Training in progress, step 1000
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:d93ca8ddb4aca0a322617c51005d351a3e8a53812d073a1b7c7c51adabace858
|
| 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 sha256:70b0c221a0ffffe125308bdbc12ff5cdaeb3d0571930cb4eda84b9e7b1979503
|
| 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:e67285e10ee252845d824ef46ff3a9d43dce1bd2e0b1a5dbf06f64b465f2e316
|
| 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 sha256:421bba55e79df5d397bc383e68d31c2550a5c4f8ce59a869fc74d38607e30215
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -161,3 +161,40 @@
|
|
| 161 |
{"current_steps": 805, "total_steps": 1652, "loss": 0.1705, "lr": 2.440329438897122e-05, "epoch": 3.4118895966029723, "percentage": 48.73, "elapsed_time": "8:31:00", "remaining_time": "8:57:40"}
|
| 162 |
{"current_steps": 810, "total_steps": 1652, "loss": 0.1584, "lr": 2.419682702289432e-05, "epoch": 3.43312101910828, "percentage": 49.03, "elapsed_time": "8:34:10", "remaining_time": "8:54:29"}
|
| 163 |
{"current_steps": 815, "total_steps": 1652, "loss": 0.1632, "lr": 2.3989890714785505e-05, "epoch": 3.454352441613588, "percentage": 49.33, "elapsed_time": "8:37:19", "remaining_time": "8:51:17"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 161 |
{"current_steps": 805, "total_steps": 1652, "loss": 0.1705, "lr": 2.440329438897122e-05, "epoch": 3.4118895966029723, "percentage": 48.73, "elapsed_time": "8:31:00", "remaining_time": "8:57:40"}
|
| 162 |
{"current_steps": 810, "total_steps": 1652, "loss": 0.1584, "lr": 2.419682702289432e-05, "epoch": 3.43312101910828, "percentage": 49.03, "elapsed_time": "8:34:10", "remaining_time": "8:54:29"}
|
| 163 |
{"current_steps": 815, "total_steps": 1652, "loss": 0.1632, "lr": 2.3989890714785505e-05, "epoch": 3.454352441613588, "percentage": 49.33, "elapsed_time": "8:37:19", "remaining_time": "8:51:17"}
|
| 164 |
+
{"current_steps": 820, "total_steps": 1652, "loss": 0.1693, "lr": 2.3782508587144774e-05, "epoch": 3.475583864118896, "percentage": 49.64, "elapsed_time": "8:40:28", "remaining_time": "8:48:05"}
|
| 165 |
+
{"current_steps": 825, "total_steps": 1652, "loss": 0.1746, "lr": 2.3574703812286766e-05, "epoch": 3.4968152866242037, "percentage": 49.94, "elapsed_time": "8:43:37", "remaining_time": "8:44:53"}
|
| 166 |
+
{"current_steps": 830, "total_steps": 1652, "loss": 0.1736, "lr": 2.3366499609751593e-05, "epoch": 3.5180467091295116, "percentage": 50.24, "elapsed_time": "8:46:45", "remaining_time": "8:41:41"}
|
| 167 |
+
{"current_steps": 835, "total_steps": 1652, "loss": 0.1789, "lr": 2.3157919243710318e-05, "epoch": 3.5392781316348194, "percentage": 50.54, "elapsed_time": "8:49:54", "remaining_time": "8:38:29"}
|
| 168 |
+
{"current_steps": 840, "total_steps": 1652, "loss": 0.1955, "lr": 2.2948986020365493e-05, "epoch": 3.5605095541401273, "percentage": 50.85, "elapsed_time": "8:53:03", "remaining_time": "8:35:17"}
|
| 169 |
+
{"current_steps": 845, "total_steps": 1652, "loss": 0.2052, "lr": 2.273972328534698e-05, "epoch": 3.581740976645435, "percentage": 51.15, "elapsed_time": "8:56:12", "remaining_time": "8:32:05"}
|
| 170 |
+
