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 sha256:849e11f5cfbac08b47d810cc50bacf075cfe95913d5fabaa6da0b82bda2371c3
|
| 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 sha256:99a62753589d582a7c5cc9258bdca0c6d572bd2799fefbf7bc6690cb57f40815
|
| 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:d974b4eeeaefa5d9547921665a13740a252cc2db168c9f39c515da5aca18476e
|
| 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:ff85ec436e42e40ab02f2e67c592b79c46cd52b35b0ca175566d6e76fc48844b
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -559,3 +559,44 @@
|
|
| 559 |
{"current_steps": 2795, "total_steps": 9128, "loss": 0.2098, "lr": 3.504488306849224e-05, "epoch": 2.1434599156118144, "percentage": 30.62, "elapsed_time": "17:57:03", "remaining_time": "1 day, 16:40:26"}
|
| 560 |
{"current_steps": 2800, "total_steps": 9128, "loss": 0.2081, "lr": 3.501965842198163e-05, "epoch": 2.1472957422324512, "percentage": 30.67, "elapsed_time": "18:00:01", "remaining_time": "1 day, 16:40:51"}
|
| 561 |
{"current_steps": 2805, "total_steps": 9128, "loss": 0.2116, "lr": 3.499437886128605e-05, "epoch": 2.1511315688530876, "percentage": 30.73, "elapsed_time": "18:04:08", "remaining_time": "1 day, 16:43:52"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 559 |
{"current_steps": 2795, "total_steps": 9128, "loss": 0.2098, "lr": 3.504488306849224e-05, "epoch": 2.1434599156118144, "percentage": 30.62, "elapsed_time": "17:57:03", "remaining_time": "1 day, 16:40:26"}
|
| 560 |
{"current_steps": 2800, "total_steps": 9128, "loss": 0.2081, "lr": 3.501965842198163e-05, "epoch": 2.1472957422324512, "percentage": 30.67, "elapsed_time": "18:00:01", "remaining_time": "1 day, 16:40:51"}
|
| 561 |
{"current_steps": 2805, "total_steps": 9128, "loss": 0.2116, "lr": 3.499437886128605e-05, "epoch": 2.1511315688530876, "percentage": 30.73, "elapsed_time": "18:04:08", "remaining_time": "1 day, 16:43:52"}
|
| 562 |
+
{"current_steps": 2810, "total_steps": 9128, "loss": 0.2027, "lr": 3.496904447883147e-05, "epoch": 2.1549673954737245, "percentage": 30.78, "elapsed_time": "18:06:55", "remaining_time": "1 day, 16:43:51"}
|
| 563 |
+
{"current_steps": 2815, "total_steps": 9128, "loss": 0.1986, "lr": 3.49436553672443e-05, "epoch": 2.1588032220943614, "percentage": 30.84, "elapsed_time": "18:09:20", "remaining_time": "1 day, 16:43:00"}
|
| 564 |
+
{"current_steps": 2820, "total_steps": 9128, "loss": 0.2009, "lr": 3.491821161935103e-05, "epoch": 2.1626390487149982, "percentage": 30.89, "elapsed_time": "18:11:48", "remaining_time": "1 day, 16:42:15"}
|
| 565 |
+
{"current_steps": 2825, "total_steps": 9128, "loss": 0.2036, "lr": 3.4892713328177936e-05, "epoch": 2.1664748753356347, "percentage": 30.95, "elapsed_time": "18:14:36", "remaining_time": "1 day, 16:42:13"}
|
| 566 |
+
{"current_steps": 2830, "total_steps": 9128, "loss": 0.2058, "lr": 3.486716058695069e-05, "epoch": 2.1703107019562715, "percentage": 31.0, "elapsed_time": "18:17:28", "remaining_time": "1 day, 16:42:21"}
|
| 567 |
+
{"current_steps": 2835, "total_steps": 9128, "loss": 0.1989, "lr": 3.484155348909405e-05, "epoch": 2.1741465285769084, "percentage": 31.06, "elapsed_time": "18:20:28", "remaining_time": "1 day, 16:42:45"}
|
| 568 |
+
{"current_steps": 2840, "total_steps": 9128, "loss": 0.2039, "lr": 3.481589212823151e-05, "epoch": 2.1779823551975452, "percentage": 31.11, "elapsed_time": "18:23:23", "remaining_time": "1 day, 16:43:00"}
