ryanmarten commited on
Commit
832725c
·
verified ·
1 Parent(s): 23fa9ba

Training in progress, epoch 6

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:beb41790be12caa6600699668968fbc582c9de82d74627ebb87f343812bf2f8c
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38bb63586f3207d41142bf4c9851306ad5e9a265e0186d0ca8776a8cbc899f7
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:b183908b9d17289d3aae02ff77e4db3db48b7c01e9e815f36bcc608335365eaf
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0de0d70bce787a129a9b8d20aec575e44767fb81aedd660afefef4148e51923
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11c29e6d8cca315dc4badea7f09ace44fe45d10f4b2d1e19285bd6fef8a8b478
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df9981c1511c1af4db6492b4f5a213d3a22c7a41fbcc62775b1dcdb02a9e74d
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:763c6461bf6ea231bc3014314d29006f52de74e3ad3aedd30bcf4740ab640c49
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7073364b1ee6871490f90e542ba47ff1010d6a6b1f93cd1f13a9529986fc9bf
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -198,3 +198,30 @@
198
  {"current_steps": 196, "total_steps": 224, "loss": 0.2598, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "5:21:25", "remaining_time": "0:45:55"}
199
  {"current_steps": 197, "total_steps": 224, "loss": 0.2216, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "5:24:00", "remaining_time": "0:44:24"}
200
  {"current_steps": 198, "total_steps": 224, "loss": 0.2205, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "5:25:34", "remaining_time": "0:42:45"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
198
  {"current_steps": 196, "total_steps": 224, "loss": 0.2598, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "5:21:25", "remaining_time": "0:45:55"}
199
  {"current_steps": 197, "total_steps": 224, "loss": 0.2216, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "5:24:00", "remaining_time": "0:44:24"}
200
  {"current_steps": 198, "total_steps": 224, "loss": 0.2205, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "5:25:34", "remaining_time": "0:42:45"}
201
+ {"current_steps": 199, "total_steps": 224, "loss": 0.2209, "lr": 7.537457234218271e-07, "epoch": 6.091139240506329, "percentage": 88.84, "elapsed_time": "5:27:11", "remaining_time": "0:41:06"}
202
+ {"current_steps": 200, "total_steps": 224, "loss": 0.2215, "lr": 6.953470369291349e-07, "epoch": 6.121518987341772, "percentage": 89.29, "elapsed_time": "5:28:50", "remaining_time": "0:39:27"}
203
+ {"current_steps": 201, "total_steps": 224, "loss": 0.2367, "lr": 6.392213479945852e-07, "epoch": 6.151898734177215, "percentage": 89.73, "elapsed_time": "5:30:31", "remaining_time": "0:37:49"}
204
+ {"current_steps": 202, "total_steps": 224, "loss": 0.2233, "lr": 5.853823673448877e-07, "epoch": 6.182278481012658, "percentage": 90.18, "elapsed_time": "5:32:12", "remaining_time": "0:36:10"}
205
+ {"current_steps": 203, "total_steps": 224, "loss": 0.2189, "lr": 5.33843247095659e-07, "epoch": 6.2126582278481015, "percentage": 90.62, "elapsed_time": "5:33:50", "remaining_time": "0:34:32"}
206
+ {"current_steps": 204, "total_steps": 224, "loss": 0.2477, "lr": 4.846165775385459e-07, "epoch": 6.243037974683545, "percentage": 91.07, "elapsed_time": "5:35:26", "remaining_time": "0:32:53"}
207
+ {"current_steps": 205, "total_steps": 224, "loss": 0.2319, "lr": 4.3771438406559173e-07, "epoch": 6.273417721518987, "percentage": 91.52, "elapsed_time": "5:37:13", "remaining_time": "0:31:15"}
208
+ {"current_steps": 206, "total_steps": 224, "loss": 0.2264, "lr": 3.931481242315993e-07, "epoch": 6.30379746835443, "percentage": 91.96, "elapsed_time": "5:39:01", "remaining_time": "0:29:37"}
