neginr commited on
Commit
ae143ef
·
verified ·
1 Parent(s): efa1155

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:d968706c0cbfea8b57dcddb57f911b98e41cf52578d243c6cbf0293679cf5f1d
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:670d9126428bfcdb949903a56be5c67c9d261563c0af4fb33c554c849d5a1e87
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:e14ad7269dc876aca26017f335dbcf2dcdcb23e7748dce30f8705d8259538fff
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a958c1e172793645acdc164734a060ae3862334f824dc122cc04eb1b34b0b3ec
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:b9c836a79b528007d071b1c04899130b7932935d5fc092e7bdb86315c5814e35
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d3a69345ffea57da8aba2c06baa914669541ab0c69a7aef02cbc9f12cc4d81d
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bebfed837af877d5462afe1d8815c717536a23ab35150f4ca619665fb3cbe77
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d1eeb4040c613b1e788d703d2025d225ab755d9efe928fbae059cd309aff911
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -118,3 +118,31 @@
118
  {"current_steps": 116, "total_steps": 145, "loss": 0.5628, "lr": 9.427371178166065e-06, "epoch": 3.968684759916493, "percentage": 80.0, "elapsed_time": "0:46:50", "remaining_time": "0:11:42"}
119
  {"current_steps": 117, "total_steps": 145, "loss": 0.5657, "lr": 8.81302583747111e-06, "epoch": 4.002087682672234, "percentage": 80.69, "elapsed_time": "0:50:27", "remaining_time": "0:12:04"}
120
  {"current_steps": 118, "total_steps": 145, "loss": 0.5431, "lr": 8.216892811449834e-06, "epoch": 4.035490605427975, "percentage": 81.38, "elapsed_time": "0:52:08", "remaining_time": "0:11:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
118
  {"current_steps": 116, "total_steps": 145, "loss": 0.5628, "lr": 9.427371178166065e-06, "epoch": 3.968684759916493, "percentage": 80.0, "elapsed_time": "0:46:50", "remaining_time": "0:11:42"}
119
  {"current_steps": 117, "total_steps": 145, "loss": 0.5657, "lr": 8.81302583747111e-06, "epoch": 4.002087682672234, "percentage": 80.69, "elapsed_time": "0:50:27", "remaining_time": "0:12:04"}
120
  {"current_steps": 118, "total_steps": 145, "loss": 0.5431, "lr": 8.216892811449834e-06, "epoch": 4.035490605427975, "percentage": 81.38, "elapsed_time": "0:52:08", "remaining_time": "0:11:55"}
121
+ {"current_steps": 119, "total_steps": 145, "loss": 0.5386, "lr": 7.639320225002106e-06, "epoch": 4.068893528183716, "percentage": 82.07, "elapsed_time": "0:53:50", "remaining_time": "0:11:45"}
122
+ {"current_steps": 120, "total_steps": 145, "loss": 0.5341, "lr": 7.080645364253747e-06, "epoch": 4.102296450939457, "percentage": 82.76, "elapsed_time": "0:55:33", "remaining_time": "0:11:34"}
123
+ {"current_steps": 121, "total_steps": 145, "loss": 0.5472, "lr": 6.541194479590931e-06, "epoch": 4.135699373695198, "percentage": 83.45, "elapsed_time": "0:57:15", "remaining_time": "0:11:21"}
124
+ {"current_steps": 122, "total_steps": 145, "loss": 0.5376, "lr": 6.021282595139167e-06, "epoch": 4.16910229645094, "percentage": 84.14, "elapsed_time": "0:58:58", "remaining_time": "0:11:07"}
125
+ {"current_steps": 123, "total_steps": 145, "loss": 0.5405, "lr": 5.521213324798029e-06, "epoch": 4.202505219206681, "percentage": 84.83, "elapsed_time": "1:00:41", "remaining_time": "0:10:51"}
126
+ {"current_steps": 124, "total_steps": 145, "loss": 0.5389, "lr": 5.0412786949392845e-06, "epoch": 4.235908141962422, "percentage": 85.52, "elapsed_time": "1:02:23", "remaining_time": "0:10:34"}
127
+ {"current_steps": 125, "total_steps": 145, "loss": 0.5443, "lr": 4.581758973871609e-06, "epoch": 4.2693110647181625, "percentage": 86.21, "elapsed_time": "1:04:06", "remaining_time": "0:10:15"}
128
+ {"current_steps": 126, "total_steps": 145, "loss": 0.5363, "lr": 4.142922508171849e-06, "epoch": 4.302713987473904, "percentage": 86.9, "elapsed_time": "1:05:51", "remaining_time": "0:09:55"}
