Training in progress, step 1400
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 sha256:2d253181c37bf2f9c403229890e52a8e06885829d38eee0fe85fb2f42969b232
|
| 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 sha256:43e9064a7b64df5d5d1d3d76744db6e5ce885697bbdaee82feab961e3f630752
|
| 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 sha256:54128798e4f3a663324713a3fcbb65d4a0e4d4f5461a1bb1203f759ddedd63dd
|
| 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 sha256:314452e5b8fc6222c6513b9009a09d61055afadc7b12b37a0a04cb86bea683a7
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -238,3 +238,43 @@
|
|
| 238 |
{"current_steps": 1190, "total_steps": 1652, "loss": 0.1813, "lr": 8.840301965743405e-06, "epoch": 5.042462845010616, "percentage": 72.03, "elapsed_time": "12:33:47", "remaining_time": "4:52:38"}
|
| 239 |
{"current_steps": 1195, "total_steps": 1652, "loss": 0.1678, "lr": 8.665487652126785e-06, "epoch": 5.063694267515924, "percentage": 72.34, "elapsed_time": "12:36:56", "remaining_time": "4:49:28"}
|
| 240 |
{"current_steps": 1200, "total_steps": 1652, "loss": 0.1691, "lr": 8.491939826078552e-06, "epoch": 5.084925690021231, "percentage": 72.64, "elapsed_time": "12:40:05", "remaining_time": "4:46:18"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 238 |
{"current_steps": 1190, "total_steps": 1652, "loss": 0.1813, "lr": 8.840301965743405e-06, "epoch": 5.042462845010616, "percentage": 72.03, "elapsed_time": "12:33:47", "remaining_time": "4:52:38"}
|
| 239 |
{"current_steps": 1195, "total_steps": 1652, "loss": 0.1678, "lr": 8.665487652126785e-06, "epoch": 5.063694267515924, "percentage": 72.34, "elapsed_time": "12:36:56", "remaining_time": "4:49:28"}
|
| 240 |
{"current_steps": 1200, "total_steps": 1652, "loss": 0.1691, "lr": 8.491939826078552e-06, "epoch": 5.084925690021231, "percentage": 72.64, "elapsed_time": "12:40:05", "remaining_time": "4:46:18"}
|
| 241 |
+
{"current_steps": 1205, "total_steps": 1652, "loss": 0.1662, "lr": 8.319677879360566e-06, "epoch": 5.10615711252654, "percentage": 72.94, "elapsed_time": "12:44:22", "remaining_time": "4:43:32"}
|
| 242 |
+
{"current_steps": 1210, "total_steps": 1652, "loss": 0.1576, "lr": 8.148721060054026e-06, "epoch": 5.127388535031847, "percentage": 73.24, "elapsed_time": "12:47:31", "remaining_time": "4:40:22"}
|
| 243 |
+
{"current_steps": 1215, "total_steps": 1652, "loss": 0.1633, "lr": 7.979088470408743e-06, "epoch": 5.148619957537155, "percentage": 73.55, "elapsed_time": "12:50:39", "remaining_time": "4:37:11"}
|
| 244 |
+
{"current_steps": 1220, "total_steps": 1652, "loss": 0.1707, "lr": 7.81079906470872e-06, "epoch": 5.169851380042463, "percentage": 73.85, "elapsed_time": "12:53:48", "remaining_time": "4:34:00"}
|
| 245 |
+
{"current_steps": 1225, "total_steps": 1652, "loss": 0.1675, "lr": 7.643871647154212e-06, "epoch": 5.191082802547771, "percentage": 74.15, "elapsed_time": "12:56:57", "remaining_time": "4:30:49"}
|
| 246 |
+
{"current_steps": 1230, "total_steps": 1652, "loss": 0.1598, "lr": 7.478324869760665e-06, "epoch": 5.2123142250530785, "percentage": 74.46, "elapsed_time": "13:00:06", "remaining_time": "4:27:38"}
|
| 247 |
+
{"current_steps": 1235, "total_steps": 1652, "loss": 0.1498, "lr": 7.314177230274522e-06, "epoch": 5.233545647558387, "percentage": 74.76, "elapsed_time": "13:03:14", "remaining_time": "4:24:27"}
|
| 248 |
+
