Training in progress, step 2800
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 sha256:19c78acf45fe31019bb9a51d53debc2fee4bfe73eed23c87518f4c250fdd7653
|
| 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 sha256:18cc3dd34c3584a500e569d89a4e81c6e3c5fcd97c8357199368ed9bad11f016
|
| 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:b87fba39e1732f42ae90b0a90e219d6899beb20ddf68348591e97fa584959800
|
| 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 sha256:63a9bffccd8e2c309017314b0d6eba2f9d87a458dc5f7c7f1dcd599b510d35c4
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -519,3 +519,43 @@
|
|
| 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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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"}
|
| 522 |
+
{"current_steps": 2610, "total_steps": 9128, "loss": 0.2503, "lr": 3.5938764204258306e-05, "epoch": 2.0015343306482545, "percentage": 28.59, "elapsed_time": "16:11:21", "remaining_time": "1 day, 16:25:48"}
|
| 523 |
+
{"current_steps": 2615, "total_steps": 9128, "loss": 0.2312, "lr": 3.5915634495860174e-05, "epoch": 2.0053701572688913, "percentage": 28.65, "elapsed_time": "16:14:14", "remaining_time": "1 day, 16:26:29"}
|
| 524 |
+
{"current_steps": 2620, "total_steps": 9128, "loss": 0.2221, "lr": 3.589244659745052e-05, "epoch": 2.009205983889528, "percentage": 28.7, "elapsed_time": "16:16:58", "remaining_time": "1 day, 16:26:47"}
|
| 525 |
+
{"current_steps": 2625, "total_steps": 9128, "loss": 0.2175, "lr": 3.5869200593807886e-05, "epoch": 2.013041810510165, "percentage": 28.76, "elapsed_time": "16:20:01", "remaining_time": "1 day, 16:27:51"}
|
| 526 |
+
{"current_steps": 2630, "total_steps": 9128, "loss": 0.2089, "lr": 3.584589656992322e-05, "epoch": 2.0168776371308015, "percentage": 28.81, "elapsed_time": "16:23:03", "remaining_time": "1 day, 16:28:52"}
|
| 527 |
+
{"current_steps": 2635, "total_steps": 9128, "loss": 0.2128, "lr": 3.5822534610999645e-05, "epoch": 2.0207134637514383, "percentage": 28.87, "elapsed_time": "16:26:08", "remaining_time": "1 day, 16:29:58"}
|
| 528 |
+
{"current_steps": 2640, "total_steps": 9128, "loss": 0.2303, "lr": 3.5799114802452064e-05, "epoch": 2.024549290372075, "percentage": 28.92, "elapsed_time": "16:29:07", "remaining_time": "1 day, 16:30:50"}
|
| 529 |
+
{"current_steps": 2645, "total_steps": 9128, "loss": 0.223, "lr": 3.577563722990691e-05, "epoch": 2.028385116992712, "percentage": 28.98, "elapsed_time": "16:32:04", "remaining_time": "1 day, 16:31:37"}
|
| 530 |
+
{"current_steps": 2650, "total_steps": 9128, "loss": 0.2111, "lr": 3.5752101979201816e-05, "epoch": 2.0322209436133485, "percentage": 29.03, "elapsed_time": "16:34:53", "remaining_time": "1 day, 16:32:02"}
|
| 531 |
+
{"current_steps": 2655, "total_steps": 9128, "loss": 0.2054, "lr": 3.572850913638527e-05, "epoch": 2.0360567702339853, "percentage": 29.09, "elapsed_time": "16:37:22", "remaining_time": "1 day, 16:31:38"}
|
