sedrickkeh commited on
Commit
5451cfd
·
verified ·
1 Parent(s): 25d39b8

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fc14ad1d8594a5f42a89a5498dcc79153ff5ac22e224ea6881e36b3ae6b71e4
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eefeb1622bf04f1779212c86ab94fb04dbf3cb073ac2aca70c2f858cbfda77fa
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15fc54a2771dc75d5de6ccb1e8de307e35236f3fd6a6f3c8c7f6b736b0b778fc
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f355a0bec623fbb366e26ee1517c861b2a4b6c41c695a98f71a115d8bf006e21
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83c4563f79859a977f2a22c953c4afd07e37a19c5af548ab225675552e6daf29
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e57b565641b9f994a173e75ff98c8cafcc23b9843fa5b1d741c6457ee80021e
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29e20838c1c365c119dcf64394ec30dde536842adc19645f2d24d0b5058132af
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e353ae7069737762cd157fa03989f05d46b7452eaebdce17ac93d76bd93fe0e3
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -103,3 +103,52 @@
103
  {"current_steps": 103, "total_steps": 153, "loss": 1.2974, "lr": 2.9419057281939106e-06, "epoch": 2.006482982171799, "percentage": 67.32, "elapsed_time": "1:24:22", "remaining_time": "0:40:57"}
104
  {"current_steps": 104, "total_steps": 153, "loss": 0.7535, "lr": 2.8379629317468604e-06, "epoch": 2.025931928687196, "percentage": 67.97, "elapsed_time": "1:25:17", "remaining_time": "0:40:11"}
105
  {"current_steps": 105, "total_steps": 153, "loss": 0.7966, "lr": 2.7351569841206792e-06, "epoch": 2.0453808752025933, "percentage": 68.63, "elapsed_time": "1:26:02", "remaining_time": "0:39:20"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
103
  {"current_steps": 103, "total_steps": 153, "loss": 1.2974, "lr": 2.9419057281939106e-06, "epoch": 2.006482982171799, "percentage": 67.32, "elapsed_time": "1:24:22", "remaining_time": "0:40:57"}
104
  {"current_steps": 104, "total_steps": 153, "loss": 0.7535, "lr": 2.8379629317468604e-06, "epoch": 2.025931928687196, "percentage": 67.97, "elapsed_time": "1:25:17", "remaining_time": "0:40:11"}
105
  {"current_steps": 105, "total_steps": 153, "loss": 0.7966, "lr": 2.7351569841206792e-06, "epoch": 2.0453808752025933, "percentage": 68.63, "elapsed_time": "1:26:02", "remaining_time": "0:39:20"}
106
+ {"current_steps": 106, "total_steps": 153, "loss": 0.8117, "lr": 2.633541943047334e-06, "epoch": 2.06482982171799, "percentage": 69.28, "elapsed_time": "1:27:02", "remaining_time": "0:38:35"}
107
+ {"current_steps": 107, "total_steps": 153, "loss": 0.8327, "lr": 2.53317124005273e-06, "epoch": 2.0842787682333874, "percentage": 69.93, "elapsed_time": "1:27:54", "remaining_time": "0:37:47"}
108
+ {"current_steps": 108, "total_steps": 153, "loss": 0.7766, "lr": 2.4340976523611957e-06, "epoch": 2.1037277147487843, "percentage": 70.59, "elapsed_time": "1:28:41", "remaining_time": "0:36:57"}
109
+ {"current_steps": 109, "total_steps": 153, "loss": 0.7372, "lr": 2.3363732751439926e-06, "epoch": 2.1231766612641816, "percentage": 71.24, "elapsed_time": "1:29:21", "remaining_time": "0:36:04"}
110
+ {"current_steps": 110, "total_steps": 153, "loss": 0.7629, "lr": 2.240049494126479e-06, "epoch": 2.1426256077795784, "percentage": 71.9, "elapsed_time": "1:30:10", "remaining_time": "0:35:15"}
111
+ {"current_steps": 111, "total_steps": 153, "loss": 0.6913, "lr": 2.1451769585683196e-06, "epoch": 2.1620745542949757, "percentage": 72.55, "elapsed_time": "1:30:53", "remaining_time": "0:34:23"}
112
+ {"current_steps": 112, "total_steps": 153, "loss": 0.8875, "lr": 2.0518055546309362e-06, "epoch": 2.1815235008103726, "percentage": 73.2, "elapsed_time": "1:31:49", "remaining_time": "0:33:36"}
113
+ {"current_steps": 113, "total_steps": 153, "loss": 0.8202, "lr": 1.9599843791462123e-06, "epoch": 2.20097244732577, "percentage": 73.86, "elapsed_time": "1:32:40", "remaining_time": "0:32:48"}
114
