Training in progress, step 8600
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 sha256:2c4ecdb67a7ee0e11694a15286500aadf4eed2c2026658bd465a69439c4f23f1
|
| 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 sha256:08e3f1e6969dd60f3ba768bf5d20e48b4d00bd8abe67ecdbee42549af4ad9402
|
| 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:d10ba1afb3dd6494c96bc13fb0ca864bb458274cfcb3464f9add9114c15eb2ea
|
| 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:bb21c8eb903b625036a786403f6714ae273d2bcd84a20c6ff88c012df26272db
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1692,3 +1692,43 @@
|
|
| 1692 |
{"current_steps": 8390, "total_steps": 9625, "loss": 0.112, "lr": 1.976128949840361e-06, "epoch": 6.102582757366315, "percentage": 87.17, "elapsed_time": "8:00:50", "remaining_time": "1:10:46"}
|
| 1693 |
{"current_steps": 8395, "total_steps": 9625, "loss": 0.0902, "lr": 1.9604391389489753e-06, "epoch": 6.106220443797745, "percentage": 87.22, "elapsed_time": "8:02:47", "remaining_time": "1:10:44"}
|
| 1694 |
{"current_steps": 8400, "total_steps": 9625, "loss": 0.1715, "lr": 1.9448086518952115e-06, "epoch": 6.109858130229174, "percentage": 87.27, "elapsed_time": "8:05:00", "remaining_time": "1:10:43"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1692 |
{"current_steps": 8390, "total_steps": 9625, "loss": 0.112, "lr": 1.976128949840361e-06, "epoch": 6.102582757366315, "percentage": 87.17, "elapsed_time": "8:00:50", "remaining_time": "1:10:46"}
|
| 1693 |
{"current_steps": 8395, "total_steps": 9625, "loss": 0.0902, "lr": 1.9604391389489753e-06, "epoch": 6.106220443797745, "percentage": 87.22, "elapsed_time": "8:02:47", "remaining_time": "1:10:44"}
|
| 1694 |
{"current_steps": 8400, "total_steps": 9625, "loss": 0.1715, "lr": 1.9448086518952115e-06, "epoch": 6.109858130229174, "percentage": 87.27, "elapsed_time": "8:05:00", "remaining_time": "1:10:43"}
|
| 1695 |
+
{"current_steps": 8405, "total_steps": 9625, "loss": 0.0763, "lr": 1.929237540080573e-06, "epoch": 6.1134958166606035, "percentage": 87.32, "elapsed_time": "8:08:00", "remaining_time": "1:10:50"}
|
| 1696 |
+
{"current_steps": 8410, "total_steps": 9625, "loss": 0.0776, "lr": 1.9137258547112904e-06, "epoch": 6.117133503092034, "percentage": 87.38, "elapsed_time": "8:09:53", "remaining_time": "1:10:46"}
|
| 1697 |
+
{"current_steps": 8415, "total_steps": 9625, "loss": 0.0789, "lr": 1.8982736467981943e-06, "epoch": 6.120771189523463, "percentage": 87.43, "elapsed_time": "8:11:35", "remaining_time": "1:10:41"}
|
| 1698 |
+
{"current_steps": 8420, "total_steps": 9625, "loss": 0.073, "lr": 1.8828809671564996e-06, "epoch": 6.1244088759548925, "percentage": 87.48, "elapsed_time": "8:13:13", "remaining_time": "1:10:35"}
|
| 1699 |
+
{"current_steps": 8425, "total_steps": 9625, "loss": 0.0731, "lr": 1.8675478664056635e-06, "epoch": 6.128046562386323, "percentage": 87.53, "elapsed_time": "8:14:58", "remaining_time": "1:10:30"}
|
| 1700 |
+
{"current_steps": 8430, "total_steps": 9625, "loss": 0.067, "lr": 1.852274394969218e-06, "epoch": 6.131684248817752, "percentage": 87.58, "elapsed_time": "8:16:28", "remaining_time": "1:10:22"}
|
| 1701 |
+
{"current_steps": 8435, "total_steps": 9625, "loss": 0.074, "lr": 1.837060603074603e-06, "epoch": 6.1353219352491815, "percentage": 87.64, "elapsed_time": "8:17:58", "remaining_time": "1:10:15"}
|
| 1702 |
+
