neginr commited on
Commit
4d325bc
·
verified ·
1 Parent(s): 9bbd630

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 sha256:52091116c1e7702d425c3d524995efb2fbe7adc769cec142067fc484cef4deda
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552847ca480c84fa8a01225a520cbb40dbc8c60b51079981dc4589d7efbe3759
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:d369e6ec1fc0fc49cc17dbabba6c9878762cbd5987bea4786f343979afd68c13
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b99f6d57ceea4a903cb026828878f1f898b6bec5a84a402db42ec688851741a5
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86a92d421ca1615160f5ad9631cc025d185684fbde161523f42e180e871bcbf1
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa2fce68578db3e1ffbffbd33605d9acf441e24718133cb1e1d3c6939756a7a
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02e40e3b9f5fcb7613df1f8485e62a8181cc1ee81267d148e5d85dc9f30a0e7f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1a7d5158684033cb34484bcbb7ec10277ecf7ef1908450c0c7e8358246cd30b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -189,3 +189,54 @@
189
  {"current_steps": 189, "total_steps": 364, "loss": 0.18, "lr": 1.1102595071354471e-05, "epoch": 3.611464968152866, "percentage": 51.92, "elapsed_time": "0:21:28", "remaining_time": "0:19:53"}
190
  {"current_steps": 190, "total_steps": 364, "loss": 0.228, "lr": 1.1007058259945584e-05, "epoch": 3.6305732484076434, "percentage": 52.2, "elapsed_time": "0:21:32", "remaining_time": "0:19:43"}
191
  {"current_steps": 191, "total_steps": 364, "loss": 0.2184, "lr": 1.0911428497230834e-05, "epoch": 3.6496815286624202, "percentage": 52.47, "elapsed_time": "0:21:37", "remaining_time": "0:19:35"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
189
  {"current_steps": 189, "total_steps": 364, "loss": 0.18, "lr": 1.1102595071354471e-05, "epoch": 3.611464968152866, "percentage": 51.92, "elapsed_time": "0:21:28", "remaining_time": "0:19:53"}
190
  {"current_steps": 190, "total_steps": 364, "loss": 0.228, "lr": 1.1007058259945584e-05, "epoch": 3.6305732484076434, "percentage": 52.2, "elapsed_time": "0:21:32", "remaining_time": "0:19:43"}
191
  {"current_steps": 191, "total_steps": 364, "loss": 0.2184, "lr": 1.0911428497230834e-05, "epoch": 3.6496815286624202, "percentage": 52.47, "elapsed_time": "0:21:37", "remaining_time": "0:19:35"}
192
+ {"current_steps": 192, "total_steps": 364, "loss": 0.2053, "lr": 1.0815714609821027e-05, "epoch": 3.6687898089171975, "percentage": 52.75, "elapsed_time": "0:21:41", "remaining_time": "0:19:26"}
193
+ {"current_steps": 193, "total_steps": 364, "loss": 0.208, "lr": 1.0719925432091671e-05, "epoch": 3.6878980891719744, "percentage": 53.02, "elapsed_time": "0:21:45", "remaining_time": "0:19:17"}
194
+ {"current_steps": 194, "total_steps": 364, "loss": 0.2075, "lr": 1.0624069805367558e-05, "epoch": 3.7070063694267517, "percentage": 53.3, "elapsed_time": "0:21:50", "remaining_time": "0:19:08"}
195
+ {"current_steps": 195, "total_steps": 364, "loss": 0.2136, "lr": 1.0528156577106703e-05, "epoch": 3.7261146496815285, "percentage": 53.57, "elapsed_time": "0:21:56", "remaining_time": "0:19:00"}
