neginr commited on
Commit
9564b9f
·
verified ·
1 Parent(s): a39f087

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:391b4390e3c3908dd4757881f77237afc78fbde09f8e6f4d8afa373eeca9b99b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39d46777be9efb26e03927650f911c28bdc01be7dbf72329a0c6499be810a8fd
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:991746ed92ad8cbe4e4e277df85434e10be489062f85ee7f85677d0f0e96e137
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8dd112708fadf24b889f42c3b955e48f80a60484ec51ca528998c723bbadf0d
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a9eba71bc9411dceb6451bde2053dc199a455d6356cd653e9047e16b5250799
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc9110714cc0cdcd6a2bb8e65acfbf951856bfc8f7856c179246b0087d17f242
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:b19316075650be25156b3990e0c27ffccdb087597da9985c9683929639b90218
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f4a208c5af0e45fe56d64a4dca68bedff1b6614b02a2c6d82c5ed660ba47ab0
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -219,3 +219,55 @@
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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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"}
222
+ {"current_steps": 222, "total_steps": 364, "loss": 0.2705, "lr": 7.949083810617357e-08, "epoch": 4.24203821656051, "percentage": 60.99, "elapsed_time": "0:56:30", "remaining_time": "0:36:08"}
223
+ {"current_steps": 223, "total_steps": 364, "loss": 0.2499, "lr": 7.855148985484945e-08, "epoch": 4.261146496815287, "percentage": 61.26, "elapsed_time": "0:56:42", "remaining_time": "0:35:51"}
224
+ {"current_steps": 224, "total_steps": 364, "loss": 0.2529, "lr": 7.761412129735851e-08, "epoch": 4.280254777070064, "percentage": 61.54, "elapsed_time": "0:56:55", "remaining_time": "0:35:34"}
225
+ {"current_steps": 225, "total_steps": 364, "loss": 0.2458, "lr": 7.667881895265893e-08, "epoch": 4.2993630573248405, "percentage": 61.81, "elapsed_time": "0:57:10", "remaining_time": "0:35:18"}
226
+ {"current_steps": 226, "total_steps": 364, "loss": 0.2548, "lr": 7.574566914899778e-08, "epoch": 4.318471337579618, "percentage": 62.09, "elapsed_time": "0:57:23", "remaining_time": "0:35:02"}
227
+ {"current_steps": 227, "total_steps": 364, "loss": 0.2534, "lr": 7.481475801594301e-08, "epoch": 4.337579617834395, "percentage": 62.36, "elapsed_time": "0:57:37", "remaining_time": "0:34:46"}
228
+ {"current_steps": 228, "total_steps": 364, "loss": 0.2422, "lr": 7.38861714764337e-08, "epoch": 4.356687898089172, "percentage": 62.64, "elapsed_time": "0:57:50", "remaining_time": "0:34:30"}
229
+ {"current_steps": 229, "total_steps": 364, "loss": 0.2592, "lr": 7.29599952388492e-08, "epoch": 4.375796178343949, "percentage": 62.91, "elapsed_time": "0:58:02", "remaining_time": "0:34:12"}
230
+ {"current_steps": 230, "total_steps": 364, "loss": 0.2487, "lr": 7.203631478909857e-08, "epoch": 4.3949044585987265, "percentage": 63.19, "elapsed_time": "0:58:11", "remaining_time": "0:33:53"}
231
+ {"current_steps": 231, "total_steps": 364, "loss": 0.2591, "lr": 7.111521538272996e-08, "epoch": 4.414012738853503, "percentage": 63.46, "elapsed_time": "0:58:26", "remaining_time": "0:33:38"}
232
+ {"current_steps": 232, "total_steps": 364, "loss": 0.2506, "lr": 7.019678203706163e-08, "epoch": 4.43312101910828, "percentage": 63.74, "elapsed_time": "0:58:41", "remaining_time": "0:33:23"}
233
+ {"current_steps": 233, "total_steps": 364, "loss": 0.2545, "lr": 6.928109952333506e-08, "epoch": 4.452229299363057, "percentage": 64.01, "elapsed_time": "0:58:56", "remaining_time": "0:33:08"}
234
+ {"current_steps": 234, "total_steps": 364, "loss": 0.2566, "lr": 6.836825235889018e-08, "epoch": 4.471337579617835, "percentage": 64.29, "elapsed_time": "0:59:10", "remaining_time": "0:32:52"}
235
