ryanmarten commited on
Commit
b78bc99
·
verified ·
1 Parent(s): 6870f95

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 sha256:593321960daa12b162ac5140b7dcfa83770169f0715a73cec195dac9460deb9e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fabeea2d668926248f9b6fd0dba8076134b7bddde836df01948eda350e3216a0
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:f54a5c8a4f639c223109869f2ff5e06bcafb915321c7a17d03af97251e8091f0
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f1b399dd222340f5d9df3b4df5fabbee7b4adf35b77c958fb4fc2513d28930
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:b6bfbafbb641f149c69d3196d9920cd3ab6a01bc87928fe19a1ea125ccab9f4b
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587158020dfb15f555e9d4f64eeee07e1fe549578589d03d924008cfe2067d09
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:f83d309b2251586a1b2545cd87c000644fa02d6c554902e7c8522b09921257bb
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704cccdaa986fb537e898b140453cd3ca2ff347c3a56c308f8fba1b5a1feea44
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -196,3 +196,30 @@
196
  {"current_steps": 196, "total_steps": 224, "loss": 0.2226, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "4:18:40", "remaining_time": "0:36:57"}
197
  {"current_steps": 197, "total_steps": 224, "loss": 0.1676, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "4:21:03", "remaining_time": "0:35:46"}
198
  {"current_steps": 198, "total_steps": 224, "loss": 0.2649, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "4:22:38", "remaining_time": "0:34:29"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
196
  {"current_steps": 196, "total_steps": 224, "loss": 0.2226, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "4:18:40", "remaining_time": "0:36:57"}
197
  {"current_steps": 197, "total_steps": 224, "loss": 0.1676, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "4:21:03", "remaining_time": "0:35:46"}
198
  {"current_steps": 198, "total_steps": 224, "loss": 0.2649, "lr": 8.144031414842012e-07, "epoch": 6.060759493670886, "percentage": 88.39, "elapsed_time": "4:22:38", "remaining_time": "0:34:29"}
199
+ {"current_steps": 199, "total_steps": 224, "loss": 0.262, "lr": 7.537457234218271e-07, "epoch": 6.091139240506329, "percentage": 88.84, "elapsed_time": "4:24:12", "remaining_time": "0:33:11"}
200
+ {"current_steps": 200, "total_steps": 224, "loss": 0.2169, "lr": 6.953470369291349e-07, "epoch": 6.121518987341772, "percentage": 89.29, "elapsed_time": "4:25:26", "remaining_time": "0:31:51"}
201
+ {"current_steps": 201, "total_steps": 224, "loss": 0.2349, "lr": 6.392213479945852e-07, "epoch": 6.151898734177215, "percentage": 89.73, "elapsed_time": "4:26:48", "remaining_time": "0:30:31"}
202
+ {"current_steps": 202, "total_steps": 224, "loss": 0.1852, "lr": 5.853823673448877e-07, "epoch": 6.182278481012658, "percentage": 90.18, "elapsed_time": "4:28:03", "remaining_time": "0:29:11"}
203
+ {"current_steps": 203, "total_steps": 224, "loss": 0.2287, "lr": 5.33843247095659e-07, "epoch": 6.2126582278481015, "percentage": 90.62, "elapsed_time": "4:29:33", "remaining_time": "0:27:53"}
204
+ {"current_steps": 204, "total_steps": 224, "loss": 0.2074, "lr": 4.846165775385459e-07, "epoch": 6.243037974683545, "percentage": 91.07, "elapsed_time": "4:31:00", "remaining_time": "0:26:34"}
205
+ {"current_steps": 205, "total_steps": 224, "loss": 0.2333, "lr": 4.3771438406559173e-07, "epoch": 6.273417721518987, "percentage": 91.52, "elapsed_time": "4:32:30", "remaining_time": "0:25:15"}
206
+ {"current_steps": 206, "total_steps": 224, "loss": 0.1976, "lr": 3.931481242315993e-07, "epoch": 6.30379746835443, "percentage": 91.96, "elapsed_time": "4:33:52", "remaining_time": "0:23:55"}
