ryanmarten commited on
Commit
e6c245b
·
verified ·
1 Parent(s): c433e9d

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 sha256:7e48c6d5e81e88da452b76d8aa77d43741f7d06bc2c43d9a23fcc102e9326232
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df5ade570315a628c6b128e40161b1d4b1f0d880ebcb843b6a1a3bb959e0a535
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b46947a44b742ded00a9d9eeb48fae60b818d1a16a41ab56ab94478c4136747
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e6f0df875640619fe0f9b1fbf01843e43be8322e76a1fd59b3f53e1dab1229
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:c6b190c3bca2ade4912486e9aa6d37ce53597cda9ad06f45ef5715648e45d93a
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d26eac49d0eaa7eafaf0dfc816c3939d85bd58ed4fadf42aacc1747a482ce64
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46db54cf29e4a84be42136b96f99dc0f85d85cdc5416792c4c945c3cf922c3cd
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3c81765a6271fc4280b573afe477e1eb47c5624f873866c0035435bb0c6148
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -234,3 +234,80 @@
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.3235, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "9:48:17", "remaining_time": "6:32:11"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.2979, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "9:51:41", "remaining_time": "6:30:15"}
236
  {"current_steps": 236, "total_steps": 390, "loss": 0.2682, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "9:54:20", "remaining_time": "6:27:49"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
234
  {"current_steps": 234, "total_steps": 390, "loss": 0.3235, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "9:48:17", "remaining_time": "6:32:11"}
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.2979, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "9:51:41", "remaining_time": "6:30:15"}
236
  {"current_steps": 236, "total_steps": 390, "loss": 0.2682, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "9:54:20", "remaining_time": "6:27:49"}
237
+ {"current_steps": 237, "total_steps": 390, "loss": 0.2616, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "9:56:42", "remaining_time": "6:25:12"}
238
+ {"current_steps": 238, "total_steps": 390, "loss": 0.263, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "9:59:16", "remaining_time": "6:22:43"}
239
+ {"current_steps": 239, "total_steps": 390, "loss": 0.2558, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "10:01:45", "remaining_time": "6:20:11"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.2666, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "10:04:29", "remaining_time": "6:17:48"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.2761, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "10:07:06", "remaining_time": "6:15:20"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.2637, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "10:09:26", "remaining_time": "6:12:42"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.2601, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "10:11:56", "remaining_time": "6:10:10"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.2552, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "10:14:08", "remaining_time": "6:07:28"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.2511, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "10:16:33", "remaining_time": "6:04:54"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.2576, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "10:19:00", "remaining_time": "6:02:20"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.256, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "10:21:24", "remaining_time": "5:59:45"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.2513, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "10:24:02", "remaining_time": "5:57:18"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.2641, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "10:26:31", "remaining_time": "5:54:46"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.2557, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "10:28:56", "remaining_time": "5:52:12"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.2665, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "10:31:25", "remaining_time": "5:49:40"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.2434, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "10:33:50", "remaining_time": "5:47:06"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.2729, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "10:36:19", "remaining_time": "5:44:34"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.2537, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "10:38:41", "remaining_time": "5:41:58"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.2618, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "10:41:03", "remaining_time": "5:39:22"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.2709, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "10:43:30", "remaining_time": "5:36:50"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.2538, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "10:46:06", "remaining_time": "5:34:22"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.2652, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "10:48:41", "remaining_time": "5:31:53"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.2549, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "10:51:03", "remaining_time": "5:29:18"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.2496, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "10:53:28", "remaining_time": "5:26:44"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.2561, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "10:56:15", "remaining_time": "5:24:21"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.2531, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "10:58:42", "remaining_time": "5:21:48"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.2497, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "11:01:02", "remaining_time": "5:19:12"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.2556, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "11:03:29", "remaining_time": "5:16:40"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.2485, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "11:05:51", "remaining_time": "5:14:05"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.2686, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "11:08:15", "remaining_time": "5:11:30"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.2498, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "11:10:40", "remaining_time": "5:08:57"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.2575, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "11:13:06", "remaining_time": "5:06:25"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.2625, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "11:15:32", "remaining_time": "5:03:52"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.2465, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "11:17:59", "remaining_time": "5:01:19"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.2627, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "11:20:23", "remaining_time": "4:58:46"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.2549, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "11:22:51", "remaining_time": "4:56:14"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.2555, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "11:25:15", "remaining_time": "4:53:41"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.2699, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "11:27:52", "remaining_time": "4:51:13"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.2615, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "11:30:20", "remaining_time": "4:48:41"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.2586, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "11:32:52", "remaining_time": "4:46:11"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.2634, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "11:35:20", "remaining_time": "4:43:39"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.2274, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "11:37:32", "remaining_time": "4:41:01"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.2562, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "11:40:14", "remaining_time": "4:38:35"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.2721, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "11:42:45", "remaining_time": "4:36:04"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.2672, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "11:45:28", "remaining_time": "4:33:39"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.2508, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "11:47:56", "remaining_time": "4:31:07"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.2662, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "11:50:27", "remaining_time": "4:28:37"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.2547, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "11:52:50", "remaining_time": "4:26:03"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.2532, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "11:55:15", "remaining_time": "4:23:31"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.2702, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "11:57:41", "remaining_time": "4:20:58"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.2542, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "12:00:13", "remaining_time": "4:18:28"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.2587, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "12:02:42", "remaining_time": "4:15:57"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.2525, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "12:05:10", "remaining_time": "4:13:25"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.2506, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "12:07:23", "remaining_time": "4:10:49"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.2555, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "12:09:49", "remaining_time": "4:08:17"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.2651, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "12:12:23", "remaining_time": "4:05:48"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.2568, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "12:15:04", "remaining_time": "4:03:21"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.2568, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "12:17:28", "remaining_time": "4:00:48"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.2469, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "12:19:51", "remaining_time": "3:58:15"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.2708, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "12:22:27", "remaining_time": "3:55:46"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.2564, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "12:24:40", "remaining_time": "3:53:10"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.2556, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "12:26:59", "remaining_time": "3:50:36"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.2517, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "12:29:28", "remaining_time": "3:48:06"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.2541, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "12:32:00", "remaining_time": "3:45:36"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.2551, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "12:34:18", "remaining_time": "3:43:02"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.2698, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "12:36:50", "remaining_time": "3:40:32"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.261, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "12:39:23", "remaining_time": "3:38:02"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.2605, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "12:41:59", "remaining_time": "3:35:33"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.2497, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "12:44:36", "remaining_time": "3:33:05"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.2571, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "12:47:03", "remaining_time": "3:30:33"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.2649, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "12:49:29", "remaining_time": "3:28:02"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.2601, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "12:52:15", "remaining_time": "3:25:36"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.2572, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "12:54:42", "remaining_time": "3:23:04"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.2649, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "12:57:14", "remaining_time": "3:20:34"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.2622, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "12:59:51", "remaining_time": "3:18:05"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.2568, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "13:02:19", "remaining_time": "3:15:34"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.2395, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "13:05:33", "remaining_time": "3:13:15"}