|
| 569 |
+
{"current_steps": 2845, "total_steps": 9128, "loss": 0.2069, "lr": 3.4790176598184966e-05, "epoch": 2.1818181818181817, "percentage": 31.17, "elapsed_time": "18:26:24", "remaining_time": "1 day, 16:43:24"}
|
| 570 |
+
{"current_steps": 2850, "total_steps": 9128, "loss": 0.2097, "lr": 3.476440699297436e-05, "epoch": 2.1856540084388185, "percentage": 31.22, "elapsed_time": "18:29:11", "remaining_time": "1 day, 16:43:20"}
|
| 571 |
+
{"current_steps": 2855, "total_steps": 9128, "loss": 0.1761, "lr": 3.473858340681732e-05, "epoch": 2.1894898350594554, "percentage": 31.28, "elapsed_time": "18:31:18", "remaining_time": "1 day, 16:41:46"}
|
| 572 |
+
{"current_steps": 2860, "total_steps": 9128, "loss": 0.2052, "lr": 3.471270593412887e-05, "epoch": 2.1933256616800922, "percentage": 31.33, "elapsed_time": "18:34:02", "remaining_time": "1 day, 16:41:31"}
|
| 573 |
+
{"current_steps": 2865, "total_steps": 9128, "loss": 0.1985, "lr": 3.4686774669521035e-05, "epoch": 2.1971614883007287, "percentage": 31.39, "elapsed_time": "18:36:51", "remaining_time": "1 day, 16:41:30"}
|
| 574 |
+
{"current_steps": 2870, "total_steps": 9128, "loss": 0.2062, "lr": 3.4660789707802505e-05, "epoch": 2.2009973149213655, "percentage": 31.44, "elapsed_time": "18:39:41", "remaining_time": "1 day, 16:41:28"}
|
| 575 |
+
{"current_steps": 2875, "total_steps": 9128, "loss": 0.1941, "lr": 3.4634751143978317e-05, "epoch": 2.2048331415420024, "percentage": 31.5, "elapsed_time": "18:42:25", "remaining_time": "1 day, 16:41:14"}
|
| 576 |
+
{"current_steps": 2880, "total_steps": 9128, "loss": 0.2, "lr": 3.4608659073249465e-05, "epoch": 2.2086689681626392, "percentage": 31.55, "elapsed_time": "18:45:15", "remaining_time": "1 day, 16:41:11"}
|
| 577 |
+
{"current_steps": 2885, "total_steps": 9128, "loss": 0.2002, "lr": 3.458251359101257e-05, "epoch": 2.2125047947832757, "percentage": 31.61, "elapsed_time": "18:48:13", "remaining_time": "1 day, 16:41:26"}
|
| 578 |
+
{"current_steps": 2890, "total_steps": 9128, "loss": 0.2199, "lr": 3.455631479285956e-05, "epoch": 2.2163406214039125, "percentage": 31.66, "elapsed_time": "18:49:49", "remaining_time": "1 day, 16:38:42"}
|
| 579 |
+
{"current_steps": 2895, "total_steps": 9128, "loss": 0.1987, "lr": 3.453006277457726e-05, "epoch": 2.2201764480245494, "percentage": 31.72, "elapsed_time": "18:51:03", "remaining_time": "1 day, 16:35:11"}
|
| 580 |
+
{"current_steps": 2900, "total_steps": 9128, "loss": 0.1955, "lr": 3.4503757632147094e-05, "epoch": 2.224012274645186, "percentage": 31.77, "elapsed_time": "18:52:19", "remaining_time": "1 day, 16:31:44"}
|
| 581 |
+
{"current_steps": 2905, "total_steps": 9128, "loss": 0.1961, "lr": 3.447739946174474e-05, "epoch": 2.2278481012658227, "percentage": 31.83, "elapsed_time": "18:53:32", "remaining_time": "1 day, 16:28:15"}
|
| 582 |
+
{"current_steps": 2910, "total_steps": 9128, "loss": 0.197, "lr": 3.445098835973969e-05, "epoch": 2.2316839278864595, "percentage": 31.88, "elapsed_time": "18:54:50", "remaining_time": "1 day, 16:24:53"}
|
| 583 |
+
{"current_steps": 2915, "total_steps": 9128, "loss": 0.1984, "lr": 3.4424524422695036e-05, "epoch": 2.2355197545070964, "percentage": 31.93, "elapsed_time": "18:56:03", "remaining_time": "1 day, 16:21:23"}
|
| 584 |
+
{"current_steps": 2920, "total_steps": 9128, "loss": 0.1871, "lr": 3.439800774736699e-05, "epoch": 2.2393555811277333, "percentage": 31.99, "elapsed_time": "18:57:17", "remaining_time": "1 day, 16:17:55"}
