ryanmarten commited on
Commit
0b43e5e
·
verified ·
1 Parent(s): 3aca77a

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:d881b9820241a78fd10c31403c335d98bf4621fb68d86ab5c0dc45d778675da2
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2332f3393bd04f2d8f7e2df5fca69ab34a971353085b8417ea22e22da0f8e53a
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4684faeb46d2a5ad67c5b1f40a31672189c5d2781b59fef8421113a03e68c8a8
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f655edf4b37c526dcf151153e251b50fcc0be4f728bfdaece15e83a3ec14710
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fb17f825100b0f4625aa644a8230f95f3d1317625da294220c3528431489801
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74ef866b613dbf076f718bdee77ce29883113eda0ecbf657b532113018f36e8b
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0733f0aebf3b4931d9e0daa8e574719e14cc045b68fc5d9bff083a5e2a5b8750
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3f976eaab391bb4667ef258114cb7e35a6c690d28cc57f7da9e0bf36b02aab
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -130,3 +130,35 @@
130
  {"current_steps": 130, "total_steps": 224, "loss": 0.5119, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:22:31", "remaining_time": "3:09:49"}
131
  {"current_steps": 131, "total_steps": 224, "loss": 0.5032, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:25:31", "remaining_time": "3:08:30"}
132
  {"current_steps": 132, "total_steps": 224, "loss": 0.4848, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:27:38", "remaining_time": "3:06:32"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
  {"current_steps": 130, "total_steps": 224, "loss": 0.5119, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:22:31", "remaining_time": "3:09:49"}
131
  {"current_steps": 131, "total_steps": 224, "loss": 0.5032, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:25:31", "remaining_time": "3:08:30"}
132
  {"current_steps": 132, "total_steps": 224, "loss": 0.4848, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:27:38", "remaining_time": "3:06:32"}
133
+ {"current_steps": 133, "total_steps": 224, "loss": 0.4804, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "4:29:27", "remaining_time": "3:04:22"}
134
+ {"current_steps": 134, "total_steps": 224, "loss": 0.4754, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "4:31:34", "remaining_time": "3:02:24"}
135
+ {"current_steps": 135, "total_steps": 224, "loss": 0.4818, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "4:33:28", "remaining_time": "3:00:17"}
136
+ {"current_steps": 136, "total_steps": 224, "loss": 0.4966, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "4:35:27", "remaining_time": "2:58:14"}
137
+ {"current_steps": 137, "total_steps": 224, "loss": 0.4526, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "4:37:22", "remaining_time": "2:56:08"}
138
+ {"current_steps": 138, "total_steps": 224, "loss": 0.6204, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "4:39:25", "remaining_time": "2:54:08"}
139
+ {"current_steps": 139, "total_steps": 224, "loss": 0.4905, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "4:41:22", "remaining_time": "2:52:04"}
140
+ {"current_steps": 140, "total_steps": 224, "loss": 0.4626, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "4:43:18", "remaining_time": "2:49:59"}
141
+ {"current_steps": 141, "total_steps": 224, "loss": 0.4598, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "4:45:21", "remaining_time": "2:47:58"}
142
+ {"current_steps": 142, "total_steps": 224, "loss": 0.4732, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "4:47:10", "remaining_time": "2:45:49"}
143
+ {"current_steps": 143, "total_steps": 224, "loss": 0.4672, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "4:49:04", "remaining_time": "2:43:44"}
144
+ {"current_steps": 144, "total_steps": 224, "loss": 0.4681, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "4:51:00", "remaining_time": "2:41:40"}
145
+ {"current_steps": 145, "total_steps": 224, "loss": 0.4715, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "4:52:54", "remaining_time": "2:39:35"}
146
+ {"current_steps": 146, "total_steps": 224, "loss": 0.4643, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "4:54:57", "remaining_time": "2:37:34"}
147
+ {"current_steps": 147, "total_steps": 224, "loss": 0.4745, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "4:57:02", "remaining_time": "2:35:35"}
148
+ {"current_steps": 148, "total_steps": 224, "loss": 0.4783, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "4:58:59", "remaining_time": "2:33:32"}
149
+ {"current_steps": 149, "total_steps": 224, "loss": 0.4685, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "5:01:13", "remaining_time": "2:31:37"}
150
+ {"current_steps": 150, "total_steps": 224, "loss": 0.4561, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "5:03:24", "remaining_time": "2:29:40"}
151
+ {"current_steps": 151, "total_steps": 224, "loss": 0.464, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "5:05:28", "remaining_time": "2:27:41"}
152
+ {"current_steps": 152, "total_steps": 224, "loss": 0.4892, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "5:07:24", "remaining_time": "2:25:36"}
153
+ {"current_steps": 153, "total_steps": 224, "loss": 0.473, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "5:09:25", "remaining_time": "2:23:35"}
154
+ {"current_steps": 154, "total_steps": 224, "loss": 0.4625, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "5:11:21", "remaining_time": "2:21:31"}
155
+ {"current_steps": 155, "total_steps": 224, "loss": 0.4628, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "5:13:24", "remaining_time": "2:19:31"}
156
+ {"current_steps": 156, "total_steps": 224, "loss": 0.489, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "5:15:18", "remaining_time": "2:17:26"}
157
+ {"current_steps": 157, "total_steps": 224, "loss": 0.4724, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "5:17:14", "remaining_time": "2:15:23"}
158
+ {"current_steps": 158, "total_steps": 224, "loss": 0.462, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "5:19:13", "remaining_time": "2:13:20"}
159
+ {"current_steps": 159, "total_steps": 224, "loss": 0.4419, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "5:21:11", "remaining_time": "2:11:18"}
160
+ {"current_steps": 160, "total_steps": 224, "loss": 0.4691, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "5:23:10", "remaining_time": "2:09:16"}
161
+ {"current_steps": 161, "total_steps": 224, "loss": 0.478, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "5:25:09", "remaining_time": "2:07:14"}
162
+ {"current_steps": 162, "total_steps": 224, "loss": 0.4747, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "5:27:09", "remaining_time": "2:05:12"}
163
+ {"current_steps": 163, "total_steps": 224, "loss": 0.477, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "5:29:05", "remaining_time": "2:03:09"}
164
+ {"current_steps": 164, "total_steps": 224, "loss": 0.4398, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "5:32:10", "remaining_time": "2:01:31"}