ryanmarten commited on
Commit
0e5a594
·
verified ·
1 Parent(s): b7a3c5e

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 sha256:711d22bfe7d8b0c214183e970e40488ec2df40673b015c5a9f56cd7d86dbb2bc
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ef606a6a1dbd2cc6781510d5f8cf52263d2499e1c2cee5c30cd6917f53ba851
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9676162ffea546fa6e1099162aa66a98725b10031a36d5036954a802ce527aad
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ec3a4ad88368590bbd27925a6518fca821ea5c86fae32dafe2332d1e1a9c62
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:120ce412abce3dfd8727da19f5a22a3537321366ed54c61595602f623db856b6
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67b7c037426baaf551dc663a3862693762c7d59c7d4488887c33cb7a3415f6d1
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ef2bfd36c81586450d88f3a997ed07e3ea1d4e3f0b8fb048c5715b53c77bb97
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f8d75e889d5b031ac146a2b7e624e6c4c712a003ef227ae50e2e98662c9545c
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -234,3 +234,80 @@
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.5001, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "8:27:38", "remaining_time": "5:38:25"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4762, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "8:30:39", "remaining_time": "5:36:48"}
236
  {"current_steps": 236, "total_steps": 390, "loss": 0.458, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "8:32:37", "remaining_time": "5:34:30"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.5001, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "8:27:38", "remaining_time": "5:38:25"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4762, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "8:30:39", "remaining_time": "5:36:48"}
236
  {"current_steps": 236, "total_steps": 390, "loss": 0.458, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "8:32:37", "remaining_time": "5:34:30"}
237
+ {"current_steps": 237, "total_steps": 390, "loss": 0.442, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "8:34:41", "remaining_time": "5:32:16"}
238
+ {"current_steps": 238, "total_steps": 390, "loss": 0.4264, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "8:36:50", "remaining_time": "5:30:04"}
239
+ {"current_steps": 239, "total_steps": 390, "loss": 0.4542, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "8:39:08", "remaining_time": "5:27:59"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.4314, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "8:41:18", "remaining_time": "5:25:48"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.4268, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "8:43:32", "remaining_time": "5:23:41"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.4426, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "8:45:45", "remaining_time": "5:21:32"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.4364, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "8:48:00", "remaining_time": "5:19:24"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.4353, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "8:50:05", "remaining_time": "5:17:11"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.4335, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "8:52:18", "remaining_time": "5:15:02"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.4253, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "8:54:32", "remaining_time": "5:12:54"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.4211, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "8:56:40", "remaining_time": "5:10:42"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.4415, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "8:58:53", "remaining_time": "5:08:33"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.4378, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "9:00:49", "remaining_time": "5:06:14"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.4126, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "9:02:47", "remaining_time": "5:03:57"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.4305, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "9:05:07", "remaining_time": "5:01:52"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.4392, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "9:07:25", "remaining_time": "4:59:46"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.4272, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "9:09:28", "remaining_time": "4:57:32"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.427, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "9:11:45", "remaining_time": "4:55:25"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.4558, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "9:13:48", "remaining_time": "4:53:11"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.4096, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "9:15:52", "remaining_time": "4:50:58"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.4126, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "9:18:07", "remaining_time": "4:48:50"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.4203, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "9:20:20", "remaining_time": "4:46:41"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.4306, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "9:22:28", "remaining_time": "4:44:29"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.4484, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "9:24:38", "remaining_time": "4:42:19"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.4409, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "9:26:58", "remaining_time": "4:40:13"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.4106, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "9:28:57", "remaining_time": "4:37:57"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.425, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "9:31:17", "remaining_time": "4:35:52"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.4342, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "9:33:32", "remaining_time": "4:33:44"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.4357, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "9:35:32", "remaining_time": "4:31:29"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.4185, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "9:37:52", "remaining_time": "4:29:23"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.4245, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "9:40:09", "remaining_time": "4:27:15"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.4172, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "9:42:16", "remaining_time": "4:25:03"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.4401, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "9:44:19", "remaining_time": "4:22:50"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.4124, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "9:46:11", "remaining_time": "4:20:31"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.4104, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "9:48:14", "remaining_time": "4:18:18"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.4376, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "9:50:26", "remaining_time": "4:16:08"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.4209, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "9:52:45", "remaining_time": "4:14:02"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.4198, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "9:54:42", "remaining_time": "4:11:46"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.4252, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "9:56:52", "remaining_time": "4:09:36"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.4129, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "9:59:09", "remaining_time": "4:07:28"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.4348, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "10:01:32", "remaining_time": "4:05:23"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.4186, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "10:03:40", "remaining_time": "4:03:12"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.4492, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "10:05:52", "remaining_time": "4:01:03"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.4425, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "10:08:14", "remaining_time": "3:58:57"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.4311, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "10:10:16", "remaining_time": "3:56:43"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.44, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "10:12:17", "remaining_time": "3:54:29"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.4246, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "10:14:26", "remaining_time": "3:52:19"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.4295, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "10:16:32", "remaining_time": "3:50:07"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.424, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "10:18:44", "remaining_time": "3:47:57"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.4231, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "10:20:57", "remaining_time": "3:45:48"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.4289, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "10:23:13", "remaining_time": "3:43:39"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.4423, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "10:25:23", "remaining_time": "3:41:29"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.4379, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "10:27:37", "remaining_time": "3:39:20"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.44, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "10:29:53", "remaining_time": "3:37:12"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.4091, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "10:31:54", "remaining_time": "3:34:58"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.444, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "10:34:13", "remaining_time": "3:32:51"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.4443, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "10:36:18", "remaining_time": "3:30:39"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.4398, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "10:38:31", "remaining_time": "3:28:29"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.4328, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "10:40:34", "remaining_time": "3:26:17"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.4238, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "10:42:37", "remaining_time": "3:24:04"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.4224, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "10:44:37", "remaining_time": "3:21:51"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.4316, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "10:46:47", "remaining_time": "3:19:40"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.427, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "10:48:47", "remaining_time": "3:17:27"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.4207, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "10:50:45", "remaining_time": "3:15:13"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.4214, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "10:52:58", "remaining_time": "3:13:04"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.4411, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "10:55:13", "remaining_time": "3:10:55"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.419, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "10:57:21", "remaining_time": "3:08:44"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.4118, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "10:59:19", "remaining_time": "3:06:31"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.4329, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "11:01:37", "remaining_time": "3:04:23"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.4292, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "11:03:46", "remaining_time": "3:02:12"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.4394, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "11:05:59", "remaining_time": "3:00:03"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.4567, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "11:08:10", "remaining_time": "2:57:53"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.4268, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "11:10:17", "remaining_time": "2:55:42"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.4377, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "11:12:47", "remaining_time": "2:53:37"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.4118, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "11:14:50", "remaining_time": "2:51:25"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.4171, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "11:17:25", "remaining_time": "2:49:21"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.4324, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "11:21:34", "remaining_time": "2:47:40"}