ryanmarten commited on
Commit
d1f90bb
·
verified ·
1 Parent(s): d23d5ce

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 sha256:772eefc8d821f89eeaf8cffeb4a7710050c5ebb8ed9c5ed7dcb7b372b48e9ae3
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c3af944bf91cd227ae1a6bf687c8108070158a24a2677295b890db9b1b7c8f
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45935244fcddfd842672128f6382dc57edfda459efe7e915b66ee2ce0415de07
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d721c5e69862eeaee0819a6579a6f0690dbf9924b80651d38418ac8446d3558
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:272d3915145d4f378582b1f11c57f79cbc73bd8db997b6c6d27ce9b84a6aeead
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec3cf724edcd232fc59775d298b0bbacd3bafd2d260c7adfe2d3f2f64a48df7
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45e19e93999a5ab7ba314b4fefdb1240926ec9b179e0d1d0455a6a08164064d7
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda041eb2afa33d120332624859f5e19960e7aed88582d7e061c6df7fbad55ea
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -233,3 +233,82 @@
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.3378, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:20:18", "remaining_time": "6:57:58"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.3432, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:22:54", "remaining_time": "6:55:16"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.3155, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:26:30", "remaining_time": "6:53:13"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  {"current_steps": 233, "total_steps": 390, "loss": 0.3378, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "10:20:18", "remaining_time": "6:57:58"}
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.3432, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "10:22:54", "remaining_time": "6:55:16"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.3155, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "10:26:30", "remaining_time": "6:53:13"}
236
+ {"current_steps": 236, "total_steps": 390, "loss": 0.2934, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "10:29:14", "remaining_time": "6:50:36"}
237
+ {"current_steps": 237, "total_steps": 390, "loss": 0.2973, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "10:31:48", "remaining_time": "6:47:52"}
238
+ {"current_steps": 238, "total_steps": 390, "loss": 0.2979, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "10:34:26", "remaining_time": "6:45:11"}
239
+ {"current_steps": 239, "total_steps": 390, "loss": 0.2946, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "10:37:04", "remaining_time": "6:42:30"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.2775, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "10:39:48", "remaining_time": "6:39:52"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.2793, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "10:42:22", "remaining_time": "6:37:09"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.2873, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "10:44:53", "remaining_time": "6:34:23"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.286, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "10:47:33", "remaining_time": "6:31:43"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.275, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "10:50:12", "remaining_time": "6:29:03"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.2832, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "10:52:44", "remaining_time": "6:26:18"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.2759, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "10:55:20", "remaining_time": "6:23:36"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.2904, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "10:57:56", "remaining_time": "6:20:54"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.2828, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "11:00:32", "remaining_time": "6:18:12"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.2785, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "11:02:49", "remaining_time": "6:15:19"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.2839, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "11:05:38", "remaining_time": "6:12:45"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.2817, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "11:08:06", "remaining_time": "6:09:59"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.2708, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "11:10:47", "remaining_time": "6:07:20"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.2719, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "11:13:21", "remaining_time": "6:04:37"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.2884, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "11:16:00", "remaining_time": "6:01:57"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.276, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "11:18:37", "remaining_time": "5:59:16"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.2814, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "11:21:14", "remaining_time": "5:56:35"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.2836, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "11:23:40", "remaining_time": "5:53:48"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.2783, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "11:26:30", "remaining_time": "5:51:13"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.2711, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "11:29:03", "remaining_time": "5:48:31"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.2781, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "11:31:39", "remaining_time": "5:45:49"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.2783, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "11:34:12", "remaining_time": "5:43:06"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.2761, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "11:36:44", "remaining_time": "5:40:23"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.2848, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "11:39:41", "remaining_time": "5:37:52"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.2757, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "11:42:20", "remaining_time": "5:35:12"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.2939, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "11:45:06", "remaining_time": "5:32:35"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.2758, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "11:47:42", "remaining_time": "5:29:54"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.2852, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "11:50:24", "remaining_time": "5:27:16"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.2865, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "11:53:01", "remaining_time": "5:24:35"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.2751, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "11:55:34", "remaining_time": "5:21:52"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.2735, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "11:57:57", "remaining_time": "5:19:05"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.2688, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "12:00:24", "remaining_time": "5:16:20"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.2863, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "12:02:56", "remaining_time": "5:13:37"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.2777, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "12:05:45", "remaining_time": "5:11:02"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.2767, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "12:08:27", "remaining_time": "5:08:23"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.2769, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "12:11:09", "remaining_time": "5:05:45"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.2803, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "12:13:44", "remaining_time": "5:03:03"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.2882, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "12:16:22", "remaining_time": "5:00:23"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.2678, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "12:18:53", "remaining_time": "4:57:40"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.2831, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "12:21:32", "remaining_time": "4:55:01"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.2896, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "12:24:07", "remaining_time": "4:52:20"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.2911, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "12:26:37", "remaining_time": "4:49:36"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.2847, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "12:29:07", "remaining_time": "4:46:53"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.2801, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "12:31:47", "remaining_time": "4:44:14"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.2915, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "12:34:25", "remaining_time": "4:41:34"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.2762, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "12:36:51", "remaining_time": "4:38:50"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.283, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "12:39:20", "remaining_time": "4:36:07"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.2651, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "12:42:01", "remaining_time": "4:33:28"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.2866, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "12:44:44", "remaining_time": "4:30:50"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.2809, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "12:47:24", "remaining_time": "4:28:11"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.2774, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "12:49:56", "remaining_time": "4:25:29"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.2787, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "12:52:45", "remaining_time": "4:22:53"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.2729, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "12:55:26", "remaining_time": "4:20:15"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.2823, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "12:58:06", "remaining_time": "4:17:36"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.2832, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "13:00:47", "remaining_time": "4:14:57"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.2784, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "13:03:27", "remaining_time": "4:12:18"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.2898, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "13:06:02", "remaining_time": "4:09:37"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.2792, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "13:08:36", "remaining_time": "4:06:56"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.2793, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "13:11:18", "remaining_time": "4:04:17"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.28, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "13:14:02", "remaining_time": "4:01:39"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.278, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "13:16:48", "remaining_time": "3:59:02"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.273, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "13:19:23", "remaining_time": "3:56:21"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.2825, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "13:22:00", "remaining_time": "3:53:41"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.2805, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "13:24:45", "remaining_time": "3:51:04"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.2746, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "13:27:18", "remaining_time": "3:48:22"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.2841, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "13:29:56", "remaining_time": "3:45:43"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.2693, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "13:32:21", "remaining_time": "3:42:59"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.2886, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "13:34:52", "remaining_time": "3:40:18"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.2884, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "13:37:37", "remaining_time": "3:37:40"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.2761, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "13:40:09", "remaining_time": "3:34:59"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.2818, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "13:42:53", "remaining_time": "3:32:21"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.2668, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "13:45:30", "remaining_time": "3:29:41"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.2808, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:48:07", "remaining_time": "3:27:01"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.2595, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:51:26", "remaining_time": "3:24:32"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.2489, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "13:53:57", "remaining_time": "3:21:50"}