neginr commited on
Commit
9b6bc0d
·
verified ·
1 Parent(s): 79f8846

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 sha256:48f1e82f0e18149023cd69dea9e8f4ede154b33e9057faf1c475a1e5bf32ad2d
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d363db69516d3a73eb162ae54c0d03dce7b60e20d1ed850cf9cb3c6175841f2
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81f8b749000e7d3d0f6c857a5cd44afa3498522ecf1eb29f71177d69d9742761
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4338cbfc42f1cd459c58bbdcb79175315c4b74daed71f8c95d48995e8a5bf8
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:d833e8693095ad70f8a0f50cb5220dc15b556a3e68dcc3b931735a142d09708f
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb7074cdda3273945179c0dd283db8e4cf471237a1f5981f7b67b16e0b2c80f
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99397d9a600a9ae9f6950623cae30e88845900572613299d7f3a0896cbd27ba9
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf17d4a9d6966d5c4ae91119e0e42e4067ddc5c2d80d8ea82eacbe3a60f11be
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -190,3 +190,56 @@
190
  {"current_steps": 190, "total_steps": 364, "loss": 0.2172, "lr": 1.1007058259945584e-05, "epoch": 3.6305732484076434, "percentage": 52.2, "elapsed_time": "0:21:12", "remaining_time": "0:19:25"}
191
  {"current_steps": 191, "total_steps": 364, "loss": 0.2218, "lr": 1.0911428497230834e-05, "epoch": 3.6496815286624202, "percentage": 52.47, "elapsed_time": "0:21:17", "remaining_time": "0:19:17"}
192
  {"current_steps": 192, "total_steps": 364, "loss": 0.2033, "lr": 1.0815714609821027e-05, "epoch": 3.6687898089171975, "percentage": 52.75, "elapsed_time": "0:21:21", "remaining_time": "0:19:08"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
190
  {"current_steps": 190, "total_steps": 364, "loss": 0.2172, "lr": 1.1007058259945584e-05, "epoch": 3.6305732484076434, "percentage": 52.2, "elapsed_time": "0:21:12", "remaining_time": "0:19:25"}
191
  {"current_steps": 191, "total_steps": 364, "loss": 0.2218, "lr": 1.0911428497230834e-05, "epoch": 3.6496815286624202, "percentage": 52.47, "elapsed_time": "0:21:17", "remaining_time": "0:19:17"}
192
  {"current_steps": 192, "total_steps": 364, "loss": 0.2033, "lr": 1.0815714609821027e-05, "epoch": 3.6687898089171975, "percentage": 52.75, "elapsed_time": "0:21:21", "remaining_time": "0:19:08"}
193
+ {"current_steps": 193, "total_steps": 364, "loss": 0.2166, "lr": 1.0719925432091671e-05, "epoch": 3.6878980891719744, "percentage": 53.02, "elapsed_time": "0:21:25", "remaining_time": "0:18:59"}
194
+ {"current_steps": 194, "total_steps": 364, "loss": 0.208, "lr": 1.0624069805367558e-05, "epoch": 3.7070063694267517, "percentage": 53.3, "elapsed_time": "0:21:31", "remaining_time": "0:18:52"}
195
+ {"current_steps": 195, "total_steps": 364, "loss": 0.2083, "lr": 1.0528156577106703e-05, "epoch": 3.7261146496815285, "percentage": 53.57, "elapsed_time": "0:21:35", "remaining_time": "0:18:42"}
196
+ {"current_steps": 196, "total_steps": 364, "loss": 0.2112, "lr": 1.043219460008374e-05, "epoch": 3.745222929936306, "percentage": 53.85, "elapsed_time": "0:21:39", "remaining_time": "0:18:34"}
197
