EtashGuha commited on
Commit
18c4d47
·
verified ·
1 Parent(s): 25bc97e

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 sha256:952818f9e0c846c92d8493dda4d5d60f9ae7028b1a506a9302fefcc25252455b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20a29d3262695bba3e3439a626b95536341574005eaadb126f842028c4ea6aee
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f2839a41595548fcfae043f0f0a919dc9a98d259edd96650bc1c0772d5e7bcb
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8370e8f729999c7e755e7a37e7a5ae848baa7a16b881255b6dfaa2a019b93510
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03c0cb9f5d0d2acb4b66dfb4fa208354b02728446298ea2e9fcd95978f1656cd
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8774445db58cc6ed7cf4b3cb465af654725e9e158540fc91339197ff147ae251
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:c8e3ccca48477799daf6b2335d2b36f1976994f08d241c49a5b00162974d2c6d
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a725d72bdac3560bc38b8dafd56c4fd6e664bbab764c2c03d3282a37097546
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -235,3 +235,81 @@
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.3229, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "2:59:14", "remaining_time": "1:58:13"}
236
  {"current_steps": 236, "total_steps": 390, "loss": 0.2905, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "2:59:59", "remaining_time": "1:57:27"}
237
  {"current_steps": 237, "total_steps": 390, "loss": 0.2972, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "3:00:44", "remaining_time": "1:56:40"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
235
  {"current_steps": 235, "total_steps": 390, "loss": 0.3229, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "2:59:14", "remaining_time": "1:58:13"}
236
  {"current_steps": 236, "total_steps": 390, "loss": 0.2905, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "2:59:59", "remaining_time": "1:57:27"}
237
  {"current_steps": 237, "total_steps": 390, "loss": 0.2972, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "3:00:44", "remaining_time": "1:56:40"}
238
+ {"current_steps": 238, "total_steps": 390, "loss": 0.2857, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "3:01:28", "remaining_time": "1:55:54"}
239
+ {"current_steps": 239, "total_steps": 390, "loss": 0.286, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "3:02:13", "remaining_time": "1:55:07"}
240
+ {"current_steps": 240, "total_steps": 390, "loss": 0.2921, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "3:02:59", "remaining_time": "1:54:22"}
241
+ {"current_steps": 241, "total_steps": 390, "loss": 0.2934, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "3:03:42", "remaining_time": "1:53:34"}
242
+ {"current_steps": 242, "total_steps": 390, "loss": 0.2981, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "3:04:24", "remaining_time": "1:52:46"}
243
+ {"current_steps": 243, "total_steps": 390, "loss": 0.282, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "3:05:09", "remaining_time": "1:52:00"}
244
+ {"current_steps": 244, "total_steps": 390, "loss": 0.2889, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "3:05:55", "remaining_time": "1:51:14"}
245
+ {"current_steps": 245, "total_steps": 390, "loss": 0.2862, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "3:06:39", "remaining_time": "1:50:28"}
246
+ {"current_steps": 246, "total_steps": 390, "loss": 0.295, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "3:07:23", "remaining_time": "1:49:41"}
247
+ {"current_steps": 247, "total_steps": 390, "loss": 0.2926, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "3:08:08", "remaining_time": "1:48:55"}
248
+ {"current_steps": 248, "total_steps": 390, "loss": 0.2883, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "3:08:51", "remaining_time": "1:48:08"}
249
+ {"current_steps": 249, "total_steps": 390, "loss": 0.2897, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "3:09:36", "remaining_time": "1:47:22"}
250
+ {"current_steps": 250, "total_steps": 390, "loss": 0.2864, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "3:10:19", "remaining_time": "1:46:34"}
251
+ {"current_steps": 251, "total_steps": 390, "loss": 0.2965, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "3:11:03", "remaining_time": "1:45:48"}
252
+ {"current_steps": 252, "total_steps": 390, "loss": 0.2881, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "3:11:48", "remaining_time": "1:45:02"}
253
+ {"current_steps": 253, "total_steps": 390, "loss": 0.2924, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "3:12:32", "remaining_time": "1:44:15"}
254
+ {"current_steps": 254, "total_steps": 390, "loss": 0.2904, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "3:13:14", "remaining_time": "1:43:28"}
255
