Training in progress, step 7600
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 sha256:2c8a4b24bb63a32345621f6b272b6eaf0e5feb30219699790516046f86484513
|
| 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 sha256:01fe14bff8706d203c2b6d04c72176421c31076b70c5687f78ab6bdefa81fb83
|
| 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 sha256:906921c60559d7cc7695832c474399b3ffd5ffa8b9a33fa34301cd0faeee029d
|
| 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 sha256:688a70e298915964acb7c361e2192d40731840d5b820f8f9295f2b376fbe557c
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1480,3 +1480,44 @@
|
|
| 1480 |
{"current_steps": 7400, "total_steps": 9128, "loss": 0.1981, "lr": 4.214964814884204e-06, "epoch": 5.675105485232067, "percentage": 81.07, "elapsed_time": "1 day, 21:50:04", "remaining_time": "10:42:10"}
|
| 1481 |
{"current_steps": 7405, "total_steps": 9128, "loss": 0.1856, "lr": 4.191510337649389e-06, "epoch": 5.678941311852705, "percentage": 81.12, "elapsed_time": "1 day, 21:53:04", "remaining_time": "10:40:35"}
|
| 1482 |
{"current_steps": 7410, "total_steps": 9128, "loss": 0.1962, "lr": 4.168113658688069e-06, "epoch": 5.682777138473341, "percentage": 81.18, "elapsed_time": "1 day, 21:54:38", "remaining_time": "10:38:39"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1480 |
{"current_steps": 7400, "total_steps": 9128, "loss": 0.1981, "lr": 4.214964814884204e-06, "epoch": 5.675105485232067, "percentage": 81.07, "elapsed_time": "1 day, 21:50:04", "remaining_time": "10:42:10"}
|
| 1481 |
{"current_steps": 7405, "total_steps": 9128, "loss": 0.1856, "lr": 4.191510337649389e-06, "epoch": 5.678941311852705, "percentage": 81.12, "elapsed_time": "1 day, 21:53:04", "remaining_time": "10:40:35"}
|
| 1482 |
{"current_steps": 7410, "total_steps": 9128, "loss": 0.1962, "lr": 4.168113658688069e-06, "epoch": 5.682777138473341, "percentage": 81.18, "elapsed_time": "1 day, 21:54:38", "remaining_time": "10:38:39"}
|
| 1483 |
+
{"current_steps": 7415, "total_steps": 9128, "loss": 0.1958, "lr": 4.144774863542127e-06, "epoch": 5.686612965093977, "percentage": 81.23, "elapsed_time": "1 day, 21:56:17", "remaining_time": "10:36:45"}
|
| 1484 |
+
{"current_steps": 7420, "total_steps": 9128, "loss": 0.1927, "lr": 4.1214940375417755e-06, "epoch": 5.690448791714615, "percentage": 81.29, "elapsed_time": "1 day, 21:57:57", "remaining_time": "10:34:50"}
|
| 1485 |
+
{"current_steps": 7425, "total_steps": 9128, "loss": 0.1953, "lr": 4.098271265805298e-06, "epoch": 5.694284618335251, "percentage": 81.34, "elapsed_time": "1 day, 21:59:41", "remaining_time": "10:32:57"}
|
| 1486 |
+
{"current_steps": 7430, "total_steps": 9128, "loss": 0.1904, "lr": 4.075106633238748e-06, "epoch": 5.698120444955888, "percentage": 81.4, "elapsed_time": "1 day, 22:01:21", "remaining_time": "10:31:03"}
|
| 1487 |
+
{"current_steps": 7435, "total_steps": 9128, "loss": 0.1929, "lr": 4.0520002245355614e-06, "epoch": 5.701956271576525, "percentage": 81.45, "elapsed_time": "1 day, 22:03:05", "remaining_time": "10:29:10"}
|
| 1488 |
+
{"current_steps": 7440, "total_steps": 9128, "loss": 0.1929, "lr": 4.028952124176351e-06, "epoch": 5.705792098197161, "percentage": 81.51, "elapsed_time": "1 day, 22:04:45", "remaining_time": "10:27:16"}
|
| 1489 |
+
{"current_steps": 7445, "total_steps": 9128, "loss": 0.1905, "lr": 4.005962416428519e-06, "epoch": 5.709627924817799, "percentage": 81.56, "elapsed_time": "1 day, 22:06:22", "remaining_time": "10:25:21"}
|
| 1490 |
+
{"current_steps": 7450, "total_steps": 9128, "loss": 0.1956, "lr": 3.983031185345963e-06, "epoch": 5.713463751438435, "percentage": 81.62, "elapsed_time": "1 day, 22:08:06", "remaining_time": "10:23:28"}
