neginr commited on
Commit
a39f087
·
verified ·
1 Parent(s): fb8560f

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:e880ca41b15369e419ef34b32c65b74948ee34131b026884fc3294e83f0b85c0
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:391b4390e3c3908dd4757881f77237afc78fbde09f8e6f4d8afa373eeca9b99b
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35f6078b96d3fd32dcf7a4b40f27797f1ca3bfa440b5ded92baf161da4342773
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:991746ed92ad8cbe4e4e277df85434e10be489062f85ee7f85677d0f0e96e137
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a0f7502a08b9a35eaeffcc16f42e270e871309d099616e4eaa40a9487610386
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a9eba71bc9411dceb6451bde2053dc199a455d6356cd653e9047e16b5250799
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:df5e44267d8bb9b5715c41173ed8583e1acee65eb56dc63ae04546b0e868c259
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19316075650be25156b3990e0c27ffccdb087597da9985c9683929639b90218
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -167,3 +167,55 @@
167
  {"current_steps": 167, "total_steps": 364, "loss": 0.248, "lr": 1.3163174764110982e-07, "epoch": 3.1910828025477707, "percentage": 45.88, "elapsed_time": "0:42:15", "remaining_time": "0:49:50"}
168
  {"current_steps": 168, "total_steps": 364, "loss": 0.2469, "lr": 1.3071890047666496e-07, "epoch": 3.210191082802548, "percentage": 46.15, "elapsed_time": "0:42:30", "remaining_time": "0:49:35"}
169
  {"current_steps": 169, "total_steps": 364, "loss": 0.2433, "lr": 1.2980321796293835e-07, "epoch": 3.229299363057325, "percentage": 46.43, "elapsed_time": "0:42:42", "remaining_time": "0:49:16"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
167
  {"current_steps": 167, "total_steps": 364, "loss": 0.248, "lr": 1.3163174764110982e-07, "epoch": 3.1910828025477707, "percentage": 45.88, "elapsed_time": "0:42:15", "remaining_time": "0:49:50"}
168
  {"current_steps": 168, "total_steps": 364, "loss": 0.2469, "lr": 1.3071890047666496e-07, "epoch": 3.210191082802548, "percentage": 46.15, "elapsed_time": "0:42:30", "remaining_time": "0:49:35"}
169
  {"current_steps": 169, "total_steps": 364, "loss": 0.2433, "lr": 1.2980321796293835e-07, "epoch": 3.229299363057325, "percentage": 46.43, "elapsed_time": "0:42:42", "remaining_time": "0:49:16"}
170
+ {"current_steps": 170, "total_steps": 364, "loss": 0.2455, "lr": 1.288847846172701e-07, "epoch": 3.248407643312102, "percentage": 46.7, "elapsed_time": "0:42:54", "remaining_time": "0:48:57"}
171
+ {"current_steps": 171, "total_steps": 364, "loss": 0.2563, "lr": 1.2796368521090143e-07, "epoch": 3.267515923566879, "percentage": 46.98, "elapsed_time": "0:43:08", "remaining_time": "0:48:41"}
172
+ {"current_steps": 172, "total_steps": 364, "loss": 0.2486, "lr": 1.270400047611508e-07, "epoch": 3.286624203821656, "percentage": 47.25, "elapsed_time": "0:43:23", "remaining_time": "0:48:25"}
173
+ {"current_steps": 173, "total_steps": 364, "loss": 0.2458, "lr": 1.261138285235663e-07, "epoch": 3.305732484076433, "percentage": 47.53, "elapsed_time": "0:43:34", "remaining_time": "0:48:06"}
174
