ryanmarten commited on
Commit
80ad6e6
·
verified ·
1 Parent(s): 28033b5

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:ce12b0da4dcb0e37e50b27cd48c525ae584cc2f777430c24efa46d2956849573
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d53820cd4e4da416737e86c9e53e185dcfdac35c73484d492fd64e9d1fdbb66b
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:ecd1efc4929e296efce1176c6df31d21bfa9eb6edacd879c39cf1d4efd6d54d1
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486b949cb9726b99451af5e193aaad23218de87658b02fbbd9671d4fd4ce37ed
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:bbffea54b84d13dabd4f357e6cc2a4c6d427a57e82d2b54db8665e7ecfeced28
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f95d18439e5c3dda22dda70abfa89ac16b24a1b20a2dc7a294710e3944e4f4
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:461b7445e9fdbc83b1cd3cf7a712d4c4cd4eb5e8f58d5c1c47386c6b4d25ab35
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce7521b7d00146f9c3ab5630e1b88775d37a050b60da61d4dca56d5179848774
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -233,3 +233,82 @@
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.5091, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:30:03", "remaining_time": "7:04:32"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.4876, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:32:45", "remaining_time": "7:01:50"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4404, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:36:00", "remaining_time": "6:59:29"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.5091, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:30:03", "remaining_time": "7:04:32"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.4876, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:32:45", "remaining_time": "7:01:50"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4404, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:36:00", "remaining_time": "6:59:29"}
236
+ {"current_steps": 236, "total_steps": 390, "loss": 0.4221, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "10:38:49", "remaining_time": "6:56:51"}
237
+ {"current_steps": 237, "total_steps": 390, "loss": 0.4452, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "10:41:33", "remaining_time": "6:54:10"}
238
+ {"current_steps": 238, "total_steps": 390, "loss": 0.433, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "10:44:12", "remaining_time": "6:51:25"}
239
+ {"current_steps": 239, "total_steps": 390, "loss": 0.4234, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "10:46:52", "remaining_time": "6:48:41"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.4103, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "10:49:29", "remaining_time": "6:45:56"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.4306, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "10:52:00", "remaining_time": "6:43:06"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.4188, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "10:54:38", "remaining_time": "6:40:21"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.4253, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "10:57:25", "remaining_time": "6:37:42"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.4395, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "11:00:10", "remaining_time": "6:35:01"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.4084, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "11:02:51", "remaining_time": "6:32:18"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.4076, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "11:05:36", "remaining_time": "6:29:37"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.4168, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "11:08:23", "remaining_time": "6:26:57"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.4259, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "11:10:59", "remaining_time": "6:24:11"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.4136, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "11:13:43", "remaining_time": "6:21:30"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.4189, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "11:16:23", "remaining_time": "6:18:47"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.4242, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "11:18:59", "remaining_time": "6:16:00"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.4173, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "11:21:28", "remaining_time": "6:13:11"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.4107, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "11:24:17", "remaining_time": "6:10:32"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.4033, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "11:27:03", "remaining_time": "6:07:52"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.4249, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "11:29:44", "remaining_time": "6:05:09"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.409, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "11:32:23", "remaining_time": "6:02:25"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.4062, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "11:35:07", "remaining_time": "5:59:44"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.4068, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "11:37:56", "remaining_time": "5:57:05"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.4191, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "11:40:32", "remaining_time": "5:54:19"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.4262, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "11:43:23", "remaining_time": "5:51:41"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.423, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "11:46:12", "remaining_time": "5:49:02"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.4188, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "11:48:46", "remaining_time": "5:46:16"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.4274, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "11:51:28", "remaining_time": "5:43:34"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.4304, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "11:54:15", "remaining_time": "5:40:53"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.4187, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "11:56:48", "remaining_time": "5:38:07"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.4293, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "11:59:24", "remaining_time": "5:35:21"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.4271, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "12:02:02", "remaining_time": "5:32:37"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.4031, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "12:04:44", "remaining_time": "5:29:55"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.4128, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "12:07:35", "remaining_time": "5:27:16"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.4211, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "12:10:14", "remaining_time": "5:24:33"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.416, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "12:13:10", "remaining_time": "5:21:57"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.4256, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "12:15:49", "remaining_time": "5:19:13"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.4205, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "12:18:40", "remaining_time": "5:16:34"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.4294, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "12:21:18", "remaining_time": "5:13:50"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.4204, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "12:23:56", "remaining_time": "5:11:05"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.4118, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "12:26:31", "remaining_time": "5:08:20"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.4072, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "12:29:21", "remaining_time": "5:05:41"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.4224, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "12:32:02", "remaining_time": "5:02:58"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.4103, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "12:34:47", "remaining_time": "5:00:17"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.4207, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "12:37:21", "remaining_time": "4:57:32"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.4155, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "12:39:53", "remaining_time": "4:54:45"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.4129, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "12:42:31", "remaining_time": "4:52:01"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.3999, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "12:45:11", "remaining_time": "4:49:18"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.4312, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "12:47:48", "remaining_time": "4:46:34"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.4305, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "12:50:36", "remaining_time": "4:43:54"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.4104, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "12:53:22", "remaining_time": "4:41:13"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.4348, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "12:56:09", "remaining_time": "4:38:33"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.4208, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "12:58:48", "remaining_time": "4:35:49"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.4068, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "13:01:29", "remaining_time": "4:33:06"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.4194, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "13:04:13", "remaining_time": "4:30:25"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.4262, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "13:06:53", "remaining_time": "4:27:42"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.4225, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "13:09:33", "remaining_time": "4:24:59"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.4163, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "13:12:06", "remaining_time": "4:22:13"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.4229, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "13:14:54", "remaining_time": "4:19:33"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.4212, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "13:17:33", "remaining_time": "4:16:50"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.4223, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "13:20:12", "remaining_time": "4:14:07"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.4233, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "13:22:56", "remaining_time": "4:11:25"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.4165, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "13:25:33", "remaining_time": "4:08:41"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.4267, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "13:28:12", "remaining_time": "4:05:58"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.4313, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "13:30:56", "remaining_time": "4:03:16"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.412, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "13:33:38", "remaining_time": "4:00:34"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.4167, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "13:36:25", "remaining_time": "3:57:53"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.4154, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "13:39:06", "remaining_time": "3:55:11"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.3953, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "13:41:50", "remaining_time": "3:52:29"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.4226, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "13:44:34", "remaining_time": "3:49:47"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.4261, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "13:47:17", "remaining_time": "3:47:06"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.4278, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "13:50:10", "remaining_time": "3:44:26"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.4314, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "13:52:54", "remaining_time": "3:41:45"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.4187, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "13:55:44", "remaining_time": "3:39:04"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.4284, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "13:58:32", "remaining_time": "3:36:23"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.4205, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:01:19", "remaining_time": "3:33:42"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.4127, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:03:40", "remaining_time": "3:30:55"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.4013, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:07:15", "remaining_time": "3:28:25"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.3924, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:10:07", "remaining_time": "3:25:45"}