neginr commited on
Commit
3b0f27a
·
verified ·
1 Parent(s): ca9993d

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4fd2f8d9d156f2fe9f4ffa68e9185b1799c3ccf263172d07487a87697827b97
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f35c8e73f45ebb07ca167e64bf417b1bacafc8bf0cb0d37aef7b2840451b968
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:cc2318b37bcef8e13e2e08212e8325a343a838a2e4b41f1cfdfef719329638c1
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0419b8f1c2728733b43dd2d11da5895e81a3f45ef19a7ffe43d205e3c4581d
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:360723db3185f51c40f6e85f7271941aa4d69dc97f9e84b5879b39eb8e2f6cce
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3513940c0002790f8c0bc3085376fc8d9423c1c4bd7f5cd075a5d1fc4622deb5
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e78cdebb2a9c7ce2895ae9c756579e1e8471427a73e3fe9da6b1e63b31cf803
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:476c1fd381d61c64f7a2a59a464bff80bd68e6d1c9746b5b4b6aff5dad5ed4df
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -198,3 +198,62 @@
198
  {"current_steps": 176, "total_steps": 295, "loss": 0.5425, "lr": 3.3625557941175145e-05, "epoch": 2.980972515856237, "percentage": 59.66, "elapsed_time": "1:39:09", "remaining_time": "1:07:02"}
199
  {"current_steps": 177, "total_steps": 295, "loss": 0.5353, "lr": 3.3157874312646324e-05, "epoch": 2.997885835095137, "percentage": 60.0, "elapsed_time": "1:40:51", "remaining_time": "1:07:14"}
200
  {"current_steps": 178, "total_steps": 295, "loss": 0.5039, "lr": 3.2691152283019707e-05, "epoch": 3.014799154334038, "percentage": 60.34, "elapsed_time": "1:44:24", "remaining_time": "1:08:37"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
198
  {"current_steps": 176, "total_steps": 295, "loss": 0.5425, "lr": 3.3625557941175145e-05, "epoch": 2.980972515856237, "percentage": 59.66, "elapsed_time": "1:39:09", "remaining_time": "1:07:02"}
199
  {"current_steps": 177, "total_steps": 295, "loss": 0.5353, "lr": 3.3157874312646324e-05, "epoch": 2.997885835095137, "percentage": 60.0, "elapsed_time": "1:40:51", "remaining_time": "1:07:14"}
200
  {"current_steps": 178, "total_steps": 295, "loss": 0.5039, "lr": 3.2691152283019707e-05, "epoch": 3.014799154334038, "percentage": 60.34, "elapsed_time": "1:44:24", "remaining_time": "1:08:37"}
201
+ {"current_steps": 179, "total_steps": 295, "loss": 0.5005, "lr": 3.2225457445856704e-05, "epoch": 3.031712473572939, "percentage": 60.68, "elapsed_time": "1:46:06", "remaining_time": "1:08:45"}
202
+ {"current_steps": 180, "total_steps": 295, "loss": 0.4999, "lr": 3.176085525035607e-05, "epoch": 3.048625792811839, "percentage": 61.02, "elapsed_time": "1:47:49", "remaining_time": "1:08:53"}
203
+ {"current_steps": 181, "total_steps": 295, "loss": 0.4967, "lr": 3.1297410992155695e-05, "epoch": 3.06553911205074, "percentage": 61.36, "elapsed_time": "1:49:32", "remaining_time": "1:08:59"}
204
+ {"current_steps": 182, "total_steps": 295, "loss": 0.494, "lr": 3.083518980415584e-05, "epoch": 3.0824524312896404, "percentage": 61.69, "elapsed_time": "1:51:14", "remaining_time": "1:09:04"}
205
+ {"current_steps": 183, "total_steps": 295, "loss": 0.5016, "lr": 3.0374256647365273e-05, "epoch": 3.0993657505285412, "percentage": 62.03, "elapsed_time": "1:52:56", "remaining_time": "1:09:07"}
206
+ {"current_steps": 184, "total_steps": 295, "loss": 0.4959, "lr": 2.9914676301771667e-05, "epoch": 3.116279069767442, "percentage": 62.37, "elapsed_time": "1:54:38", "remaining_time": "1:09:09"}