+ {"current_steps": 255, "total_steps": 390, "loss": 0.2937, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "3:13:58", "remaining_time": "1:42:41"}
256
+ {"current_steps": 256, "total_steps": 390, "loss": 0.2856, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "3:14:40", "remaining_time": "1:41:53"}
257
+ {"current_steps": 257, "total_steps": 390, "loss": 0.2923, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "3:15:23", "remaining_time": "1:41:07"}
258
+ {"current_steps": 258, "total_steps": 390, "loss": 0.2861, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "3:16:08", "remaining_time": "1:40:21"}
259
+ {"current_steps": 259, "total_steps": 390, "loss": 0.2748, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "3:16:51", "remaining_time": "1:39:34"}
260
+ {"current_steps": 260, "total_steps": 390, "loss": 0.2829, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "3:17:37", "remaining_time": "1:38:48"}
261
+ {"current_steps": 261, "total_steps": 390, "loss": 0.2898, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "3:18:19", "remaining_time": "1:38:01"}
262
+ {"current_steps": 262, "total_steps": 390, "loss": 0.2997, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "3:19:04", "remaining_time": "1:37:15"}
263
+ {"current_steps": 263, "total_steps": 390, "loss": 0.2917, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "3:19:50", "remaining_time": "1:36:30"}
264
+ {"current_steps": 264, "total_steps": 390, "loss": 0.2948, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "3:20:33", "remaining_time": "1:35:43"}
265
+ {"current_steps": 265, "total_steps": 390, "loss": 0.2979, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "3:21:20", "remaining_time": "1:34:58"}
266
+ {"current_steps": 266, "total_steps": 390, "loss": 0.292, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "3:22:01", "remaining_time": "1:34:10"}
267
+ {"current_steps": 267, "total_steps": 390, "loss": 0.2864, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "3:22:43", "remaining_time": "1:33:23"}
268
+ {"current_steps": 268, "total_steps": 390, "loss": 0.2897, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "3:23:24", "remaining_time": "1:32:35"}
269
+ {"current_steps": 269, "total_steps": 390, "loss": 0.2754, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "3:24:06", "remaining_time": "1:31:48"}
270
+ {"current_steps": 270, "total_steps": 390, "loss": 0.2848, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "3:24:49", "remaining_time": "1:31:02"}
271
+ {"current_steps": 271, "total_steps": 390, "loss": 0.2937, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "3:25:36", "remaining_time": "1:30:16"}
272
+ {"current_steps": 272, "total_steps": 390, "loss": 0.2919, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "3:26:18", "remaining_time": "1:29:30"}
273
+ {"current_steps": 273, "total_steps": 390, "loss": 0.2982, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "3:27:03", "remaining_time": "1:28:44"}
274
+ {"current_steps": 274, "total_steps": 390, "loss": 0.2837, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "3:27:49", "remaining_time": "1:27:59"}
275
+ {"current_steps": 275, "total_steps": 390, "loss": 0.2872, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "3:28:33", "remaining_time": "1:27:12"}
276
+ {"current_steps": 276, "total_steps": 390, "loss": 0.2954, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "3:29:16", "remaining_time": "1:26:26"}
277
+ {"current_steps": 277, "total_steps": 390, "loss": 0.3012, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "3:30:00", "remaining_time": "1:25:40"}
278
+ {"current_steps": 278, "total_steps": 390, "loss": 0.2928, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "3:30:44", "remaining_time": "1:24:54"}
279
+ {"current_steps": 279, "total_steps": 390, "loss": 0.2924, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "3:31:27", "remaining_time": "1:24:07"}
280
+ {"current_steps": 280, "total_steps": 390, "loss": 0.2901, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "3:32:12", "remaining_time": "1:23:22"}
281
+ {"current_steps": 281, "total_steps": 390, "loss": 0.2881, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "3:32:56", "remaining_time": "1:22:36"}
282
+ {"current_steps": 282, "total_steps": 390, "loss": 0.2868, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "3:33:40", "remaining_time": "1:21:50"}
283
+ {"current_steps": 283, "total_steps": 390, "loss": 0.2971, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "3:34:26", "remaining_time": "1:21:04"}
284
+ {"current_steps": 284, "total_steps": 390, "loss": 0.2849, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "3:35:11", "remaining_time": "1:20:19"}
285
+ {"current_steps": 285, "total_steps": 390, "loss": 0.2788, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "3:35:58", "remaining_time": "1:19:34"}
