sedrickkeh commited on
Commit
39e46c9
·
verified ·
1 Parent(s): b74a431

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5649322b9e77d2f4d4eaa3dd9da87ed158c215f66b2cb96eb5164f23f7bcb02
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23642c86566daa329202131c2f2e876a5cb45b7cfa9dce7500c18fe000fe3b79
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d4596af4a97c272a84010bc1487d6d8373bb06a6f823cb09389371e5f389653
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c29980a0fc3b63acd5d3f4ddf5366d9cf80f53bf0fd24eae7d3568fc1e9e0e7
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:e6c562c41b2b63ca20e380a565625de9ec9b3caabc58be1e4fb8b1a99b8e6ebb
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db304868c17e5c373bf4dce845a384ca3843589e5730aebbf0e3c08572c73c1d
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:234f1882e82b83ad4d5f2c7429db860ddb962dd514bc2c608a6faa6df72aa82c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c3b2f243fe3ddc535cd5fbc004e064513d5cbd3f4d3d8207266515871aaeef
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -266,3 +266,71 @@
266
  {"current_steps": 266, "total_steps": 335, "loss": 0.3227, "lr": 9.932143173565225e-06, "epoch": 3.9627560521415273, "percentage": 79.4, "elapsed_time": "11:15:23", "remaining_time": "2:55:11"}
267
  {"current_steps": 267, "total_steps": 335, "loss": 0.3216, "lr": 9.658449063975875e-06, "epoch": 3.977653631284916, "percentage": 79.7, "elapsed_time": "11:17:54", "remaining_time": "2:52:38"}
268
  {"current_steps": 268, "total_steps": 335, "loss": 0.3226, "lr": 9.388060176030907e-06, "epoch": 3.9925512104283056, "percentage": 80.0, "elapsed_time": "11:20:23", "remaining_time": "2:50:05"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
266
  {"current_steps": 266, "total_steps": 335, "loss": 0.3227, "lr": 9.932143173565225e-06, "epoch": 3.9627560521415273, "percentage": 79.4, "elapsed_time": "11:15:23", "remaining_time": "2:55:11"}
267
  {"current_steps": 267, "total_steps": 335, "loss": 0.3216, "lr": 9.658449063975875e-06, "epoch": 3.977653631284916, "percentage": 79.7, "elapsed_time": "11:17:54", "remaining_time": "2:52:38"}
268
  {"current_steps": 268, "total_steps": 335, "loss": 0.3226, "lr": 9.388060176030907e-06, "epoch": 3.9925512104283056, "percentage": 80.0, "elapsed_time": "11:20:23", "remaining_time": "2:50:05"}
269
+ {"current_steps": 269, "total_steps": 335, "loss": 0.577, "lr": 9.12100596423009e-06, "epoch": 4.007448789571694, "percentage": 80.3, "elapsed_time": "11:24:35", "remaining_time": "2:47:58"}
270
+ {"current_steps": 270, "total_steps": 335, "loss": 0.306, "lr": 8.857315519814111e-06, "epoch": 4.022346368715084, "percentage": 80.6, "elapsed_time": "11:27:05", "remaining_time": "2:45:24"}
271
+ {"current_steps": 271, "total_steps": 335, "loss": 0.3064, "lr": 8.597017567595562e-06, "epoch": 4.037243947858473, "percentage": 80.9, "elapsed_time": "11:29:36", "remaining_time": "2:42:51"}
272
+ {"current_steps": 272, "total_steps": 335, "loss": 0.302, "lr": 8.34014046282984e-06, "epoch": 4.052141527001862, "percentage": 81.19, "elapsed_time": "11:32:08", "remaining_time": "2:40:18"}
