Training in progress, step 4800
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:fab000089051e4ffa40af8197890cca19f2c950621c26b4ded2c8fddffec104e
|
| 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 sha256:5f1535dba425e038a893bb52445edbf7cee5a92ebcea160690cb0b1ed500053b
|
| 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 sha256:8ddadccd39bfc3eb0924270514a04fc33497a20b116bd99486c59811fd0c7070
|
| 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 sha256:5841577ed2dcb4b2ffa655bb5f450c3c90012fcd90a141608034ce26685f17c5
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -925,3 +925,40 @@
|
|
| 925 |
{"current_steps": 4625, "total_steps": 9128, "loss": 0.156, "lr": 2.302099509795778e-05, "epoch": 3.5469888761028, "percentage": 50.67, "elapsed_time": "1 day, 4:43:07", "remaining_time": "1 day, 3:57:40"}
|
| 926 |
{"current_steps": 4630, "total_steps": 9128, "loss": 0.1658, "lr": 2.2983186232268966e-05, "epoch": 3.5508247027234368, "percentage": 50.72, "elapsed_time": "1 day, 4:44:25", "remaining_time": "1 day, 3:55:15"}
|
| 927 |
{"current_steps": 4635, "total_steps": 9128, "loss": 0.267, "lr": 2.2945366459591735e-05, "epoch": 3.5546605293440736, "percentage": 50.78, "elapsed_time": "1 day, 4:46:46", "remaining_time": "1 day, 3:53:51"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 925 |
{"current_steps": 4625, "total_steps": 9128, "loss": 0.156, "lr": 2.302099509795778e-05, "epoch": 3.5469888761028, "percentage": 50.67, "elapsed_time": "1 day, 4:43:07", "remaining_time": "1 day, 3:57:40"}
|
| 926 |
{"current_steps": 4630, "total_steps": 9128, "loss": 0.1658, "lr": 2.2983186232268966e-05, "epoch": 3.5508247027234368, "percentage": 50.72, "elapsed_time": "1 day, 4:44:25", "remaining_time": "1 day, 3:55:15"}
|
| 927 |
{"current_steps": 4635, "total_steps": 9128, "loss": 0.267, "lr": 2.2945366459591735e-05, "epoch": 3.5546605293440736, "percentage": 50.78, "elapsed_time": "1 day, 4:46:46", "remaining_time": "1 day, 3:53:51"}
|
| 928 |
+
{"current_steps": 4640, "total_steps": 9128, "loss": 0.2461, "lr": 2.290753591820099e-05, "epoch": 3.5584963559647105, "percentage": 50.83, "elapsed_time": "1 day, 4:48:56", "remaining_time": "1 day, 3:52:17"}
|
| 929 |
+
{"current_steps": 4645, "total_steps": 9128, "loss": 0.2386, "lr": 2.2869694746411016e-05, "epoch": 3.5623321825853473, "percentage": 50.89, "elapsed_time": "1 day, 4:51:28", "remaining_time": "1 day, 3:51:04"}
|
| 930 |
+
{"current_steps": 4650, "total_steps": 9128, "loss": 0.2386, "lr": 2.2831843082574984e-05, "epoch": 3.5661680092059838, "percentage": 50.94, "elapsed_time": "1 day, 4:53:47", "remaining_time": "1 day, 3:49:39"}
|
| 931 |
+
{"current_steps": 4655, "total_steps": 9128, "loss": 0.2492, "lr": 2.2793981065084396e-05, "epoch": 3.5700038358266206, "percentage": 51.0, "elapsed_time": "1 day, 4:56:02", "remaining_time": "1 day, 3:48:09"}
|
| 932 |
+
{"current_steps": 4660, "total_steps": 9128, "loss": 0.2439, "lr": 2.2756108832368614e-05, "epoch": 3.5738396624472575, "percentage": 51.05, "elapsed_time": "1 day, 4:58:18", "remaining_time": "1 day, 3:46:40"}
|
| 933 |
+
{"current_steps": 4665, "total_steps": 9128, "loss": 0.2376, "lr": 2.2718226522894367e-05, "epoch": 3.577675489067894, "percentage": 51.11, "elapsed_time": "1 day, 5:00:39", "remaining_time": "1 day, 3:45:17"}
|
| 934 |
+