|
| 585 |
+
{"current_steps": 2925, "total_steps": 9128, "loss": 0.2054, "lr": 3.437143843070462e-05, "epoch": 2.2431914077483697, "percentage": 32.04, "elapsed_time": "18:58:32", "remaining_time": "1 day, 16:14:28"}
|
| 586 |
+
{"current_steps": 2930, "total_steps": 9128, "loss": 0.1897, "lr": 3.434481656984941e-05, "epoch": 2.2470272343690065, "percentage": 32.1, "elapsed_time": "18:59:44", "remaining_time": "1 day, 16:10:58"}
|
| 587 |
+
{"current_steps": 2935, "total_steps": 9128, "loss": 0.1952, "lr": 3.431814226213501e-05, "epoch": 2.2508630609896434, "percentage": 32.15, "elapsed_time": "19:01:02", "remaining_time": "1 day, 16:07:38"}
|
| 588 |
+
{"current_steps": 2940, "total_steps": 9128, "loss": 0.187, "lr": 3.429141560508679e-05, "epoch": 2.25469888761028, "percentage": 32.21, "elapsed_time": "19:02:18", "remaining_time": "1 day, 16:04:17"}
|
| 589 |
+
{"current_steps": 2945, "total_steps": 9128, "loss": 0.1987, "lr": 3.426463669642153e-05, "epoch": 2.2585347142309167, "percentage": 32.26, "elapsed_time": "19:03:35", "remaining_time": "1 day, 16:00:56"}
|
| 590 |
+
{"current_steps": 2950, "total_steps": 9128, "loss": 0.1869, "lr": 3.423780563404703e-05, "epoch": 2.2623705408515535, "percentage": 32.32, "elapsed_time": "19:04:50", "remaining_time": "1 day, 15:57:33"}
|
| 591 |
+
{"current_steps": 2955, "total_steps": 9128, "loss": 0.1816, "lr": 3.4210922516061804e-05, "epoch": 2.2662063674721904, "percentage": 32.37, "elapsed_time": "19:06:04", "remaining_time": "1 day, 15:54:08"}
|
| 592 |
+
{"current_steps": 2960, "total_steps": 9128, "loss": 0.1795, "lr": 3.418398744075467e-05, "epoch": 2.270042194092827, "percentage": 32.43, "elapsed_time": "19:07:19", "remaining_time": "1 day, 15:50:47"}
|
| 593 |
+
{"current_steps": 2965, "total_steps": 9128, "loss": 0.1931, "lr": 3.415700050660441e-05, "epoch": 2.2738780207134637, "percentage": 32.48, "elapsed_time": "19:08:36", "remaining_time": "1 day, 15:47:27"}
|
| 594 |
+
{"current_steps": 2970, "total_steps": 9128, "loss": 0.1954, "lr": 3.412996181227941e-05, "epoch": 2.2777138473341005, "percentage": 32.54, "elapsed_time": "19:09:51", "remaining_time": "1 day, 15:44:06"}
|
| 595 |
+
{"current_steps": 2975, "total_steps": 9128, "loss": 0.2004, "lr": 3.410287145663731e-05, "epoch": 2.2815496739547374, "percentage": 32.59, "elapsed_time": "19:11:08", "remaining_time": "1 day, 15:40:49"}
|
| 596 |
+
{"current_steps": 2980, "total_steps": 9128, "loss": 0.1899, "lr": 3.4075729538724605e-05, "epoch": 2.285385500575374, "percentage": 32.65, "elapsed_time": "19:12:23", "remaining_time": "1 day, 15:37:28"}
|
| 597 |
+
{"current_steps": 2985, "total_steps": 9128, "loss": 0.1872, "lr": 3.404853615777635e-05, "epoch": 2.2892213271960107, "percentage": 32.7, "elapsed_time": "19:13:37", "remaining_time": "1 day, 15:34:07"}
|
| 598 |
+
{"current_steps": 2990, "total_steps": 9128, "loss": 0.1929, "lr": 3.402129141321572e-05, "epoch": 2.2930571538166475, "percentage": 32.76, "elapsed_time": "19:14:57", "remaining_time": "1 day, 15:30:56"}
|
| 599 |
+
{"current_steps": 2995, "total_steps": 9128, "loss": 0.1992, "lr": 3.3993995404653714e-05, "epoch": 2.2968929804372844, "percentage": 32.81, "elapsed_time": "19:16:16", "remaining_time": "1 day, 15:27:45"}
|
| 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"}
|