273
+ {"current_steps": 273, "total_steps": 335, "loss": 0.3021, "lr": 8.086712188126263e-06, "epoch": 4.067039106145251, "percentage": 81.49, "elapsed_time": "11:34:41", "remaining_time": "2:37:46"}
274
+ {"current_steps": 274, "total_steps": 335, "loss": 0.2992, "lr": 7.836760350399881e-06, "epoch": 4.081936685288641, "percentage": 81.79, "elapsed_time": "11:37:14", "remaining_time": "2:35:13"}
275
+ {"current_steps": 275, "total_steps": 335, "loss": 0.3077, "lr": 7.5903121778641096e-06, "epoch": 4.0968342644320295, "percentage": 82.09, "elapsed_time": "11:39:45", "remaining_time": "2:32:40"}
276
+ {"current_steps": 276, "total_steps": 335, "loss": 0.3068, "lr": 7.347394517064663e-06, "epoch": 4.111731843575419, "percentage": 82.39, "elapsed_time": "11:42:15", "remaining_time": "2:30:07"}
277
+ {"current_steps": 277, "total_steps": 335, "loss": 0.3077, "lr": 7.108033829955028e-06, "epoch": 4.126629422718808, "percentage": 82.69, "elapsed_time": "11:44:47", "remaining_time": "2:27:34"}
278
+ {"current_steps": 278, "total_steps": 335, "loss": 0.3061, "lr": 6.87225619101394e-06, "epoch": 4.1415270018621975, "percentage": 82.99, "elapsed_time": "11:47:18", "remaining_time": "2:25:01"}
279
+ {"current_steps": 279, "total_steps": 335, "loss": 0.3054, "lr": 6.640087284404888e-06, "epoch": 4.156424581005586, "percentage": 83.28, "elapsed_time": "11:49:49", "remaining_time": "2:22:28"}
280
+ {"current_steps": 280, "total_steps": 335, "loss": 0.3098, "lr": 6.411552401178327e-06, "epoch": 4.171322160148976, "percentage": 83.58, "elapsed_time": "11:52:19", "remaining_time": "2:19:55"}
281
+ {"current_steps": 281, "total_steps": 335, "loss": 0.3008, "lr": 6.186676436516581e-06, "epoch": 4.186219739292365, "percentage": 83.88, "elapsed_time": "11:54:49", "remaining_time": "2:17:22"}
282
+ {"current_steps": 282, "total_steps": 335, "loss": 0.3087, "lr": 5.965483887021934e-06, "epoch": 4.201117318435754, "percentage": 84.18, "elapsed_time": "11:57:20", "remaining_time": "2:14:49"}
283
+ {"current_steps": 283, "total_steps": 335, "loss": 0.3091, "lr": 5.747998848048091e-06, "epoch": 4.216014897579143, "percentage": 84.48, "elapsed_time": "11:59:51", "remaining_time": "2:12:16"}
284
+ {"current_steps": 284, "total_steps": 335, "loss": 0.298, "lr": 5.534245011075414e-06, "epoch": 4.230912476722533, "percentage": 84.78, "elapsed_time": "12:02:22", "remaining_time": "2:09:43"}
285
+ {"current_steps": 285, "total_steps": 335, "loss": 0.3, "lr": 5.3242456611301095e-06, "epoch": 4.245810055865922, "percentage": 85.07, "elapsed_time": "12:04:54", "remaining_time": "2:07:10"}
286
+ {"current_steps": 286, "total_steps": 335, "loss": 0.2984, "lr": 5.118023674247692e-06, "epoch": 4.260707635009311, "percentage": 85.37, "elapsed_time": "12:07:25", "remaining_time": "2:04:37"}
287
+ {"current_steps": 287, "total_steps": 335, "loss": 0.3078, "lr": 4.915601514981024e-06, "epoch": 4.275605214152701, "percentage": 85.67, "elapsed_time": "12:09:56", "remaining_time": "2:02:04"}
288
