Training in progress, step 5800
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 sha256:37a60221ad5a787b71707630162c2e751e0707860f39541104d3bffb96d4d975
|
| 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:c02443c1e400253c447f4d9fdd5def0ecbed90cd00ca99cccfe34d2f900dc300
|
| 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 sha256:60c2222b0479ddd3e62c2aacffed5af5c7a2d128b700c7b875075ec2fc7db289
|
| 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:de0be374e90af3db2aa01ed4eb3eafa611cf3b1ac15c1c6f8c824e7fd5cc655d
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1141,3 +1141,43 @@
|
|
| 1141 |
{"current_steps": 5590, "total_steps": 6713, "loss": 0.2034, "lr": 3.320577511261589e-06, "epoch": 5.830464267083985, "percentage": 83.27, "elapsed_time": "19:32:14", "remaining_time": "3:55:29"}
|
| 1142 |
{"current_steps": 5595, "total_steps": 6713, "loss": 0.1948, "lr": 3.291937418815376e-06, "epoch": 5.835680751173709, "percentage": 83.35, "elapsed_time": "19:33:53", "remaining_time": "3:54:34"}
|
| 1143 |
{"current_steps": 5600, "total_steps": 6713, "loss": 0.1961, "lr": 3.2634102924159982e-06, "epoch": 5.840897235263433, "percentage": 83.42, "elapsed_time": "19:35:37", "remaining_time": "3:53:39"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1141 |
{"current_steps": 5590, "total_steps": 6713, "loss": 0.2034, "lr": 3.320577511261589e-06, "epoch": 5.830464267083985, "percentage": 83.27, "elapsed_time": "19:32:14", "remaining_time": "3:55:29"}
|
| 1142 |
{"current_steps": 5595, "total_steps": 6713, "loss": 0.1948, "lr": 3.291937418815376e-06, "epoch": 5.835680751173709, "percentage": 83.35, "elapsed_time": "19:33:53", "remaining_time": "3:54:34"}
|
| 1143 |
{"current_steps": 5600, "total_steps": 6713, "loss": 0.1961, "lr": 3.2634102924159982e-06, "epoch": 5.840897235263433, "percentage": 83.42, "elapsed_time": "19:35:37", "remaining_time": "3:53:39"}
|
| 1144 |
+
{"current_steps": 5605, "total_steps": 6713, "loss": 0.1992, "lr": 3.2349963249401894e-06, "epoch": 5.846113719353156, "percentage": 83.49, "elapsed_time": "19:38:43", "remaining_time": "3:53:00"}
|
| 1145 |
+
{"current_steps": 5610, "total_steps": 6713, "loss": 0.1968, "lr": 3.2066957084996163e-06, "epoch": 5.851330203442879, "percentage": 83.57, "elapsed_time": "19:40:19", "remaining_time": "3:52:04"}
|
| 1146 |
+
{"current_steps": 5615, "total_steps": 6713, "loss": 0.1998, "lr": 3.178508634439539e-06, "epoch": 5.856546687532603, "percentage": 83.64, "elapsed_time": "19:41:59", "remaining_time": "3:51:08"}
|
| 1147 |
+
{"current_steps": 5620, "total_steps": 6713, "loss": 0.1856, "lr": 3.150435293337557e-06, "epoch": 5.861763171622327, "percentage": 83.72, "elapsed_time": "19:43:41", "remaining_time": "3:50:12"}
|
| 1148 |
+
{"current_steps": 5625, "total_steps": 6713, "loss": 0.1885, "lr": 3.1224758750022934e-06, "epoch": 5.86697965571205, "percentage": 83.79, "elapsed_time": "19:45:26", "remaining_time": "3:49:17"}
|
| 1149 |
+
{"current_steps": 5630, "total_steps": 6713, "loss": 0.193, "lr": 3.0946305684721145e-06, "epoch": 5.8721961398017735, "percentage": 83.87, "elapsed_time": "19:47:08", "remaining_time": "3:48:21"}
|
| 1150 |
+
{"current_steps": 5635, "total_steps": 6713, "loss": 0.2008, "lr": 3.066899562013872e-06, "epoch": 5.877412623891497, "percentage": 83.94, "elapsed_time": "19:48:51", "remaining_time": "3:47:25"}
|
| 1151 |
+