207
+ {"current_steps": 185, "total_steps": 295, "loss": 0.492, "lr": 2.9456513357237305e-05, "epoch": 3.1331923890063424, "percentage": 62.71, "elapsed_time": "1:56:20", "remaining_time": "1:09:10"}
208
+ {"current_steps": 186, "total_steps": 295, "loss": 0.4957, "lr": 2.8999832204421533e-05, "epoch": 3.1501057082452433, "percentage": 63.05, "elapsed_time": "1:58:01", "remaining_time": "1:09:09"}
209
+ {"current_steps": 187, "total_steps": 295, "loss": 0.4938, "lr": 2.8544697025731312e-05, "epoch": 3.1670190274841437, "percentage": 63.39, "elapsed_time": "1:59:43", "remaining_time": "1:09:08"}
210
+ {"current_steps": 188, "total_steps": 295, "loss": 0.4936, "lr": 2.809117178630089e-05, "epoch": 3.1839323467230445, "percentage": 63.73, "elapsed_time": "2:01:27", "remaining_time": "1:09:07"}
211
+ {"current_steps": 189, "total_steps": 295, "loss": 0.4939, "lr": 2.7639320225002108e-05, "epoch": 3.200845665961945, "percentage": 64.07, "elapsed_time": "2:03:10", "remaining_time": "1:09:05"}
212
+ {"current_steps": 190, "total_steps": 295, "loss": 0.4919, "lr": 2.7189205845486503e-05, "epoch": 3.2177589852008457, "percentage": 64.41, "elapsed_time": "2:04:53", "remaining_time": "1:09:00"}
213
+ {"current_steps": 191, "total_steps": 295, "loss": 0.4945, "lr": 2.674089190726039e-05, "epoch": 3.234672304439746, "percentage": 64.75, "elapsed_time": "2:06:36", "remaining_time": "1:08:56"}
214
+ {"current_steps": 192, "total_steps": 295, "loss": 0.4955, "lr": 2.6294441416794348e-05, "epoch": 3.251585623678647, "percentage": 65.08, "elapsed_time": "2:08:18", "remaining_time": "1:08:50"}
215
+ {"current_steps": 193, "total_steps": 295, "loss": 0.4941, "lr": 2.584991711866825e-05, "epoch": 3.2684989429175477, "percentage": 65.42, "elapsed_time": "2:10:00", "remaining_time": "1:08:42"}
216
+ {"current_steps": 194, "total_steps": 295, "loss": 0.4972, "lr": 2.5407381486753e-05, "epoch": 3.285412262156448, "percentage": 65.76, "elapsed_time": "2:11:42", "remaining_time": "1:08:34"}
217
+ {"current_steps": 195, "total_steps": 295, "loss": 0.4944, "lr": 2.4966896715430484e-05, "epoch": 3.302325581395349, "percentage": 66.1, "elapsed_time": "2:13:24", "remaining_time": "1:08:24"}
218
+ {"current_steps": 196, "total_steps": 295, "loss": 0.4874, "lr": 2.452852471085266e-05, "epoch": 3.3192389006342493, "percentage": 66.44, "elapsed_time": "2:15:06", "remaining_time": "1:08:14"}
219
+ {"current_steps": 197, "total_steps": 295, "loss": 0.49, "lr": 2.4092327082241228e-05, "epoch": 3.33615221987315, "percentage": 66.78, "elapsed_time": "2:16:47", "remaining_time": "1:08:02"}
220
+ {"current_steps": 198, "total_steps": 295, "loss": 0.4949, "lr": 2.3658365133229014e-05, "epoch": 3.353065539112051, "percentage": 67.12, "elapsed_time": "2:18:30", "remaining_time": "1:07:51"}
221
+ {"current_steps": 199, "total_steps": 295, "loss": 0.496, "lr": 2.322669985324427e-05, "epoch": 3.3699788583509513, "percentage": 67.46, "elapsed_time": "2:20:12", "remaining_time": "1:07:38"}
222
+ {"current_steps": 200, "total_steps": 295, "loss": 0.496, "lr": 2.2797391908939196e-05, "epoch": 3.386892177589852, "percentage": 67.8, "elapsed_time": "2:21:54", "remaining_time": "1:07:24"}
223
+ {"current_steps": 201, "total_steps": 295, "loss": 0.4987, "lr": 2.2370501635663758e-05, "epoch": 3.4038054968287526, "percentage": 68.14, "elapsed_time": "2:23:37", "remaining_time": "1:07:10"}
224
+ {"current_steps": 202, "total_steps": 295, "loss": 0.4912, "lr": 2.194608902898615e-05, "epoch": 3.4207188160676534, "percentage": 68.47, "elapsed_time": "2:25:19", "remaining_time": "1:06:54"}