|
| 1491 |
+
{"current_steps": 7455, "total_steps": 9128, "loss": 0.1895, "lr": 3.96015851476881e-06, "epoch": 5.717299578059071, "percentage": 81.67, "elapsed_time": "1 day, 22:09:50", "remaining_time": "10:21:35"}
|
| 1492 |
+
{"current_steps": 7460, "total_steps": 9128, "loss": 0.1906, "lr": 3.937344488323067e-06, "epoch": 5.721135404679709, "percentage": 81.73, "elapsed_time": "1 day, 22:11:29", "remaining_time": "10:19:41"}
|
| 1493 |
+
{"current_steps": 7465, "total_steps": 9128, "loss": 0.1879, "lr": 3.914589189420323e-06, "epoch": 5.724971231300345, "percentage": 81.78, "elapsed_time": "1 day, 22:13:07", "remaining_time": "10:17:46"}
|
| 1494 |
+
{"current_steps": 7470, "total_steps": 9128, "loss": 0.1897, "lr": 3.891892701257463e-06, "epoch": 5.7288070579209815, "percentage": 81.84, "elapsed_time": "1 day, 22:14:52", "remaining_time": "10:15:53"}
|
| 1495 |
+
{"current_steps": 7475, "total_steps": 9128, "loss": 0.1957, "lr": 3.869255106816339e-06, "epoch": 5.732642884541619, "percentage": 81.89, "elapsed_time": "1 day, 22:16:29", "remaining_time": "10:13:59"}
|
| 1496 |
+
{"current_steps": 7480, "total_steps": 9128, "loss": 0.1944, "lr": 3.846676488863483e-06, "epoch": 5.736478711162255, "percentage": 81.95, "elapsed_time": "1 day, 22:18:08", "remaining_time": "10:12:04"}
|
| 1497 |
+
{"current_steps": 7485, "total_steps": 9128, "loss": 0.1942, "lr": 3.824156929949809e-06, "epoch": 5.740314537782893, "percentage": 82.0, "elapsed_time": "1 day, 22:19:49", "remaining_time": "10:10:11"}
|
| 1498 |
+
{"current_steps": 7490, "total_steps": 9128, "loss": 0.1974, "lr": 3.8016965124102778e-06, "epoch": 5.744150364403529, "percentage": 82.06, "elapsed_time": "1 day, 22:21:32", "remaining_time": "10:08:18"}
|
| 1499 |
+
{"current_steps": 7495, "total_steps": 9128, "loss": 0.1943, "lr": 3.7792953183636517e-06, "epoch": 5.747986191024165, "percentage": 82.11, "elapsed_time": "1 day, 22:23:06", "remaining_time": "10:06:22"}
|
| 1500 |
+
{"current_steps": 7500, "total_steps": 9128, "loss": 0.1912, "lr": 3.756953429712138e-06, "epoch": 5.751822017644803, "percentage": 82.16, "elapsed_time": "1 day, 22:24:50", "remaining_time": "10:04:29"}
|
| 1501 |
+
{"current_steps": 7505, "total_steps": 9128, "loss": 0.1822, "lr": 3.7346709281411263e-06, "epoch": 5.755657844265439, "percentage": 82.22, "elapsed_time": "1 day, 22:26:32", "remaining_time": "10:02:36"}
|
| 1502 |
+
{"current_steps": 7510, "total_steps": 9128, "loss": 0.1918, "lr": 3.712447895118876e-06, "epoch": 5.759493670886076, "percentage": 82.27, "elapsed_time": "1 day, 22:28:08", "remaining_time": "10:00:41"}
|
| 1503 |
+
{"current_steps": 7515, "total_steps": 9128, "loss": 0.1776, "lr": 3.690284411896219e-06, "epoch": 5.763329497506713, "percentage": 82.33, "elapsed_time": "1 day, 22:29:51", "remaining_time": "9:58:48"}
|
| 1504 |
+
{"current_steps": 7520, "total_steps": 9128, "loss": 0.2051, "lr": 3.6681805595062603e-06, "epoch": 5.767165324127349, "percentage": 82.38, "elapsed_time": "1 day, 22:31:32", "remaining_time": "9:56:54"}
|
| 1505 |
+
{"current_steps": 7525, "total_steps": 9128, "loss": 0.1928, "lr": 3.6461364187640948e-06, "epoch": 5.771001150747987, "percentage": 82.44, "elapsed_time": "1 day, 22:33:22", "remaining_time": "9:55:03"}
|
| 1506 |
+
{"current_steps": 7530, "total_steps": 9128, "loss": 0.1968, "lr": 3.6241520702664913e-06, "epoch": 5.774836977368623, "percentage": 82.49, "elapsed_time": "1 day, 22:35:06", "remaining_time": "9:53:10"}
|
| 1507 |
+