+ {"current_steps": 288, "total_steps": 335, "loss": 0.2987, "lr": 4.717001233953116e-06, "epoch": 4.290502793296089, "percentage": 85.97, "elapsed_time": "12:12:26", "remaining_time": "1:59:31"}
289
+ {"current_steps": 289, "total_steps": 335, "loss": 0.3038, "lr": 4.522244465455154e-06, "epoch": 4.305400372439479, "percentage": 86.27, "elapsed_time": "12:14:57", "remaining_time": "1:56:58"}
290
+ {"current_steps": 290, "total_steps": 335, "loss": 0.3043, "lr": 4.33135242508973e-06, "epoch": 4.320297951582868, "percentage": 86.57, "elapsed_time": "12:17:28", "remaining_time": "1:54:26"}
291
+ {"current_steps": 291, "total_steps": 335, "loss": 0.3013, "lr": 4.144345907459753e-06, "epoch": 4.335195530726257, "percentage": 86.87, "elapsed_time": "12:19:58", "remaining_time": "1:51:53"}
292
+ {"current_steps": 292, "total_steps": 335, "loss": 0.308, "lr": 3.961245283903239e-06, "epoch": 4.350093109869646, "percentage": 87.16, "elapsed_time": "12:22:30", "remaining_time": "1:49:20"}
293
+ {"current_steps": 293, "total_steps": 335, "loss": 0.3052, "lr": 3.7820705002741353e-06, "epoch": 4.364990689013036, "percentage": 87.46, "elapsed_time": "12:25:01", "remaining_time": "1:46:47"}
294
+ {"current_steps": 294, "total_steps": 335, "loss": 0.3002, "lr": 3.6068410747696112e-06, "epoch": 4.379888268156424, "percentage": 87.76, "elapsed_time": "12:27:31", "remaining_time": "1:44:14"}
295
+ {"current_steps": 295, "total_steps": 335, "loss": 0.3021, "lr": 3.435576095803792e-06, "epoch": 4.394785847299814, "percentage": 88.06, "elapsed_time": "12:30:02", "remaining_time": "1:41:42"}
296
+ {"current_steps": 296, "total_steps": 335, "loss": 0.3046, "lr": 3.268294219928434e-06, "epoch": 4.409683426443203, "percentage": 88.36, "elapsed_time": "12:32:34", "remaining_time": "1:39:09"}
297
+ {"current_steps": 297, "total_steps": 335, "loss": 0.3025, "lr": 3.1050136698005963e-06, "epoch": 4.424581005586592, "percentage": 88.66, "elapsed_time": "12:35:06", "remaining_time": "1:36:36"}
298
+ {"current_steps": 298, "total_steps": 335, "loss": 0.3079, "lr": 2.9457522321975253e-06, "epoch": 4.439478584729981, "percentage": 88.96, "elapsed_time": "12:37:38", "remaining_time": "1:34:04"}
299
+ {"current_steps": 299, "total_steps": 335, "loss": 0.3066, "lr": 2.790527256079134e-06, "epoch": 4.454376163873371, "percentage": 89.25, "elapsed_time": "12:40:08", "remaining_time": "1:31:31"}
300
+ {"current_steps": 300, "total_steps": 335, "loss": 0.3071, "lr": 2.6393556506980834e-06, "epoch": 4.4692737430167595, "percentage": 89.55, "elapsed_time": "12:42:39", "remaining_time": "1:28:58"}
301
+ {"current_steps": 301, "total_steps": 335, "loss": 0.3078, "lr": 2.4922538837577916e-06, "epoch": 4.484171322160149, "percentage": 89.85, "elapsed_time": "12:45:11", "remaining_time": "1:26:26"}
302
+ {"current_steps": 302, "total_steps": 335, "loss": 0.3112, "lr": 2.349237979618555e-06, "epoch": 4.499068901303538, "percentage": 90.15, "elapsed_time": "12:47:42", "remaining_time": "1:23:53"}
303