225
+ {"current_steps": 203, "total_steps": 295, "loss": 0.4935, "lr": 2.1524213736260914e-05, "epoch": 3.4376321353065538, "percentage": 68.81, "elapsed_time": "2:27:00", "remaining_time": "1:06:37"}
226
+ {"current_steps": 204, "total_steps": 295, "loss": 0.4931, "lr": 2.110493504824603e-05, "epoch": 3.4545454545454546, "percentage": 69.15, "elapsed_time": "2:28:42", "remaining_time": "1:06:20"}
227
+ {"current_steps": 205, "total_steps": 295, "loss": 0.4915, "lr": 2.068831189077021e-05, "epoch": 3.471458773784355, "percentage": 69.49, "elapsed_time": "2:30:23", "remaining_time": "1:06:01"}
228
+ {"current_steps": 206, "total_steps": 295, "loss": 0.4901, "lr": 2.0274402816451327e-05, "epoch": 3.488372093023256, "percentage": 69.83, "elapsed_time": "2:32:05", "remaining_time": "1:05:42"}
229
+ {"current_steps": 207, "total_steps": 295, "loss": 0.4948, "lr": 1.9863265996467395e-05, "epoch": 3.5052854122621566, "percentage": 70.17, "elapsed_time": "2:33:48", "remaining_time": "1:05:23"}
230
+ {"current_steps": 208, "total_steps": 295, "loss": 0.4848, "lr": 1.9454959212381196e-05, "epoch": 3.522198731501057, "percentage": 70.51, "elapsed_time": "2:35:30", "remaining_time": "1:05:02"}
231
+ {"current_steps": 209, "total_steps": 295, "loss": 0.4888, "lr": 1.9049539848019508e-05, "epoch": 3.539112050739958, "percentage": 70.85, "elapsed_time": "2:37:11", "remaining_time": "1:04:41"}
232
+ {"current_steps": 210, "total_steps": 295, "loss": 0.494, "lr": 1.864706488140839e-05, "epoch": 3.556025369978858, "percentage": 71.19, "elapsed_time": "2:38:53", "remaining_time": "1:04:18"}
233
+ {"current_steps": 211, "total_steps": 295, "loss": 0.4913, "lr": 1.8247590876765397e-05, "epoch": 3.572938689217759, "percentage": 71.53, "elapsed_time": "2:40:34", "remaining_time": "1:03:55"}
234
+ {"current_steps": 212, "total_steps": 295, "loss": 0.4896, "lr": 1.7851173976550074e-05, "epoch": 3.58985200845666, "percentage": 71.86, "elapsed_time": "2:42:15", "remaining_time": "1:03:31"}
235
+ {"current_steps": 213, "total_steps": 295, "loss": 0.4934, "lr": 1.745786989357352e-05, "epoch": 3.6067653276955602, "percentage": 72.2, "elapsed_time": "2:43:56", "remaining_time": "1:03:06"}
236
+ {"current_steps": 214, "total_steps": 295, "loss": 0.4981, "lr": 1.7067733903168514e-05, "epoch": 3.6236786469344606, "percentage": 72.54, "elapsed_time": "2:45:38", "remaining_time": "1:02:41"}
237
+ {"current_steps": 215, "total_steps": 295, "loss": 0.491, "lr": 1.6680820835421124e-05, "epoch": 3.6405919661733614, "percentage": 72.88, "elapsed_time": "2:47:21", "remaining_time": "1:02:16"}
238
+ {"current_steps": 216, "total_steps": 295, "loss": 0.4911, "lr": 1.629718506746473e-05, "epoch": 3.6575052854122623, "percentage": 73.22, "elapsed_time": "2:49:02", "remaining_time": "1:01:49"}
239
+ {"current_steps": 217, "total_steps": 295, "loss": 0.491, "lr": 1.5916880515837853e-05, "epoch": 3.6744186046511627, "percentage": 73.56, "elapsed_time": "2:50:44", "remaining_time": "1:01:22"}
240
+ {"current_steps": 218, "total_steps": 295, "loss": 0.4901, "lr": 1.553996062890673e-05, "epoch": 3.6913319238900635, "percentage": 73.9, "elapsed_time": "2:52:26", "remaining_time": "1:00:54"}
241
+ {"current_steps": 219, "total_steps": 295, "loss": 0.4896, "lr": 1.5166478379353527e-05, "epoch": 3.708245243128964, "percentage": 74.24, "elapsed_time": "2:54:07", "remaining_time": "1:00:25"}
242