+ {"current_steps": 235, "total_steps": 364, "loss": 0.2528, "lr": 6.74583247993649e-08, "epoch": 4.490445859872612, "percentage": 64.56, "elapsed_time": "0:59:25", "remaining_time": "0:32:37"}
236
+ {"current_steps": 236, "total_steps": 364, "loss": 0.2467, "lr": 6.655140083091793e-08, "epoch": 4.509554140127388, "percentage": 64.84, "elapsed_time": "0:59:38", "remaining_time": "0:32:20"}
237
+ {"current_steps": 237, "total_steps": 364, "loss": 0.2639, "lr": 6.56475641624771e-08, "epoch": 4.528662420382165, "percentage": 65.11, "elapsed_time": "0:59:49", "remaining_time": "0:32:03"}
238
+ {"current_steps": 238, "total_steps": 364, "loss": 0.2687, "lr": 6.474689821801294e-08, "epoch": 4.547770700636943, "percentage": 65.38, "elapsed_time": "1:00:01", "remaining_time": "0:31:46"}
239
+ {"current_steps": 239, "total_steps": 364, "loss": 0.2603, "lr": 6.384948612883871e-08, "epoch": 4.56687898089172, "percentage": 65.66, "elapsed_time": "1:00:13", "remaining_time": "0:31:30"}
240
+ {"current_steps": 240, "total_steps": 364, "loss": 0.2477, "lr": 6.29554107259374e-08, "epoch": 4.585987261146497, "percentage": 65.93, "elapsed_time": "1:00:27", "remaining_time": "0:31:14"}
241
+ {"current_steps": 241, "total_steps": 364, "loss": 0.2498, "lr": 6.206475453231643e-08, "epoch": 4.6050955414012735, "percentage": 66.21, "elapsed_time": "1:00:43", "remaining_time": "0:30:59"}
242
+ {"current_steps": 242, "total_steps": 364, "loss": 0.2536, "lr": 6.117759975539074e-08, "epoch": 4.624203821656051, "percentage": 66.48, "elapsed_time": "1:00:55", "remaining_time": "0:30:42"}
243
+ {"current_steps": 243, "total_steps": 364, "loss": 0.2475, "lr": 6.029402827939519e-08, "epoch": 4.643312101910828, "percentage": 66.76, "elapsed_time": "1:01:08", "remaining_time": "0:30:26"}
244
+ {"current_steps": 244, "total_steps": 364, "loss": 0.2646, "lr": 5.941412165782644e-08, "epoch": 4.662420382165605, "percentage": 67.03, "elapsed_time": "1:01:20", "remaining_time": "0:30:10"}
245
+ {"current_steps": 245, "total_steps": 364, "loss": 0.2516, "lr": 5.853796110591582e-08, "epoch": 4.681528662420382, "percentage": 67.31, "elapsed_time": "1:01:33", "remaining_time": "0:29:53"}
246
+ {"current_steps": 246, "total_steps": 364, "loss": 0.254, "lr": 5.7665627493133084e-08, "epoch": 4.7006369426751595, "percentage": 67.58, "elapsed_time": "1:01:48", "remaining_time": "0:29:39"}
247
+ {"current_steps": 247, "total_steps": 364, "loss": 0.2636, "lr": 5.6797201335722055e-08, "epoch": 4.719745222929936, "percentage": 67.86, "elapsed_time": "1:02:00", "remaining_time": "0:29:22"}
248
+ {"current_steps": 248, "total_steps": 364, "loss": 0.2439, "lr": 5.593276278926912e-08, "epoch": 4.738853503184713, "percentage": 68.13, "elapsed_time": "1:02:11", "remaining_time": "0:29:05"}
249
+ {"current_steps": 249, "total_steps": 364, "loss": 0.2547, "lr": 5.5072391641305003e-08, "epoch": 4.757961783439491, "percentage": 68.41, "elapsed_time": "1:02:24", "remaining_time": "0:28:49"}
250
+ {"current_steps": 250, "total_steps": 364, "loss": 0.2526, "lr": 5.4216167303939996e-08, "epoch": 4.777070063694268, "percentage": 68.68, "elapsed_time": "1:02:34", "remaining_time": "0:28:32"}
251
+ {"current_steps": 251, "total_steps": 364, "loss": 0.2547, "lr": 5.33641688065346e-08, "epoch": 4.796178343949045, "percentage": 68.96, "elapsed_time": "1:02:44", "remaining_time": "0:28:14"}
252
+ {"current_steps": 252, "total_steps": 364, "loss": 0.2484, "lr": 5.251647478840511e-08, "epoch": 4.8152866242038215, "percentage": 69.23, "elapsed_time": "1:02:59", "remaining_time": "0:27:59"}
253
+ {"current_steps": 253, "total_steps": 364, "loss": 0.2419, "lr": 5.167316349156494e-08, "epoch": 4.834394904458598, "percentage": 69.51, "elapsed_time": "1:03:11", "remaining_time": "0:27:43"}
254
+ {"current_steps": 254, "total_steps": 364, "loss": 0.2589, "lr": 5.0834312753503117e-08, "epoch": 4.853503184713376, "percentage": 69.78, "elapsed_time": "1:03:25", "remaining_time": "0:27:28"}