+ {"current_steps": 174, "total_steps": 364, "loss": 0.2709, "lr": 1.2518524198405698e-07, "epoch": 3.3248407643312103, "percentage": 47.8, "elapsed_time": "0:43:48", "remaining_time": "0:47:50"}
175
+ {"current_steps": 175, "total_steps": 364, "loss": 0.249, "lr": 1.2425433085100222e-07, "epoch": 3.343949044585987, "percentage": 48.08, "elapsed_time": "0:44:01", "remaining_time": "0:47:32"}
176
+ {"current_steps": 176, "total_steps": 364, "loss": 0.2593, "lr": 1.2332118104734109e-07, "epoch": 3.3630573248407645, "percentage": 48.35, "elapsed_time": "0:44:15", "remaining_time": "0:47:17"}
177
+ {"current_steps": 177, "total_steps": 364, "loss": 0.2571, "lr": 1.223858787026415e-07, "epoch": 3.3821656050955413, "percentage": 48.63, "elapsed_time": "0:44:29", "remaining_time": "0:47:00"}
178
+ {"current_steps": 178, "total_steps": 364, "loss": 0.2433, "lr": 1.2144851014515054e-07, "epoch": 3.4012738853503186, "percentage": 48.9, "elapsed_time": "0:44:45", "remaining_time": "0:46:45"}
179
+ {"current_steps": 179, "total_steps": 364, "loss": 0.2612, "lr": 1.2050916189382645e-07, "epoch": 3.4203821656050954, "percentage": 49.18, "elapsed_time": "0:44:58", "remaining_time": "0:46:28"}
180
+ {"current_steps": 180, "total_steps": 364, "loss": 0.2549, "lr": 1.195679206503528e-07, "epoch": 3.4394904458598727, "percentage": 49.45, "elapsed_time": "0:45:10", "remaining_time": "0:46:10"}
181
+ {"current_steps": 181, "total_steps": 364, "loss": 0.2622, "lr": 1.1862487329113604e-07, "epoch": 3.4585987261146496, "percentage": 49.73, "elapsed_time": "0:45:22", "remaining_time": "0:45:52"}
182
+ {"current_steps": 182, "total_steps": 364, "loss": 0.2556, "lr": 1.1768010685928685e-07, "epoch": 3.477707006369427, "percentage": 50.0, "elapsed_time": "0:45:37", "remaining_time": "0:45:37"}
183
+ {"current_steps": 183, "total_steps": 364, "loss": 0.2564, "lr": 1.1673370855658591e-07, "epoch": 3.4968152866242037, "percentage": 50.27, "elapsed_time": "0:45:51", "remaining_time": "0:45:21"}
184
+ {"current_steps": 184, "total_steps": 364, "loss": 0.2603, "lr": 1.1578576573543539e-07, "epoch": 3.515923566878981, "percentage": 50.55, "elapsed_time": "0:46:06", "remaining_time": "0:45:06"}
185
+ {"current_steps": 185, "total_steps": 364, "loss": 0.2537, "lr": 1.1483636589079626e-07, "epoch": 3.535031847133758, "percentage": 50.82, "elapsed_time": "0:46:21", "remaining_time": "0:44:51"}
186
+ {"current_steps": 186, "total_steps": 364, "loss": 0.2605, "lr": 1.138855966521124e-07, "epoch": 3.554140127388535, "percentage": 51.1, "elapsed_time": "0:46:32", "remaining_time": "0:44:32"}
187
+ {"current_steps": 187, "total_steps": 364, "loss": 0.2642, "lr": 1.1293354577522263e-07, "epoch": 3.573248407643312, "percentage": 51.37, "elapsed_time": "0:46:47", "remaining_time": "0:44:17"}
188
+ {"current_steps": 188, "total_steps": 364, "loss": 0.2689, "lr": 1.1198030113426074e-07, "epoch": 3.5923566878980893, "percentage": 51.65, "elapsed_time": "0:47:01", "remaining_time": "0:44:01"}
189
+ {"current_steps": 189, "total_steps": 364, "loss": 0.268, "lr": 1.110259507135447e-07, "epoch": 3.611464968152866, "percentage": 51.92, "elapsed_time": "0:47:12", "remaining_time": "0:43:42"}
190
