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 sha256:2efaffba84c280b90b032c852e182f88ea38b7a86789835a58c1d243a86157d2
|
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 sha256:2c49588c5fc09e2166d8df4391239b7ba30d9aadfd2a679d16ea65ead547592a
|
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:e9ec5fb002cd7bc4b6e6cdf5ad6eb9b4b59d269decde20acd41a65314258393a
|
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 sha256:38269afe94d77146d5d80726e4ef309743656538f9a56cf0a03452924859ff29
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -130,3 +130,36 @@
|
|
130 |
{"current_steps": 130, "total_steps": 224, "loss": 0.4898, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:17:34", "remaining_time": "3:06:14"}
|
131 |
{"current_steps": 131, "total_steps": 224, "loss": 0.4654, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:20:21", "remaining_time": "3:04:50"}
|
132 |
{"current_steps": 132, "total_steps": 224, "loss": 0.4492, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:22:22", "remaining_time": "3:02:52"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
130 |
{"current_steps": 130, "total_steps": 224, "loss": 0.4898, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:17:34", "remaining_time": "3:06:14"}
|
131 |
{"current_steps": 131, "total_steps": 224, "loss": 0.4654, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:20:21", "remaining_time": "3:04:50"}
|
132 |
{"current_steps": 132, "total_steps": 224, "loss": 0.4492, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:22:22", "remaining_time": "3:02:52"}
|
133 |
+
{"current_steps": 133, "total_steps": 224, "loss": 0.4402, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "4:24:17", "remaining_time": "3:00:49"}
|
134 |
+
{"current_steps": 134, "total_steps": 224, "loss": 0.4273, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "4:26:06", "remaining_time": "2:58:43"}
|
135 |
+
{"current_steps": 135, "total_steps": 224, "loss": 0.4379, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "4:28:14", "remaining_time": "2:56:50"}
|
136 |
+
{"current_steps": 136, "total_steps": 224, "loss": 0.4415, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "4:30:12", "remaining_time": "2:54:50"}
|
137 |
+
{"current_steps": 137, "total_steps": 224, "loss": 0.4641, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "4:32:15", "remaining_time": "2:52:53"}
|
138 |
+
{"current_steps": 138, "total_steps": 224, "loss": 0.445, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "4:34:16", "remaining_time": "2:50:55"}
|
139 |
+
{"current_steps": 139, "total_steps": 224, "loss": 0.4196, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "4:36:02", "remaining_time": "2:48:48"}
|
140 |
+
{"current_steps": 140, "total_steps": 224, "loss": 0.4533, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "4:38:02", "remaining_time": "2:46:49"}
|
141 |
+
{"current_steps": 141, "total_steps": 224, "loss": 0.4439, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "4:40:00", "remaining_time": "2:44:49"}
|
142 |
+
{"current_steps": 142, "total_steps": 224, "loss": 0.4297, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "4:42:00", "remaining_time": "2:42:51"}
|
143 |
+
{"current_steps": 143, "total_steps": 224, "loss": 0.4287, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "4:44:05", "remaining_time": "2:40:55"}
|
144 |
+
{"current_steps": 144, "total_steps": 224, "loss": 0.4227, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "4:45:57", "remaining_time": "2:38:51"}
|
145 |
+
{"current_steps": 145, "total_steps": 224, "loss": 0.4198, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "4:47:54", "remaining_time": "2:36:51"}
|
146 |
+
{"current_steps": 146, "total_steps": 224, "loss": 0.4291, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "4:49:51", "remaining_time": "2:34:51"}
|
147 |
+
{"current_steps": 147, "total_steps": 224, "loss": 0.4285, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "4:52:01", "remaining_time": "2:32:57"}
|
148 |
+
{"current_steps": 148, "total_steps": 224, "loss": 0.4386, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "4:53:57", "remaining_time": "2:30:56"}
|
149 |
+
{"current_steps": 149, "total_steps": 224, "loss": 0.445, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "4:55:46", "remaining_time": "2:28:52"}
|
150 |
+
{"current_steps": 150, "total_steps": 224, "loss": 0.4256, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "4:57:37", "remaining_time": "2:26:49"}
|
151 |
+
{"current_steps": 151, "total_steps": 224, "loss": 0.4197, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "4:59:31", "remaining_time": "2:24:47"}
|
152 |
+
{"current_steps": 152, "total_steps": 224, "loss": 0.4181, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "5:01:22", "remaining_time": "2:22:45"}
|
153 |
+
{"current_steps": 153, "total_steps": 224, "loss": 0.4406, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "5:03:14", "remaining_time": "2:20:43"}
|
154 |
+
{"current_steps": 154, "total_steps": 224, "loss": 0.4347, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "5:05:12", "remaining_time": "2:18:44"}
|
155 |
+
{"current_steps": 155, "total_steps": 224, "loss": 0.4539, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "5:07:14", "remaining_time": "2:16:46"}
|
156 |
+
{"current_steps": 156, "total_steps": 224, "loss": 0.4355, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "5:09:15", "remaining_time": "2:14:48"}
|
157 |
+
{"current_steps": 157, "total_steps": 224, "loss": 0.4072, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "5:11:09", "remaining_time": "2:12:47"}
|
158 |
+
{"current_steps": 158, "total_steps": 224, "loss": 0.4478, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "5:13:02", "remaining_time": "2:10:46"}
|
159 |
+
{"current_steps": 159, "total_steps": 224, "loss": 0.4359, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "5:15:00", "remaining_time": "2:08:46"}
|
160 |
+
{"current_steps": 160, "total_steps": 224, "loss": 0.4106, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "5:16:56", "remaining_time": "2:06:46"}
|
161 |
+
{"current_steps": 161, "total_steps": 224, "loss": 0.4455, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "5:19:05", "remaining_time": "2:04:51"}
|
162 |
+
{"current_steps": 162, "total_steps": 224, "loss": 0.4247, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "5:20:58", "remaining_time": "2:02:50"}
|
163 |
+
{"current_steps": 163, "total_steps": 224, "loss": 0.4101, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "5:22:56", "remaining_time": "2:00:51"}
|
164 |
+
{"current_steps": 164, "total_steps": 224, "loss": 0.4184, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "5:25:50", "remaining_time": "1:59:12"}
|
165 |
+
{"current_steps": 165, "total_steps": 224, "loss": 0.3856, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "5:27:44", "remaining_time": "1:57:11"}
|