ryanmarten commited on
Commit
3df2364
·
verified ·
1 Parent(s): e6c2296

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 sha256:36ab3a512326afbfb91e564fa3aebd75d4a0bec68ee6a7d8119dbf502d8d3f6e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530b5fe68f256ec754016d6ea4d4c4143a50c27349815540d1ced1142cc277cc
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:e64dde9f02d5a6a4d92c75d1417fd887836c6cfe13d04490fde8649abdbd6be2
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:438fae48906d99040c30b8a7142d6902876b5adf1c3332cd61757d9133ff1d85
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64002d3f6dc24011e2667902de587efe522e50ac40697ef22c1c46cba58f944d
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af952f4ffc57b57f242ece1448151addcddea2dc8fc86ed94b19e6600d511dc9
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c3773cfd0f6b0962ea89b61415cd0d4b7b1a53b9d026e86030263d0fa2c2a08
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f4a3fdeeedef7ec88eae187b58b101b79cc78be93d9ec320c8c5652f0f419a
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -233,3 +233,82 @@
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.5153, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:37:24", "remaining_time": "7:09:29"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.4941, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:40:08", "remaining_time": "7:06:45"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4681, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:43:39", "remaining_time": "7:04:32"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.5153, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:37:24", "remaining_time": "7:09:29"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.4941, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:40:08", "remaining_time": "7:06:45"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4681, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:43:39", "remaining_time": "7:04:32"}
236
+ {"current_steps": 236, "total_steps": 390, "loss": 0.4347, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "10:46:26", "remaining_time": "7:01:49"}
237
+ {"current_steps": 237, "total_steps": 390, "loss": 0.422, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "10:49:10", "remaining_time": "6:59:05"}
238
+ {"current_steps": 238, "total_steps": 390, "loss": 0.4455, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "10:51:59", "remaining_time": "6:56:23"}
239
+ {"current_steps": 239, "total_steps": 390, "loss": 0.4216, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "10:54:41", "remaining_time": "6:53:38"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.4176, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "10:57:33", "remaining_time": "6:50:58"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.4325, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "11:00:17", "remaining_time": "6:48:13"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.4365, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "11:03:01", "remaining_time": "6:45:29"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.442, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "11:05:38", "remaining_time": "6:42:40"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.4237, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "11:08:07", "remaining_time": "6:39:46"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.435, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "11:10:45", "remaining_time": "6:36:58"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.4312, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "11:13:27", "remaining_time": "6:34:13"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.4269, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "11:16:10", "remaining_time": "6:31:28"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.4149, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "11:19:05", "remaining_time": "6:28:50"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.4307, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "11:21:50", "remaining_time": "6:26:06"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.4395, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "11:24:36", "remaining_time": "6:23:22"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.4165, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "11:27:08", "remaining_time": "6:20:31"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.4321, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "11:30:05", "remaining_time": "6:17:54"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.4251, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "11:32:56", "remaining_time": "6:15:13"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.4343, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "11:35:40", "remaining_time": "6:12:29"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.4275, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "11:38:28", "remaining_time": "6:09:47"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.419, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "11:41:16", "remaining_time": "6:07:04"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.423, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "11:44:00", "remaining_time": "6:04:20"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.433, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "11:46:35", "remaining_time": "6:01:30"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.4334, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "11:49:15", "remaining_time": "5:58:44"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.4341, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "11:51:49", "remaining_time": "5:55:54"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.4203, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "11:54:34", "remaining_time": "5:53:10"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.4103, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "11:57:05", "remaining_time": "5:50:20"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.4072, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "11:59:47", "remaining_time": "5:47:34"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.4268, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "12:02:31", "remaining_time": "5:44:50"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.4347, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "12:05:20", "remaining_time": "5:42:08"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.4422, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "12:08:06", "remaining_time": "5:39:24"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.4118, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "12:10:55", "remaining_time": "5:36:43"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.4181, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "12:13:29", "remaining_time": "5:33:54"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.4095, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "12:16:18", "remaining_time": "5:31:12"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.4339, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "12:19:08", "remaining_time": "5:28:30"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.4249, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "12:21:53", "remaining_time": "5:25:46"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.427, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "12:24:57", "remaining_time": "5:23:10"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.4205, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "12:27:44", "remaining_time": "5:20:27"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.4214, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "12:30:27", "remaining_time": "5:17:42"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.4299, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "12:33:16", "remaining_time": "5:15:00"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.4324, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "12:36:02", "remaining_time": "5:12:16"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.4385, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "12:38:38", "remaining_time": "5:09:28"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.4325, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "12:41:12", "remaining_time": "5:06:40"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.4194, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "12:44:08", "remaining_time": "5:04:00"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.4254, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "12:47:06", "remaining_time": "5:01:21"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.426, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "12:49:59", "remaining_time": "4:58:40"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.4213, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "12:52:40", "remaining_time": "4:55:55"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.4211, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "12:55:23", "remaining_time": "4:53:09"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.4338, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "12:58:19", "remaining_time": "4:50:29"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.4411, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "13:01:02", "remaining_time": "4:47:45"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.4216, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "13:03:42", "remaining_time": "4:44:58"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.4334, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "13:06:21", "remaining_time": "4:42:12"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.4287, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "13:08:57", "remaining_time": "4:39:25"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.4387, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "13:11:22", "remaining_time": "4:36:34"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.431, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "13:14:04", "remaining_time": "4:33:49"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.4302, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "13:16:43", "remaining_time": "4:31:03"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.4222, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "13:19:24", "remaining_time": "4:28:17"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.4378, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "13:22:15", "remaining_time": "4:25:35"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.4337, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "13:25:06", "remaining_time": "4:22:53"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.4313, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "13:27:41", "remaining_time": "4:20:06"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.4381, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "13:30:27", "remaining_time": "4:17:22"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.4377, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "13:33:18", "remaining_time": "4:14:40"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.4287, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "13:36:04", "remaining_time": "4:11:56"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.427, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "13:38:50", "remaining_time": "4:09:12"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.4409, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "13:41:33", "remaining_time": "4:06:28"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.4326, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "13:44:18", "remaining_time": "4:03:43"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.4245, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "13:47:04", "remaining_time": "4:01:00"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.4283, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "13:49:45", "remaining_time": "3:58:14"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.4239, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "13:52:33", "remaining_time": "3:55:31"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.4233, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "13:55:22", "remaining_time": "3:52:48"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.417, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "13:58:01", "remaining_time": "3:50:02"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.4236, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "14:00:44", "remaining_time": "3:47:18"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.4363, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "14:03:32", "remaining_time": "3:44:34"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.4307, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "14:06:15", "remaining_time": "3:41:50"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.4236, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "14:08:59", "remaining_time": "3:39:05"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.4351, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:11:38", "remaining_time": "3:36:19"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.4465, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:14:26", "remaining_time": "3:33:36"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.4174, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:17:52", "remaining_time": "3:31:02"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.3831, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "14:20:48", "remaining_time": "3:28:20"}