{"current_steps": 4670, "total_steps": 9128, "loss": 0.2416, "lr": 2.268033427516521e-05, "epoch": 3.5815113156885308, "percentage": 51.16, "elapsed_time": "1 day, 5:02:54", "remaining_time": "1 day, 3:43:47"}
|
| 935 |
+
{"current_steps": 4675, "total_steps": 9128, "loss": 0.2493, "lr": 2.264243222772104e-05, "epoch": 3.5853471423091676, "percentage": 51.22, "elapsed_time": "1 day, 5:05:18", "remaining_time": "1 day, 3:42:25"}
|
| 936 |
+
{"current_steps": 4680, "total_steps": 9128, "loss": 0.2428, "lr": 2.260452051913757e-05, "epoch": 3.5891829689298045, "percentage": 51.27, "elapsed_time": "1 day, 5:07:32", "remaining_time": "1 day, 3:40:54"}
|
| 937 |
+
{"current_steps": 4685, "total_steps": 9128, "loss": 0.2399, "lr": 2.256659928802586e-05, "epoch": 3.5930187955504413, "percentage": 51.33, "elapsed_time": "1 day, 5:10:01", "remaining_time": "1 day, 3:39:37"}
|
| 938 |
+
{"current_steps": 4690, "total_steps": 9128, "loss": 0.2362, "lr": 2.252866867303177e-05, "epoch": 3.5968546221710778, "percentage": 51.38, "elapsed_time": "1 day, 5:12:21", "remaining_time": "1 day, 3:38:12"}
|
| 939 |
+
{"current_steps": 4695, "total_steps": 9128, "loss": 0.2448, "lr": 2.249072881283547e-05, "epoch": 3.6006904487917146, "percentage": 51.44, "elapsed_time": "1 day, 5:14:32", "remaining_time": "1 day, 3:36:37"}
|
| 940 |
+
{"current_steps": 4700, "total_steps": 9128, "loss": 0.2377, "lr": 2.2452779846150934e-05, "epoch": 3.6045262754123515, "percentage": 51.49, "elapsed_time": "1 day, 5:16:22", "remaining_time": "1 day, 3:34:43"}
|
| 941 |
+
{"current_steps": 4705, "total_steps": 9128, "loss": 0.2476, "lr": 2.2414821911725433e-05, "epoch": 3.608362102032988, "percentage": 51.54, "elapsed_time": "1 day, 5:18:02", "remaining_time": "1 day, 3:32:40"}
|
| 942 |
+
{"current_steps": 4710, "total_steps": 9128, "loss": 0.2288, "lr": 2.2376855148339013e-05, "epoch": 3.6121979286536248, "percentage": 51.6, "elapsed_time": "1 day, 5:19:43", "remaining_time": "1 day, 3:30:37"}
|
| 943 |
+
{"current_steps": 4715, "total_steps": 9128, "loss": 0.2371, "lr": 2.233887969480402e-05, "epoch": 3.6160337552742616, "percentage": 51.65, "elapsed_time": "1 day, 5:21:23", "remaining_time": "1 day, 3:28:34"}
|
| 944 |
+
{"current_steps": 4720, "total_steps": 9128, "loss": 0.2492, "lr": 2.230089568996456e-05, "epoch": 3.6198695818948985, "percentage": 51.71, "elapsed_time": "1 day, 5:23:02", "remaining_time": "1 day, 3:26:29"}
|
| 945 |
+
{"current_steps": 4725, "total_steps": 9128, "loss": 0.2453, "lr": 2.2262903272695998e-05, "epoch": 3.6237054085155354, "percentage": 51.76, "elapsed_time": "1 day, 5:24:40", "remaining_time": "1 day, 3:24:24"}
|
| 946 |
+
{"current_steps": 4730, "total_steps": 9128, "loss": 0.241, "lr": 2.2224902581904476e-05, "epoch": 3.6275412351361718, "percentage": 51.82, "elapsed_time": "1 day, 5:26:28", "remaining_time": "1 day, 3:22:29"}
|
| 947 |
+
{"current_steps": 4735, "total_steps": 9128, "loss": 0.2258, "lr": 2.2186893756526366e-05, "epoch": 3.6313770617568086, "percentage": 51.87, "elapsed_time": "1 day, 5:28:05", "remaining_time": "1 day, 3:20:22"}
|
| 948 |
+
{"current_steps": 4740, "total_steps": 9128, "loss": 0.2353, "lr": 2.2148876935527794e-05, "epoch": 3.6352128883774455, "percentage": 51.93, "elapsed_time": "1 day, 5:29:49", "remaining_time": "1 day, 3:18:24"}
|
| 949 |
+
{"current_steps": 4745, "total_steps": 9128, "loss": 0.2173, "lr": 2.2110852257904108e-05, "epoch": 3.639048714998082, "percentage": 51.98, "elapsed_time": "1 day, 5:31:26", "remaining_time": "1 day, 3:16:18"}