{"current_steps": 8440, "total_steps": 9625, "loss": 0.0654, "lr": 1.8219065407530045e-06, "epoch": 6.138959621680611, "percentage": 87.69, "elapsed_time": "8:19:33", "remaining_time": "1:10:08"}
|
| 1703 |
+
{"current_steps": 8445, "total_steps": 9625, "loss": 0.1065, "lr": 1.80681225783917e-06, "epoch": 6.142597308112041, "percentage": 87.74, "elapsed_time": "8:21:29", "remaining_time": "1:10:04"}
|
| 1704 |
+
{"current_steps": 8450, "total_steps": 9625, "loss": 0.0614, "lr": 1.7917778039712798e-06, "epoch": 6.14623499454347, "percentage": 87.79, "elapsed_time": "8:23:02", "remaining_time": "1:09:57"}
|
| 1705 |
+
{"current_steps": 8455, "total_steps": 9625, "loss": 0.0664, "lr": 1.776803228590742e-06, "epoch": 6.1498726809749, "percentage": 87.84, "elapsed_time": "8:24:35", "remaining_time": "1:09:49"}
|
| 1706 |
+
{"current_steps": 8460, "total_steps": 9625, "loss": 0.0639, "lr": 1.7618885809420706e-06, "epoch": 6.153510367406329, "percentage": 87.9, "elapsed_time": "8:26:08", "remaining_time": "1:09:42"}
|
| 1707 |
+
{"current_steps": 8465, "total_steps": 9625, "loss": 0.1094, "lr": 1.7470339100726997e-06, "epoch": 6.157148053837759, "percentage": 87.95, "elapsed_time": "8:28:30", "remaining_time": "1:09:41"}
|
| 1708 |
+
{"current_steps": 8470, "total_steps": 9625, "loss": 0.0728, "lr": 1.7322392648328179e-06, "epoch": 6.160785740269189, "percentage": 88.0, "elapsed_time": "8:30:07", "remaining_time": "1:09:33"}
|
| 1709 |
+
{"current_steps": 8475, "total_steps": 9625, "loss": 0.1028, "lr": 1.7175046938752316e-06, "epoch": 6.164423426700618, "percentage": 88.05, "elapsed_time": "8:31:53", "remaining_time": "1:09:27"}
|
| 1710 |
+
{"current_steps": 8480, "total_steps": 9625, "loss": 0.0722, "lr": 1.7028302456551782e-06, "epoch": 6.168061113132048, "percentage": 88.1, "elapsed_time": "8:33:27", "remaining_time": "1:09:19"}
|
| 1711 |
+
{"current_steps": 8485, "total_steps": 9625, "loss": 0.0965, "lr": 1.6882159684301846e-06, "epoch": 6.171698799563478, "percentage": 88.16, "elapsed_time": "8:35:22", "remaining_time": "1:09:14"}
|
| 1712 |
+
{"current_steps": 8490, "total_steps": 9625, "loss": 0.1015, "lr": 1.6736619102599073e-06, "epoch": 6.175336485994907, "percentage": 88.21, "elapsed_time": "8:37:02", "remaining_time": "1:09:07"}
|
| 1713 |
+
{"current_steps": 8495, "total_steps": 9625, "loss": 0.1001, "lr": 1.6591681190059582e-06, "epoch": 6.1789741724263365, "percentage": 88.26, "elapsed_time": "8:38:40", "remaining_time": "1:08:59"}
|
| 1714 |
+
{"current_steps": 8500, "total_steps": 9625, "loss": 0.0724, "lr": 1.644734642331769e-06, "epoch": 6.182611858857767, "percentage": 88.31, "elapsed_time": "8:40:11", "remaining_time": "1:08:50"}
|
| 1715 |
+
{"current_steps": 8505, "total_steps": 9625, "loss": 0.0791, "lr": 1.6303615277024222e-06, "epoch": 6.186249545289196, "percentage": 88.36, "elapsed_time": "8:41:56", "remaining_time": "1:08:44"}
|
| 1716 |
+
{"current_steps": 8510, "total_steps": 9625, "loss": 0.0784, "lr": 1.6160488223844972e-06, "epoch": 6.1898872317206255, "percentage": 88.42, "elapsed_time": "8:44:03", "remaining_time": "1:08:39"}
|
| 1717 |
+
{"current_steps": 8515, "total_steps": 9625, "loss": 0.0665, "lr": 1.6017965734459129e-06, "epoch": 6.193524918152056, "percentage": 88.47, "elapsed_time": "8:45:50", "remaining_time": "1:08:32"}
|
| 1718 |
+
{"current_steps": 8520, "total_steps": 9625, "loss": 0.0629, "lr": 1.5876048277557688e-06, "epoch": 6.197162604583485, "percentage": 88.52, "elapsed_time": "8:47:44", "remaining_time": "1:08:26"}
