ryanmarten commited on
Commit
0ff8fb2
·
verified ·
1 Parent(s): 9b5ddb8

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 sha256:96b3348ce0b40a3958584cf273f668143b2ff57928ff3ebb47cb2a5643ad6e30
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c688872bd89e71c167bbd46754a294a8bb3f50cc1196ea2221efa588492df94
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16b3db465f521684ebc55d98077ed0e270b758f85295055816e967ad68b374f7
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc8169cf40dc2857603c57cdc1550eabcef0df4d78849e22eda1d560597ce16
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c947d61cb007899c56985f8ed35bf8efd38f2589f5587c9c9f9e9a703ae033c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916ce71e42226bfe14cdba9ba4f5acc79d0f86a2d94a175efc2f87d4d81a7fb5
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:cd7ef09e862137d9eb5220077094d0defe1cead1ea4348839a6bd7c3fe3eb9a9
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c5978416d9b805c1d0f5dea028597b1987fd777f168a1d7be2a3ea1adc4d63
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -130,3 +130,36 @@
130
  {"current_steps": 130, "total_steps": 224, "loss": 0.4839, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:21:36", "remaining_time": "3:09:10"}
131
  {"current_steps": 131, "total_steps": 224, "loss": 0.4684, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:24:32", "remaining_time": "3:07:48"}
132
  {"current_steps": 132, "total_steps": 224, "loss": 0.4512, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:26:32", "remaining_time": "3:05:46"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
  {"current_steps": 130, "total_steps": 224, "loss": 0.4839, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:21:36", "remaining_time": "3:09:10"}
131
  {"current_steps": 131, "total_steps": 224, "loss": 0.4684, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:24:32", "remaining_time": "3:07:48"}
132
  {"current_steps": 132, "total_steps": 224, "loss": 0.4512, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:26:32", "remaining_time": "3:05:46"}
133
+ {"current_steps": 133, "total_steps": 224, "loss": 0.4729, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "4:28:38", "remaining_time": "3:03:48"}
134
+ {"current_steps": 134, "total_steps": 224, "loss": 0.4527, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "4:30:33", "remaining_time": "3:01:43"}
135
+ {"current_steps": 135, "total_steps": 224, "loss": 0.4387, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "4:32:28", "remaining_time": "2:59:37"}
136
+ {"current_steps": 136, "total_steps": 224, "loss": 0.4557, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "4:34:21", "remaining_time": "2:57:31"}
137
+ {"current_steps": 137, "total_steps": 224, "loss": 0.4454, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "4:36:15", "remaining_time": "2:55:26"}
138
+ {"current_steps": 138, "total_steps": 224, "loss": 0.4282, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "4:38:12", "remaining_time": "2:53:22"}
139
+ {"current_steps": 139, "total_steps": 224, "loss": 0.4324, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "4:40:04", "remaining_time": "2:51:16"}
140
+ {"current_steps": 140, "total_steps": 224, "loss": 0.4388, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "4:42:07", "remaining_time": "2:49:16"}
141
+ {"current_steps": 141, "total_steps": 224, "loss": 0.4555, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "4:44:18", "remaining_time": "2:47:21"}
142
+ {"current_steps": 142, "total_steps": 224, "loss": 0.4515, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "4:46:19", "remaining_time": "2:45:20"}
143
+ {"current_steps": 143, "total_steps": 224, "loss": 0.4531, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "4:48:13", "remaining_time": "2:43:15"}
144
+ {"current_steps": 144, "total_steps": 224, "loss": 0.4341, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "4:50:15", "remaining_time": "2:41:15"}
145
+ {"current_steps": 145, "total_steps": 224, "loss": 0.4303, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "4:52:12", "remaining_time": "2:39:12"}
146
+ {"current_steps": 146, "total_steps": 224, "loss": 0.4327, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "4:54:10", "remaining_time": "2:37:09"}
147
+ {"current_steps": 147, "total_steps": 224, "loss": 0.4456, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "4:56:07", "remaining_time": "2:35:06"}
148
+ {"current_steps": 148, "total_steps": 224, "loss": 0.4496, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "4:58:10", "remaining_time": "2:33:07"}
149
+ {"current_steps": 149, "total_steps": 224, "loss": 0.4377, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "5:00:06", "remaining_time": "2:31:03"}
150
+ {"current_steps": 150, "total_steps": 224, "loss": 0.4594, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "5:02:13", "remaining_time": "2:29:06"}
151
+ {"current_steps": 151, "total_steps": 224, "loss": 0.4399, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "5:04:16", "remaining_time": "2:27:06"}
152
+ {"current_steps": 152, "total_steps": 224, "loss": 0.4403, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "5:06:08", "remaining_time": "2:25:00"}
153
+ {"current_steps": 153, "total_steps": 224, "loss": 0.4392, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "5:08:13", "remaining_time": "2:23:01"}
154
+ {"current_steps": 154, "total_steps": 224, "loss": 0.4384, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "5:10:08", "remaining_time": "2:20:58"}
155
+ {"current_steps": 155, "total_steps": 224, "loss": 0.4426, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "5:12:09", "remaining_time": "2:18:57"}
156
+ {"current_steps": 156, "total_steps": 224, "loss": 0.4573, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "5:14:06", "remaining_time": "2:16:55"}
157
+ {"current_steps": 157, "total_steps": 224, "loss": 0.4525, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "5:16:08", "remaining_time": "2:14:54"}
158
+ {"current_steps": 158, "total_steps": 224, "loss": 0.4311, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "5:18:09", "remaining_time": "2:12:54"}
159
+ {"current_steps": 159, "total_steps": 224, "loss": 0.4432, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "5:20:05", "remaining_time": "2:10:51"}
160
+ {"current_steps": 160, "total_steps": 224, "loss": 0.4498, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "5:22:08", "remaining_time": "2:08:51"}
161
+ {"current_steps": 161, "total_steps": 224, "loss": 0.4381, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "5:24:13", "remaining_time": "2:06:52"}
162
+ {"current_steps": 162, "total_steps": 224, "loss": 0.436, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "5:26:16", "remaining_time": "2:04:52"}
163
+ {"current_steps": 163, "total_steps": 224, "loss": 0.4614, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "5:28:17", "remaining_time": "2:02:51"}
164
+ {"current_steps": 164, "total_steps": 224, "loss": 0.4416, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "5:31:18", "remaining_time": "2:01:12"}
165
+ {"current_steps": 165, "total_steps": 224, "loss": 0.4141, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "5:33:18", "remaining_time": "1:59:10"}