286
+ {"current_steps": 286, "total_steps": 390, "loss": 0.2719, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "3:36:40", "remaining_time": "1:18:47"}
287
+ {"current_steps": 287, "total_steps": 390, "loss": 0.2918, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "3:37:24", "remaining_time": "1:18:01"}
288
+ {"current_steps": 288, "total_steps": 390, "loss": 0.284, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "3:38:08", "remaining_time": "1:17:15"}
289
+ {"current_steps": 289, "total_steps": 390, "loss": 0.283, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "3:38:52", "remaining_time": "1:16:29"}
290
+ {"current_steps": 290, "total_steps": 390, "loss": 0.2926, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "3:39:36", "remaining_time": "1:15:43"}
291
+ {"current_steps": 291, "total_steps": 390, "loss": 0.2792, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "3:40:19", "remaining_time": "1:14:57"}
292
+ {"current_steps": 292, "total_steps": 390, "loss": 0.2817, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "3:41:04", "remaining_time": "1:14:11"}
293
+ {"current_steps": 293, "total_steps": 390, "loss": 0.2899, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "3:41:47", "remaining_time": "1:13:25"}
294
+ {"current_steps": 294, "total_steps": 390, "loss": 0.2927, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "3:42:31", "remaining_time": "1:12:39"}
295
+ {"current_steps": 295, "total_steps": 390, "loss": 0.2908, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "3:43:16", "remaining_time": "1:11:54"}
296
+ {"current_steps": 296, "total_steps": 390, "loss": 0.2926, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "3:44:00", "remaining_time": "1:11:08"}
297
+ {"current_steps": 297, "total_steps": 390, "loss": 0.2846, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "3:44:41", "remaining_time": "1:10:21"}
298
+ {"current_steps": 298, "total_steps": 390, "loss": 0.2879, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "3:45:26", "remaining_time": "1:09:36"}
299
+ {"current_steps": 299, "total_steps": 390, "loss": 0.2904, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "3:46:11", "remaining_time": "1:08:50"}
300
+ {"current_steps": 300, "total_steps": 390, "loss": 0.2911, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "3:46:57", "remaining_time": "1:08:05"}
301
+ {"current_steps": 301, "total_steps": 390, "loss": 0.2988, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "3:47:39", "remaining_time": "1:07:18"}
302
+ {"current_steps": 302, "total_steps": 390, "loss": 0.2814, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "3:48:24", "remaining_time": "1:06:33"}
303
+ {"current_steps": 303, "total_steps": 390, "loss": 0.2812, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "3:49:05", "remaining_time": "1:05:46"}
304
+ {"current_steps": 304, "total_steps": 390, "loss": 0.2895, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "3:49:49", "remaining_time": "1:05:01"}
305
+ {"current_steps": 305, "total_steps": 390, "loss": 0.2888, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "3:50:34", "remaining_time": "1:04:15"}
306
+ {"current_steps": 306, "total_steps": 390, "loss": 0.2901, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "3:51:18", "remaining_time": "1:03:29"}
307
+ {"current_steps": 307, "total_steps": 390, "loss": 0.2854, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "3:52:00", "remaining_time": "1:02:43"}
308
+ {"current_steps": 308, "total_steps": 390, "loss": 0.2978, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "3:52:44", "remaining_time": "1:01:57"}
309
+ {"current_steps": 309, "total_steps": 390, "loss": 0.2877, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "3:53:25", "remaining_time": "1:01:11"}
310
+ {"current_steps": 310, "total_steps": 390, "loss": 0.2886, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "3:54:08", "remaining_time": "1:00:25"}
311
+ {"current_steps": 311, "total_steps": 390, "loss": 0.2934, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "3:54:54", "remaining_time": "0:59:40"}
312
+ {"current_steps": 312, "total_steps": 390, "loss": 0.2935, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "3:55:35", "remaining_time": "0:58:53"}
313
+ {"current_steps": 313, "total_steps": 390, "loss": 0.2735, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "3:58:26", "remaining_time": "0:58:39"}
314
+ {"current_steps": 314, "total_steps": 390, "loss": 0.2568, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "3:59:09", "remaining_time": "0:57:53"}
315
+ {"current_steps": 315, "total_steps": 390, "loss": 0.2571, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "3:59:53", "remaining_time": "0:57:07"}