ryanmarten commited on
Commit
bd3b385
·
verified ·
1 Parent(s): ef5714a

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 sha256:3ecfe7c7a460363e58b26f97818d9809ed2fa932926e332c1bf3363456b10c8e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee13a3b07c7b5e46e8cffa748e78d08c235594e61fa97bb93f07dbb374d935f
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:d9859578f61ee847a0428f0745fdead6dfd1566f77dc6133aeb5a44dc864d852
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b847e4b772ae13883c96030b6b798beb1cca591078a2ea2c121f364a5d582e0b
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c2c0aa8cf7287002f4285a137ae031c466f8277e41b700cc0f655d2f38fe242
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:161a767cb8fafa31641f42a4888fe5ebe719038c414f508e9d723a33337def39
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:e274f04aecea9105c0700b3b2cb4f16864a5844151b05c0cfbf1631903bb948b
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66edd0f9aa281fb90782ddce888636ecd7e7110b4c4a81b3ea1e9b27e9ad137f
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -237,3 +237,80 @@
237
  {"current_steps": 237, "total_steps": 390, "loss": 0.2045, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "5:28:02", "remaining_time": "3:31:46"}
238
  {"current_steps": 238, "total_steps": 390, "loss": 0.1701, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "5:29:20", "remaining_time": "3:30:19"}
239
  {"current_steps": 239, "total_steps": 390, "loss": 0.1856, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "5:30:39", "remaining_time": "3:28:54"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
237
  {"current_steps": 237, "total_steps": 390, "loss": 0.2045, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "5:28:02", "remaining_time": "3:31:46"}
238
  {"current_steps": 238, "total_steps": 390, "loss": 0.1701, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "5:29:20", "remaining_time": "3:30:19"}
239
  {"current_steps": 239, "total_steps": 390, "loss": 0.1856, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "5:30:39", "remaining_time": "3:28:54"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.1933, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "5:32:11", "remaining_time": "3:27:36"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.1826, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "5:33:33", "remaining_time": "3:26:13"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.1796, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "5:34:41", "remaining_time": "3:24:41"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.1836, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "5:36:02", "remaining_time": "3:23:17"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.1638, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "5:37:18", "remaining_time": "3:21:49"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.1771, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "5:38:42", "remaining_time": "3:20:27"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.1902, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "5:40:05", "remaining_time": "3:19:04"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.1754, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "5:41:28", "remaining_time": "3:17:41"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.1832, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "5:42:55", "remaining_time": "3:16:20"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.1812, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "5:44:12", "remaining_time": "3:14:54"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.1549, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "5:45:11", "remaining_time": "3:13:18"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.1951, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "5:46:43", "remaining_time": "3:12:00"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.1929, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "5:48:12", "remaining_time": "3:10:41"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.1885, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "5:49:35", "remaining_time": "3:09:18"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.1562, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "5:50:42", "remaining_time": "3:07:46"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.1694, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "5:51:55", "remaining_time": "3:06:18"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.1854, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "5:53:18", "remaining_time": "3:04:55"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.1733, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "5:54:43", "remaining_time": "3:03:34"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.173, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "5:56:17", "remaining_time": "3:02:17"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.1988, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "5:57:35", "remaining_time": "3:00:51"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.199, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "5:58:58", "remaining_time": "2:59:29"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.1861, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "6:00:21", "remaining_time": "2:58:06"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.1647, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "6:01:38", "remaining_time": "2:56:40"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.2021, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "6:03:01", "remaining_time": "2:55:18"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.1726, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "6:04:18", "remaining_time": "2:53:52"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.1778, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "6:05:59", "remaining_time": "2:52:38"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.1747, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "6:07:24", "remaining_time": "2:51:16"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.2, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "6:08:53", "remaining_time": "2:49:56"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.1743, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "6:10:03", "remaining_time": "2:48:27"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.2065, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "6:11:39", "remaining_time": "2:47:10"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.1719, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "6:12:46", "remaining_time": "2:45:40"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.1786, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "6:14:07", "remaining_time": "2:44:16"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.196, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "6:15:25", "remaining_time": "2:42:52"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.1869, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "6:16:48", "remaining_time": "2:41:29"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.1835, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "6:17:55", "remaining_time": "2:39:59"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.1833, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "6:19:28", "remaining_time": "2:38:41"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.1793, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "6:20:52", "remaining_time": "2:37:18"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.1831, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "6:22:07", "remaining_time": "2:35:52"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.1995, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "6:23:48", "remaining_time": "2:34:37"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.1825, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "6:25:05", "remaining_time": "2:33:12"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.1792, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "6:26:14", "remaining_time": "2:31:44"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.1647, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "6:27:29", "remaining_time": "2:30:18"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.16, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "6:28:44", "remaining_time": "2:28:52"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.206, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "6:30:07", "remaining_time": "2:27:30"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.171, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "6:31:20", "remaining_time": "2:26:03"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.1727, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "6:32:40", "remaining_time": "2:24:40"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.175, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "6:34:07", "remaining_time": "2:23:19"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.194, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "6:35:27", "remaining_time": "2:21:55"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.1851, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "6:36:58", "remaining_time": "2:20:35"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.161, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "6:38:12", "remaining_time": "2:19:09"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.2011, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "6:39:39", "remaining_time": "2:17:48"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.1844, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "6:40:50", "remaining_time": "2:16:22"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.1681, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "6:41:57", "remaining_time": "2:14:54"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.1913, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "6:43:21", "remaining_time": "2:13:32"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.1879, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "6:44:50", "remaining_time": "2:12:11"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.1673, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "6:46:00", "remaining_time": "2:10:44"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.1466, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "6:47:17", "remaining_time": "2:09:20"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.197, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "6:48:39", "remaining_time": "2:07:57"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.1706, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "6:49:57", "remaining_time": "2:06:33"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.1864, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "6:51:23", "remaining_time": "2:05:12"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.2074, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "6:52:53", "remaining_time": "2:03:51"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.1977, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "6:54:25", "remaining_time": "2:02:32"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.1888, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "6:55:48", "remaining_time": "2:01:09"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.1734, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "6:57:01", "remaining_time": "1:59:44"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.1855, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "6:58:32", "remaining_time": "1:58:24"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.1961, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "6:59:55", "remaining_time": "1:57:01"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.1795, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "7:01:09", "remaining_time": "1:55:36"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.175, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "7:02:23", "remaining_time": "1:54:11"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.1811, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "7:03:44", "remaining_time": "1:52:48"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.1806, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "7:05:15", "remaining_time": "1:51:28"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.1868, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "7:06:48", "remaining_time": "1:50:08"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.17, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "7:08:07", "remaining_time": "1:48:45"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.1616, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "7:09:24", "remaining_time": "1:47:21"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.147, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "7:12:07", "remaining_time": "1:46:18"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.1303, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "7:13:15", "remaining_time": "1:44:52"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.1392, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "7:14:42", "remaining_time": "1:43:30"}
316
+ {"current_steps": 316, "total_steps": 390, "loss": 0.1489, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "7:16:04", "remaining_time": "1:42:07"}