|
| 1719 |
+
{"current_steps": 8525, "total_steps": 9625, "loss": 0.0735, "lr": 1.5734736319842125e-06, "epoch": 6.2008002910149145, "percentage": 88.57, "elapsed_time": "8:49:24", "remaining_time": "1:08:18"}
|
| 1720 |
+
{"current_steps": 8530, "total_steps": 9625, "loss": 0.0868, "lr": 1.5594030326022602e-06, "epoch": 6.204437977446344, "percentage": 88.62, "elapsed_time": "8:51:46", "remaining_time": "1:08:15"}
|
| 1721 |
+
{"current_steps": 8535, "total_steps": 9625, "loss": 0.0833, "lr": 1.5453930758816605e-06, "epoch": 6.208075663877774, "percentage": 88.68, "elapsed_time": "8:53:20", "remaining_time": "1:08:06"}
|
| 1722 |
+
{"current_steps": 8540, "total_steps": 9625, "loss": 0.0774, "lr": 1.5314438078947258e-06, "epoch": 6.2117133503092035, "percentage": 88.73, "elapsed_time": "8:54:52", "remaining_time": "1:07:57"}
|
| 1723 |
+
{"current_steps": 8545, "total_steps": 9625, "loss": 0.0681, "lr": 1.5175552745141952e-06, "epoch": 6.215351036740633, "percentage": 88.78, "elapsed_time": "8:56:31", "remaining_time": "1:07:48"}
|
| 1724 |
+
{"current_steps": 8550, "total_steps": 9625, "loss": 0.0787, "lr": 1.503727521413092e-06, "epoch": 6.218988723172062, "percentage": 88.83, "elapsed_time": "8:58:18", "remaining_time": "1:07:40"}
|
| 1725 |
+
{"current_steps": 8555, "total_steps": 9625, "loss": 0.0651, "lr": 1.4899605940645413e-06, "epoch": 6.2226264096034924, "percentage": 88.88, "elapsed_time": "8:59:50", "remaining_time": "1:07:31"}
|
| 1726 |
+
{"current_steps": 8560, "total_steps": 9625, "loss": 0.0742, "lr": 1.476254537741657e-06, "epoch": 6.226264096034922, "percentage": 88.94, "elapsed_time": "9:01:29", "remaining_time": "1:07:22"}
|
| 1727 |
+
{"current_steps": 8565, "total_steps": 9625, "loss": 0.0723, "lr": 1.4626093975173627e-06, "epoch": 6.229901782466351, "percentage": 88.99, "elapsed_time": "9:03:04", "remaining_time": "1:07:12"}
|
| 1728 |
+
{"current_steps": 8570, "total_steps": 9625, "loss": 0.0742, "lr": 1.449025218264266e-06, "epoch": 6.233539468897781, "percentage": 89.04, "elapsed_time": "9:04:40", "remaining_time": "1:07:03"}
|
| 1729 |
+
{"current_steps": 8575, "total_steps": 9625, "loss": 0.0897, "lr": 1.435502044654502e-06, "epoch": 6.237177155329211, "percentage": 89.09, "elapsed_time": "9:06:31", "remaining_time": "1:06:55"}
|
| 1730 |
+
{"current_steps": 8580, "total_steps": 9625, "loss": 0.071, "lr": 1.4220399211595748e-06, "epoch": 6.24081484176064, "percentage": 89.14, "elapsed_time": "9:08:00", "remaining_time": "1:06:44"}
|
| 1731 |
+
{"current_steps": 8585, "total_steps": 9625, "loss": 0.0816, "lr": 1.4086388920502403e-06, "epoch": 6.2444525281920695, "percentage": 89.19, "elapsed_time": "9:09:31", "remaining_time": "1:06:34"}
|
| 1732 |
+
{"current_steps": 8590, "total_steps": 9625, "loss": 0.0965, "lr": 1.3952990013963264e-06, "epoch": 6.2480902146235, "percentage": 89.25, "elapsed_time": "9:11:30", "remaining_time": "1:06:27"}
|
| 1733 |
+
{"current_steps": 8595, "total_steps": 9625, "loss": 0.0738, "lr": 1.3820202930666148e-06, "epoch": 6.251727901054929, "percentage": 89.3, "elapsed_time": "9:13:06", "remaining_time": "1:06:17"}
|
| 1734 |
+
{"current_steps": 8600, "total_steps": 9625, "loss": 0.0642, "lr": 1.3688028107286888e-06, "epoch": 6.2553655874863585, "percentage": 89.35, "elapsed_time": "9:14:40", "remaining_time": "1:06:06"}
|