ryanmarten commited on
Commit
89dc811
·
verified ·
1 Parent(s): 611095b

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 sha256:734496dc0968271249fb7332972f8ee521b70acfb5393bce913f82736f167f6a
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56360302a6a784f7a617cf5daaaa53bb22cb5b2e2c5d15a048da38cedf42d8f7
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99083b4c4c8067379fed894b942430e4aa0f3a45c1b1745c548f6001ed0bc86f
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:742895f89c0ad155ce7f9c5b80fd849be9b16bd3770de7df85bc35f94bb5a586
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:ca6fc49efa7dec7524d2919ebdd48a3fcb48319f9ab5f7363f5c05217d3769ed
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:947b25005ce9913d0bc043ffa1b4be202519e9f698ae16347454c7e00d342ecc
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:d7e9f637d2ace71166483f2ea50743b6be32c3d3dc36ba02972f54778e21234f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824d63f1b8d2e9bbbf5cbe466be386c94b45adf34c0593d269a3a0f79e3fea52
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -233,3 +233,82 @@
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.503, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:33:22", "remaining_time": "7:06:47"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.4947, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:36:12", "remaining_time": "7:04:08"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4604, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:39:41", "remaining_time": "7:01:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.503, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:33:22", "remaining_time": "7:06:47"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.4947, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:36:12", "remaining_time": "7:04:08"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4604, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:39:41", "remaining_time": "7:01:55"}
236
+ {"current_steps": 236, "total_steps": 390, "loss": 0.4234, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "10:42:38", "remaining_time": "6:59:20"}
237
+ {"current_steps": 237, "total_steps": 390, "loss": 0.4251, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "10:45:20", "remaining_time": "6:56:36"}
238
+ {"current_steps": 238, "total_steps": 390, "loss": 0.4083, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "10:47:58", "remaining_time": "6:53:49"}
239
+ {"current_steps": 239, "total_steps": 390, "loss": 0.4193, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "10:50:45", "remaining_time": "6:51:08"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.4302, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "10:53:40", "remaining_time": "6:48:32"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.4174, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "10:56:30", "remaining_time": "6:45:53"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.4397, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "10:59:12", "remaining_time": "6:43:09"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.4166, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "11:01:55", "remaining_time": "6:40:25"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.4188, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "11:04:37", "remaining_time": "6:37:40"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.4262, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "11:07:14", "remaining_time": "6:34:53"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.4172, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "11:09:59", "remaining_time": "6:32:11"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.4311, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "11:12:48", "remaining_time": "6:29:31"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.4207, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "11:15:29", "remaining_time": "6:26:46"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.4226, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "11:18:13", "remaining_time": "6:24:03"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.428, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "11:20:59", "remaining_time": "6:21:21"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.4301, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "11:23:45", "remaining_time": "6:18:39"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.4195, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "11:26:21", "remaining_time": "6:15:52"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.4289, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "11:28:53", "remaining_time": "6:13:01"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.4165, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "11:31:36", "remaining_time": "6:10:18"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.4218, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "11:34:22", "remaining_time": "6:07:36"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.4174, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "11:37:00", "remaining_time": "6:04:50"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.4116, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "11:39:41", "remaining_time": "6:02:06"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.4065, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "11:42:35", "remaining_time": "5:59:27"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.4146, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "11:45:16", "remaining_time": "5:56:43"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.4189, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "11:48:01", "remaining_time": "5:54:00"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.4198, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "11:50:42", "remaining_time": "5:51:16"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.4262, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "11:53:18", "remaining_time": "5:48:29"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.4174, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "11:55:53", "remaining_time": "5:45:42"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.4097, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "11:58:36", "remaining_time": "5:42:58"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.4209, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "12:01:25", "remaining_time": "5:40:17"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.4237, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "12:04:11", "remaining_time": "5:37:35"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.4197, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "12:06:58", "remaining_time": "5:34:53"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.4259, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "12:09:45", "remaining_time": "5:32:12"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.4167, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "12:12:23", "remaining_time": "5:29:26"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.4345, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "12:15:24", "remaining_time": "5:26:50"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.4093, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "12:17:51", "remaining_time": "5:24:00"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.4339, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "12:20:37", "remaining_time": "5:21:17"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.4226, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "12:23:29", "remaining_time": "5:18:38"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.434, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "12:26:19", "remaining_time": "5:15:57"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.4213, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "12:28:58", "remaining_time": "5:13:12"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.4214, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "12:31:48", "remaining_time": "5:10:31"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.4275, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "12:34:39", "remaining_time": "5:07:51"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.4128, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "12:37:20", "remaining_time": "5:05:06"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.4247, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "12:40:13", "remaining_time": "5:02:27"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.4162, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "12:42:56", "remaining_time": "4:59:43"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.4346, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "12:45:50", "remaining_time": "4:57:04"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.425, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "12:48:11", "remaining_time": "4:54:12"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.4149, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "12:51:04", "remaining_time": "4:51:32"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.4105, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "12:53:39", "remaining_time": "4:48:45"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.4169, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "12:56:15", "remaining_time": "4:45:59"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.4216, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "12:59:04", "remaining_time": "4:43:18"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.4324, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "13:01:49", "remaining_time": "4:40:35"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.4146, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "13:04:35", "remaining_time": "4:37:52"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.429, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "13:07:13", "remaining_time": "4:35:07"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.4195, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "13:09:44", "remaining_time": "4:32:19"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.4368, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "13:12:28", "remaining_time": "4:29:36"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.4206, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "13:14:59", "remaining_time": "4:26:48"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.4229, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "13:17:43", "remaining_time": "4:24:05"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.4435, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "13:20:25", "remaining_time": "4:21:21"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.4282, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "13:23:11", "remaining_time": "4:18:39"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.4251, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "13:25:51", "remaining_time": "4:15:55"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.4076, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "13:28:31", "remaining_time": "4:13:10"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.4349, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "13:31:19", "remaining_time": "4:10:28"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.4329, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "13:34:04", "remaining_time": "4:07:45"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.4216, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "13:36:42", "remaining_time": "4:05:00"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.4112, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "13:39:15", "remaining_time": "4:02:14"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.4271, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "13:41:49", "remaining_time": "3:59:28"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.4269, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "13:44:33", "remaining_time": "3:56:45"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.4075, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "13:47:19", "remaining_time": "3:54:02"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.4346, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "13:50:13", "remaining_time": "3:51:22"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.4315, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "13:52:42", "remaining_time": "3:48:35"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.4211, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "13:55:21", "remaining_time": "3:45:50"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.4358, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "13:58:07", "remaining_time": "3:43:08"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.424, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "14:00:52", "remaining_time": "3:40:25"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.4082, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "14:03:34", "remaining_time": "3:37:41"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.4326, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:06:00", "remaining_time": "3:34:54"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.4236, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:08:37", "remaining_time": "3:32:09"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.4076, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:12:21", "remaining_time": "3:29:41"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.3949, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:15:03", "remaining_time": "3:26:57"}