{"current_steps": 7535, "total_steps": 9128, "loss": 0.1982, "lr": 3.6022275943916205e-06, "epoch": 5.778672803989259, "percentage": 82.55, "elapsed_time": "1 day, 22:36:48", "remaining_time": "9:51:17"}
|
| 1508 |
+
{"current_steps": 7540, "total_steps": 9128, "loss": 0.1989, "lr": 3.58036307129874e-06, "epoch": 5.782508630609897, "percentage": 82.6, "elapsed_time": "1 day, 22:38:31", "remaining_time": "9:49:23"}
|
| 1509 |
+
{"current_steps": 7545, "total_steps": 9128, "loss": 0.1944, "lr": 3.5585585809279155e-06, "epoch": 5.786344457230533, "percentage": 82.66, "elapsed_time": "1 day, 22:40:12", "remaining_time": "9:47:30"}
|
| 1510 |
+
{"current_steps": 7550, "total_steps": 9128, "loss": 0.1839, "lr": 3.536814202999723e-06, "epoch": 5.79018028385117, "percentage": 82.71, "elapsed_time": "1 day, 22:41:54", "remaining_time": "9:45:36"}
|
| 1511 |
+
{"current_steps": 7555, "total_steps": 9128, "loss": 0.1871, "lr": 3.515130017014956e-06, "epoch": 5.794016110471807, "percentage": 82.77, "elapsed_time": "1 day, 22:43:29", "remaining_time": "9:43:42"}
|
| 1512 |
+
{"current_steps": 7560, "total_steps": 9128, "loss": 0.1838, "lr": 3.4935061022543403e-06, "epoch": 5.797851937092443, "percentage": 82.82, "elapsed_time": "1 day, 22:45:07", "remaining_time": "9:41:48"}
|
| 1513 |
+
{"current_steps": 7565, "total_steps": 9128, "loss": 0.1861, "lr": 3.4719425377782414e-06, "epoch": 5.80168776371308, "percentage": 82.88, "elapsed_time": "1 day, 22:46:49", "remaining_time": "9:39:55"}
|
| 1514 |
+
{"current_steps": 7570, "total_steps": 9128, "loss": 0.1732, "lr": 3.450439402426371e-06, "epoch": 5.805523590333717, "percentage": 82.93, "elapsed_time": "1 day, 22:48:29", "remaining_time": "9:38:01"}
|
| 1515 |
+
{"current_steps": 7575, "total_steps": 9128, "loss": 0.1736, "lr": 3.4289967748175033e-06, "epoch": 5.809359416954353, "percentage": 82.99, "elapsed_time": "1 day, 22:50:07", "remaining_time": "9:36:07"}
|
| 1516 |
+
{"current_steps": 7580, "total_steps": 9128, "loss": 0.189, "lr": 3.4076147333491895e-06, "epoch": 5.813195243574991, "percentage": 83.04, "elapsed_time": "1 day, 22:51:47", "remaining_time": "9:34:13"}
|
| 1517 |
+
{"current_steps": 7585, "total_steps": 9128, "loss": 0.2079, "lr": 3.3862933561974676e-06, "epoch": 5.817031070195627, "percentage": 83.1, "elapsed_time": "1 day, 22:53:25", "remaining_time": "9:32:19"}
|
| 1518 |
+
{"current_steps": 7590, "total_steps": 9128, "loss": 0.184, "lr": 3.365032721316577e-06, "epoch": 5.820866896816264, "percentage": 83.15, "elapsed_time": "1 day, 22:55:03", "remaining_time": "9:30:25"}
|
| 1519 |
+
{"current_steps": 7595, "total_steps": 9128, "loss": 0.1962, "lr": 3.343832906438671e-06, "epoch": 5.824702723436901, "percentage": 83.21, "elapsed_time": "1 day, 22:56:42", "remaining_time": "9:28:32"}
|
| 1520 |
+
{"current_steps": 7600, "total_steps": 9128, "loss": 0.1865, "lr": 3.322693989073542e-06, "epoch": 5.828538550057537, "percentage": 83.26, "elapsed_time": "1 day, 22:58:24", "remaining_time": "9:26:38"}
|
| 1521 |
+
{"current_steps": 7605, "total_steps": 9128, "loss": 0.1958, "lr": 3.3016160465083293e-06, "epoch": 5.832374376678175, "percentage": 83.32, "elapsed_time": "1 day, 23:01:26", "remaining_time": "9:25:01"}
|
| 1522 |
+
{"current_steps": 7610, "total_steps": 9128, "loss": 0.1879, "lr": 3.280599155807229e-06, "epoch": 5.836210203298811, "percentage": 83.37, "elapsed_time": "1 day, 23:03:10", "remaining_time": "9:23:09"}
|
| 1523 |
+
{"current_steps": 7615, "total_steps": 9128, "loss": 0.1799, "lr": 3.2596433938112495e-06, "epoch": 5.840046029919447, "percentage": 83.42, "elapsed_time": "1 day, 23:04:56", "remaining_time": "9:21:16"}
|