+ {"current_steps": 303, "total_steps": 335, "loss": 0.3052, "lr": 2.2103235175519355e-06, "epoch": 4.5139664804469275, "percentage": 90.45, "elapsed_time": "12:50:15", "remaining_time": "1:21:20"}
304
+ {"current_steps": 304, "total_steps": 335, "loss": 0.3014, "lr": 2.0755256300436687e-06, "epoch": 4.528864059590316, "percentage": 90.75, "elapsed_time": "12:52:45", "remaining_time": "1:18:48"}
305
+ {"current_steps": 305, "total_steps": 335, "loss": 0.3065, "lr": 1.944859001145223e-06, "epoch": 4.543761638733706, "percentage": 91.04, "elapsed_time": "12:55:15", "remaining_time": "1:16:15"}
306
+ {"current_steps": 306, "total_steps": 335, "loss": 0.3049, "lr": 1.8183378648741979e-06, "epoch": 4.558659217877095, "percentage": 91.34, "elapsed_time": "12:57:46", "remaining_time": "1:13:42"}
307
+ {"current_steps": 307, "total_steps": 335, "loss": 0.304, "lr": 1.6959760036637662e-06, "epoch": 4.573556797020484, "percentage": 91.64, "elapsed_time": "13:00:17", "remaining_time": "1:11:09"}
308
+ {"current_steps": 308, "total_steps": 335, "loss": 0.3011, "lr": 1.5777867468612874e-06, "epoch": 4.588454376163874, "percentage": 91.94, "elapsed_time": "13:02:47", "remaining_time": "1:08:37"}
309
+ {"current_steps": 309, "total_steps": 335, "loss": 0.3029, "lr": 1.4637829692763128e-06, "epoch": 4.603351955307263, "percentage": 92.24, "elapsed_time": "13:05:18", "remaining_time": "1:06:04"}
310
+ {"current_steps": 310, "total_steps": 335, "loss": 0.3046, "lr": 1.353977089778078e-06, "epoch": 4.618249534450651, "percentage": 92.54, "elapsed_time": "13:07:48", "remaining_time": "1:03:32"}
311
+ {"current_steps": 311, "total_steps": 335, "loss": 0.3068, "lr": 1.2483810699426458e-06, "epoch": 4.633147113594041, "percentage": 92.84, "elapsed_time": "13:10:19", "remaining_time": "1:00:59"}
312
+ {"current_steps": 312, "total_steps": 335, "loss": 0.3064, "lr": 1.1470064127499091e-06, "epoch": 4.648044692737431, "percentage": 93.13, "elapsed_time": "13:12:49", "remaining_time": "0:58:26"}
313
+ {"current_steps": 313, "total_steps": 335, "loss": 0.3007, "lr": 1.0498641613305182e-06, "epoch": 4.662942271880819, "percentage": 93.43, "elapsed_time": "13:15:20", "remaining_time": "0:55:54"}
314
+ {"current_steps": 314, "total_steps": 335, "loss": 0.3049, "lr": 9.569648977629176e-07, "epoch": 4.677839851024208, "percentage": 93.73, "elapsed_time": "13:17:51", "remaining_time": "0:53:21"}
315
+ {"current_steps": 315, "total_steps": 335, "loss": 0.3013, "lr": 8.683187419205797e-07, "epoch": 4.692737430167598, "percentage": 94.03, "elapsed_time": "13:20:22", "remaining_time": "0:50:49"}
316
+ {"current_steps": 316, "total_steps": 335, "loss": 0.3071, "lr": 7.839353503696379e-07, "epoch": 4.707635009310987, "percentage": 94.33, "elapsed_time": "13:22:53", "remaining_time": "0:48:16"}
317
+ {"current_steps": 317, "total_steps": 335, "loss": 0.301, "lr": 7.038239153169324e-07, "epoch": 4.722532588454376, "percentage": 94.63, "elapsed_time": "13:25:23", "remaining_time": "0:45:43"}
318
+ {"current_steps": 318, "total_steps": 335, "loss": 0.3086, "lr": 6.279931636086912e-07, "epoch": 4.737430167597766, "percentage": 94.93, "elapsed_time": "13:27:53", "remaining_time": "0:43:11"}