| 532 |
+
{"current_steps": 2660, "total_steps": 9128, "loss": 0.2094, "lr": 3.5704858787716344e-05, "epoch": 2.039892596854622, "percentage": 29.14, "elapsed_time": "16:40:18", "remaining_time": "1 day, 16:32:18"}
|
| 533 |
+
{"current_steps": 2665, "total_steps": 9128, "loss": 0.2029, "lr": 3.5681151019664364e-05, "epoch": 2.043728423475259, "percentage": 29.2, "elapsed_time": "16:43:10", "remaining_time": "1 day, 16:32:49"}
|
| 534 |
+
{"current_steps": 2670, "total_steps": 9128, "loss": 0.2126, "lr": 3.5657385918908566e-05, "epoch": 2.0475642500958955, "percentage": 29.25, "elapsed_time": "16:45:55", "remaining_time": "1 day, 16:33:03"}
|
| 535 |
+
{"current_steps": 2675, "total_steps": 9128, "loss": 0.2026, "lr": 3.563356357233783e-05, "epoch": 2.0514000767165324, "percentage": 29.31, "elapsed_time": "16:48:43", "remaining_time": "1 day, 16:33:23"}
|
| 536 |
+
{"current_steps": 2680, "total_steps": 9128, "loss": 0.2011, "lr": 3.560968406705034e-05, "epoch": 2.055235903337169, "percentage": 29.36, "elapsed_time": "16:51:30", "remaining_time": "1 day, 16:33:39"}
|
| 537 |
+
{"current_steps": 2685, "total_steps": 9128, "loss": 0.2092, "lr": 3.55857474903532e-05, "epoch": 2.059071729957806, "percentage": 29.41, "elapsed_time": "16:54:10", "remaining_time": "1 day, 16:33:38"}
|
| 538 |
+
{"current_steps": 2690, "total_steps": 9128, "loss": 0.2029, "lr": 3.5561753929762276e-05, "epoch": 2.0629075565784425, "percentage": 29.47, "elapsed_time": "16:56:59", "remaining_time": "1 day, 16:33:58"}
|
| 539 |
+
{"current_steps": 2695, "total_steps": 9128, "loss": 0.205, "lr": 3.553770347300169e-05, "epoch": 2.0667433831990794, "percentage": 29.52, "elapsed_time": "16:59:56", "remaining_time": "1 day, 16:34:37"}
|
| 540 |
+
{"current_steps": 2700, "total_steps": 9128, "loss": 0.2218, "lr": 3.5513596208003625e-05, "epoch": 2.070579209819716, "percentage": 29.58, "elapsed_time": "17:02:46", "remaining_time": "1 day, 16:34:57"}
|
| 541 |
+
{"current_steps": 2705, "total_steps": 9128, "loss": 0.226, "lr": 3.548943222290794e-05, "epoch": 2.074415036440353, "percentage": 29.63, "elapsed_time": "17:05:24", "remaining_time": "1 day, 16:34:49"}
|
| 542 |
+
{"current_steps": 2710, "total_steps": 9128, "loss": 0.1872, "lr": 3.546521160606192e-05, "epoch": 2.0782508630609895, "percentage": 29.69, "elapsed_time": "17:08:04", "remaining_time": "1 day, 16:34:44"}
|
| 543 |
+
{"current_steps": 2715, "total_steps": 9128, "loss": 0.2023, "lr": 3.544093444601985e-05, "epoch": 2.0820866896816264, "percentage": 29.74, "elapsed_time": "17:10:53", "remaining_time": "1 day, 16:35:01"}
|
| 544 |
+
{"current_steps": 2720, "total_steps": 9128, "loss": 0.2028, "lr": 3.5416600831542763e-05, "epoch": 2.085922516302263, "percentage": 29.8, "elapsed_time": "17:13:47", "remaining_time": "1 day, 16:35:28"}
|
| 545 |
+
{"current_steps": 2725, "total_steps": 9128, "loss": 0.2104, "lr": 3.539221085159811e-05, "epoch": 2.0897583429229, "percentage": 29.85, "elapsed_time": "17:16:32", "remaining_time": "1 day, 16:35:35"}
