Training in progress, step 3800
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:c9298364c58a53e3ae5d3b3fc35401319de37a6f4db2be8f512f55a14ce593f8
|
| 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 sha256:9499b43623afaa8eff16427d992cc4e7560d3e3e9c19095f56f54611c2b9187f
|
| 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 sha256:8024c593e549eb246474ab5f300a65514df1b3d882bd4458ccda1d373451caa5
|
| 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 sha256:048a78c5f2371ac4a3e57b0057c31975057759853c57e6ffb8eb71c06b3e0bf6
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -723,3 +723,43 @@
|
|
| 723 |
{"current_steps": 3590, "total_steps": 6188, "loss": 0.0801, "lr": 1.791092682372449e-05, "epoch": 4.062252405206565, "percentage": 58.02, "elapsed_time": "3:41:46", "remaining_time": "2:40:29"}
|
| 724 |
{"current_steps": 3595, "total_steps": 6188, "loss": 0.0875, "lr": 1.7854831646197426e-05, "epoch": 4.067911714770798, "percentage": 58.1, "elapsed_time": "3:43:42", "remaining_time": "2:41:21"}
|
| 725 |
{"current_steps": 3600, "total_steps": 6188, "loss": 0.0906, "lr": 1.7798753535246856e-05, "epoch": 4.073571024335031, "percentage": 58.18, "elapsed_time": "3:45:33", "remaining_time": "2:42:09"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 723 |
{"current_steps": 3590, "total_steps": 6188, "loss": 0.0801, "lr": 1.791092682372449e-05, "epoch": 4.062252405206565, "percentage": 58.02, "elapsed_time": "3:41:46", "remaining_time": "2:40:29"}
|
| 724 |
{"current_steps": 3595, "total_steps": 6188, "loss": 0.0875, "lr": 1.7854831646197426e-05, "epoch": 4.067911714770798, "percentage": 58.1, "elapsed_time": "3:43:42", "remaining_time": "2:41:21"}
|
| 725 |
{"current_steps": 3600, "total_steps": 6188, "loss": 0.0906, "lr": 1.7798753535246856e-05, "epoch": 4.073571024335031, "percentage": 58.18, "elapsed_time": "3:45:33", "remaining_time": "2:42:09"}
|
| 726 |
+
{"current_steps": 3605, "total_steps": 6188, "loss": 0.1162, "lr": 1.7742692937020234e-05, "epoch": 4.079230333899265, "percentage": 58.26, "elapsed_time": "3:48:35", "remaining_time": "2:43:47"}
|
| 727 |
+
{"current_steps": 3610, "total_steps": 6188, "loss": 0.0836, "lr": 1.768665029752567e-05, "epoch": 4.084889643463497, "percentage": 58.34, "elapsed_time": "3:50:18", "remaining_time": "2:44:28"}
|
| 728 |
+
{"current_steps": 3615, "total_steps": 6188, "loss": 0.0831, "lr": 1.763062606262839e-05, "epoch": 4.090548953027731, "percentage": 58.42, "elapsed_time": "3:51:53", "remaining_time": "2:45:03"}
|
| 729 |
+
{"current_steps": 3620, "total_steps": 6188, "loss": 0.0762, "lr": 1.7574620678047215e-05, "epoch": 4.096208262591964, "percentage": 58.5, "elapsed_time": "3:53:30", "remaining_time": "2:45:38"}
|
| 730 |
+
{"current_steps": 3625, "total_steps": 6188, "loss": 0.096, "lr": 1.751863458935099e-05, "epoch": 4.101867572156197, "percentage": 58.58, "elapsed_time": "3:55:02", "remaining_time": "2:46:11"}
|
| 731 |
+
{"current_steps": 3630, "total_steps": 6188, "loss": 0.0974, "lr": 1.746266824195504e-05, "epoch": 4.10752688172043, "percentage": 58.66, "elapsed_time": "3:56:51", "remaining_time": "2:46:54"}
|
| 732 |
+
{"current_steps": 3635, "total_steps": 6188, "loss": 0.097, "lr": 1.7406722081117632e-05, "epoch": 4.1131861912846635, "percentage": 58.74, "elapsed_time": "3:58:32", "remaining_time": "2:47:32"}
|
| 733 |
+