{"current_steps": 1240, "total_steps": 1652, "loss": 0.1557, "lr": 7.151447070106372e-06, "epoch": 5.254777070063694, "percentage": 75.06, "elapsed_time": "13:06:23", "remaining_time": "4:21:17"}
|
| 249 |
+
{"current_steps": 1245, "total_steps": 1652, "loss": 0.1682, "lr": 6.990152572281523e-06, "epoch": 5.2760084925690025, "percentage": 75.36, "elapsed_time": "13:09:32", "remaining_time": "4:18:06"}
|
| 250 |
+
{"current_steps": 1250, "total_steps": 1652, "loss": 0.1478, "lr": 6.830311759408275e-06, "epoch": 5.29723991507431, "percentage": 75.67, "elapsed_time": "13:12:40", "remaining_time": "4:14:55"}
|
| 251 |
+
{"current_steps": 1255, "total_steps": 1652, "loss": 0.1583, "lr": 6.671942491664128e-06, "epoch": 5.318471337579618, "percentage": 75.97, "elapsed_time": "13:15:50", "remaining_time": "4:11:45"}
|
| 252 |
+
{"current_steps": 1260, "total_steps": 1652, "loss": 0.1617, "lr": 6.515062464800139e-06, "epoch": 5.339702760084926, "percentage": 76.27, "elapsed_time": "13:18:59", "remaining_time": "4:08:34"}
|
| 253 |
+
{"current_steps": 1265, "total_steps": 1652, "loss": 0.1786, "lr": 6.359689208163635e-06, "epoch": 5.360934182590234, "percentage": 76.57, "elapsed_time": "13:22:06", "remaining_time": "4:05:23"}
|
| 254 |
+
{"current_steps": 1270, "total_steps": 1652, "loss": 0.1704, "lr": 6.205840082739538e-06, "epoch": 5.382165605095541, "percentage": 76.88, "elapsed_time": "13:25:15", "remaining_time": "4:02:12"}
|
| 255 |
+
{"current_steps": 1275, "total_steps": 1652, "loss": 0.1819, "lr": 6.053532279210494e-06, "epoch": 5.40339702760085, "percentage": 77.18, "elapsed_time": "13:28:23", "remaining_time": "3:59:01"}
|
| 256 |
+
{"current_steps": 1280, "total_steps": 1652, "loss": 0.1516, "lr": 5.90278281603605e-06, "epoch": 5.424628450106157, "percentage": 77.48, "elapsed_time": "13:31:32", "remaining_time": "3:55:51"}
|
| 257 |
+
{"current_steps": 1285, "total_steps": 1652, "loss": 0.1751, "lr": 5.753608537551023e-06, "epoch": 5.445859872611465, "percentage": 77.78, "elapsed_time": "13:34:41", "remaining_time": "3:52:40"}
|
| 258 |
+
{"current_steps": 1290, "total_steps": 1652, "loss": 0.172, "lr": 5.606026112083383e-06, "epoch": 5.467091295116773, "percentage": 78.09, "elapsed_time": "13:37:51", "remaining_time": "3:49:30"}
|
| 259 |
+
{"current_steps": 1295, "total_steps": 1652, "loss": 0.1669, "lr": 5.460052030091782e-06, "epoch": 5.488322717622081, "percentage": 78.39, "elapsed_time": "13:41:01", "remaining_time": "3:46:20"}
|
| 260 |
+
{"current_steps": 1300, "total_steps": 1652, "loss": 0.159, "lr": 5.315702602322943e-06, "epoch": 5.509554140127388, "percentage": 78.69, "elapsed_time": "13:44:10", "remaining_time": "3:43:09"}
|
| 261 |
+
{"current_steps": 1305, "total_steps": 1652, "loss": 0.162, "lr": 5.1729939579891476e-06, "epoch": 5.530785562632697, "percentage": 79.0, "elapsed_time": "13:47:20", "remaining_time": "3:39:59"}
|
| 262 |
+
{"current_steps": 1310, "total_steps": 1652, "loss": 0.1647, "lr": 5.031942042966e-06, "epoch": 5.552016985138004, "percentage": 79.3, "elapsed_time": "13:50:29", "remaining_time": "3:36:48"}
|
| 263 |
+
{"current_steps": 1315, "total_steps": 1652, "loss": 0.1361, "lr": 4.892562618010684e-06, "epoch": 5.573248407643312, "percentage": 79.6, "elapsed_time": "13:53:38", "remaining_time": "3:33:38"}
|
| 264 |
+
{"current_steps": 1320, "total_steps": 1652, "loss": 0.1583, "lr": 4.754871257000888e-06, "epoch": 5.59447983014862, "percentage": 79.9, "elapsed_time": "13:56:46", "remaining_time": "3:30:27"}