255
+ {"current_steps": 255, "total_steps": 364, "loss": 0.2599, "lr": 5.000000000000002e-08, "epoch": 4.872611464968153, "percentage": 70.05, "elapsed_time": "1:03:37", "remaining_time": "0:27:11"}
256
+ {"current_steps": 256, "total_steps": 364, "loss": 0.2457, "lr": 4.9170302237980564e-08, "epoch": 4.89171974522293, "percentage": 70.33, "elapsed_time": "1:03:51", "remaining_time": "0:26:56"}
257
+ {"current_steps": 257, "total_steps": 364, "loss": 0.2538, "lr": 4.8345296048406856e-08, "epoch": 4.9108280254777075, "percentage": 70.6, "elapsed_time": "1:04:05", "remaining_time": "0:26:41"}
258
+ {"current_steps": 258, "total_steps": 364, "loss": 0.2486, "lr": 4.752505757920977e-08, "epoch": 4.929936305732484, "percentage": 70.88, "elapsed_time": "1:04:18", "remaining_time": "0:26:25"}
259
+ {"current_steps": 259, "total_steps": 364, "loss": 0.2581, "lr": 4.6709662538260266e-08, "epoch": 4.949044585987261, "percentage": 71.15, "elapsed_time": "1:04:35", "remaining_time": "0:26:11"}
260
+ {"current_steps": 260, "total_steps": 364, "loss": 0.2537, "lr": 4.5899186186381725e-08, "epoch": 4.968152866242038, "percentage": 71.43, "elapsed_time": "1:04:50", "remaining_time": "0:25:56"}
261
+ {"current_steps": 261, "total_steps": 364, "loss": 0.2535, "lr": 4.5093703330403374e-08, "epoch": 4.987261146496815, "percentage": 71.7, "elapsed_time": "1:05:04", "remaining_time": "0:25:40"}
262
+ {"current_steps": 262, "total_steps": 364, "loss": 0.2585, "lr": 4.429328831625565e-08, "epoch": 5.006369426751593, "percentage": 71.98, "elapsed_time": "1:07:07", "remaining_time": "0:26:07"}
263
+ {"current_steps": 263, "total_steps": 364, "loss": 0.2653, "lr": 4.3498015022108e-08, "epoch": 5.025477707006369, "percentage": 72.25, "elapsed_time": "1:07:21", "remaining_time": "0:25:51"}
264
+ {"current_steps": 264, "total_steps": 364, "loss": 0.257, "lr": 4.270795685155001e-08, "epoch": 5.044585987261146, "percentage": 72.53, "elapsed_time": "1:07:35", "remaining_time": "0:25:36"}
265
+ {"current_steps": 265, "total_steps": 364, "loss": 0.2559, "lr": 4.1923186726816305e-08, "epoch": 5.063694267515924, "percentage": 72.8, "elapsed_time": "1:07:51", "remaining_time": "0:25:21"}
266
+ {"current_steps": 266, "total_steps": 364, "loss": 0.2627, "lr": 4.114377708205571e-08, "epoch": 5.082802547770701, "percentage": 73.08, "elapsed_time": "1:08:03", "remaining_time": "0:25:04"}
267
+ {"current_steps": 267, "total_steps": 364, "loss": 0.2494, "lr": 4.036979985664566e-08, "epoch": 5.101910828025478, "percentage": 73.35, "elapsed_time": "1:08:16", "remaining_time": "0:24:48"}
268
+ {"current_steps": 268, "total_steps": 364, "loss": 0.258, "lr": 3.9601326488552255e-08, "epoch": 5.1210191082802545, "percentage": 73.63, "elapsed_time": "1:08:27", "remaining_time": "0:24:31"}
269
+ {"current_steps": 269, "total_steps": 364, "loss": 0.2427, "lr": 3.883842790773647e-08, "epoch": 5.140127388535032, "percentage": 73.9, "elapsed_time": "1:08:43", "remaining_time": "0:24:16"}
270
+ {"current_steps": 270, "total_steps": 364, "loss": 0.2547, "lr": 3.808117452960734e-08, "epoch": 5.159235668789809, "percentage": 74.18, "elapsed_time": "1:08:57", "remaining_time": "0:24:00"}
271
+ {"current_steps": 271, "total_steps": 364, "loss": 0.2535, "lr": 3.732963624852274e-08, "epoch": 5.178343949044586, "percentage": 74.45, "elapsed_time": "1:09:11", "remaining_time": "0:23:44"}
272
+ {"current_steps": 272, "total_steps": 364, "loss": 0.2587, "lr": 3.658388243133804e-08, "epoch": 5.197452229299363, "percentage": 74.73, "elapsed_time": "1:09:22", "remaining_time": "0:23:27"}
273
+ {"current_steps": 273, "total_steps": 364, "loss": 0.2452, "lr": 3.584398191100341e-08, "epoch": 5.2165605095541405, "percentage": 75.0, "elapsed_time": "1:09:32", "remaining_time": "0:23:10"}