{"current_steps": 3640, "total_steps": 6188, "loss": 0.0974, "lr": 1.7350796551936432e-05, "epoch": 4.118845500848896, "percentage": 58.82, "elapsed_time": "4:00:17", "remaining_time": "2:48:12"}
|
| 734 |
+
{"current_steps": 3645, "total_steps": 6188, "loss": 0.1315, "lr": 1.7294892099344975e-05, "epoch": 4.124504810413129, "percentage": 58.9, "elapsed_time": "4:02:05", "remaining_time": "2:48:53"}
|
| 735 |
+
{"current_steps": 3650, "total_steps": 6188, "loss": 0.0821, "lr": 1.7239009168109108e-05, "epoch": 4.130164119977363, "percentage": 58.99, "elapsed_time": "4:03:38", "remaining_time": "2:49:24"}
|
| 736 |
+
{"current_steps": 3655, "total_steps": 6188, "loss": 0.1109, "lr": 1.7183148202823445e-05, "epoch": 4.135823429541596, "percentage": 59.07, "elapsed_time": "4:05:09", "remaining_time": "2:49:54"}
|
| 737 |
+
{"current_steps": 3660, "total_steps": 6188, "loss": 0.1078, "lr": 1.7127309647907867e-05, "epoch": 4.141482739105829, "percentage": 59.15, "elapsed_time": "4:07:01", "remaining_time": "2:50:37"}
|
| 738 |
+
{"current_steps": 3665, "total_steps": 6188, "loss": 0.0884, "lr": 1.7071493947603942e-05, "epoch": 4.147142048670062, "percentage": 59.23, "elapsed_time": "4:08:42", "remaining_time": "2:51:13"}
|
| 739 |
+
{"current_steps": 3670, "total_steps": 6188, "loss": 0.2033, "lr": 1.7015701545971417e-05, "epoch": 4.152801358234296, "percentage": 59.31, "elapsed_time": "4:10:48", "remaining_time": "2:52:04"}
|
| 740 |
+
{"current_steps": 3675, "total_steps": 6188, "loss": 0.1865, "lr": 1.695993288688469e-05, "epoch": 4.158460667798528, "percentage": 59.39, "elapsed_time": "4:12:43", "remaining_time": "2:52:48"}
|
| 741 |
+
{"current_steps": 3680, "total_steps": 6188, "loss": 0.0996, "lr": 1.6904188414029248e-05, "epoch": 4.164119977362762, "percentage": 59.47, "elapsed_time": "4:14:35", "remaining_time": "2:53:30"}
|
| 742 |
+
{"current_steps": 3685, "total_steps": 6188, "loss": 0.1673, "lr": 1.6848468570898172e-05, "epoch": 4.169779286926995, "percentage": 59.55, "elapsed_time": "4:16:40", "remaining_time": "2:54:20"}
|
| 743 |
+
{"current_steps": 3690, "total_steps": 6188, "loss": 0.1099, "lr": 1.6792773800788583e-05, "epoch": 4.175438596491228, "percentage": 59.63, "elapsed_time": "4:18:37", "remaining_time": "2:55:04"}
|
| 744 |
+
{"current_steps": 3695, "total_steps": 6188, "loss": 0.0871, "lr": 1.673710454679813e-05, "epoch": 4.181097906055461, "percentage": 59.71, "elapsed_time": "4:20:29", "remaining_time": "2:55:44"}
|
| 745 |
+
{"current_steps": 3700, "total_steps": 6188, "loss": 0.0963, "lr": 1.668146125182147e-05, "epoch": 4.186757215619695, "percentage": 59.79, "elapsed_time": "4:22:09", "remaining_time": "2:56:17"}
|
| 746 |
+
{"current_steps": 3705, "total_steps": 6188, "loss": 0.0842, "lr": 1.6625844358546715e-05, "epoch": 4.192416525183927, "percentage": 59.87, "elapsed_time": "4:23:50", "remaining_time": "2:56:49"}
|
| 747 |
+
{"current_steps": 3710, "total_steps": 6188, "loss": 0.0858, "lr": 1.657025430945195e-05, "epoch": 4.198075834748161, "percentage": 59.95, "elapsed_time": "4:25:38", "remaining_time": "2:57:25"}
|
| 748 |
+
{"current_steps": 3715, "total_steps": 6188, "loss": 0.0808, "lr": 1.651469154680167e-05, "epoch": 4.203735144312394, "percentage": 60.04, "elapsed_time": "4:27:09", "remaining_time": "2:57:50"}
|
| 749 |
+
{"current_steps": 3720, "total_steps": 6188, "loss": 0.083, "lr": 1.6459156512643303e-05, "epoch": 4.2093944538766275, "percentage": 60.12, "elapsed_time": "4:28:40", "remaining_time": "2:58:14"}