+ {"current_steps": 114, "total_steps": 153, "loss": 0.6574, "lr": 1.8697617138002545e-06, "epoch": 2.2204213938411668, "percentage": 74.51, "elapsed_time": "1:33:28", "remaining_time": "0:31:58"}
115
+ {"current_steps": 115, "total_steps": 153, "loss": 0.766, "lr": 1.7811849997457681e-06, "epoch": 2.239870340356564, "percentage": 75.16, "elapsed_time": "1:34:13", "remaining_time": "0:31:08"}
116
+ {"current_steps": 116, "total_steps": 153, "loss": 0.86, "lr": 1.6943008126564164e-06, "epoch": 2.259319286871961, "percentage": 75.82, "elapsed_time": "1:35:06", "remaining_time": "0:30:20"}
117
+ {"current_steps": 117, "total_steps": 153, "loss": 0.7715, "lr": 1.609154838236246e-06, "epoch": 2.2787682333873582, "percentage": 76.47, "elapsed_time": "1:35:56", "remaining_time": "0:29:31"}
118
+ {"current_steps": 118, "total_steps": 153, "loss": 0.7503, "lr": 1.5257918481971028e-06, "epoch": 2.298217179902755, "percentage": 77.12, "elapsed_time": "1:36:44", "remaining_time": "0:28:41"}
119
+ {"current_steps": 119, "total_steps": 153, "loss": 0.7868, "lr": 1.4442556767166371e-06, "epoch": 2.3176661264181524, "percentage": 77.78, "elapsed_time": "1:37:35", "remaining_time": "0:27:53"}
120
+ {"current_steps": 120, "total_steps": 153, "loss": 0.7287, "lr": 1.3645891973892772e-06, "epoch": 2.3371150729335493, "percentage": 78.43, "elapsed_time": "1:38:31", "remaining_time": "0:27:05"}
121
+ {"current_steps": 121, "total_steps": 153, "loss": 0.7135, "lr": 1.2868343006823113e-06, "epoch": 2.3565640194489466, "percentage": 79.08, "elapsed_time": "1:39:18", "remaining_time": "0:26:15"}
122
+ {"current_steps": 122, "total_steps": 153, "loss": 0.8523, "lr": 1.211031871908916e-06, "epoch": 2.3760129659643434, "percentage": 79.74, "elapsed_time": "1:40:07", "remaining_time": "0:25:26"}
123
+ {"current_steps": 123, "total_steps": 153, "loss": 0.7157, "lr": 1.137221769729725e-06, "epoch": 2.3954619124797407, "percentage": 80.39, "elapsed_time": "1:40:56", "remaining_time": "0:24:37"}
124
+ {"current_steps": 124, "total_steps": 153, "loss": 0.8451, "lr": 1.065442805194214e-06, "epoch": 2.4149108589951376, "percentage": 81.05, "elapsed_time": "1:41:46", "remaining_time": "0:23:48"}
125
+ {"current_steps": 125, "total_steps": 153, "loss": 0.7459, "lr": 9.957327213329687e-07, "epoch": 2.434359805510535, "percentage": 81.7, "elapsed_time": "1:42:29", "remaining_time": "0:22:57"}
126
+ {"current_steps": 126, "total_steps": 153, "loss": 0.8074, "lr": 9.281281733115288e-07, "epoch": 2.4538087520259317, "percentage": 82.35, "elapsed_time": "1:43:21", "remaining_time": "0:22:08"}
127
+ {"current_steps": 127, "total_steps": 153, "loss": 0.7581, "lr": 8.626647091562612e-07, "epoch": 2.473257698541329, "percentage": 83.01, "elapsed_time": "1:44:04", "remaining_time": "0:21:18"}
128
+ {"current_steps": 128, "total_steps": 153, "loss": 0.761, "lr": 7.993767510623834e-07, "epoch": 2.492706645056726, "percentage": 83.66, "elapsed_time": "1:44:54", "remaining_time": "0:20:29"}
129
+ {"current_steps": 129, "total_steps": 153, "loss": 0.783, "lr": 7.382975772939866e-07, "epoch": 2.512155591572123, "percentage": 84.31, "elapsed_time": "1:45:41", "remaining_time": "0:19:39"}
130
+ {"current_steps": 130, "total_steps": 153, "loss": 0.7739, "lr": 6.794593046855613e-07, "epoch": 2.53160453808752, "percentage": 84.97, "elapsed_time": "1:46:26", "remaining_time": "0:18:49"}
131
+ {"current_steps": 131, "total_steps": 153, "loss": 0.7713, "lr": 6.228928717542205e-07, "epoch": 2.5510534846029174, "percentage": 85.62, "elapsed_time": "1:47:11", "remaining_time": "0:18:00"}
132
+ {"current_steps": 132, "total_steps": 153, "loss": 0.7643, "lr": 5.686280224315189e-07, "epoch": 2.5705024311183147, "percentage": 86.27, "elapsed_time": "1:47:55", "remaining_time": "0:17:10"}
133
+ {"current_steps": 133, "total_steps": 153, "loss": 0.8228, "lr": 5.166932904234101e-07, "epoch": 2.5899513776337115, "percentage": 86.93, "elapsed_time": "1:48:48", "remaining_time": "0:16:21"}
134
+ {"current_steps": 134, "total_steps": 153, "loss": 0.8042, "lr": 4.671159842065698e-07, "epoch": 2.6094003241491084, "percentage": 87.58, "elapsed_time": "1:49:31", "remaining_time": "0:15:31"}
