Training in progress, epoch 4
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 sha256:9dcdfc8ab782286bc7130508b77e88bda84ac5a4a6003f39ad4ff10e73481a99
|
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 sha256:99486cd46a622a641187697559437b005e16d9a9b5e812a6c68a1925c82d2cda
|
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 sha256:460c98cba16231aaddb5ec15bcc9766ef57698dea9739125e50a53daf8a8eb3b
|
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:d21f7bdcb2686272e6487580ff15a2fab79e3084662c98310f949ea2eae7b56e
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -136,3 +136,33 @@
|
|
136 |
{"current_steps": 136, "total_steps": 224, "loss": 0.2421, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "1:40:11", "remaining_time": "1:04:50"}
|
137 |
{"current_steps": 137, "total_steps": 224, "loss": 0.2126, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "1:40:50", "remaining_time": "1:04:02"}
|
138 |
{"current_steps": 138, "total_steps": 224, "loss": 0.2341, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "1:41:41", "remaining_time": "1:03:22"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
{"current_steps": 136, "total_steps": 224, "loss": 0.2421, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "1:40:11", "remaining_time": "1:04:50"}
|
137 |
{"current_steps": 137, "total_steps": 224, "loss": 0.2126, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "1:40:50", "remaining_time": "1:04:02"}
|
138 |
{"current_steps": 138, "total_steps": 224, "loss": 0.2341, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "1:41:41", "remaining_time": "1:03:22"}
|
139 |
+
{"current_steps": 139, "total_steps": 224, "loss": 0.2211, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "1:42:33", "remaining_time": "1:02:42"}
|
140 |
+
{"current_steps": 140, "total_steps": 224, "loss": 0.2206, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "1:43:27", "remaining_time": "1:02:04"}
|
141 |
+
{"current_steps": 141, "total_steps": 224, "loss": 0.2103, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "1:44:16", "remaining_time": "1:01:23"}
|
142 |
+
{"current_steps": 142, "total_steps": 224, "loss": 0.1936, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "1:44:56", "remaining_time": "1:00:35"}
|
143 |
+
{"current_steps": 143, "total_steps": 224, "loss": 0.1836, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "1:45:24", "remaining_time": "0:59:42"}
|
144 |
+
{"current_steps": 144, "total_steps": 224, "loss": 0.2174, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "1:46:13", "remaining_time": "0:59:00"}
|
145 |
+
{"current_steps": 145, "total_steps": 224, "loss": 0.1948, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "1:46:48", "remaining_time": "0:58:11"}
|
146 |
+
{"current_steps": 146, "total_steps": 224, "loss": 0.2031, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "1:47:41", "remaining_time": "0:57:32"}
|
147 |
+
{"current_steps": 147, "total_steps": 224, "loss": 0.2341, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "1:48:32", "remaining_time": "0:56:51"}
|
148 |
+
{"current_steps": 148, "total_steps": 224, "loss": 0.205, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "1:49:13", "remaining_time": "0:56:05"}
|
149 |
+
{"current_steps": 149, "total_steps": 224, "loss": 0.1784, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "1:49:47", "remaining_time": "0:55:16"}
|
150 |
+
{"current_steps": 150, "total_steps": 224, "loss": 0.1828, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "1:50:26", "remaining_time": "0:54:29"}
|
151 |
+
{"current_steps": 151, "total_steps": 224, "loss": 0.2021, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "1:51:04", "remaining_time": "0:53:41"}
|
152 |
+
{"current_steps": 152, "total_steps": 224, "loss": 0.2081, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "1:51:50", "remaining_time": "0:52:58"}
|
153 |
+
{"current_steps": 153, "total_steps": 224, "loss": 0.1959, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "1:52:47", "remaining_time": "0:52:20"}
|
154 |
+
{"current_steps": 154, "total_steps": 224, "loss": 0.2304, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "1:53:22", "remaining_time": "0:51:32"}
|
155 |
+
{"current_steps": 155, "total_steps": 224, "loss": 0.1915, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "1:54:00", "remaining_time": "0:50:45"}
|
156 |
+
{"current_steps": 156, "total_steps": 224, "loss": 0.1855, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "1:54:37", "remaining_time": "0:49:57"}
|
157 |
+
{"current_steps": 157, "total_steps": 224, "loss": 0.2222, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "1:55:17", "remaining_time": "0:49:12"}
|
158 |
+
{"current_steps": 158, "total_steps": 224, "loss": 0.1809, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "1:55:50", "remaining_time": "0:48:23"}
|
159 |
+
{"current_steps": 159, "total_steps": 224, "loss": 0.1893, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "1:56:28", "remaining_time": "0:47:36"}
|
160 |
+
{"current_steps": 160, "total_steps": 224, "loss": 0.2049, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "1:57:12", "remaining_time": "0:46:52"}
|
161 |
+
{"current_steps": 161, "total_steps": 224, "loss": 0.2146, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "1:57:47", "remaining_time": "0:46:05"}
|
162 |
+
{"current_steps": 162, "total_steps": 224, "loss": 0.2052, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "1:58:40", "remaining_time": "0:45:25"}
|
163 |
+
{"current_steps": 163, "total_steps": 224, "loss": 0.2207, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "1:59:29", "remaining_time": "0:44:43"}
|
164 |
+
{"current_steps": 164, "total_steps": 224, "loss": 0.1676, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "2:00:58", "remaining_time": "0:44:15"}
|
165 |
+
{"current_steps": 165, "total_steps": 224, "loss": 0.1576, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "2:01:32", "remaining_time": "0:43:27"}
|
166 |
+
{"current_steps": 166, "total_steps": 224, "loss": 0.1526, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "2:02:14", "remaining_time": "0:42:42"}
|
167 |
+
{"current_steps": 167, "total_steps": 224, "loss": 0.1462, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "2:03:01", "remaining_time": "0:41:59"}
|
168 |
+
{"current_steps": 168, "total_steps": 224, "loss": 0.146, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "2:03:35", "remaining_time": "0:41:11"}
|