+ {"current_steps": 190, "total_steps": 364, "loss": 0.25, "lr": 1.1007058259945583e-07, "epoch": 3.6305732484076434, "percentage": 52.2, "elapsed_time": "0:47:26", "remaining_time": "0:43:26"}
191
+ {"current_steps": 191, "total_steps": 364, "loss": 0.2398, "lr": 1.0911428497230832e-07, "epoch": 3.6496815286624202, "percentage": 52.47, "elapsed_time": "0:47:37", "remaining_time": "0:43:08"}
192
+ {"current_steps": 192, "total_steps": 364, "loss": 0.2568, "lr": 1.0815714609821025e-07, "epoch": 3.6687898089171975, "percentage": 52.75, "elapsed_time": "0:47:47", "remaining_time": "0:42:49"}
193
+ {"current_steps": 193, "total_steps": 364, "loss": 0.2401, "lr": 1.071992543209167e-07, "epoch": 3.6878980891719744, "percentage": 53.02, "elapsed_time": "0:47:56", "remaining_time": "0:42:28"}
194
+ {"current_steps": 194, "total_steps": 364, "loss": 0.2477, "lr": 1.0624069805367557e-07, "epoch": 3.7070063694267517, "percentage": 53.3, "elapsed_time": "0:48:08", "remaining_time": "0:42:11"}
195
+ {"current_steps": 195, "total_steps": 364, "loss": 0.2463, "lr": 1.0528156577106702e-07, "epoch": 3.7261146496815285, "percentage": 53.57, "elapsed_time": "0:48:23", "remaining_time": "0:41:55"}
196
+ {"current_steps": 196, "total_steps": 364, "loss": 0.2574, "lr": 1.0432194600083739e-07, "epoch": 3.745222929936306, "percentage": 53.85, "elapsed_time": "0:48:34", "remaining_time": "0:41:38"}
197
+ {"current_steps": 197, "total_steps": 364, "loss": 0.2582, "lr": 1.0336192731572803e-07, "epoch": 3.7643312101910826, "percentage": 54.12, "elapsed_time": "0:48:44", "remaining_time": "0:41:19"}
198
+ {"current_steps": 198, "total_steps": 364, "loss": 0.2555, "lr": 1.0240159832530007e-07, "epoch": 3.78343949044586, "percentage": 54.4, "elapsed_time": "0:49:00", "remaining_time": "0:41:04"}
199
+ {"current_steps": 199, "total_steps": 364, "loss": 0.2614, "lr": 1.0144104766775572e-07, "epoch": 3.802547770700637, "percentage": 54.67, "elapsed_time": "0:49:11", "remaining_time": "0:40:47"}
200
+ {"current_steps": 200, "total_steps": 364, "loss": 0.235, "lr": 1.0048036400175708e-07, "epoch": 3.821656050955414, "percentage": 54.95, "elapsed_time": "0:49:25", "remaining_time": "0:40:31"}
201
+ {"current_steps": 201, "total_steps": 364, "loss": 0.2433, "lr": 9.951963599824293e-08, "epoch": 3.840764331210191, "percentage": 55.22, "elapsed_time": "0:49:35", "remaining_time": "0:40:13"}
202
+ {"current_steps": 202, "total_steps": 364, "loss": 0.2589, "lr": 9.855895233224429e-08, "epoch": 3.859872611464968, "percentage": 55.49, "elapsed_time": "0:49:51", "remaining_time": "0:39:58"}
203
+ {"current_steps": 203, "total_steps": 364, "loss": 0.257, "lr": 9.759840167469994e-08, "epoch": 3.8789808917197455, "percentage": 55.77, "elapsed_time": "0:50:04", "remaining_time": "0:39:43"}
204
+ {"current_steps": 204, "total_steps": 364, "loss": 0.2489, "lr": 9.663807268427197e-08, "epoch": 3.8980891719745223, "percentage": 56.04, "elapsed_time": "0:50:19", "remaining_time": "0:39:28"}
205
+ {"current_steps": 205, "total_steps": 364, "loss": 0.2552, "lr": 9.567805399916259e-08, "epoch": 3.917197452229299, "percentage": 56.32, "elapsed_time": "0:50:33", "remaining_time": "0:39:12"}
206
