Training in progress, epoch 5
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 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a59bd135dabf0deafca1f57554ac9329aa5bc71ac2af0a51025b1c1a9cafed42
|
3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8c4496868679d7a74929cf0c727afc2ad89df56baab21feca0d303e2672e437
|
3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b03c162b2b6c940b7f6bc1c8621c512e3beef219978acd3f4bb6e3f02be8bcea
|
3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac9423ef18b2bf4c20f6373dc895d9e1c77474ae2649e895d1d39400bc0f234a
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -164,3 +164,35 @@
|
|
164 |
{"current_steps": 164, "total_steps": 224, "loss": 1.1736, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "3:34:26", "remaining_time": "1:18:27"}
|
165 |
{"current_steps": 165, "total_steps": 224, "loss": 1.1528, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "3:35:40", "remaining_time": "1:17:07"}
|
166 |
{"current_steps": 166, "total_steps": 224, "loss": 1.1458, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "3:36:55", "remaining_time": "1:15:47"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
164 |
{"current_steps": 164, "total_steps": 224, "loss": 1.1736, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "3:34:26", "remaining_time": "1:18:27"}
|
165 |
{"current_steps": 165, "total_steps": 224, "loss": 1.1528, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "3:35:40", "remaining_time": "1:17:07"}
|
166 |
{"current_steps": 166, "total_steps": 224, "loss": 1.1458, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "3:36:55", "remaining_time": "1:15:47"}
|
167 |
+
{"current_steps": 167, "total_steps": 224, "loss": 1.1536, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "3:38:11", "remaining_time": "1:14:28"}
|
168 |
+
{"current_steps": 168, "total_steps": 224, "loss": 1.166, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "3:39:27", "remaining_time": "1:13:09"}
|
169 |
+
{"current_steps": 169, "total_steps": 224, "loss": 1.1417, "lr": 3.4728958475459052e-06, "epoch": 5.172151898734177, "percentage": 75.45, "elapsed_time": "3:40:47", "remaining_time": "1:11:51"}
|
170 |
+
{"current_steps": 170, "total_steps": 224, "loss": 1.2028, "lr": 3.355285265611784e-06, "epoch": 5.2025316455696204, "percentage": 75.89, "elapsed_time": "3:42:10", "remaining_time": "1:10:34"}
|
171 |
+
{"current_steps": 171, "total_steps": 224, "loss": 1.1646, "lr": 3.2392978952499553e-06, "epoch": 5.232911392405064, "percentage": 76.34, "elapsed_time": "3:43:28", "remaining_time": "1:09:15"}
|
172 |
+
{"current_steps": 172, "total_steps": 224, "loss": 1.1127, "lr": 3.1249620705649417e-06, "epoch": 5.263291139240506, "percentage": 76.79, "elapsed_time": "3:44:51", "remaining_time": "1:07:58"}
|
173 |
+
{"current_steps": 173, "total_steps": 224, "loss": 1.1768, "lr": 3.0123057222115835e-06, "epoch": 5.293670886075949, "percentage": 77.23, "elapsed_time": "3:46:09", "remaining_time": "1:06:40"}
|
174 |
+
{"current_steps": 174, "total_steps": 224, "loss": 1.1295, "lr": 2.9013563705719673e-06, "epoch": 5.324050632911392, "percentage": 77.68, "elapsed_time": "3:47:21", "remaining_time": "1:05:20"}
|
175 |
+
{"current_steps": 175, "total_steps": 224, "loss": 1.1409, "lr": 2.7921411190325753e-06, "epoch": 5.3544303797468356, "percentage": 78.12, "elapsed_time": "3:48:53", "remaining_time": "1:04:05"}
|
176 |
+
{"current_steps": 176, "total_steps": 224, "loss": 1.1648, "lr": 2.6846866473633126e-06, "epoch": 5.384810126582279, "percentage": 78.57, "elapsed_time": "3:50:04", "remaining_time": "1:02:44"}
|
177 |
+
{"current_steps": 177, "total_steps": 224, "loss": 1.1181, "lr": 2.579019205199992e-06, "epoch": 5.415189873417722, "percentage": 79.02, "elapsed_time": "3:51:20", "remaining_time": "1:01:25"}
|
178 |
+
{"current_steps": 178, "total_steps": 224, "loss": 1.1314, "lr": 2.4751646056319334e-06, "epoch": 5.445569620253164, "percentage": 79.46, "elapsed_time": "3:52:45", "remaining_time": "1:00:09"}