129
+ {"current_steps": 127, "total_steps": 145, "loss": 0.5364, "lr": 3.7250255659781844e-06, "epoch": 4.336116910229645, "percentage": 87.59, "elapsed_time": "1:07:35", "remaining_time": "0:09:34"}
130
+ {"current_steps": 128, "total_steps": 145, "loss": 0.5432, "lr": 3.3283121873367043e-06, "epoch": 4.369519832985386, "percentage": 88.28, "elapsed_time": "1:09:17", "remaining_time": "0:09:12"}
131
+ {"current_steps": 129, "total_steps": 145, "loss": 0.5373, "lr": 2.9530140416889465e-06, "epoch": 4.402922755741128, "percentage": 88.97, "elapsed_time": "1:10:59", "remaining_time": "0:08:48"}
132
+ {"current_steps": 130, "total_steps": 145, "loss": 0.5333, "lr": 2.5993502925834115e-06, "epoch": 4.4363256784968685, "percentage": 89.66, "elapsed_time": "1:12:43", "remaining_time": "0:08:23"}
133
+ {"current_steps": 131, "total_steps": 145, "loss": 0.5315, "lr": 2.2675274696902737e-06, "epoch": 4.469728601252609, "percentage": 90.34, "elapsed_time": "1:14:26", "remaining_time": "0:07:57"}
134
+ {"current_steps": 132, "total_steps": 145, "loss": 0.5334, "lr": 1.957739348193859e-06, "epoch": 4.503131524008351, "percentage": 91.03, "elapsed_time": "1:16:10", "remaining_time": "0:07:30"}
135
+ {"current_steps": 133, "total_steps": 145, "loss": 0.5384, "lr": 1.670166835633351e-06, "epoch": 4.536534446764092, "percentage": 91.72, "elapsed_time": "1:17:52", "remaining_time": "0:07:01"}
136
+ {"current_steps": 134, "total_steps": 145, "loss": 0.53, "lr": 1.4049778662579462e-06, "epoch": 4.569937369519833, "percentage": 92.41, "elapsed_time": "1:19:36", "remaining_time": "0:06:32"}
137
+ {"current_steps": 135, "total_steps": 145, "loss": 0.538, "lr": 1.1623273029579195e-06, "epoch": 4.603340292275574, "percentage": 93.1, "elapsed_time": "1:21:18", "remaining_time": "0:06:01"}
138
+ {"current_steps": 136, "total_steps": 145, "loss": 0.541, "lr": 9.423568468291156e-07, "epoch": 4.6367432150313155, "percentage": 93.79, "elapsed_time": "1:23:00", "remaining_time": "0:05:29"}
139
+ {"current_steps": 137, "total_steps": 145, "loss": 0.5379, "lr": 7.451949544234627e-07, "epoch": 4.670146137787056, "percentage": 94.48, "elapsed_time": "1:24:43", "remaining_time": "0:04:56"}
140
+ {"current_steps": 138, "total_steps": 145, "loss": 0.5443, "lr": 5.709567627339674e-07, "epoch": 4.703549060542797, "percentage": 95.17, "elapsed_time": "1:26:26", "remaining_time": "0:04:23"}
141
+ {"current_steps": 139, "total_steps": 145, "loss": 0.535, "lr": 4.1974402195795514e-07, "epoch": 4.736951983298539, "percentage": 95.86, "elapsed_time": "1:28:07", "remaining_time": "0:03:48"}
142
+ {"current_steps": 140, "total_steps": 145, "loss": 0.5333, "lr": 2.916450360778411e-07, "epoch": 4.77035490605428, "percentage": 96.55, "elapsed_time": "1:29:49", "remaining_time": "0:03:12"}
143
+ {"current_steps": 141, "total_steps": 145, "loss": 0.5462, "lr": 1.867346112940549e-07, "epoch": 4.803757828810021, "percentage": 97.24, "elapsed_time": "1:31:30", "remaining_time": "0:02:35"}
144
+ {"current_steps": 142, "total_steps": 145, "loss": 0.5377, "lr": 1.0507401234035819e-07, "epoch": 4.8371607515657615, "percentage": 97.93, "elapsed_time": "1:33:12", "remaining_time": "0:01:58"}
145
+ {"current_steps": 143, "total_steps": 145, "loss": 0.5305, "lr": 4.6710926706934336e-08, "epoch": 4.870563674321503, "percentage": 98.62, "elapsed_time": "1:34:54", "remaining_time": "0:01:19"}
146
+ {"current_steps": 144, "total_steps": 145, "loss": 0.54, "lr": 1.1679436792282339e-08, "epoch": 4.903966597077244, "percentage": 99.31, "elapsed_time": "1:36:36", "remaining_time": "0:00:40"}
147
+ {"current_steps": 145, "total_steps": 145, "loss": 0.54, "lr": 0.0, "epoch": 4.937369519832985, "percentage": 100.0, "elapsed_time": "1:38:18", "remaining_time": "0:00:00"}
148
+ {"current_steps": 145, "total_steps": 145, "epoch": 4.937369519832985, "percentage": 100.0, "elapsed_time": "1:41:17", "remaining_time": "0:00:00"}