+ {"current_steps": 206, "total_steps": 364, "loss": 0.2545, "lr": 9.471843422893297e-08, "epoch": 3.9363057324840764, "percentage": 56.59, "elapsed_time": "0:50:43", "remaining_time": "0:38:54"}
207
+ {"current_steps": 207, "total_steps": 364, "loss": 0.2541, "lr": 9.375930194632446e-08, "epoch": 3.9554140127388537, "percentage": 56.87, "elapsed_time": "0:50:57", "remaining_time": "0:38:39"}
208
+ {"current_steps": 208, "total_steps": 364, "loss": 0.2651, "lr": 9.28007456790833e-08, "epoch": 3.9745222929936306, "percentage": 57.14, "elapsed_time": "0:51:12", "remaining_time": "0:38:24"}
209
+ {"current_steps": 209, "total_steps": 364, "loss": 0.245, "lr": 9.184285390178977e-08, "epoch": 3.9936305732484074, "percentage": 57.42, "elapsed_time": "0:51:23", "remaining_time": "0:38:07"}
210
+ {"current_steps": 210, "total_steps": 364, "loss": 0.261, "lr": 9.088571502769167e-08, "epoch": 4.012738853503185, "percentage": 57.69, "elapsed_time": "0:53:53", "remaining_time": "0:39:31"}
211
+ {"current_steps": 211, "total_steps": 364, "loss": 0.2435, "lr": 8.992941740054417e-08, "epoch": 4.031847133757962, "percentage": 57.97, "elapsed_time": "0:54:06", "remaining_time": "0:39:14"}
212
+ {"current_steps": 212, "total_steps": 364, "loss": 0.2445, "lr": 8.897404928645527e-08, "epoch": 4.050955414012739, "percentage": 58.24, "elapsed_time": "0:54:20", "remaining_time": "0:38:57"}
213
+ {"current_steps": 213, "total_steps": 364, "loss": 0.2698, "lr": 8.801969886573929e-08, "epoch": 4.070063694267516, "percentage": 58.52, "elapsed_time": "0:54:33", "remaining_time": "0:38:40"}
214
+ {"current_steps": 214, "total_steps": 364, "loss": 0.2597, "lr": 8.706645422477737e-08, "epoch": 4.089171974522293, "percentage": 58.79, "elapsed_time": "0:54:48", "remaining_time": "0:38:24"}
215
+ {"current_steps": 215, "total_steps": 364, "loss": 0.2586, "lr": 8.611440334788762e-08, "epoch": 4.10828025477707, "percentage": 59.07, "elapsed_time": "0:55:01", "remaining_time": "0:38:08"}
216
+ {"current_steps": 216, "total_steps": 364, "loss": 0.2478, "lr": 8.516363410920375e-08, "epoch": 4.127388535031847, "percentage": 59.34, "elapsed_time": "0:55:11", "remaining_time": "0:37:49"}
217
+ {"current_steps": 217, "total_steps": 364, "loss": 0.2602, "lr": 8.42142342645646e-08, "epoch": 4.146496815286624, "percentage": 59.62, "elapsed_time": "0:55:24", "remaining_time": "0:37:32"}
218
+ {"current_steps": 218, "total_steps": 364, "loss": 0.2515, "lr": 8.326629144341405e-08, "epoch": 4.165605095541402, "percentage": 59.89, "elapsed_time": "0:55:36", "remaining_time": "0:37:14"}
219
+ {"current_steps": 219, "total_steps": 364, "loss": 0.2471, "lr": 8.231989314071316e-08, "epoch": 4.1847133757961785, "percentage": 60.16, "elapsed_time": "0:55:47", "remaining_time": "0:36:56"}
220
+ {"current_steps": 220, "total_steps": 364, "loss": 0.2615, "lr": 8.137512670886396e-08, "epoch": 4.203821656050955, "percentage": 60.44, "elapsed_time": "0:56:03", "remaining_time": "0:36:41"}
221
+ {"current_steps": 221, "total_steps": 364, "loss": 0.2577, "lr": 8.04320793496472e-08, "epoch": 4.222929936305732, "percentage": 60.71, "elapsed_time": "0:56:17", "remaining_time": "0:36:25"}