Training in progress, step 6000
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 sha256:5b66c0ecd54ab18eba61fb3a481869cc208728e33924dd732cc98e330ed4f033
|
| 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 sha256:8a59d185a3338107aa64544be73a49a7d0223c9344619428df329c7cddb63366
|
| 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 sha256:7690ddc8ac612a80cc25b45d343d5d8fc448f9911f1a6aa07900acf7a560b066
|
| 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 sha256:6677acb7da7712b0cafe22db63850b637931c017f30d9b020fc6e9889c9be68c
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1165,3 +1165,43 @@
|
|
| 1165 |
{"current_steps": 5800, "total_steps": 6188, "loss": 0.1375, "lr": 4.796241165399939e-07, "epoch": 6.562535370684777, "percentage": 93.73, "elapsed_time": "19:51:52", "remaining_time": "1:19:43"}
|
| 1166 |
{"current_steps": 5805, "total_steps": 6188, "loss": 0.0676, "lr": 4.674216323762881e-07, "epoch": 6.568194680249009, "percentage": 93.81, "elapsed_time": "19:54:50", "remaining_time": "1:18:49"}
|
| 1167 |
{"current_steps": 5810, "total_steps": 6188, "loss": 0.0651, "lr": 4.5537454591943584e-07, "epoch": 6.573853989813243, "percentage": 93.89, "elapsed_time": "19:56:26", "remaining_time": "1:17:50"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1165 |
{"current_steps": 5800, "total_steps": 6188, "loss": 0.1375, "lr": 4.796241165399939e-07, "epoch": 6.562535370684777, "percentage": 93.73, "elapsed_time": "19:51:52", "remaining_time": "1:19:43"}
|
| 1166 |
{"current_steps": 5805, "total_steps": 6188, "loss": 0.0676, "lr": 4.674216323762881e-07, "epoch": 6.568194680249009, "percentage": 93.81, "elapsed_time": "19:54:50", "remaining_time": "1:18:49"}
|
| 1167 |
{"current_steps": 5810, "total_steps": 6188, "loss": 0.0651, "lr": 4.5537454591943584e-07, "epoch": 6.573853989813243, "percentage": 93.89, "elapsed_time": "19:56:26", "remaining_time": "1:17:50"}
|
| 1168 |
+
{"current_steps": 5815, "total_steps": 6188, "loss": 0.1232, "lr": 4.434829530139095e-07, "epoch": 6.579513299377476, "percentage": 93.97, "elapsed_time": "19:58:51", "remaining_time": "1:16:54"}
|
| 1169 |
+
{"current_steps": 5820, "total_steps": 6188, "loss": 0.1544, "lr": 4.3174694826709107e-07, "epoch": 6.5851726089417095, "percentage": 94.05, "elapsed_time": "20:01:46", "remaining_time": "1:15:59"}
|
| 1170 |
+
{"current_steps": 5825, "total_steps": 6188, "loss": 0.1506, "lr": 4.201666250485503e-07, "epoch": 6.590831918505942, "percentage": 94.13, "elapsed_time": "20:04:45", "remaining_time": "1:15:04"}
|
| 1171 |
+
{"current_steps": 5830, "total_steps": 6188, "loss": 0.146, "lr": 4.087420754892635e-07, "epoch": 6.5964912280701755, "percentage": 94.21, "elapsed_time": "20:07:44", "remaining_time": "1:14:09"}
|
| 1172 |
+
{"current_steps": 5835, "total_steps": 6188, "loss": 0.1454, "lr": 3.9747339048091136e-07, "epoch": 6.602150537634409, "percentage": 94.3, "elapsed_time": "20:10:40", "remaining_time": "1:13:14"}
|
| 1173 |
+
{"current_steps": 5840, "total_steps": 6188, "loss": 0.1597, "lr": 3.863606596751379e-07, "epoch": 6.6078098471986415, "percentage": 94.38, "elapsed_time": "20:13:36", "remaining_time": "1:12:19"}
|
| 1174 |
+
{"current_steps": 5845, "total_steps": 6188, "loss": 0.1497, "lr": 3.7540397148284837e-07, "epoch": 6.613469156762875, "percentage": 94.46, "elapsed_time": "20:16:40", "remaining_time": "1:11:23"}
|
| 1175 |
+