209
+ {"current_steps": 207, "total_steps": 224, "loss": 0.2139, "lr": 3.5092868495520294e-07, "epoch": 6.334177215189873, "percentage": 92.41, "elapsed_time": "5:40:30", "remaining_time": "0:27:57"}
210
+ {"current_steps": 208, "total_steps": 224, "loss": 0.223, "lr": 3.110663798593616e-07, "epoch": 6.364556962025317, "percentage": 92.86, "elapsed_time": "5:42:14", "remaining_time": "0:26:19"}
211
+ {"current_steps": 209, "total_steps": 224, "loss": 0.2379, "lr": 2.735709467518699e-07, "epoch": 6.39493670886076, "percentage": 93.3, "elapsed_time": "5:43:52", "remaining_time": "0:24:40"}
212
+ {"current_steps": 210, "total_steps": 224, "loss": 0.2266, "lr": 2.384515452465475e-07, "epoch": 6.425316455696202, "percentage": 93.75, "elapsed_time": "5:45:12", "remaining_time": "0:23:00"}
213
+ {"current_steps": 211, "total_steps": 224, "loss": 0.218, "lr": 2.0571675452567997e-07, "epoch": 6.455696202531645, "percentage": 94.2, "elapsed_time": "5:46:45", "remaining_time": "0:21:21"}
214
+ {"current_steps": 212, "total_steps": 224, "loss": 0.229, "lr": 1.7537457124423896e-07, "epoch": 6.4860759493670885, "percentage": 94.64, "elapsed_time": "5:48:29", "remaining_time": "0:19:43"}
215
+ {"current_steps": 213, "total_steps": 224, "loss": 0.2433, "lr": 1.474324075764111e-07, "epoch": 6.516455696202532, "percentage": 95.09, "elapsed_time": "5:50:06", "remaining_time": "0:18:04"}
216
+ {"current_steps": 214, "total_steps": 224, "loss": 0.2447, "lr": 1.2189708940490653e-07, "epoch": 6.546835443037975, "percentage": 95.54, "elapsed_time": "5:51:49", "remaining_time": "0:16:26"}
217
+ {"current_steps": 215, "total_steps": 224, "loss": 0.2064, "lr": 9.877485465349057e-08, "epoch": 6.577215189873417, "percentage": 95.98, "elapsed_time": "5:53:17", "remaining_time": "0:14:47"}
218
+ {"current_steps": 216, "total_steps": 224, "loss": 0.2327, "lr": 7.807135176314707e-08, "epoch": 6.6075949367088604, "percentage": 96.43, "elapsed_time": "5:55:04", "remaining_time": "0:13:09"}
219
+ {"current_steps": 217, "total_steps": 224, "loss": 0.2425, "lr": 5.979163831223988e-08, "epoch": 6.637974683544304, "percentage": 96.88, "elapsed_time": "5:56:37", "remaining_time": "0:11:30"}
220
+ {"current_steps": 218, "total_steps": 224, "loss": 0.2147, "lr": 4.394017978101905e-08, "epoch": 6.668354430379747, "percentage": 97.32, "elapsed_time": "5:58:15", "remaining_time": "0:09:51"}
221
+ {"current_steps": 219, "total_steps": 224, "loss": 0.2333, "lr": 3.0520848460765525e-08, "epoch": 6.69873417721519, "percentage": 97.77, "elapsed_time": "5:59:59", "remaining_time": "0:08:13"}
222
+ {"current_steps": 220, "total_steps": 224, "loss": 0.2595, "lr": 1.9536922507841227e-08, "epoch": 6.729113924050633, "percentage": 98.21, "elapsed_time": "6:01:37", "remaining_time": "0:06:34"}
223
+ {"current_steps": 221, "total_steps": 224, "loss": 0.2122, "lr": 1.099108514288627e-08, "epoch": 6.759493670886076, "percentage": 98.66, "elapsed_time": "6:03:04", "remaining_time": "0:04:55"}
224
+ {"current_steps": 222, "total_steps": 224, "loss": 0.2174, "lr": 4.885423995341088e-09, "epoch": 6.789873417721519, "percentage": 99.11, "elapsed_time": "6:04:34", "remaining_time": "0:03:17"}
225
+ {"current_steps": 223, "total_steps": 224, "loss": 0.2415, "lr": 1.2214305934699078e-09, "epoch": 6.820253164556962, "percentage": 99.55, "elapsed_time": "6:06:11", "remaining_time": "0:01:38"}
226
+ {"current_steps": 224, "total_steps": 224, "loss": 0.2494, "lr": 0.0, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "6:07:43", "remaining_time": "0:00:00"}
227
+ {"current_steps": 224, "total_steps": 224, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "6:09:39", "remaining_time": "0:00:00"}