|
| 546 |
+
{"current_steps": 2730, "total_steps": 9128, "loss": 0.206, "lr": 3.536776459535942e-05, "epoch": 2.0935941695435365, "percentage": 29.91, "elapsed_time": "17:19:32", "remaining_time": "1 day, 16:36:16"}
|
| 547 |
+
{"current_steps": 2735, "total_steps": 9128, "loss": 0.1981, "lr": 3.5343262152205966e-05, "epoch": 2.0974299961641734, "percentage": 29.96, "elapsed_time": "17:22:32", "remaining_time": "1 day, 16:36:55"}
|
| 548 |
+
{"current_steps": 2740, "total_steps": 9128, "loss": 0.1793, "lr": 3.531870361172245e-05, "epoch": 2.1012658227848102, "percentage": 30.02, "elapsed_time": "17:25:34", "remaining_time": "1 day, 16:37:38"}
|
| 549 |
+
{"current_steps": 2745, "total_steps": 9128, "loss": 0.1844, "lr": 3.529408906369868e-05, "epoch": 2.105101649405447, "percentage": 30.07, "elapsed_time": "17:28:27", "remaining_time": "1 day, 16:38:00"}
|
| 550 |
+
{"current_steps": 2750, "total_steps": 9128, "loss": 0.1967, "lr": 3.5269418598129254e-05, "epoch": 2.1089374760260835, "percentage": 30.13, "elapsed_time": "17:31:27", "remaining_time": "1 day, 16:38:37"}
|
| 551 |
+
{"current_steps": 2755, "total_steps": 9128, "loss": 0.2037, "lr": 3.524469230521317e-05, "epoch": 2.1127733026467204, "percentage": 30.18, "elapsed_time": "17:33:32", "remaining_time": "1 day, 16:37:06"}
|
| 552 |
+
{"current_steps": 2760, "total_steps": 9128, "loss": 0.21, "lr": 3.521991027535357e-05, "epoch": 2.1166091292673572, "percentage": 30.24, "elapsed_time": "17:36:22", "remaining_time": "1 day, 16:37:19"}
|
| 553 |
+
{"current_steps": 2765, "total_steps": 9128, "loss": 0.2235, "lr": 3.519507259915738e-05, "epoch": 2.1204449558879936, "percentage": 30.29, "elapsed_time": "17:39:20", "remaining_time": "1 day, 16:37:49"}
|
| 554 |
+
{"current_steps": 2770, "total_steps": 9128, "loss": 0.2153, "lr": 3.5170179367434964e-05, "epoch": 2.1242807825086305, "percentage": 30.35, "elapsed_time": "17:42:12", "remaining_time": "1 day, 16:38:05"}
|
| 555 |
+
{"current_steps": 2775, "total_steps": 9128, "loss": 0.2039, "lr": 3.514523067119982e-05, "epoch": 2.1281166091292674, "percentage": 30.4, "elapsed_time": "17:45:04", "remaining_time": "1 day, 16:38:20"}
|
| 556 |
+
{"current_steps": 2780, "total_steps": 9128, "loss": 0.2061, "lr": 3.512022660166822e-05, "epoch": 2.1319524357499042, "percentage": 30.46, "elapsed_time": "17:48:06", "remaining_time": "1 day, 16:38:58"}
|
| 557 |
+
{"current_steps": 2785, "total_steps": 9128, "loss": 0.2103, "lr": 3.509516725025889e-05, "epoch": 2.1357882623705406, "percentage": 30.51, "elapsed_time": "17:51:02", "remaining_time": "1 day, 16:39:22"}
|
| 558 |
+
{"current_steps": 2790, "total_steps": 9128, "loss": 0.2062, "lr": 3.507005270859269e-05, "epoch": 2.1396240889911775, "percentage": 30.57, "elapsed_time": "17:54:01", "remaining_time": "1 day, 16:39:51"}
|
| 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"}
|