{"current_steps": 850, "total_steps": 1652, "loss": 0.1627, "lr": 2.2530154421103386e-05, "epoch": 3.602972399150743, "percentage": 51.45, "elapsed_time": "8:59:21", "remaining_time": "8:28:54"}
|
| 171 |
+
{"current_steps": 855, "total_steps": 1652, "loss": 0.2028, "lr": 2.2320302844289366e-05, "epoch": 3.624203821656051, "percentage": 51.76, "elapsed_time": "9:02:29", "remaining_time": "8:25:41"}
|
| 172 |
+
{"current_steps": 860, "total_steps": 1652, "loss": 0.1643, "lr": 2.21101920031491e-05, "epoch": 3.6454352441613587, "percentage": 52.06, "elapsed_time": "9:05:38", "remaining_time": "8:22:29"}
|
| 173 |
+
{"current_steps": 865, "total_steps": 1652, "loss": 0.1724, "lr": 2.1899845374896264e-05, "epoch": 3.6666666666666665, "percentage": 52.36, "elapsed_time": "9:08:46", "remaining_time": "8:19:17"}
|
| 174 |
+
{"current_steps": 870, "total_steps": 1652, "loss": 0.1844, "lr": 2.168928646309074e-05, "epoch": 3.6878980891719744, "percentage": 52.66, "elapsed_time": "9:11:55", "remaining_time": "8:16:05"}
|
| 175 |
+
{"current_steps": 875, "total_steps": 1652, "loss": 0.2002, "lr": 2.14785387950124e-05, "epoch": 3.709129511677282, "percentage": 52.97, "elapsed_time": "9:15:03", "remaining_time": "8:12:53"}
|
| 176 |
+
{"current_steps": 880, "total_steps": 1652, "loss": 0.1949, "lr": 2.1267625919032233e-05, "epoch": 3.73036093418259, "percentage": 53.27, "elapsed_time": "9:18:11", "remaining_time": "8:09:40"}
|
| 177 |
+
{"current_steps": 885, "total_steps": 1652, "loss": 0.1882, "lr": 2.10565714019811e-05, "epoch": 3.7515923566878984, "percentage": 53.57, "elapsed_time": "9:21:19", "remaining_time": "8:06:29"}
|
| 178 |
+
{"current_steps": 890, "total_steps": 1652, "loss": 0.1844, "lr": 2.0845398826516457e-05, "epoch": 3.7728237791932058, "percentage": 53.87, "elapsed_time": "9:24:29", "remaining_time": "8:03:18"}
|
| 179 |
+
{"current_steps": 895, "total_steps": 1652, "loss": 0.187, "lr": 2.0634131788487278e-05, "epoch": 3.794055201698514, "percentage": 54.18, "elapsed_time": "9:27:37", "remaining_time": "8:00:06"}
|
| 180 |
+
{"current_steps": 900, "total_steps": 1652, "loss": 0.1743, "lr": 2.0422793894297533e-05, "epoch": 3.8152866242038215, "percentage": 54.48, "elapsed_time": "9:30:46", "remaining_time": "7:56:54"}
|
| 181 |
+
{"current_steps": 905, "total_steps": 1652, "loss": 0.1832, "lr": 2.0211408758268468e-05, "epoch": 3.8365180467091298, "percentage": 54.78, "elapsed_time": "9:33:54", "remaining_time": "7:53:42"}
|
| 182 |
+
{"current_steps": 910, "total_steps": 1652, "loss": 0.1815, "lr": 2e-05, "epoch": 3.857749469214437, "percentage": 55.08, "elapsed_time": "9:37:02", "remaining_time": "7:50:30"}
|
| 183 |
+
{"current_steps": 915, "total_steps": 1652, "loss": 0.1781, "lr": 1.9788591241731535e-05, "epoch": 3.8789808917197455, "percentage": 55.39, "elapsed_time": "9:40:10", "remaining_time": "7:47:18"}
|
| 184 |
+
{"current_steps": 920, "total_steps": 1652, "loss": 0.1811, "lr": 1.9577206105702474e-05, "epoch": 3.900212314225053, "percentage": 55.69, "elapsed_time": "9:43:19", "remaining_time": "7:44:07"}
|
| 185 |
+
{"current_steps": 925, "total_steps": 1652, "loss": 0.1958, "lr": 1.9365868211512725e-05, "epoch": 3.921443736730361, "percentage": 55.99, "elapsed_time": "9:46:27", "remaining_time": "7:40:55"}