{"current_steps": 5640, "total_steps": 6713, "loss": 0.1936, "lr": 3.0392830431216037e-06, "epoch": 5.882629107981221, "percentage": 84.02, "elapsed_time": "19:50:31", "remaining_time": "3:46:29"}
|
| 1152 |
+
{"current_steps": 5645, "total_steps": 6713, "loss": 0.2006, "lr": 3.01178119851528e-06, "epoch": 5.887845592070944, "percentage": 84.09, "elapsed_time": "19:52:09", "remaining_time": "3:45:32"}
|
| 1153 |
+
{"current_steps": 5650, "total_steps": 6713, "loss": 0.197, "lr": 2.9843942141395365e-06, "epoch": 5.893062076160668, "percentage": 84.17, "elapsed_time": "19:53:51", "remaining_time": "3:44:36"}
|
| 1154 |
+
{"current_steps": 5655, "total_steps": 6713, "loss": 0.1993, "lr": 2.9571222751624317e-06, "epoch": 5.898278560250391, "percentage": 84.24, "elapsed_time": "19:55:25", "remaining_time": "3:43:39"}
|
| 1155 |
+
{"current_steps": 5660, "total_steps": 6713, "loss": 0.1967, "lr": 2.9299655659741622e-06, "epoch": 5.903495044340115, "percentage": 84.31, "elapsed_time": "19:57:13", "remaining_time": "3:42:44"}
|
| 1156 |
+
{"current_steps": 5665, "total_steps": 6713, "loss": 0.1914, "lr": 2.9029242701858606e-06, "epoch": 5.908711528429838, "percentage": 84.39, "elapsed_time": "19:59:03", "remaining_time": "3:41:49"}
|
| 1157 |
+
{"current_steps": 5670, "total_steps": 6713, "loss": 0.1858, "lr": 2.8759985706283068e-06, "epoch": 5.913928012519562, "percentage": 84.46, "elapsed_time": "20:00:48", "remaining_time": "3:40:53"}
|
| 1158 |
+
{"current_steps": 5675, "total_steps": 6713, "loss": 0.1936, "lr": 2.8491886493507313e-06, "epoch": 5.919144496609285, "percentage": 84.54, "elapsed_time": "20:02:30", "remaining_time": "3:39:56"}
|
| 1159 |
+
{"current_steps": 5680, "total_steps": 6713, "loss": 0.1899, "lr": 2.8224946876195593e-06, "epoch": 5.924360980699009, "percentage": 84.61, "elapsed_time": "20:04:11", "remaining_time": "3:39:00"}
|
| 1160 |
+
{"current_steps": 5685, "total_steps": 6713, "loss": 0.1881, "lr": 2.795916865917201e-06, "epoch": 5.929577464788732, "percentage": 84.69, "elapsed_time": "20:05:53", "remaining_time": "3:38:03"}
|
| 1161 |
+
{"current_steps": 5690, "total_steps": 6713, "loss": 0.1821, "lr": 2.7694553639408163e-06, "epoch": 5.934793948878456, "percentage": 84.76, "elapsed_time": "20:07:33", "remaining_time": "3:37:06"}
|
| 1162 |
+
{"current_steps": 5695, "total_steps": 6713, "loss": 0.1869, "lr": 2.7431103606011113e-06, "epoch": 5.9400104329681795, "percentage": 84.84, "elapsed_time": "20:09:09", "remaining_time": "3:36:08"}
|
| 1163 |
+
{"current_steps": 5700, "total_steps": 6713, "loss": 0.1883, "lr": 2.71688203402112e-06, "epoch": 5.945226917057903, "percentage": 84.91, "elapsed_time": "20:10:52", "remaining_time": "3:35:11"}
|
| 1164 |
+
{"current_steps": 5705, "total_steps": 6713, "loss": 0.207, "lr": 2.690770561535019e-06, "epoch": 5.950443401147626, "percentage": 84.98, "elapsed_time": "20:12:31", "remaining_time": "3:34:14"}
|
| 1165 |
+
{"current_steps": 5710, "total_steps": 6713, "loss": 0.1933, "lr": 2.664776119686896e-06, "epoch": 5.95565988523735, "percentage": 85.06, "elapsed_time": "20:14:04", "remaining_time": "3:33:15"}
|
| 1166 |
+
{"current_steps": 5715, "total_steps": 6713, "loss": 0.1877, "lr": 2.6388988842295947e-06, "epoch": 5.960876369327074, "percentage": 85.13, "elapsed_time": "20:15:48", "remaining_time": "3:32:18"}
|
| 1167 |
+
{"current_steps": 5720, "total_steps": 6713, "loss": 0.1829, "lr": 2.6131390301234927e-06, "epoch": 5.966092853416797, "percentage": 85.21, "elapsed_time": "20:17:27", "remaining_time": "3:31:21"}