{"current_steps": 5850, "total_steps": 6188, "loss": 0.1427, "lr": 3.6460341307349653e-07, "epoch": 6.619128466327108, "percentage": 94.54, "elapsed_time": "20:19:38", "remaining_time": "1:10:28"}
|
| 1176 |
+
{"current_steps": 5855, "total_steps": 6188, "loss": 0.1672, "lr": 3.539590703743967e-07, "epoch": 6.624787775891341, "percentage": 94.62, "elapsed_time": "20:22:23", "remaining_time": "1:09:31"}
|
| 1177 |
+
{"current_steps": 5860, "total_steps": 6188, "loss": 0.1405, "lr": 3.434710280700415e-07, "epoch": 6.630447085455574, "percentage": 94.7, "elapsed_time": "20:25:23", "remaining_time": "1:08:35"}
|
| 1178 |
+
{"current_steps": 5865, "total_steps": 6188, "loss": 0.1523, "lr": 3.331393696014207e-07, "epoch": 6.636106395019808, "percentage": 94.78, "elapsed_time": "20:28:26", "remaining_time": "1:07:39"}
|
| 1179 |
+
{"current_steps": 5870, "total_steps": 6188, "loss": 0.1402, "lr": 3.22964177165368e-07, "epoch": 6.64176570458404, "percentage": 94.86, "elapsed_time": "20:31:13", "remaining_time": "1:06:42"}
|
| 1180 |
+
{"current_steps": 5875, "total_steps": 6188, "loss": 0.149, "lr": 3.129455317138952e-07, "epoch": 6.647425014148274, "percentage": 94.94, "elapsed_time": "20:34:05", "remaining_time": "1:05:44"}
|
| 1181 |
+
{"current_steps": 5880, "total_steps": 6188, "loss": 0.1374, "lr": 3.030835129535592e-07, "epoch": 6.653084323712507, "percentage": 95.02, "elapsed_time": "20:37:07", "remaining_time": "1:04:48"}
|
| 1182 |
+
{"current_steps": 5885, "total_steps": 6188, "loss": 0.1361, "lr": 2.9337819934481814e-07, "epoch": 6.658743633276741, "percentage": 95.1, "elapsed_time": "20:39:52", "remaining_time": "1:03:50"}
|
| 1183 |
+
{"current_steps": 5890, "total_steps": 6188, "loss": 0.1353, "lr": 2.838296681014185e-07, "epoch": 6.664402942840973, "percentage": 95.18, "elapsed_time": "20:42:47", "remaining_time": "1:02:52"}
|
| 1184 |
+
{"current_steps": 5895, "total_steps": 6188, "loss": 0.1434, "lr": 2.744379951897691e-07, "epoch": 6.670062252405207, "percentage": 95.27, "elapsed_time": "20:45:43", "remaining_time": "1:01:55"}
|
| 1185 |
+
{"current_steps": 5900, "total_steps": 6188, "loss": 0.1415, "lr": 2.65203255328339e-07, "epoch": 6.67572156196944, "percentage": 95.35, "elapsed_time": "20:48:33", "remaining_time": "1:00:56"}
|
| 1186 |
+
{"current_steps": 5905, "total_steps": 6188, "loss": 0.1256, "lr": 2.561255219870762e-07, "epoch": 6.681380871533673, "percentage": 95.43, "elapsed_time": "20:51:39", "remaining_time": "0:59:59"}
|
| 1187 |
+
{"current_steps": 5910, "total_steps": 6188, "loss": 0.1324, "lr": 2.472048673868033e-07, "epoch": 6.687040181097906, "percentage": 95.51, "elapsed_time": "20:54:41", "remaining_time": "0:59:01"}
|
| 1188 |
+
{"current_steps": 5915, "total_steps": 6188, "loss": 0.1537, "lr": 2.3844136249865367e-07, "epoch": 6.6926994906621395, "percentage": 95.59, "elapsed_time": "20:57:41", "remaining_time": "0:58:02"}
|
| 1189 |
+
{"current_steps": 5920, "total_steps": 6188, "loss": 0.1509, "lr": 2.2983507704351426e-07, "epoch": 6.698358800226372, "percentage": 95.67, "elapsed_time": "21:00:35", "remaining_time": "0:57:04"}
|
| 1190 |
+
{"current_steps": 5925, "total_steps": 6188, "loss": 0.1348, "lr": 2.213860794914524e-07, "epoch": 6.7040181097906055, "percentage": 95.75, "elapsed_time": "21:03:31", "remaining_time": "0:56:05"}
|
| 1191 |
+
{"current_steps": 5930, "total_steps": 6188, "loss": 0.1444, "lr": 2.1309443706118538e-07, "epoch": 6.709677419354839, "percentage": 95.83, "elapsed_time": "21:06:30", "remaining_time": "0:55:06"}
