ryanmarten commited on
Commit
86449f4
·
verified ·
1 Parent(s): 28f93ed

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 sha256:0169cb22f3dad96085977cced7453ff18954c0c1c840114ff46913382f553e8e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23bc230b55a23c409fc9fcdc3a6bfa93887af7b377ec9fdc626aa5ce99726ad2
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e4fcf19a8ec2c631b30be97697369dd85a373e79b61a20474780c149cbcf082
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93f7535dbabff6c2f106dc7c2f00a91f7dfe60732701e5cc0d3c06ec110b019
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e4b24345098b50f195d82c1ef79a7f89875acb31023ce0e1e8f39de3c58bf77
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f4ff9456ddef2342ad55000fd83bd3c4885229287a60d5c9abdbee333d5d35
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b91c8a58a6e3b46822ce66c98bb5b9d538116a14d1ad96b53fa82b334b72c5b
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf712e1b9038d7e68d3ab791f4b149ffd4966da2095b634bf35f1a87add39da
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -130,3 +130,35 @@
130
  {"current_steps": 130, "total_steps": 224, "loss": 0.5018, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:26:13", "remaining_time": "3:12:29"}
131
  {"current_steps": 131, "total_steps": 224, "loss": 0.4854, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:29:20", "remaining_time": "3:11:12"}
132
  {"current_steps": 132, "total_steps": 224, "loss": 0.4629, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:31:28", "remaining_time": "3:09:12"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
  {"current_steps": 130, "total_steps": 224, "loss": 0.5018, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:26:13", "remaining_time": "3:12:29"}
131
  {"current_steps": 131, "total_steps": 224, "loss": 0.4854, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:29:20", "remaining_time": "3:11:12"}
132
  {"current_steps": 132, "total_steps": 224, "loss": 0.4629, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:31:28", "remaining_time": "3:09:12"}
133
+ {"current_steps": 133, "total_steps": 224, "loss": 0.4672, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "4:33:31", "remaining_time": "3:07:08"}
134
+ {"current_steps": 134, "total_steps": 224, "loss": 0.4474, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "4:35:37", "remaining_time": "3:05:07"}
135
+ {"current_steps": 135, "total_steps": 224, "loss": 0.4557, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "4:37:45", "remaining_time": "3:03:06"}
136
+ {"current_steps": 136, "total_steps": 224, "loss": 0.4482, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "4:39:54", "remaining_time": "3:01:07"}
137
+ {"current_steps": 137, "total_steps": 224, "loss": 0.4431, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "4:42:06", "remaining_time": "2:59:08"}
138
+ {"current_steps": 138, "total_steps": 224, "loss": 0.4622, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "4:44:02", "remaining_time": "2:57:00"}
139
+ {"current_steps": 139, "total_steps": 224, "loss": 0.4281, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "4:46:05", "remaining_time": "2:54:56"}
140
+ {"current_steps": 140, "total_steps": 224, "loss": 0.4452, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "4:48:02", "remaining_time": "2:52:49"}
141
+ {"current_steps": 141, "total_steps": 224, "loss": 0.4518, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "4:50:07", "remaining_time": "2:50:46"}
142
+ {"current_steps": 142, "total_steps": 224, "loss": 0.4558, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "4:52:11", "remaining_time": "2:48:43"}
143
+ {"current_steps": 143, "total_steps": 224, "loss": 0.4536, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "4:54:07", "remaining_time": "2:46:36"}
144
+ {"current_steps": 144, "total_steps": 224, "loss": 0.4288, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "4:56:01", "remaining_time": "2:44:27"}
145
+ {"current_steps": 145, "total_steps": 224, "loss": 0.4552, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "4:57:56", "remaining_time": "2:42:19"}
146
+ {"current_steps": 146, "total_steps": 224, "loss": 0.4445, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "4:59:57", "remaining_time": "2:40:14"}
147
+ {"current_steps": 147, "total_steps": 224, "loss": 0.457, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "5:01:59", "remaining_time": "2:38:11"}
148
+ {"current_steps": 148, "total_steps": 224, "loss": 0.4538, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "5:04:01", "remaining_time": "2:36:07"}
149
+ {"current_steps": 149, "total_steps": 224, "loss": 0.4462, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "5:06:04", "remaining_time": "2:34:03"}
150
+ {"current_steps": 150, "total_steps": 224, "loss": 0.4528, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "5:08:09", "remaining_time": "2:32:01"}
151
+ {"current_steps": 151, "total_steps": 224, "loss": 0.4256, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "5:10:04", "remaining_time": "2:29:54"}
152
+ {"current_steps": 152, "total_steps": 224, "loss": 0.4484, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "5:12:03", "remaining_time": "2:27:48"}
153
+ {"current_steps": 153, "total_steps": 224, "loss": 0.4247, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "5:14:10", "remaining_time": "2:25:47"}
154
+ {"current_steps": 154, "total_steps": 224, "loss": 0.4471, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "5:16:07", "remaining_time": "2:23:41"}
155
+ {"current_steps": 155, "total_steps": 224, "loss": 0.4642, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "5:18:19", "remaining_time": "2:21:42"}
156
+ {"current_steps": 156, "total_steps": 224, "loss": 0.4571, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "5:20:20", "remaining_time": "2:19:38"}
157
+ {"current_steps": 157, "total_steps": 224, "loss": 0.4564, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "5:22:21", "remaining_time": "2:17:33"}
158
+ {"current_steps": 158, "total_steps": 224, "loss": 0.4353, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "5:24:14", "remaining_time": "2:15:26"}
159
+ {"current_steps": 159, "total_steps": 224, "loss": 0.4221, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "5:26:13", "remaining_time": "2:13:21"}
160
+ {"current_steps": 160, "total_steps": 224, "loss": 0.4294, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "5:28:14", "remaining_time": "2:11:17"}
161
+ {"current_steps": 161, "total_steps": 224, "loss": 0.4447, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "5:30:13", "remaining_time": "2:09:12"}
162
+ {"current_steps": 162, "total_steps": 224, "loss": 0.4377, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "5:32:21", "remaining_time": "2:07:12"}
163
+ {"current_steps": 163, "total_steps": 224, "loss": 0.4507, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "5:34:19", "remaining_time": "2:05:06"}
164
+ {"current_steps": 164, "total_steps": 224, "loss": 0.436, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "5:37:08", "remaining_time": "2:03:20"}