps": 9128, "loss": 0.1783, "lr": 3.3352270226512684e-05, "epoch": 2.3851169927119296, "percentage": 34.07, "elapsed_time": "19:46:34", "remaining_time": "1 day, 14:16:04"}
|
| 623 |
+
{"current_steps": 3115, "total_steps": 9128, "loss": 0.1874, "lr": 3.332377424702837e-05, "epoch": 2.388952819332566, "percentage": 34.13, "elapsed_time": "19:47:50", "remaining_time": "1 day, 14:12:55"}
|
| 624 |
+
{"current_steps": 3120, "total_steps": 9128, "loss": 0.1849, "lr": 3.3295229553772874e-05, "epoch": 2.392788645953203, "percentage": 34.18, "elapsed_time": "19:49:05", "remaining_time": "1 day, 14:09:45"}
|
| 625 |
+
{"current_steps": 3125, "total_steps": 9128, "loss": 0.1723, "lr": 3.326663625111001e-05, "epoch": 2.3966244725738397, "percentage": 34.24, "elapsed_time": "19:50:17", "remaining_time": "1 day, 14:06:30"}
|
| 626 |
+
{"current_steps": 3130, "total_steps": 9128, "loss": 0.1766, "lr": 3.3237994443581274e-05, "epoch": 2.4004602991944766, "percentage": 34.29, "elapsed_time": "19:51:31", "remaining_time": "1 day, 14:03:18"}
|
| 627 |
+
{"current_steps": 3135, "total_steps": 9128, "loss": 0.1813, "lr": 3.3209304235905545e-05, "epoch": 2.404296125815113, "percentage": 34.34, "elapsed_time": "19:52:47", "remaining_time": "1 day, 14:00:12"}
|
| 628 |
+
{"current_steps": 3140, "total_steps": 9128, "loss": 0.1872, "lr": 3.318056573297864e-05, "epoch": 2.40813195243575, "percentage": 34.4, "elapsed_time": "19:54:02", "remaining_time": "1 day, 13:57:02"}
|
| 629 |
+
{"current_steps": 3145, "total_steps": 9128, "loss": 0.1816, "lr": 3.315177903987295e-05, "epoch": 2.4119677790563867, "percentage": 34.45, "elapsed_time": "19:55:17", "remaining_time": "1 day, 13:53:55"}
|
| 630 |
+
{"current_steps": 3150, "total_steps": 9128, "loss": 0.1785, "lr": 3.312294426183706e-05, "epoch": 2.4158036056770236, "percentage": 34.51, "elapsed_time": "19:56:34", "remaining_time": "1 day, 13:50:50"}
|
| 631 |
+
{"current_steps": 3155, "total_steps": 9128, "loss": 0.1844, "lr": 3.3094061504295355e-05, "epoch": 2.41963943229766, "percentage": 34.56, "elapsed_time": "19:57:52", "remaining_time": "1 day, 13:47:47"}
|
| 632 |
+
{"current_steps": 3160, "total_steps": 9128, "loss": 0.1774, "lr": 3.306513087284765e-05, "epoch": 2.423475258918297, "percentage": 34.62, "elapsed_time": "19:59:06", "remaining_time": "1 day, 13:44:37"}
|
| 633 |
+
{"current_steps": 3165, "total_steps": 9128, "loss": 0.1783, "lr": 3.303615247326879e-05, "epoch": 2.4273110855389337, "percentage": 34.67, "elapsed_time": "20:00:21", "remaining_time": "1 day, 13:41:31"}
|
| 634 |
+
{"current_steps": 3170, "total_steps": 9128, "loss": 0.1767, "lr": 3.300712641150828e-05, "epoch": 2.4311469121595706, "percentage": 34.73, "elapsed_time": "20:01:36", "remaining_time": "1 day, 13:38:24"}
|
| 635 |
+
{"current_steps": 3175, "total_steps": 9128, "loss": 0.167, "lr": 3.2978052793689845e-05, "epoch": 2.434982738780207, "percentage": 34.78, "elapsed_time": "20:02:49", "remaining_time": "1 day, 13:35:15"}
|
| 636 |
+
{"current_steps": 3180, "total_steps": 9128, "loss": 0.1805, "lr": 3.2948931726111144e-05, "epoch": 2.438818565400844, "percentage": 34.84, "elapsed_time": "20:04:07", "remaining_time": "1 day, 13:32:14"}
|
| 637 |
+
{"current_steps": 3185, "total_steps": 9128, "loss": 0.1786, "lr": 3.291976331524326e-05, "epoch": 2.4426543920214807, "percentage": 34.89, "elapsed_time": "20:05:24", "remaining_time": "1 day, 13:29:13"}
|
| 638 |
+
{"current_steps": 3190, "total_steps": 9128, "loss": 0.1737, "lr": 3.289054766773041e-05, "epoch": 2.4464902186421176, "percentage": 34.95, "elapsed_time": "20:06:38", "remaining_time": "1 day, 13:26:06"}
|
| 639 |
+
{"current_steps": 3195, "total_steps": 9128, "loss": 0.1813, "lr": 3.28612848903895e-05, "epoch": 2.450326045262754, "percentage": 35.0, "elapsed_time": "20:07:53", "remaining_time": "1 day, 13:23:00"}
|
| 640 |
+
{"current_steps": 3200, "total_steps": 9128, "loss": 0.1815, "lr": 3.2831975090209746e-05, "epoch": 2.454161871883391, "percentage": 35.06, "elapsed_time": "20:09:08", "remaining_time": "1 day, 13:19:56"}
|
| 641 |
+
{"current_steps": 3205, "total_steps": 9128, "loss": 0.1796, "lr": 3.2802618374352295e-05, "epoch": 2.4579976985040277, "percentage": 35.11, "elapsed_time": "20:11:37", "remaining_time": "1 day, 13:19:09"}
|
| 642 |
+
{"current_steps": 3210, "total_steps": 9128, "loss": 0.1807, "lr": 3.277321485014983e-05, "epoch": 2.461833525124664, "percentage": 35.17, "elapsed_time": "20:12:55", "remaining_time": "1 day, 13:16:09"}
|