196
+ {"current_steps": 196, "total_steps": 364, "loss": 0.2306, "lr": 1.043219460008374e-05, "epoch": 3.745222929936306, "percentage": 53.85, "elapsed_time": "0:22:01", "remaining_time": "0:18:52"}
197
+ {"current_steps": 197, "total_steps": 364, "loss": 0.1892, "lr": 1.0336192731572805e-05, "epoch": 3.7643312101910826, "percentage": 54.12, "elapsed_time": "0:22:05", "remaining_time": "0:18:43"}
198
+ {"current_steps": 198, "total_steps": 364, "loss": 0.2007, "lr": 1.0240159832530007e-05, "epoch": 3.78343949044586, "percentage": 54.4, "elapsed_time": "0:22:11", "remaining_time": "0:18:36"}
199
+ {"current_steps": 199, "total_steps": 364, "loss": 0.2022, "lr": 1.0144104766775574e-05, "epoch": 3.802547770700637, "percentage": 54.67, "elapsed_time": "0:22:15", "remaining_time": "0:18:27"}
200
+ {"current_steps": 200, "total_steps": 364, "loss": 0.1823, "lr": 1.004803640017571e-05, "epoch": 3.821656050955414, "percentage": 54.95, "elapsed_time": "0:22:19", "remaining_time": "0:18:18"}
201
+ {"current_steps": 201, "total_steps": 364, "loss": 0.2201, "lr": 9.951963599824294e-06, "epoch": 3.840764331210191, "percentage": 55.22, "elapsed_time": "0:22:24", "remaining_time": "0:18:10"}
202
+ {"current_steps": 202, "total_steps": 364, "loss": 0.2381, "lr": 9.855895233224431e-06, "epoch": 3.859872611464968, "percentage": 55.49, "elapsed_time": "0:22:37", "remaining_time": "0:18:08"}
203
+ {"current_steps": 203, "total_steps": 364, "loss": 0.159, "lr": 9.759840167469995e-06, "epoch": 3.8789808917197455, "percentage": 55.77, "elapsed_time": "0:22:41", "remaining_time": "0:17:59"}
204
+ {"current_steps": 204, "total_steps": 364, "loss": 0.2114, "lr": 9.663807268427197e-06, "epoch": 3.8980891719745223, "percentage": 56.04, "elapsed_time": "0:22:45", "remaining_time": "0:17:51"}
205
+ {"current_steps": 205, "total_steps": 364, "loss": 0.1834, "lr": 9.56780539991626e-06, "epoch": 3.917197452229299, "percentage": 56.32, "elapsed_time": "0:22:49", "remaining_time": "0:17:42"}
206
+ {"current_steps": 206, "total_steps": 364, "loss": 0.2224, "lr": 9.471843422893299e-06, "epoch": 3.9363057324840764, "percentage": 56.59, "elapsed_time": "0:22:56", "remaining_time": "0:17:35"}
207
+ {"current_steps": 207, "total_steps": 364, "loss": 0.1822, "lr": 9.375930194632447e-06, "epoch": 3.9554140127388537, "percentage": 56.87, "elapsed_time": "0:22:59", "remaining_time": "0:17:26"}
208
+ {"current_steps": 208, "total_steps": 364, "loss": 0.2582, "lr": 9.28007456790833e-06, "epoch": 3.9745222929936306, "percentage": 57.14, "elapsed_time": "0:23:05", "remaining_time": "0:17:19"}
209
+ {"current_steps": 209, "total_steps": 364, "loss": 0.1941, "lr": 9.184285390178978e-06, "epoch": 3.9936305732484074, "percentage": 57.42, "elapsed_time": "0:23:15", "remaining_time": "0:17:14"}
210
+ {"current_steps": 210, "total_steps": 364, "loss": 0.1618, "lr": 9.08857150276917e-06, "epoch": 4.012738853503185, "percentage": 57.69, "elapsed_time": "0:25:05", "remaining_time": "0:18:24"}
211
+ {"current_steps": 211, "total_steps": 364, "loss": 0.1326, "lr": 8.992941740054418e-06, "epoch": 4.031847133757962, "percentage": 57.97, "elapsed_time": "0:25:12", "remaining_time": "0:18:17"}
