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:b4f37740cbd866d0db625a4a236bc7ecb9e45600cf0c053f7861155364ad0bfe
|
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 sha256:36d2c545f938ec2fc1c6a18b7723bbb454b5861deae0e776ad1797be25c75758
|
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:d6fdbb0ad340cc7a96e4bf12e951c8cb47c7a797aa1646eea875607db8c9eda5
|
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 sha256:0210f8f01f55061e7a27d1f5beeedf31142f36678bc7692d31b20041bb23cdea
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -131,3 +131,35 @@
|
|
131 |
{"current_steps": 131, "total_steps": 224, "loss": 0.5119, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "3:39:07", "remaining_time": "2:35:33"}
|
132 |
{"current_steps": 132, "total_steps": 224, "loss": 0.4309, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "3:40:34", "remaining_time": "2:33:44"}
|
133 |
{"current_steps": 133, "total_steps": 224, "loss": 0.4589, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "3:42:11", "remaining_time": "2:32:01"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
131 |
{"current_steps": 131, "total_steps": 224, "loss": 0.5119, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "3:39:07", "remaining_time": "2:35:33"}
|
132 |
{"current_steps": 132, "total_steps": 224, "loss": 0.4309, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "3:40:34", "remaining_time": "2:33:44"}
|
133 |
{"current_steps": 133, "total_steps": 224, "loss": 0.4589, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "3:42:11", "remaining_time": "2:32:01"}
|
134 |
+
{"current_steps": 134, "total_steps": 224, "loss": 0.4355, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "3:43:49", "remaining_time": "2:30:20"}
|
135 |
+
{"current_steps": 135, "total_steps": 224, "loss": 0.4588, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "3:45:35", "remaining_time": "2:28:43"}
|
136 |
+
{"current_steps": 136, "total_steps": 224, "loss": 0.4725, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "3:47:19", "remaining_time": "2:27:05"}
|
137 |
+
{"current_steps": 137, "total_steps": 224, "loss": 0.4474, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "3:48:55", "remaining_time": "2:25:22"}
|
138 |
+
{"current_steps": 138, "total_steps": 224, "loss": 0.4406, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "3:50:35", "remaining_time": "2:23:42"}
|
139 |
+
{"current_steps": 139, "total_steps": 224, "loss": 0.4465, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "3:52:21", "remaining_time": "2:22:05"}
|
140 |
+
{"current_steps": 140, "total_steps": 224, "loss": 0.4566, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "3:54:08", "remaining_time": "2:20:28"}
|
141 |
+
{"current_steps": 141, "total_steps": 224, "loss": 0.4483, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "3:55:49", "remaining_time": "2:18:49"}
|
142 |
+
{"current_steps": 142, "total_steps": 224, "loss": 0.4386, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "3:57:26", "remaining_time": "2:17:07"}
|
143 |
+
{"current_steps": 143, "total_steps": 224, "loss": 0.4569, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "3:59:02", "remaining_time": "2:15:24"}
|
144 |
+
{"current_steps": 144, "total_steps": 224, "loss": 0.4397, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "4:00:32", "remaining_time": "2:13:38"}
|
145 |
+
{"current_steps": 145, "total_steps": 224, "loss": 0.4523, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "4:02:21", "remaining_time": "2:12:02"}
|
146 |
+
{"current_steps": 146, "total_steps": 224, "loss": 0.4826, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "4:03:59", "remaining_time": "2:10:20"}
|
147 |
+
{"current_steps": 147, "total_steps": 224, "loss": 0.449, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "4:05:32", "remaining_time": "2:08:36"}
|
148 |
+
{"current_steps": 148, "total_steps": 224, "loss": 0.455, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "4:07:12", "remaining_time": "2:06:56"}
|
149 |
+
{"current_steps": 149, "total_steps": 224, "loss": 0.4441, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "4:08:56", "remaining_time": "2:05:18"}
|
150 |
+
{"current_steps": 150, "total_steps": 224, "loss": 0.4114, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "4:10:33", "remaining_time": "2:03:36"}
|
151 |
+
{"current_steps": 151, "total_steps": 224, "loss": 0.4199, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "4:12:03", "remaining_time": "2:01:51"}
|
152 |
+
{"current_steps": 152, "total_steps": 224, "loss": 0.4605, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "4:13:25", "remaining_time": "2:00:02"}
|
153 |
+
{"current_steps": 153, "total_steps": 224, "loss": 0.444, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "4:15:06", "remaining_time": "1:58:22"}
|
154 |
+
{"current_steps": 154, "total_steps": 224, "loss": 0.448, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "4:16:45", "remaining_time": "1:56:42"}
|
155 |
+
{"current_steps": 155, "total_steps": 224, "loss": 0.4696, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "4:18:32", "remaining_time": "1:55:05"}
|
156 |
+
{"current_steps": 156, "total_steps": 224, "loss": 0.4594, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "4:20:00", "remaining_time": "1:53:20"}
|
157 |
+
{"current_steps": 157, "total_steps": 224, "loss": 0.465, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "4:21:38", "remaining_time": "1:51:39"}
|
158 |
+
{"current_steps": 158, "total_steps": 224, "loss": 0.4637, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "4:23:19", "remaining_time": "1:49:59"}
|
159 |
+
{"current_steps": 159, "total_steps": 224, "loss": 0.4663, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "4:25:00", "remaining_time": "1:48:20"}
|
160 |
+
{"current_steps": 160, "total_steps": 224, "loss": 0.4594, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "4:26:32", "remaining_time": "1:46:37"}
|
161 |
+
{"current_steps": 161, "total_steps": 224, "loss": 0.4197, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "4:28:14", "remaining_time": "1:44:57"}
|
162 |
+
{"current_steps": 162, "total_steps": 224, "loss": 0.4841, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "4:29:51", "remaining_time": "1:43:16"}
|
163 |
+
{"current_steps": 163, "total_steps": 224, "loss": 0.4298, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "4:31:27", "remaining_time": "1:41:35"}
|
164 |
+
{"current_steps": 164, "total_steps": 224, "loss": 0.4481, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "4:33:55", "remaining_time": "1:40:12"}
|
165 |
+
{"current_steps": 165, "total_steps": 224, "loss": 0.4047, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "4:35:27", "remaining_time": "1:38:29"}
|