|
| 1168 |
+
{"current_steps": 5725, "total_steps": 6713, "loss": 0.1935, "lr": 2.587496731535326e-06, "epoch": 5.97130933750652, "percentage": 85.28, "elapsed_time": "20:19:05", "remaining_time": "3:30:23"}
|
| 1169 |
+
{"current_steps": 5730, "total_steps": 6713, "loss": 0.1991, "lr": 2.561972161837041e-06, "epoch": 5.976525821596244, "percentage": 85.36, "elapsed_time": "20:20:44", "remaining_time": "3:29:25"}
|
| 1170 |
+
{"current_steps": 5735, "total_steps": 6713, "loss": 0.1985, "lr": 2.536565493604575e-06, "epoch": 5.981742305685968, "percentage": 85.43, "elapsed_time": "20:22:25", "remaining_time": "3:28:27"}
|
| 1171 |
+
{"current_steps": 5740, "total_steps": 6713, "loss": 0.1955, "lr": 2.511276898616737e-06, "epoch": 5.9869587897756915, "percentage": 85.51, "elapsed_time": "20:24:08", "remaining_time": "3:27:30"}
|
| 1172 |
+
{"current_steps": 5745, "total_steps": 6713, "loss": 0.1943, "lr": 2.4861065478539925e-06, "epoch": 5.992175273865414, "percentage": 85.58, "elapsed_time": "20:25:46", "remaining_time": "3:26:32"}
|
| 1173 |
+
{"current_steps": 5750, "total_steps": 6713, "loss": 0.1928, "lr": 2.4610546114973666e-06, "epoch": 5.997391757955138, "percentage": 85.65, "elapsed_time": "20:27:28", "remaining_time": "3:25:34"}
|
| 1174 |
+
{"current_steps": 5755, "total_steps": 6713, "loss": 0.1749, "lr": 2.4361212589272488e-06, "epoch": 6.002086593635889, "percentage": 85.73, "elapsed_time": "20:29:41", "remaining_time": "3:24:41"}
|
| 1175 |
+
{"current_steps": 5760, "total_steps": 6713, "loss": 0.1511, "lr": 2.41130665872227e-06, "epoch": 6.007303077725613, "percentage": 85.8, "elapsed_time": "20:32:33", "remaining_time": "3:23:55"}
|
| 1176 |
+
{"current_steps": 5765, "total_steps": 6713, "loss": 0.1464, "lr": 2.3866109786581484e-06, "epoch": 6.012519561815337, "percentage": 85.88, "elapsed_time": "20:35:30", "remaining_time": "3:23:10"}
|
| 1177 |
+
{"current_steps": 5770, "total_steps": 6713, "loss": 0.1443, "lr": 2.3620343857065776e-06, "epoch": 6.01773604590506, "percentage": 85.95, "elapsed_time": "20:38:24", "remaining_time": "3:22:23"}
|
| 1178 |
+
{"current_steps": 5775, "total_steps": 6713, "loss": 0.1507, "lr": 2.3375770460340654e-06, "epoch": 6.022952529994783, "percentage": 86.03, "elapsed_time": "20:41:16", "remaining_time": "3:21:36"}
|
| 1179 |
+
{"current_steps": 5780, "total_steps": 6713, "loss": 0.1569, "lr": 2.313239125000841e-06, "epoch": 6.028169014084507, "percentage": 86.1, "elapsed_time": "20:44:13", "remaining_time": "3:20:50"}
|
| 1180 |
+
{"current_steps": 5785, "total_steps": 6713, "loss": 0.1513, "lr": 2.2890207871597192e-06, "epoch": 6.033385498174231, "percentage": 86.18, "elapsed_time": "20:47:13", "remaining_time": "3:20:04"}
|
| 1181 |
+
{"current_steps": 5790, "total_steps": 6713, "loss": 0.1449, "lr": 2.2649221962549905e-06, "epoch": 6.0386019822639545, "percentage": 86.25, "elapsed_time": "20:50:10", "remaining_time": "3:19:17"}
|
| 1182 |
+
{"current_steps": 5795, "total_steps": 6713, "loss": 0.1698, "lr": 2.2409435152213123e-06, "epoch": 6.043818466353677, "percentage": 86.33, "elapsed_time": "20:52:51", "remaining_time": "3:18:28"}
|
| 1183 |
+
{"current_steps": 5800, "total_steps": 6713, "loss": 0.1479, "lr": 2.217084906182629e-06, "epoch": 6.049034950443401, "percentage": 86.4, "elapsed_time": "20:55:48", "remaining_time": "3:17:40"}
|