+ {"current_steps": 197, "total_steps": 364, "loss": 0.2181, "lr": 1.0336192731572805e-05, "epoch": 3.7643312101910826, "percentage": 54.12, "elapsed_time": "0:21:43", "remaining_time": "0:18:24"}
198
+ {"current_steps": 198, "total_steps": 364, "loss": 0.1875, "lr": 1.0240159832530007e-05, "epoch": 3.78343949044586, "percentage": 54.4, "elapsed_time": "0:21:47", "remaining_time": "0:18:16"}
199
+ {"current_steps": 199, "total_steps": 364, "loss": 0.2243, "lr": 1.0144104766775574e-05, "epoch": 3.802547770700637, "percentage": 54.67, "elapsed_time": "0:21:53", "remaining_time": "0:18:08"}
200
+ {"current_steps": 200, "total_steps": 364, "loss": 0.2107, "lr": 1.004803640017571e-05, "epoch": 3.821656050955414, "percentage": 54.95, "elapsed_time": "0:21:56", "remaining_time": "0:17:59"}
201
+ {"current_steps": 201, "total_steps": 364, "loss": 0.2522, "lr": 9.951963599824294e-06, "epoch": 3.840764331210191, "percentage": 55.22, "elapsed_time": "0:22:01", "remaining_time": "0:17:52"}
202
+ {"current_steps": 202, "total_steps": 364, "loss": 0.2271, "lr": 9.855895233224431e-06, "epoch": 3.859872611464968, "percentage": 55.49, "elapsed_time": "0:22:10", "remaining_time": "0:17:47"}
203
+ {"current_steps": 203, "total_steps": 364, "loss": 0.2111, "lr": 9.759840167469995e-06, "epoch": 3.8789808917197455, "percentage": 55.77, "elapsed_time": "0:22:16", "remaining_time": "0:17:40"}
204
+ {"current_steps": 204, "total_steps": 364, "loss": 0.2085, "lr": 9.663807268427197e-06, "epoch": 3.8980891719745223, "percentage": 56.04, "elapsed_time": "0:22:20", "remaining_time": "0:17:31"}
205
+ {"current_steps": 205, "total_steps": 364, "loss": 0.2054, "lr": 9.56780539991626e-06, "epoch": 3.917197452229299, "percentage": 56.32, "elapsed_time": "0:22:25", "remaining_time": "0:17:23"}
206
+ {"current_steps": 206, "total_steps": 364, "loss": 0.1696, "lr": 9.471843422893299e-06, "epoch": 3.9363057324840764, "percentage": 56.59, "elapsed_time": "0:22:29", "remaining_time": "0:17:15"}
207
+ {"current_steps": 207, "total_steps": 364, "loss": 0.2088, "lr": 9.375930194632447e-06, "epoch": 3.9554140127388537, "percentage": 56.87, "elapsed_time": "0:22:34", "remaining_time": "0:17:07"}
208
+ {"current_steps": 208, "total_steps": 364, "loss": 0.1856, "lr": 9.28007456790833e-06, "epoch": 3.9745222929936306, "percentage": 57.14, "elapsed_time": "0:22:40", "remaining_time": "0:17:00"}
209
+ {"current_steps": 209, "total_steps": 364, "loss": 0.1888, "lr": 9.184285390178978e-06, "epoch": 3.9936305732484074, "percentage": 57.42, "elapsed_time": "0:22:47", "remaining_time": "0:16:54"}
210
+ {"current_steps": 210, "total_steps": 364, "loss": 0.1449, "lr": 9.08857150276917e-06, "epoch": 4.012738853503185, "percentage": 57.69, "elapsed_time": "0:24:38", "remaining_time": "0:18:04"}
211
+ {"current_steps": 211, "total_steps": 364, "loss": 0.1393, "lr": 8.992941740054418e-06, "epoch": 4.031847133757962, "percentage": 57.97, "elapsed_time": "0:24:42", "remaining_time": "0:17:55"}
212
+ {"current_steps": 212, "total_steps": 364, "loss": 0.1382, "lr": 8.897404928645529e-06, "epoch": 4.050955414012739, "percentage": 58.24, "elapsed_time": "0:24:46", "remaining_time": "0:17:45"}
213
+ {"current_steps": 213, "total_steps": 364, "loss": 0.1179, "lr": 8.80196988657393e-06, "epoch": 4.070063694267516, "percentage": 58.52, "elapsed_time": "0:24:50", "remaining_time": "0:17:36"}