|
| 186 |
+
{"current_steps": 930, "total_steps": 1652, "loss": 0.1675, "lr": 1.915460117348355e-05, "epoch": 3.9426751592356686, "percentage": 56.3, "elapsed_time": "9:49:36", "remaining_time": "7:37:44"}
|
| 187 |
+
{"current_steps": 935, "total_steps": 1652, "loss": 0.1729, "lr": 1.8943428598018904e-05, "epoch": 3.963906581740977, "percentage": 56.6, "elapsed_time": "9:52:45", "remaining_time": "7:34:33"}
|
| 188 |
+
{"current_steps": 940, "total_steps": 1652, "loss": 0.1664, "lr": 1.8732374080967774e-05, "epoch": 3.9851380042462843, "percentage": 56.9, "elapsed_time": "9:55:54", "remaining_time": "7:31:21"}
|
| 189 |
+
{"current_steps": 945, "total_steps": 1652, "loss": 0.1569, "lr": 1.8521461204987606e-05, "epoch": 4.004246284501062, "percentage": 57.2, "elapsed_time": "9:58:44", "remaining_time": "7:27:57"}
|
| 190 |
+
{"current_steps": 950, "total_steps": 1652, "loss": 0.1668, "lr": 1.8310713536909265e-05, "epoch": 4.025477707006369, "percentage": 57.51, "elapsed_time": "10:01:52", "remaining_time": "7:24:45"}
|
| 191 |
+
{"current_steps": 955, "total_steps": 1652, "loss": 0.1697, "lr": 1.810015462510374e-05, "epoch": 4.046709129511678, "percentage": 57.81, "elapsed_time": "10:05:01", "remaining_time": "7:21:34"}
|
| 192 |
+
{"current_steps": 960, "total_steps": 1652, "loss": 0.2036, "lr": 1.7889807996850906e-05, "epoch": 4.067940552016985, "percentage": 58.11, "elapsed_time": "10:08:10", "remaining_time": "7:18:23"}
|
| 193 |
+
{"current_steps": 965, "total_steps": 1652, "loss": 0.1686, "lr": 1.767969715571064e-05, "epoch": 4.089171974522293, "percentage": 58.41, "elapsed_time": "10:11:18", "remaining_time": "7:15:12"}
|
| 194 |
+
{"current_steps": 970, "total_steps": 1652, "loss": 0.1837, "lr": 1.746984557889662e-05, "epoch": 4.110403397027601, "percentage": 58.72, "elapsed_time": "10:14:26", "remaining_time": "7:12:00"}
|
| 195 |
+
{"current_steps": 975, "total_steps": 1652, "loss": 0.1704, "lr": 1.7260276714653023e-05, "epoch": 4.131634819532909, "percentage": 59.02, "elapsed_time": "10:17:35", "remaining_time": "7:08:49"}
|
| 196 |
+
{"current_steps": 980, "total_steps": 1652, "loss": 0.1607, "lr": 1.7051013979634514e-05, "epoch": 4.1528662420382165, "percentage": 59.32, "elapsed_time": "10:20:44", "remaining_time": "7:05:39"}
|
| 197 |
+
{"current_steps": 985, "total_steps": 1652, "loss": 0.1826, "lr": 1.684208075628969e-05, "epoch": 4.174097664543525, "percentage": 59.62, "elapsed_time": "10:23:52", "remaining_time": "7:02:27"}
|
| 198 |
+
{"current_steps": 990, "total_steps": 1652, "loss": 0.1573, "lr": 1.6633500390248414e-05, "epoch": 4.195329087048832, "percentage": 59.93, "elapsed_time": "10:27:00", "remaining_time": "6:59:16"}
|
| 199 |
+
{"current_steps": 995, "total_steps": 1652, "loss": 0.1518, "lr": 1.642529618771324e-05, "epoch": 4.2165605095541405, "percentage": 60.23, "elapsed_time": "10:30:09", "remaining_time": "6:56:05"}
|
| 200 |
+
{"current_steps": 1000, "total_steps": 1652, "loss": 0.1813, "lr": 1.6217491412855233e-05, "epoch": 4.237791932059448, "percentage": 60.53, "elapsed_time": "10:33:17", "remaining_time": "6:52:54"}
|