212
+ {"current_steps": 212, "total_steps": 364, "loss": 0.1239, "lr": 8.897404928645529e-06, "epoch": 4.050955414012739, "percentage": 58.24, "elapsed_time": "0:25:17", "remaining_time": "0:18:08"}
213
+ {"current_steps": 213, "total_steps": 364, "loss": 0.1174, "lr": 8.80196988657393e-06, "epoch": 4.070063694267516, "percentage": 58.52, "elapsed_time": "0:25:24", "remaining_time": "0:18:01"}
214
+ {"current_steps": 214, "total_steps": 364, "loss": 0.1459, "lr": 8.706645422477739e-06, "epoch": 4.089171974522293, "percentage": 58.79, "elapsed_time": "0:25:32", "remaining_time": "0:17:54"}
215
+ {"current_steps": 215, "total_steps": 364, "loss": 0.1365, "lr": 8.611440334788762e-06, "epoch": 4.10828025477707, "percentage": 59.07, "elapsed_time": "0:25:36", "remaining_time": "0:17:44"}
216
+ {"current_steps": 216, "total_steps": 364, "loss": 0.1055, "lr": 8.516363410920376e-06, "epoch": 4.127388535031847, "percentage": 59.34, "elapsed_time": "0:25:45", "remaining_time": "0:17:39"}
217
+ {"current_steps": 217, "total_steps": 364, "loss": 0.1167, "lr": 8.42142342645646e-06, "epoch": 4.146496815286624, "percentage": 59.62, "elapsed_time": "0:25:50", "remaining_time": "0:17:30"}
218
+ {"current_steps": 218, "total_steps": 364, "loss": 0.1091, "lr": 8.326629144341408e-06, "epoch": 4.165605095541402, "percentage": 59.89, "elapsed_time": "0:25:56", "remaining_time": "0:17:22"}
219
+ {"current_steps": 219, "total_steps": 364, "loss": 0.108, "lr": 8.231989314071318e-06, "epoch": 4.1847133757961785, "percentage": 60.16, "elapsed_time": "0:26:00", "remaining_time": "0:17:13"}
220
+ {"current_steps": 220, "total_steps": 364, "loss": 0.1358, "lr": 8.137512670886397e-06, "epoch": 4.203821656050955, "percentage": 60.44, "elapsed_time": "0:26:06", "remaining_time": "0:17:05"}
221
+ {"current_steps": 221, "total_steps": 364, "loss": 0.1323, "lr": 8.043207934964722e-06, "epoch": 4.222929936305732, "percentage": 60.71, "elapsed_time": "0:26:16", "remaining_time": "0:17:00"}
222
+ {"current_steps": 222, "total_steps": 364, "loss": 0.1203, "lr": 7.949083810617358e-06, "epoch": 4.24203821656051, "percentage": 60.99, "elapsed_time": "0:26:20", "remaining_time": "0:16:50"}
223
+ {"current_steps": 223, "total_steps": 364, "loss": 0.1198, "lr": 7.855148985484946e-06, "epoch": 4.261146496815287, "percentage": 61.26, "elapsed_time": "0:26:24", "remaining_time": "0:16:42"}
224
+ {"current_steps": 224, "total_steps": 364, "loss": 0.1328, "lr": 7.761412129735853e-06, "epoch": 4.280254777070064, "percentage": 61.54, "elapsed_time": "0:26:28", "remaining_time": "0:16:32"}
225
+ {"current_steps": 225, "total_steps": 364, "loss": 0.099, "lr": 7.667881895265895e-06, "epoch": 4.2993630573248405, "percentage": 61.81, "elapsed_time": "0:26:32", "remaining_time": "0:16:24"}
226
+ {"current_steps": 226, "total_steps": 364, "loss": 0.1268, "lr": 7.574566914899779e-06, "epoch": 4.318471337579618, "percentage": 62.09, "elapsed_time": "0:26:38", "remaining_time": "0:16:16"}
227