|
| 1192 |
+
{"current_steps": 5935, "total_steps": 6188, "loss": 0.1571, "lr": 2.049602157195363e-07, "epoch": 6.7153367289190715, "percentage": 95.91, "elapsed_time": "21:09:25", "remaining_time": "0:54:06"}
|
| 1193 |
+
{"current_steps": 5940, "total_steps": 6188, "loss": 0.1711, "lr": 1.9698348018092338e-07, "epoch": 6.720996038483305, "percentage": 95.99, "elapsed_time": "21:12:19", "remaining_time": "0:53:07"}
|
| 1194 |
+
{"current_steps": 5945, "total_steps": 6188, "loss": 0.1601, "lr": 1.8916429390682944e-07, "epoch": 6.726655348047538, "percentage": 96.07, "elapsed_time": "21:15:22", "remaining_time": "0:52:07"}
|
| 1195 |
+
{"current_steps": 5950, "total_steps": 6188, "loss": 0.1447, "lr": 1.8150271910530204e-07, "epoch": 6.732314657611772, "percentage": 96.15, "elapsed_time": "21:18:28", "remaining_time": "0:51:08"}
|
| 1196 |
+
{"current_steps": 5955, "total_steps": 6188, "loss": 0.145, "lr": 1.7399881673046736e-07, "epoch": 6.737973967176004, "percentage": 96.23, "elapsed_time": "21:21:33", "remaining_time": "0:50:08"}
|
| 1197 |
+
{"current_steps": 5960, "total_steps": 6188, "loss": 0.1526, "lr": 1.666526464820284e-07, "epoch": 6.743633276740238, "percentage": 96.32, "elapsed_time": "21:24:34", "remaining_time": "0:49:08"}
|
| 1198 |
+
{"current_steps": 5965, "total_steps": 6188, "loss": 0.1467, "lr": 1.594642668048052e-07, "epoch": 6.74929258630447, "percentage": 96.4, "elapsed_time": "21:27:29", "remaining_time": "0:48:07"}
|
| 1199 |
+
{"current_steps": 5970, "total_steps": 6188, "loss": 0.148, "lr": 1.5243373488826653e-07, "epoch": 6.754951895868704, "percentage": 96.48, "elapsed_time": "21:30:37", "remaining_time": "0:47:07"}
|
| 1200 |
+
{"current_steps": 5975, "total_steps": 6188, "loss": 0.156, "lr": 1.4556110666606783e-07, "epoch": 6.760611205432937, "percentage": 96.56, "elapsed_time": "21:33:43", "remaining_time": "0:46:07"}
|
| 1201 |
+
{"current_steps": 5980, "total_steps": 6188, "loss": 0.1473, "lr": 1.388464368156095e-07, "epoch": 6.766270514997171, "percentage": 96.64, "elapsed_time": "21:36:39", "remaining_time": "0:45:06"}
|
| 1202 |
+
{"current_steps": 5985, "total_steps": 6188, "loss": 0.1338, "lr": 1.322897787576105e-07, "epoch": 6.771929824561403, "percentage": 96.72, "elapsed_time": "21:39:34", "remaining_time": "0:44:04"}
|
| 1203 |
+
{"current_steps": 5990, "total_steps": 6188, "loss": 0.1336, "lr": 1.2589118465566875e-07, "epoch": 6.777589134125637, "percentage": 96.8, "elapsed_time": "21:42:42", "remaining_time": "0:43:03"}
|
| 1204 |
+
{"current_steps": 5995, "total_steps": 6188, "loss": 0.1547, "lr": 1.1965070541585912e-07, "epoch": 6.78324844368987, "percentage": 96.88, "elapsed_time": "21:45:44", "remaining_time": "0:42:02"}
|
| 1205 |
+
{"current_steps": 6000, "total_steps": 6188, "loss": 0.1545, "lr": 1.1356839068632053e-07, "epoch": 6.788907753254103, "percentage": 96.96, "elapsed_time": "21:48:44", "remaining_time": "0:41:00"}
|
| 1206 |
+
{"current_steps": 6005, "total_steps": 6188, "loss": 0.1438, "lr": 1.0764428885686073e-07, "epoch": 6.794567062818336, "percentage": 97.04, "elapsed_time": "21:52:50", "remaining_time": "0:40:00"}
|
| 1207 |
+
{"current_steps": 6010, "total_steps": 6188, "loss": 0.1422, "lr": 1.0187844705857875e-07, "epoch": 6.8002263723825696, "percentage": 97.12, "elapsed_time": "21:55:34", "remaining_time": "0:38:57"}
|