ryanmarten commited on
Commit
e12e6dc
·
verified ·
1 Parent(s): 4214463

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:dd925c4c401f9f04d9848002bc1feb3928ac470104c2b555a05978e15f4ab72e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da0d64a50aaebaa876fb6f78b3f18d7f3e4e38722de35a1c32670db927ce513a
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcf3c7ba3ae0a9f78568e8eff6d92f0cc2ce44e94a2e97740c551c4d03ec920
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e7dad299c4732ff65d52d06ac96e3b9548917e2f621f09a49ca09e79d73026
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:350643f6cff6bfd8f98981830b0e950419127bf66b5ad2748afdbefb5848a118
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882bec17f576e5d8f48f5b818b6cd924db5bcfab3f152c34d334ca3ba5f6408b
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:a4dc61815bc7ca31100d3ae8b6657f7d5aab0de2d39ac5a7992af5235feb8a54
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89850a89ac6f38ae35f64d16af0083b9389fae677a86c8ba0a06d27380e05f76
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -233,3 +233,81 @@
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.4939, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:21:12", "remaining_time": "6:58:34"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.473, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:23:59", "remaining_time": "6:55:59"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.444, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:27:36", "remaining_time": "6:53:57"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.4939, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:21:12", "remaining_time": "6:58:34"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.473, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:23:59", "remaining_time": "6:55:59"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.444, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:27:36", "remaining_time": "6:53:57"}
236
+ {"current_steps": 236, "total_steps": 390, "loss": 0.4121, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "10:30:15", "remaining_time": "6:51:16"}
237
+ {"current_steps": 237, "total_steps": 390, "loss": 0.4085, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "10:33:00", "remaining_time": "6:48:39"}
238
+ {"current_steps": 238, "total_steps": 390, "loss": 0.4236, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "10:35:34", "remaining_time": "6:45:54"}
239
+ {"current_steps": 239, "total_steps": 390, "loss": 0.4164, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "10:38:19", "remaining_time": "6:43:17"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.4163, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "10:41:08", "remaining_time": "6:40:42"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.3953, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "10:43:59", "remaining_time": "6:38:08"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.4084, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "10:46:29", "remaining_time": "6:35:22"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.4119, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "10:49:01", "remaining_time": "6:32:37"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.398, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "10:51:27", "remaining_time": "6:29:48"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.4115, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "10:54:14", "remaining_time": "6:27:12"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.4137, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "10:56:49", "remaining_time": "6:24:29"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.4215, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "10:59:27", "remaining_time": "6:21:47"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.4189, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "11:02:21", "remaining_time": "6:19:15"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.4322, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "11:04:54", "remaining_time": "6:16:31"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.3898, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "11:07:30", "remaining_time": "6:13:48"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.3897, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "11:10:06", "remaining_time": "6:11:05"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.4116, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "11:12:50", "remaining_time": "6:08:27"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.413, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "11:15:25", "remaining_time": "6:05:44"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.4092, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "11:18:01", "remaining_time": "6:03:02"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.3925, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "11:20:44", "remaining_time": "6:00:23"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.4175, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "11:23:28", "remaining_time": "5:57:45"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.4014, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "11:26:12", "remaining_time": "5:55:06"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.4133, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "11:28:56", "remaining_time": "5:52:28"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.3982, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "11:31:35", "remaining_time": "5:49:47"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.4206, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "11:34:23", "remaining_time": "5:47:11"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.4023, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "11:36:55", "remaining_time": "5:44:27"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.4023, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "11:39:37", "remaining_time": "5:41:48"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.4028, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "11:42:16", "remaining_time": "5:39:07"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.4157, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "11:44:57", "remaining_time": "5:36:27"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.407, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "11:47:45", "remaining_time": "5:33:51"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.4125, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "11:50:25", "remaining_time": "5:31:10"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.4083, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "11:53:11", "remaining_time": "5:28:33"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.4036, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "11:55:49", "remaining_time": "5:25:51"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.4082, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "11:58:27", "remaining_time": "5:23:10"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.4083, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "12:01:07", "remaining_time": "5:20:30"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.415, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "12:03:52", "remaining_time": "5:17:51"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.402, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "12:06:24", "remaining_time": "5:15:07"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.4086, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "12:09:11", "remaining_time": "5:12:30"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.4056, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "12:11:53", "remaining_time": "5:09:51"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.4058, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "12:14:30", "remaining_time": "5:07:09"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.41, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "12:17:20", "remaining_time": "5:04:33"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.4031, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "12:19:49", "remaining_time": "5:01:48"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.4151, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "12:22:24", "remaining_time": "4:59:06"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.4121, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "12:25:00", "remaining_time": "4:56:23"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.4179, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "12:27:46", "remaining_time": "4:53:45"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.414, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "12:30:28", "remaining_time": "4:51:06"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.4068, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "12:33:09", "remaining_time": "4:48:26"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.4061, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "12:35:54", "remaining_time": "4:45:48"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.4099, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "12:38:30", "remaining_time": "4:43:06"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.4106, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "12:41:06", "remaining_time": "4:40:24"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.4045, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "12:43:56", "remaining_time": "4:37:47"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.4263, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "12:46:42", "remaining_time": "4:35:09"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.4015, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "12:49:21", "remaining_time": "4:32:29"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.3845, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "12:52:10", "remaining_time": "4:29:51"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.4069, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "12:54:43", "remaining_time": "4:27:08"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.3962, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "12:57:31", "remaining_time": "4:24:31"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.4079, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "13:00:07", "remaining_time": "4:21:49"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.3917, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "13:02:50", "remaining_time": "4:19:10"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.4014, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "13:05:37", "remaining_time": "4:16:31"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.4072, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "13:08:16", "remaining_time": "4:13:50"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.4108, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "13:10:40", "remaining_time": "4:11:05"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.4072, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "13:13:29", "remaining_time": "4:08:28"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.4024, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "13:16:04", "remaining_time": "4:05:46"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.4175, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "13:18:45", "remaining_time": "4:03:06"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.3929, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "13:21:29", "remaining_time": "4:00:26"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.4125, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "13:24:00", "remaining_time": "3:57:43"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.4093, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "13:26:45", "remaining_time": "3:55:04"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.4134, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "13:29:17", "remaining_time": "3:52:22"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.4051, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "13:31:46", "remaining_time": "3:49:38"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.4068, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "13:34:33", "remaining_time": "3:47:00"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.3922, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "13:37:11", "remaining_time": "3:44:19"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.4144, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "13:39:45", "remaining_time": "3:41:37"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.4124, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "13:42:38", "remaining_time": "3:39:00"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.4087, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "13:45:19", "remaining_time": "3:36:20"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.4008, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "13:47:53", "remaining_time": "3:33:38"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.408, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "13:50:32", "remaining_time": "3:30:58"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.4116, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:53:05", "remaining_time": "3:28:16"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.3876, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:56:45", "remaining_time": "3:25:50"}