+ {"current_steps": 227, "total_steps": 364, "loss": 0.1164, "lr": 7.481475801594302e-06, "epoch": 4.337579617834395, "percentage": 62.36, "elapsed_time": "0:26:43", "remaining_time": "0:16:07"}
228
+ {"current_steps": 228, "total_steps": 364, "loss": 0.1194, "lr": 7.388617147643371e-06, "epoch": 4.356687898089172, "percentage": 62.64, "elapsed_time": "0:26:47", "remaining_time": "0:15:58"}
229
+ {"current_steps": 229, "total_steps": 364, "loss": 0.1316, "lr": 7.295999523884921e-06, "epoch": 4.375796178343949, "percentage": 62.91, "elapsed_time": "0:26:51", "remaining_time": "0:15:50"}
230
+ {"current_steps": 230, "total_steps": 364, "loss": 0.129, "lr": 7.203631478909857e-06, "epoch": 4.3949044585987265, "percentage": 63.19, "elapsed_time": "0:26:57", "remaining_time": "0:15:42"}
231
+ {"current_steps": 231, "total_steps": 364, "loss": 0.1526, "lr": 7.111521538272997e-06, "epoch": 4.414012738853503, "percentage": 63.46, "elapsed_time": "0:27:01", "remaining_time": "0:15:33"}
232
+ {"current_steps": 232, "total_steps": 364, "loss": 0.1217, "lr": 7.019678203706164e-06, "epoch": 4.43312101910828, "percentage": 63.74, "elapsed_time": "0:27:05", "remaining_time": "0:15:24"}
233
+ {"current_steps": 233, "total_steps": 364, "loss": 0.1308, "lr": 6.928109952333506e-06, "epoch": 4.452229299363057, "percentage": 64.01, "elapsed_time": "0:27:11", "remaining_time": "0:15:17"}
234
+ {"current_steps": 234, "total_steps": 364, "loss": 0.141, "lr": 6.83682523588902e-06, "epoch": 4.471337579617835, "percentage": 64.29, "elapsed_time": "0:27:16", "remaining_time": "0:15:09"}
235
+ {"current_steps": 235, "total_steps": 364, "loss": 0.1076, "lr": 6.745832479936492e-06, "epoch": 4.490445859872612, "percentage": 64.56, "elapsed_time": "0:27:22", "remaining_time": "0:15:01"}
236
+ {"current_steps": 236, "total_steps": 364, "loss": 0.1093, "lr": 6.655140083091794e-06, "epoch": 4.509554140127388, "percentage": 64.84, "elapsed_time": "0:27:26", "remaining_time": "0:14:53"}
237
+ {"current_steps": 237, "total_steps": 364, "loss": 0.1121, "lr": 6.564756416247712e-06, "epoch": 4.528662420382165, "percentage": 65.11, "elapsed_time": "0:27:30", "remaining_time": "0:14:44"}
238
+ {"current_steps": 238, "total_steps": 364, "loss": 0.1194, "lr": 6.474689821801295e-06, "epoch": 4.547770700636943, "percentage": 65.38, "elapsed_time": "0:27:34", "remaining_time": "0:14:35"}
239
+ {"current_steps": 239, "total_steps": 364, "loss": 0.1048, "lr": 6.384948612883872e-06, "epoch": 4.56687898089172, "percentage": 65.66, "elapsed_time": "0:27:38", "remaining_time": "0:14:27"}
240
+ {"current_steps": 240, "total_steps": 364, "loss": 0.1336, "lr": 6.2955410725937405e-06, "epoch": 4.585987261146497, "percentage": 65.93, "elapsed_time": "0:27:42", "remaining_time": "0:14:18"}
241
+ {"current_steps": 241, "total_steps": 364, "loss": 0.1158, "lr": 6.206475453231644e-06, "epoch": 4.6050955414012735, "percentage": 66.21, "elapsed_time": "0:27:48", "remaining_time": "0:14:11"}
242
+ {"current_steps": 242, "total_steps": 364, "loss": 0.1252, "lr": 6.117759975539075e-06, "epoch": 4.624203821656051, "percentage": 66.48, "elapsed_time": "0:27:51", "remaining_time": "0:14:02"}