|
| 265 |
+
{"current_steps": 1325, "total_steps": 1652, "loss": 0.1579, "lr": 4.618883345194627e-06, "epoch": 5.615711252653928, "percentage": 80.21, "elapsed_time": "13:59:55", "remaining_time": "3:27:17"}
|
| 266 |
+
{"current_steps": 1330, "total_steps": 1652, "loss": 0.1633, "lr": 4.484614077511153e-06, "epoch": 5.6369426751592355, "percentage": 80.51, "elapsed_time": "14:03:03", "remaining_time": "3:24:06"}
|
| 267 |
+
{"current_steps": 1335, "total_steps": 1652, "loss": 0.1719, "lr": 4.352078456833082e-06, "epoch": 5.658174097664544, "percentage": 80.81, "elapsed_time": "14:06:12", "remaining_time": "3:20:56"}
|
| 268 |
+
{"current_steps": 1340, "total_steps": 1652, "loss": 0.1775, "lr": 4.221291292330036e-06, "epoch": 5.679405520169851, "percentage": 81.11, "elapsed_time": "14:09:21", "remaining_time": "3:17:45"}
|
| 269 |
+
{"current_steps": 1345, "total_steps": 1652, "loss": 0.1676, "lr": 4.0922671978039055e-06, "epoch": 5.7006369426751595, "percentage": 81.42, "elapsed_time": "14:12:30", "remaining_time": "3:14:35"}
|
| 270 |
+
{"current_steps": 1350, "total_steps": 1652, "loss": 0.1975, "lr": 3.965020590055934e-06, "epoch": 5.721868365180467, "percentage": 81.72, "elapsed_time": "14:15:39", "remaining_time": "3:11:24"}
|
| 271 |
+
{"current_steps": 1355, "total_steps": 1652, "loss": 0.1555, "lr": 3.839565687275835e-06, "epoch": 5.743099787685775, "percentage": 82.02, "elapsed_time": "14:18:48", "remaining_time": "3:08:14"}
|
| 272 |
+
{"current_steps": 1360, "total_steps": 1652, "loss": 0.1423, "lr": 3.715916507453079e-06, "epoch": 5.764331210191083, "percentage": 82.32, "elapsed_time": "14:21:57", "remaining_time": "3:05:04"}
|
| 273 |
+
{"current_steps": 1365, "total_steps": 1652, "loss": 0.1408, "lr": 3.5940868668105644e-06, "epoch": 5.785562632696391, "percentage": 82.63, "elapsed_time": "14:25:07", "remaining_time": "3:01:53"}
|
| 274 |
+
{"current_steps": 1370, "total_steps": 1652, "loss": 0.1697, "lr": 3.4740903782608416e-06, "epoch": 5.806794055201698, "percentage": 82.93, "elapsed_time": "14:28:16", "remaining_time": "2:58:43"}
|
| 275 |
+
{"current_steps": 1375, "total_steps": 1652, "loss": 0.1836, "lr": 3.3559404498850245e-06, "epoch": 5.828025477707007, "percentage": 83.23, "elapsed_time": "14:31:24", "remaining_time": "2:55:32"}
|
| 276 |
+
{"current_steps": 1380, "total_steps": 1652, "loss": 0.158, "lr": 3.2396502834346277e-06, "epoch": 5.849256900212314, "percentage": 83.54, "elapsed_time": "14:34:32", "remaining_time": "2:52:22"}
|
| 277 |
+
{"current_steps": 1385, "total_steps": 1652, "loss": 0.1609, "lr": 3.1252328728564206e-06, "epoch": 5.870488322717622, "percentage": 83.84, "elapsed_time": "14:37:41", "remaining_time": "2:49:12"}
|
| 278 |
+
{"current_steps": 1390, "total_steps": 1652, "loss": 0.1604, "lr": 3.0127010028405303e-06, "epoch": 5.89171974522293, "percentage": 84.14, "elapsed_time": "14:40:49", "remaining_time": "2:46:01"}
|
| 279 |
+
{"current_steps": 1395, "total_steps": 1652, "loss": 0.1683, "lr": 2.9020672473919107e-06, "epoch": 5.912951167728238, "percentage": 84.44, "elapsed_time": "14:43:58", "remaining_time": "2:42:51"}
|
| 280 |
+
{"current_steps": 1400, "total_steps": 1652, "loss": 0.1706, "lr": 2.7933439684253616e-06, "epoch": 5.934182590233545, "percentage": 84.75, "elapsed_time": "14:47:07", "remaining_time": "2:39:41"}
|