|
179 |
+
{"current_steps": 179, "total_steps": 224, "loss": 1.1669, "lr": 2.373148218896182e-06, "epoch": 5.4759493670886075, "percentage": 79.91, "elapsed_time": "3:53:53", "remaining_time": "0:58:48"}
|
180 |
+
{"current_steps": 180, "total_steps": 224, "loss": 1.1574, "lr": 2.2729949661798876e-06, "epoch": 5.506329113924051, "percentage": 80.36, "elapsed_time": "3:55:22", "remaining_time": "0:57:32"}
|
181 |
+
{"current_steps": 181, "total_steps": 224, "loss": 1.1552, "lr": 2.174729313532433e-06, "epoch": 5.536708860759494, "percentage": 80.8, "elapsed_time": "3:56:40", "remaining_time": "0:56:13"}
|
182 |
+
{"current_steps": 182, "total_steps": 224, "loss": 1.117, "lr": 2.078375265888707e-06, "epoch": 5.567088607594937, "percentage": 81.25, "elapsed_time": "3:57:57", "remaining_time": "0:54:54"}
|
183 |
+
{"current_steps": 183, "total_steps": 224, "loss": 1.1216, "lr": 1.9839563612050273e-06, "epoch": 5.597468354430379, "percentage": 81.7, "elapsed_time": "3:59:09", "remaining_time": "0:53:34"}
|
184 |
+
{"current_steps": 184, "total_steps": 224, "loss": 1.1587, "lr": 1.8914956647091497e-06, "epoch": 5.627848101265823, "percentage": 82.14, "elapsed_time": "4:00:26", "remaining_time": "0:52:16"}
|
185 |
+
{"current_steps": 185, "total_steps": 224, "loss": 1.1341, "lr": 1.8010157632657544e-06, "epoch": 5.658227848101266, "percentage": 82.59, "elapsed_time": "4:01:45", "remaining_time": "0:50:58"}
|
186 |
+
{"current_steps": 186, "total_steps": 224, "loss": 1.1242, "lr": 1.7125387598587862e-06, "epoch": 5.688607594936709, "percentage": 83.04, "elapsed_time": "4:02:51", "remaining_time": "0:49:37"}
|
187 |
+
{"current_steps": 187, "total_steps": 224, "loss": 1.1381, "lr": 1.6260862681919965e-06, "epoch": 5.718987341772152, "percentage": 83.48, "elapsed_time": "4:04:08", "remaining_time": "0:48:18"}
|
188 |
+
{"current_steps": 188, "total_steps": 224, "loss": 1.1462, "lr": 1.5416794074090258e-06, "epoch": 5.749367088607595, "percentage": 83.93, "elapsed_time": "4:05:23", "remaining_time": "0:46:59"}
|
189 |
+
{"current_steps": 189, "total_steps": 224, "loss": 1.1376, "lr": 1.459338796934293e-06, "epoch": 5.779746835443038, "percentage": 84.38, "elapsed_time": "4:06:50", "remaining_time": "0:45:42"}
|
190 |
+
{"current_steps": 190, "total_steps": 224, "loss": 1.1571, "lr": 1.3790845514359363e-06, "epoch": 5.810126582278481, "percentage": 84.82, "elapsed_time": "4:08:05", "remaining_time": "0:44:23"}
|
191 |
+
{"current_steps": 191, "total_steps": 224, "loss": 1.1485, "lr": 1.300936275912098e-06, "epoch": 5.840506329113924, "percentage": 85.27, "elapsed_time": "4:09:24", "remaining_time": "0:43:05"}
|
192 |
+
{"current_steps": 192, "total_steps": 224, "loss": 1.1532, "lr": 1.224913060901688e-06, "epoch": 5.870886075949367, "percentage": 85.71, "elapsed_time": "4:10:35", "remaining_time": "0:41:45"}
|
193 |
+
{"current_steps": 193, "total_steps": 224, "loss": 1.132, "lr": 1.1510334778208332e-06, "epoch": 5.9012658227848105, "percentage": 86.16, "elapsed_time": "4:11:49", "remaining_time": "0:40:26"}
|
194 |
+
{"current_steps": 194, "total_steps": 224, "loss": 1.1665, "lr": 1.0793155744261352e-06, "epoch": 5.931645569620253, "percentage": 86.61, "elapsed_time": "4:13:05", "remaining_time": "0:39:08"}
|
195 |
+
{"current_steps": 195, "total_steps": 224, "loss": 1.148, "lr": 1.0097768704058542e-06, "epoch": 5.962025316455696, "percentage": 87.05, "elapsed_time": "4:14:17", "remaining_time": "0:37:49"}
|
196 |
+
{"current_steps": 196, "total_steps": 224, "loss": 1.1819, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "4:15:30", "remaining_time": "0:36:30"}
|
197 |
+
{"current_steps": 197, "total_steps": 224, "loss": 1.1257, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "4:17:50", "remaining_time": "0:35:20"}
|
198 |
+
{"current_steps": 198, "total_steps": 224, "loss": 1.1339, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "4:19:06", "remaining_time": "0:34:01"}
|