135
+ {"current_steps": 135, "total_steps": 153, "loss": 0.6469, "lr": 4.199221726689634e-07, "epoch": 2.6288492706645057, "percentage": 88.24, "elapsed_time": "1:50:10", "remaining_time": "0:14:41"}
136
+ {"current_steps": 136, "total_steps": 153, "loss": 0.84, "lr": 3.751366714022342e-07, "epoch": 2.648298217179903, "percentage": 88.89, "elapsed_time": "1:51:05", "remaining_time": "0:13:53"}
137
+ {"current_steps": 137, "total_steps": 153, "loss": 0.8341, "lr": 3.3278302965308593e-07, "epoch": 2.6677471636953, "percentage": 89.54, "elapsed_time": "1:51:56", "remaining_time": "0:13:04"}
138
+ {"current_steps": 138, "total_steps": 153, "loss": 0.7816, "lr": 2.928835179405548e-07, "epoch": 2.6871961102106967, "percentage": 90.2, "elapsed_time": "1:52:44", "remaining_time": "0:12:15"}
139
+ {"current_steps": 139, "total_steps": 153, "loss": 0.7624, "lr": 2.5545911634565266e-07, "epoch": 2.706645056726094, "percentage": 90.85, "elapsed_time": "1:53:29", "remaining_time": "0:11:25"}
140
+ {"current_steps": 140, "total_steps": 153, "loss": 0.7452, "lr": 2.205295034795596e-07, "epoch": 2.7260940032414913, "percentage": 91.5, "elapsed_time": "1:54:08", "remaining_time": "0:10:35"}
141
+ {"current_steps": 141, "total_steps": 153, "loss": 0.7443, "lr": 1.881130461361591e-07, "epoch": 2.745542949756888, "percentage": 92.16, "elapsed_time": "1:54:54", "remaining_time": "0:09:46"}
142
+ {"current_steps": 142, "total_steps": 153, "loss": 0.8023, "lr": 1.5822678963435479e-07, "epoch": 2.764991896272285, "percentage": 92.81, "elapsed_time": "1:55:43", "remaining_time": "0:08:57"}
143
+ {"current_steps": 143, "total_steps": 153, "loss": 0.7411, "lr": 1.3088644885524637e-07, "epoch": 2.7844408427876823, "percentage": 93.46, "elapsed_time": "1:56:26", "remaining_time": "0:08:08"}
144
+ {"current_steps": 144, "total_steps": 153, "loss": 0.742, "lr": 1.0610639997888917e-07, "epoch": 2.8038897893030796, "percentage": 94.12, "elapsed_time": "1:57:06", "remaining_time": "0:07:19"}
145
+ {"current_steps": 145, "total_steps": 153, "loss": 0.7157, "lr": 8.38996729249636e-08, "epoch": 2.8233387358184765, "percentage": 94.77, "elapsed_time": "1:57:49", "remaining_time": "0:06:30"}
146
+ {"current_steps": 146, "total_steps": 153, "loss": 0.8331, "lr": 6.427794450134529e-08, "epoch": 2.8427876823338734, "percentage": 95.42, "elapsed_time": "1:58:47", "remaining_time": "0:05:41"}
147
+ {"current_steps": 147, "total_steps": 153, "loss": 0.9018, "lr": 4.72515322641709e-08, "epoch": 2.8622366288492707, "percentage": 96.08, "elapsed_time": "1:59:38", "remaining_time": "0:04:53"}
148
+ {"current_steps": 148, "total_steps": 153, "loss": 0.6865, "lr": 3.282938909263122e-08, "epoch": 2.881685575364668, "percentage": 96.73, "elapsed_time": "2:00:23", "remaining_time": "0:04:04"}
149
+ {"current_steps": 149, "total_steps": 153, "loss": 0.7197, "lr": 2.101909848133743e-08, "epoch": 2.901134521880065, "percentage": 97.39, "elapsed_time": "2:01:09", "remaining_time": "0:03:15"}
150
+ {"current_steps": 150, "total_steps": 153, "loss": 0.8062, "lr": 1.1826870552749669e-08, "epoch": 2.9205834683954617, "percentage": 98.04, "elapsed_time": "2:01:53", "remaining_time": "0:02:26"}
151
+ {"current_steps": 151, "total_steps": 153, "loss": 0.799, "lr": 5.257538791749173e-09, "epoch": 2.940032414910859, "percentage": 98.69, "elapsed_time": "2:02:45", "remaining_time": "0:01:37"}
152
+ {"current_steps": 152, "total_steps": 153, "loss": 0.8033, "lr": 1.3145575040801605e-09, "epoch": 2.9594813614262563, "percentage": 99.35, "elapsed_time": "2:03:30", "remaining_time": "0:00:48"}
153
+ {"current_steps": 153, "total_steps": 153, "loss": 0.6416, "lr": 0.0, "epoch": 2.978930307941653, "percentage": 100.0, "elapsed_time": "2:04:12", "remaining_time": "0:00:00"}
154
+ {"current_steps": 153, "total_steps": 153, "epoch": 2.978930307941653, "percentage": 100.0, "elapsed_time": "2:06:23", "remaining_time": "0:00:00"}