214
+ {"current_steps": 214, "total_steps": 364, "loss": 0.1296, "lr": 8.706645422477739e-06, "epoch": 4.089171974522293, "percentage": 58.79, "elapsed_time": "0:24:57", "remaining_time": "0:17:29"}
215
+ {"current_steps": 215, "total_steps": 364, "loss": 0.1485, "lr": 8.611440334788762e-06, "epoch": 4.10828025477707, "percentage": 59.07, "elapsed_time": "0:25:02", "remaining_time": "0:17:21"}
216
+ {"current_steps": 216, "total_steps": 364, "loss": 0.1182, "lr": 8.516363410920376e-06, "epoch": 4.127388535031847, "percentage": 59.34, "elapsed_time": "0:25:06", "remaining_time": "0:17:12"}
217
+ {"current_steps": 217, "total_steps": 364, "loss": 0.1575, "lr": 8.42142342645646e-06, "epoch": 4.146496815286624, "percentage": 59.62, "elapsed_time": "0:25:12", "remaining_time": "0:17:04"}
218
+ {"current_steps": 218, "total_steps": 364, "loss": 0.1021, "lr": 8.326629144341408e-06, "epoch": 4.165605095541402, "percentage": 59.89, "elapsed_time": "0:25:16", "remaining_time": "0:16:55"}
219
+ {"current_steps": 219, "total_steps": 364, "loss": 0.1243, "lr": 8.231989314071318e-06, "epoch": 4.1847133757961785, "percentage": 60.16, "elapsed_time": "0:25:20", "remaining_time": "0:16:46"}
220
+ {"current_steps": 220, "total_steps": 364, "loss": 0.0998, "lr": 8.137512670886397e-06, "epoch": 4.203821656050955, "percentage": 60.44, "elapsed_time": "0:25:26", "remaining_time": "0:16:39"}
221
+ {"current_steps": 221, "total_steps": 364, "loss": 0.148, "lr": 8.043207934964722e-06, "epoch": 4.222929936305732, "percentage": 60.71, "elapsed_time": "0:25:34", "remaining_time": "0:16:33"}
222
+ {"current_steps": 222, "total_steps": 364, "loss": 0.1246, "lr": 7.949083810617358e-06, "epoch": 4.24203821656051, "percentage": 60.99, "elapsed_time": "0:25:41", "remaining_time": "0:16:25"}
223
+ {"current_steps": 223, "total_steps": 364, "loss": 0.1198, "lr": 7.855148985484946e-06, "epoch": 4.261146496815287, "percentage": 61.26, "elapsed_time": "0:25:47", "remaining_time": "0:16:18"}
224
+ {"current_steps": 224, "total_steps": 364, "loss": 0.1212, "lr": 7.761412129735853e-06, "epoch": 4.280254777070064, "percentage": 61.54, "elapsed_time": "0:25:52", "remaining_time": "0:16:10"}
225
+ {"current_steps": 225, "total_steps": 364, "loss": 0.1298, "lr": 7.667881895265895e-06, "epoch": 4.2993630573248405, "percentage": 61.81, "elapsed_time": "0:25:56", "remaining_time": "0:16:01"}
226
+ {"current_steps": 226, "total_steps": 364, "loss": 0.1225, "lr": 7.574566914899779e-06, "epoch": 4.318471337579618, "percentage": 62.09, "elapsed_time": "0:26:01", "remaining_time": "0:15:53"}
227
+ {"current_steps": 227, "total_steps": 364, "loss": 0.0954, "lr": 7.481475801594302e-06, "epoch": 4.337579617834395, "percentage": 62.36, "elapsed_time": "0:26:06", "remaining_time": "0:15:45"}
228
+ {"current_steps": 228, "total_steps": 364, "loss": 0.1156, "lr": 7.388617147643371e-06, "epoch": 4.356687898089172, "percentage": 62.64, "elapsed_time": "0:26:10", "remaining_time": "0:15:37"}
229
+ {"current_steps": 229, "total_steps": 364, "loss": 0.1123, "lr": 7.295999523884921e-06, "epoch": 4.375796178343949, "percentage": 62.91, "elapsed_time": "0:26:15", "remaining_time": "0:15:28"}