|
| 750 |
+
{"current_steps": 3725, "total_steps": 6188, "loss": 0.0734, "lr": 1.640364964880367e-05, "epoch": 4.21505376344086, "percentage": 60.2, "elapsed_time": "4:30:16", "remaining_time": "2:58:42"}
|
| 751 |
+
{"current_steps": 3730, "total_steps": 6188, "loss": 0.1272, "lr": 1.6348171396885468e-05, "epoch": 4.2207130730050935, "percentage": 60.28, "elapsed_time": "4:32:14", "remaining_time": "2:59:24"}
|
| 752 |
+
{"current_steps": 3735, "total_steps": 6188, "loss": 0.0666, "lr": 1.6292722198263766e-05, "epoch": 4.226372382569327, "percentage": 60.36, "elapsed_time": "4:33:44", "remaining_time": "2:59:46"}
|
| 753 |
+
{"current_steps": 3740, "total_steps": 6188, "loss": 0.0743, "lr": 1.623730249408249e-05, "epoch": 4.2320316921335595, "percentage": 60.44, "elapsed_time": "4:35:21", "remaining_time": "3:00:13"}
|
| 754 |
+
{"current_steps": 3745, "total_steps": 6188, "loss": 0.0778, "lr": 1.618191272525092e-05, "epoch": 4.237691001697793, "percentage": 60.52, "elapsed_time": "4:36:56", "remaining_time": "3:00:39"}
|
| 755 |
+
{"current_steps": 3750, "total_steps": 6188, "loss": 0.095, "lr": 1.612655333244016e-05, "epoch": 4.243350311262026, "percentage": 60.6, "elapsed_time": "4:39:00", "remaining_time": "3:01:23"}
|
| 756 |
+
{"current_steps": 3755, "total_steps": 6188, "loss": 0.1064, "lr": 1.6071224756079666e-05, "epoch": 4.249009620826259, "percentage": 60.68, "elapsed_time": "4:40:51", "remaining_time": "3:01:58"}
|
| 757 |
+
{"current_steps": 3760, "total_steps": 6188, "loss": 0.1135, "lr": 1.6015927436353713e-05, "epoch": 4.254668930390492, "percentage": 60.76, "elapsed_time": "4:42:39", "remaining_time": "3:02:31"}
|
| 758 |
+
{"current_steps": 3765, "total_steps": 6188, "loss": 0.0903, "lr": 1.59606618131979e-05, "epoch": 4.260328239954726, "percentage": 60.84, "elapsed_time": "4:44:16", "remaining_time": "3:02:57"}
|
| 759 |
+
{"current_steps": 3770, "total_steps": 6188, "loss": 0.1041, "lr": 1.5905428326295663e-05, "epoch": 4.265987549518958, "percentage": 60.92, "elapsed_time": "4:46:03", "remaining_time": "3:03:28"}
|
| 760 |
+
{"current_steps": 3775, "total_steps": 6188, "loss": 0.1197, "lr": 1.585022741507477e-05, "epoch": 4.271646859083192, "percentage": 61.01, "elapsed_time": "4:47:52", "remaining_time": "3:04:00"}
|
| 761 |
+
{"current_steps": 3780, "total_steps": 6188, "loss": 0.0889, "lr": 1.579505951870381e-05, "epoch": 4.277306168647425, "percentage": 61.09, "elapsed_time": "4:49:29", "remaining_time": "3:04:25"}
|
| 762 |
+
{"current_steps": 3785, "total_steps": 6188, "loss": 0.1105, "lr": 1.573992507608872e-05, "epoch": 4.282965478211658, "percentage": 61.17, "elapsed_time": "4:51:04", "remaining_time": "3:04:47"}
|
| 763 |
+
{"current_steps": 3790, "total_steps": 6188, "loss": 0.0924, "lr": 1.568482452586929e-05, "epoch": 4.288624787775891, "percentage": 61.25, "elapsed_time": "4:52:49", "remaining_time": "3:05:16"}
|
| 764 |
+
{"current_steps": 3795, "total_steps": 6188, "loss": 0.0858, "lr": 1.5629758306415652e-05, "epoch": 4.294284097340125, "percentage": 61.33, "elapsed_time": "4:54:53", "remaining_time": "3:05:57"}
|
| 765 |
+
{"current_steps": 3800, "total_steps": 6188, "loss": 0.0765, "lr": 1.5574726855824827e-05, "epoch": 4.299943406904358, "percentage": 61.41, "elapsed_time": "4:56:35", "remaining_time": "3:06:23"}
|