|
| 950 |
+
{"current_steps": 4750, "total_steps": 9128, "loss": 0.2393, "lr": 2.2072819862679396e-05, "epoch": 3.6428845416187188, "percentage": 52.04, "elapsed_time": "1 day, 5:33:06", "remaining_time": "1 day, 3:14:14"}
|
| 951 |
+
{"current_steps": 4755, "total_steps": 9128, "loss": 0.2319, "lr": 2.2034779888905943e-05, "epoch": 3.6467203682393556, "percentage": 52.09, "elapsed_time": "1 day, 5:34:43", "remaining_time": "1 day, 3:12:09"}
|
| 952 |
+
{"current_steps": 4760, "total_steps": 9128, "loss": 0.233, "lr": 2.199673247566376e-05, "epoch": 3.650556194859992, "percentage": 52.15, "elapsed_time": "1 day, 5:36:24", "remaining_time": "1 day, 3:10:07"}
|
| 953 |
+
{"current_steps": 4765, "total_steps": 9128, "loss": 0.2358, "lr": 2.1958677762060043e-05, "epoch": 3.654392021480629, "percentage": 52.2, "elapsed_time": "1 day, 5:38:03", "remaining_time": "1 day, 3:08:03"}
|
| 954 |
+
{"current_steps": 4770, "total_steps": 9128, "loss": 0.2231, "lr": 2.1920615887228705e-05, "epoch": 3.6582278481012658, "percentage": 52.26, "elapsed_time": "1 day, 5:39:44", "remaining_time": "1 day, 3:06:01"}
|
| 955 |
+
{"current_steps": 4775, "total_steps": 9128, "loss": 0.2388, "lr": 2.1882546990329806e-05, "epoch": 3.6620636747219026, "percentage": 52.31, "elapsed_time": "1 day, 5:41:25", "remaining_time": "1 day, 3:03:58"}
|
| 956 |
+
{"current_steps": 4780, "total_steps": 9128, "loss": 0.2295, "lr": 2.1844471210549102e-05, "epoch": 3.6658995013425395, "percentage": 52.37, "elapsed_time": "1 day, 5:43:05", "remaining_time": "1 day, 3:01:56"}
|
| 957 |
+
{"current_steps": 4785, "total_steps": 9128, "loss": 0.2277, "lr": 2.1806388687097517e-05, "epoch": 3.669735327963176, "percentage": 52.42, "elapsed_time": "1 day, 5:44:46", "remaining_time": "1 day, 2:59:54"}
|
| 958 |
+
{"current_steps": 4790, "total_steps": 9128, "loss": 0.2279, "lr": 2.1768299559210617e-05, "epoch": 3.673571154583813, "percentage": 52.48, "elapsed_time": "1 day, 5:46:24", "remaining_time": "1 day, 2:57:50"}
|
| 959 |
+
{"current_steps": 4795, "total_steps": 9128, "loss": 0.2318, "lr": 2.1730203966148123e-05, "epoch": 3.6774069812044496, "percentage": 52.53, "elapsed_time": "1 day, 5:48:10", "remaining_time": "1 day, 2:55:53"}
|
| 960 |
+
{"current_steps": 4800, "total_steps": 9128, "loss": 0.2231, "lr": 2.1692102047193383e-05, "epoch": 3.681242807825086, "percentage": 52.59, "elapsed_time": "1 day, 5:49:45", "remaining_time": "1 day, 2:53:46"}
|
| 961 |
+
{"current_steps": 4805, "total_steps": 9128, "loss": 0.2341, "lr": 2.1653993941652898e-05, "epoch": 3.685078634445723, "percentage": 52.64, "elapsed_time": "1 day, 5:52:45", "remaining_time": "1 day, 2:52:55"}
|
| 962 |
+
{"current_steps": 4810, "total_steps": 9128, "loss": 0.2391, "lr": 2.1615879788855763e-05, "epoch": 3.68891446106636, "percentage": 52.7, "elapsed_time": "1 day, 5:54:20", "remaining_time": "1 day, 2:50:48"}
|
| 963 |
+
{"current_steps": 4815, "total_steps": 9128, "loss": 0.2257, "lr": 2.157775972815319e-05, "epoch": 3.6927502876869966, "percentage": 52.75, "elapsed_time": "1 day, 5:56:07", "remaining_time": "1 day, 2:48:52"}
|
| 964 |
+
{"current_steps": 4820, "total_steps": 9128, "loss": 0.2274, "lr": 2.1539633898918004e-05, "epoch": 3.6965861143076335, "percentage": 52.8, "elapsed_time": "1 day, 5:57:45", "remaining_time": "1 day, 2:46:47"}
|