230
+ {"current_steps": 230, "total_steps": 364, "loss": 0.113, "lr": 7.203631478909857e-06, "epoch": 4.3949044585987265, "percentage": 63.19, "elapsed_time": "0:26:22", "remaining_time": "0:15:21"}
231
+ {"current_steps": 231, "total_steps": 364, "loss": 0.1179, "lr": 7.111521538272997e-06, "epoch": 4.414012738853503, "percentage": 63.46, "elapsed_time": "0:26:25", "remaining_time": "0:15:13"}
232
+ {"current_steps": 232, "total_steps": 364, "loss": 0.1284, "lr": 7.019678203706164e-06, "epoch": 4.43312101910828, "percentage": 63.74, "elapsed_time": "0:26:29", "remaining_time": "0:15:04"}
233
+ {"current_steps": 233, "total_steps": 364, "loss": 0.1318, "lr": 6.928109952333506e-06, "epoch": 4.452229299363057, "percentage": 64.01, "elapsed_time": "0:26:37", "remaining_time": "0:14:58"}
234
+ {"current_steps": 234, "total_steps": 364, "loss": 0.1361, "lr": 6.83682523588902e-06, "epoch": 4.471337579617835, "percentage": 64.29, "elapsed_time": "0:26:42", "remaining_time": "0:14:50"}
235
+ {"current_steps": 235, "total_steps": 364, "loss": 0.1202, "lr": 6.745832479936492e-06, "epoch": 4.490445859872612, "percentage": 64.56, "elapsed_time": "0:26:47", "remaining_time": "0:14:42"}
236
+ {"current_steps": 236, "total_steps": 364, "loss": 0.1142, "lr": 6.655140083091794e-06, "epoch": 4.509554140127388, "percentage": 64.84, "elapsed_time": "0:26:52", "remaining_time": "0:14:34"}
237
+ {"current_steps": 237, "total_steps": 364, "loss": 0.1132, "lr": 6.564756416247712e-06, "epoch": 4.528662420382165, "percentage": 65.11, "elapsed_time": "0:26:56", "remaining_time": "0:14:26"}
238
+ {"current_steps": 238, "total_steps": 364, "loss": 0.1224, "lr": 6.474689821801295e-06, "epoch": 4.547770700636943, "percentage": 65.38, "elapsed_time": "0:27:03", "remaining_time": "0:14:19"}
239
+ {"current_steps": 239, "total_steps": 364, "loss": 0.1081, "lr": 6.384948612883872e-06, "epoch": 4.56687898089172, "percentage": 65.66, "elapsed_time": "0:27:07", "remaining_time": "0:14:11"}
240
+ {"current_steps": 240, "total_steps": 364, "loss": 0.142, "lr": 6.2955410725937405e-06, "epoch": 4.585987261146497, "percentage": 65.93, "elapsed_time": "0:27:11", "remaining_time": "0:14:02"}
241
+ {"current_steps": 241, "total_steps": 364, "loss": 0.1098, "lr": 6.206475453231644e-06, "epoch": 4.6050955414012735, "percentage": 66.21, "elapsed_time": "0:27:15", "remaining_time": "0:13:54"}
242
+ {"current_steps": 242, "total_steps": 364, "loss": 0.1084, "lr": 6.117759975539075e-06, "epoch": 4.624203821656051, "percentage": 66.48, "elapsed_time": "0:27:20", "remaining_time": "0:13:46"}
243
+ {"current_steps": 243, "total_steps": 364, "loss": 0.1356, "lr": 6.029402827939519e-06, "epoch": 4.643312101910828, "percentage": 66.76, "elapsed_time": "0:27:25", "remaining_time": "0:13:39"}
244
+ {"current_steps": 244, "total_steps": 364, "loss": 0.1072, "lr": 5.941412165782645e-06, "epoch": 4.662420382165605, "percentage": 67.03, "elapsed_time": "0:27:29", "remaining_time": "0:13:31"}
245
+ {"current_steps": 245, "total_steps": 364, "loss": 0.1199, "lr": 5.853796110591583e-06, "epoch": 4.681528662420382, "percentage": 67.31, "elapsed_time": "0:27:34", "remaining_time": "0:13:23"}