207
+ {"current_steps": 207, "total_steps": 224, "loss": 0.1904, "lr": 3.5092868495520294e-07, "epoch": 6.334177215189873, "percentage": 92.41, "elapsed_time": "4:35:15", "remaining_time": "0:22:36"}
208
+ {"current_steps": 208, "total_steps": 224, "loss": 0.225, "lr": 3.110663798593616e-07, "epoch": 6.364556962025317, "percentage": 92.86, "elapsed_time": "4:36:37", "remaining_time": "0:21:16"}
209
+ {"current_steps": 209, "total_steps": 224, "loss": 0.1904, "lr": 2.735709467518699e-07, "epoch": 6.39493670886076, "percentage": 93.3, "elapsed_time": "4:37:56", "remaining_time": "0:19:56"}
210
+ {"current_steps": 210, "total_steps": 224, "loss": 0.2034, "lr": 2.384515452465475e-07, "epoch": 6.425316455696202, "percentage": 93.75, "elapsed_time": "4:39:08", "remaining_time": "0:18:36"}
211
+ {"current_steps": 211, "total_steps": 224, "loss": 0.2876, "lr": 2.0571675452567997e-07, "epoch": 6.455696202531645, "percentage": 94.2, "elapsed_time": "4:40:34", "remaining_time": "0:17:17"}
212
+ {"current_steps": 212, "total_steps": 224, "loss": 0.247, "lr": 1.7537457124423896e-07, "epoch": 6.4860759493670885, "percentage": 94.64, "elapsed_time": "4:42:07", "remaining_time": "0:15:58"}
213
+ {"current_steps": 213, "total_steps": 224, "loss": 0.2189, "lr": 1.474324075764111e-07, "epoch": 6.516455696202532, "percentage": 95.09, "elapsed_time": "4:43:27", "remaining_time": "0:14:38"}
214
+ {"current_steps": 214, "total_steps": 224, "loss": 0.2168, "lr": 1.2189708940490653e-07, "epoch": 6.546835443037975, "percentage": 95.54, "elapsed_time": "4:44:44", "remaining_time": "0:13:18"}
215
+ {"current_steps": 215, "total_steps": 224, "loss": 0.1432, "lr": 9.877485465349057e-08, "epoch": 6.577215189873417, "percentage": 95.98, "elapsed_time": "4:45:43", "remaining_time": "0:11:57"}
216
+ {"current_steps": 216, "total_steps": 224, "loss": 0.2058, "lr": 7.807135176314707e-08, "epoch": 6.6075949367088604, "percentage": 96.43, "elapsed_time": "4:46:53", "remaining_time": "0:10:37"}
217
+ {"current_steps": 217, "total_steps": 224, "loss": 0.2248, "lr": 5.979163831223988e-08, "epoch": 6.637974683544304, "percentage": 96.88, "elapsed_time": "4:48:02", "remaining_time": "0:09:17"}
218
+ {"current_steps": 218, "total_steps": 224, "loss": 0.1879, "lr": 4.394017978101905e-08, "epoch": 6.668354430379747, "percentage": 97.32, "elapsed_time": "4:49:05", "remaining_time": "0:07:57"}
219
+ {"current_steps": 219, "total_steps": 224, "loss": 0.1625, "lr": 3.0520848460765525e-08, "epoch": 6.69873417721519, "percentage": 97.77, "elapsed_time": "4:50:13", "remaining_time": "0:06:37"}
220
+ {"current_steps": 220, "total_steps": 224, "loss": 0.2155, "lr": 1.9536922507841227e-08, "epoch": 6.729113924050633, "percentage": 98.21, "elapsed_time": "4:51:24", "remaining_time": "0:05:17"}
221
+ {"current_steps": 221, "total_steps": 224, "loss": 0.1992, "lr": 1.099108514288627e-08, "epoch": 6.759493670886076, "percentage": 98.66, "elapsed_time": "4:52:36", "remaining_time": "0:03:58"}
222
+ {"current_steps": 222, "total_steps": 224, "loss": 0.1576, "lr": 4.885423995341088e-09, "epoch": 6.789873417721519, "percentage": 99.11, "elapsed_time": "4:53:40", "remaining_time": "0:02:38"}
223
+ {"current_steps": 223, "total_steps": 224, "loss": 0.2295, "lr": 1.2214305934699078e-09, "epoch": 6.820253164556962, "percentage": 99.55, "elapsed_time": "4:54:57", "remaining_time": "0:01:19"}
224
+ {"current_steps": 224, "total_steps": 224, "loss": 0.1949, "lr": 0.0, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "4:56:14", "remaining_time": "0:00:00"}
225
+ {"current_steps": 224, "total_steps": 224, "epoch": 6.850632911392405, "percentage": 100.0, "elapsed_time": "4:58:24", "remaining_time": "0:00:00"}