ryanmarten commited on
Commit
97957e4
·
verified ·
1 Parent(s): 11f2f8c

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:e1e97dc99e9570ebc6969e632deaa39514c96393bf5da82d090796e582d7cb81
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d4e7d4d5f58daa215ecaf99cef39bfb969c8a9625008d379ab6078b13148e9
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b3bd5a5f4f17460160e794c133239356864c683046d5f91860e536ba7a18868
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbd32c37255d06f0d7dcca68b7ccd44a6ce5d5094d712e6424be76b479f283b2
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:f6ee32515504e4ad08d0225a413c2a6d168c4f1a01b236ea8f7cac1a3cbc0c3b
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d50955468ad0a3d45b80ba1b3168309f7458dcf44bf848bf3877355a69efbfd4
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:adb9dbaf07b0c079adf7f9305d112ea247cf7c825e0c8685a6c76a234ab7a563
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c991d1fb397011211f45145739d25bc51dbe4fec033a6d9291118e2b42bf7adc
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -233,3 +233,81 @@
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.511, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:45:43", "remaining_time": "7:15:06"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.4873, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:48:30", "remaining_time": "7:12:20"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4636, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:52:13", "remaining_time": "7:10:11"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.511, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:45:43", "remaining_time": "7:15:06"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.4873, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:48:30", "remaining_time": "7:12:20"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.4636, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:52:13", "remaining_time": "7:10:11"}
236
+ {"current_steps": 236, "total_steps": 390, "loss": 0.4117, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "10:54:57", "remaining_time": "7:07:23"}
237
+ {"current_steps": 237, "total_steps": 390, "loss": 0.417, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "10:57:48", "remaining_time": "7:04:39"}
238
+ {"current_steps": 238, "total_steps": 390, "loss": 0.4022, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "11:00:29", "remaining_time": "7:01:49"}
239
+ {"current_steps": 239, "total_steps": 390, "loss": 0.411, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "11:03:21", "remaining_time": "6:59:06"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.415, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "11:06:06", "remaining_time": "6:56:19"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.4098, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "11:08:54", "remaining_time": "6:53:33"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.4113, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "11:11:36", "remaining_time": "6:50:43"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.4182, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "11:14:22", "remaining_time": "6:47:57"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.415, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "11:16:58", "remaining_time": "6:45:04"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.4123, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "11:19:50", "remaining_time": "6:42:21"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.4059, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "11:22:43", "remaining_time": "6:39:38"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.421, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "11:25:30", "remaining_time": "6:36:52"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.4126, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "11:28:01", "remaining_time": "6:33:57"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.4232, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "11:30:46", "remaining_time": "6:31:09"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.4127, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "11:33:27", "remaining_time": "6:28:20"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.3953, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "11:36:16", "remaining_time": "6:25:35"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.4011, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "11:38:50", "remaining_time": "6:22:41"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.4153, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "11:41:39", "remaining_time": "6:19:56"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.4154, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "11:44:31", "remaining_time": "6:17:13"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.4158, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "11:47:27", "remaining_time": "6:14:32"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.4232, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "11:50:25", "remaining_time": "6:11:51"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.4037, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "11:53:07", "remaining_time": "6:09:02"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.4036, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "11:55:44", "remaining_time": "6:06:11"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.4098, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "11:58:33", "remaining_time": "6:03:26"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.4129, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "12:01:21", "remaining_time": "6:00:40"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.4205, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "12:04:21", "remaining_time": "5:58:00"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.4128, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "12:07:11", "remaining_time": "5:55:16"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.4169, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "12:10:04", "remaining_time": "5:52:32"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.4047, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "12:12:54", "remaining_time": "5:49:47"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.4273, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "12:15:46", "remaining_time": "5:47:03"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.4088, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "12:18:29", "remaining_time": "5:44:15"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.4038, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "12:21:01", "remaining_time": "5:41:22"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.4169, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "12:23:51", "remaining_time": "5:38:37"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.4249, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "12:26:41", "remaining_time": "5:35:52"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.4138, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "12:29:27", "remaining_time": "5:33:05"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.4118, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "12:32:15", "remaining_time": "5:30:19"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.4106, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "12:35:05", "remaining_time": "5:27:34"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.414, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "12:37:55", "remaining_time": "5:24:49"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.4011, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "12:40:37", "remaining_time": "5:22:00"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.4138, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "12:43:21", "remaining_time": "5:19:13"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.4216, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "12:46:12", "remaining_time": "5:16:28"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.4023, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "12:48:53", "remaining_time": "5:13:39"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.4041, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "12:51:30", "remaining_time": "5:10:49"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.4019, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "12:54:13", "remaining_time": "5:08:01"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.4324, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "12:57:09", "remaining_time": "5:05:18"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.4177, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "12:59:55", "remaining_time": "5:02:31"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.3984, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "13:02:56", "remaining_time": "4:59:51"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.4216, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "13:05:52", "remaining_time": "4:57:07"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.4122, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "13:08:43", "remaining_time": "4:54:22"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.4134, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "13:11:23", "remaining_time": "4:51:34"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.3889, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "13:14:00", "remaining_time": "4:48:43"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.4205, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "13:16:44", "remaining_time": "4:45:56"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.4166, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "13:19:22", "remaining_time": "4:43:06"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.4086, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "13:22:15", "remaining_time": "4:40:22"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.4047, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "13:24:47", "remaining_time": "4:37:30"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.4049, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "13:27:37", "remaining_time": "4:34:45"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.4017, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "13:30:25", "remaining_time": "4:31:59"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.4118, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "13:33:12", "remaining_time": "4:29:13"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.4279, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "13:36:10", "remaining_time": "4:26:30"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.4122, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "13:38:53", "remaining_time": "4:23:42"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.4246, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "13:41:34", "remaining_time": "4:20:54"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.4194, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "13:44:20", "remaining_time": "4:18:07"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.4161, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "13:47:00", "remaining_time": "4:15:18"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.4253, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "13:49:37", "remaining_time": "4:12:29"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.416, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "13:52:23", "remaining_time": "4:09:43"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.4064, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "13:55:08", "remaining_time": "4:06:56"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.422, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "13:57:55", "remaining_time": "4:04:09"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.4196, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "14:00:43", "remaining_time": "4:01:23"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.42, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "14:03:34", "remaining_time": "3:58:38"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.4171, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "14:06:35", "remaining_time": "3:55:56"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.4022, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "14:09:03", "remaining_time": "3:53:04"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.4064, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "14:11:59", "remaining_time": "3:50:20"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.4081, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "14:14:34", "remaining_time": "3:47:30"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.4214, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "14:17:21", "remaining_time": "3:44:44"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.4185, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "14:20:12", "remaining_time": "3:41:59"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.4179, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "14:22:58", "remaining_time": "3:39:12"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.4091, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "14:25:40", "remaining_time": "3:36:25"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.3988, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "14:29:15", "remaining_time": "3:33:50"}