+ {"current_steps": 220, "total_steps": 295, "loss": 0.4884, "lr": 1.4796486256731561e-05, "epoch": 3.7251585623678647, "percentage": 74.58, "elapsed_time": "2:55:48", "remaining_time": "0:59:56"}
243
+ {"current_steps": 221, "total_steps": 295, "loss": 0.4914, "lr": 1.4430036260088405e-05, "epoch": 3.7420718816067655, "percentage": 74.92, "elapsed_time": "2:57:31", "remaining_time": "0:59:26"}
244
+ {"current_steps": 222, "total_steps": 295, "loss": 0.4932, "lr": 1.4067179890657818e-05, "epoch": 3.758985200845666, "percentage": 75.25, "elapsed_time": "2:59:13", "remaining_time": "0:58:56"}
245
+ {"current_steps": 223, "total_steps": 295, "loss": 0.4906, "lr": 1.3707968144621737e-05, "epoch": 3.7758985200845667, "percentage": 75.59, "elapsed_time": "3:00:54", "remaining_time": "0:58:24"}
246
+ {"current_steps": 224, "total_steps": 295, "loss": 0.4916, "lr": 1.3352451505943283e-05, "epoch": 3.792811839323467, "percentage": 75.93, "elapsed_time": "3:02:37", "remaining_time": "0:57:53"}
247
+ {"current_steps": 225, "total_steps": 295, "loss": 0.4899, "lr": 1.3000679939271588e-05, "epoch": 3.809725158562368, "percentage": 76.27, "elapsed_time": "3:04:18", "remaining_time": "0:57:20"}
248
+ {"current_steps": 226, "total_steps": 295, "loss": 0.4892, "lr": 1.2652702882919816e-05, "epoch": 3.8266384778012688, "percentage": 76.61, "elapsed_time": "3:06:00", "remaining_time": "0:56:47"}
249
+ {"current_steps": 227, "total_steps": 295, "loss": 0.4882, "lr": 1.2308569241916982e-05, "epoch": 3.843551797040169, "percentage": 76.95, "elapsed_time": "3:07:42", "remaining_time": "0:56:13"}
250
+ {"current_steps": 228, "total_steps": 295, "loss": 0.4905, "lr": 1.196832738113486e-05, "epoch": 3.8604651162790695, "percentage": 77.29, "elapsed_time": "3:09:24", "remaining_time": "0:55:39"}
251
+ {"current_steps": 229, "total_steps": 295, "loss": 0.4909, "lr": 1.1632025118490668e-05, "epoch": 3.8773784355179703, "percentage": 77.63, "elapsed_time": "3:11:06", "remaining_time": "0:55:04"}
252
+ {"current_steps": 230, "total_steps": 295, "loss": 0.4944, "lr": 1.1299709718226745e-05, "epoch": 3.894291754756871, "percentage": 77.97, "elapsed_time": "3:12:49", "remaining_time": "0:54:29"}
253
+ {"current_steps": 231, "total_steps": 295, "loss": 0.4917, "lr": 1.0971427884267984e-05, "epoch": 3.9112050739957716, "percentage": 78.31, "elapsed_time": "3:14:32", "remaining_time": "0:53:53"}
254
+ {"current_steps": 232, "total_steps": 295, "loss": 0.4882, "lr": 1.064722575365797e-05, "epoch": 3.9281183932346724, "percentage": 78.64, "elapsed_time": "3:16:13", "remaining_time": "0:53:17"}
255
+ {"current_steps": 233, "total_steps": 295, "loss": 0.491, "lr": 1.032714889007488e-05, "epoch": 3.9450317124735728, "percentage": 78.98, "elapsed_time": "3:17:55", "remaining_time": "0:52:39"}
256
+ {"current_steps": 234, "total_steps": 295, "loss": 0.4934, "lr": 1.0011242277427903e-05, "epoch": 3.9619450317124736, "percentage": 79.32, "elapsed_time": "3:19:36", "remaining_time": "0:52:02"}
257
+ {"current_steps": 235, "total_steps": 295, "loss": 0.4935, "lr": 9.699550313535196e-06, "epoch": 3.9788583509513744, "percentage": 79.66, "elapsed_time": "3:21:17", "remaining_time": "0:51:23"}
258
+ {"current_steps": 236, "total_steps": 295, "loss": 0.4957, "lr": 9.392116803884113e-06, "epoch": 3.995771670190275, "percentage": 80.0, "elapsed_time": "3:22:59", "remaining_time": "0:50:44"}
259
+ {"current_steps": 237, "total_steps": 295, "loss": 0.4642, "lr": 9.088984955474749e-06, "epoch": 4.012684989429175, "percentage": 80.34, "elapsed_time": "3:26:36", "remaining_time": "0:50:33"}