319
+ {"current_steps": 319, "total_steps": 335, "loss": 0.3048, "lr": 5.564513557798501e-07, "epoch": 4.752327746741154, "percentage": 95.22, "elapsed_time": "13:30:24", "remaining_time": "0:40:38"}
320
+ {"current_steps": 320, "total_steps": 335, "loss": 0.309, "lr": 4.892062851542356e-07, "epoch": 4.767225325884544, "percentage": 95.52, "elapsed_time": "13:32:54", "remaining_time": "0:38:06"}
321
+ {"current_steps": 321, "total_steps": 335, "loss": 0.3018, "lr": 4.2626527699558996e-07, "epoch": 4.782122905027933, "percentage": 95.82, "elapsed_time": "13:35:25", "remaining_time": "0:35:33"}
322
+ {"current_steps": 322, "total_steps": 335, "loss": 0.3051, "lr": 3.6763518770960517e-07, "epoch": 4.797020484171322, "percentage": 96.12, "elapsed_time": "13:37:57", "remaining_time": "0:33:01"}
323
+ {"current_steps": 323, "total_steps": 335, "loss": 0.3071, "lr": 3.133224040970273e-07, "epoch": 4.811918063314711, "percentage": 96.42, "elapsed_time": "13:40:29", "remaining_time": "0:30:28"}
324
+ {"current_steps": 324, "total_steps": 335, "loss": 0.3047, "lr": 2.6333284265790627e-07, "epoch": 4.826815642458101, "percentage": 96.72, "elapsed_time": "13:43:00", "remaining_time": "0:27:56"}
325
+ {"current_steps": 325, "total_steps": 335, "loss": 0.305, "lr": 2.1767194894712462e-07, "epoch": 4.8417132216014895, "percentage": 97.01, "elapsed_time": "13:45:32", "remaining_time": "0:25:24"}
326
+ {"current_steps": 326, "total_steps": 335, "loss": 0.306, "lr": 1.763446969811522e-07, "epoch": 4.856610800744879, "percentage": 97.31, "elapsed_time": "13:48:02", "remaining_time": "0:22:51"}
327
+ {"current_steps": 327, "total_steps": 335, "loss": 0.3042, "lr": 1.3935558869622168e-07, "epoch": 4.871508379888268, "percentage": 97.61, "elapsed_time": "13:50:34", "remaining_time": "0:20:19"}
328
+ {"current_steps": 328, "total_steps": 335, "loss": 0.3094, "lr": 1.0670865345793425e-07, "epoch": 4.8864059590316575, "percentage": 97.91, "elapsed_time": "13:53:04", "remaining_time": "0:17:46"}
329
+ {"current_steps": 329, "total_steps": 335, "loss": 0.3054, "lr": 7.840744762229069e-08, "epoch": 4.901303538175046, "percentage": 98.21, "elapsed_time": "13:55:35", "remaining_time": "0:15:14"}
330
+ {"current_steps": 330, "total_steps": 335, "loss": 0.3054, "lr": 5.445505414831242e-08, "epoch": 4.916201117318436, "percentage": 98.51, "elapsed_time": "13:58:06", "remaining_time": "0:12:41"}
331
+ {"current_steps": 331, "total_steps": 335, "loss": 0.2998, "lr": 3.485408226218567e-08, "epoch": 4.931098696461825, "percentage": 98.81, "elapsed_time": "14:00:36", "remaining_time": "0:10:09"}
332
+ {"current_steps": 332, "total_steps": 335, "loss": 0.3058, "lr": 1.960666717304438e-08, "epoch": 4.945996275605214, "percentage": 99.1, "elapsed_time": "14:03:08", "remaining_time": "0:07:37"}
333
+ {"current_steps": 333, "total_steps": 335, "loss": 0.2984, "lr": 8.714469840351848e-09, "epoch": 4.960893854748603, "percentage": 99.4, "elapsed_time": "14:05:38", "remaining_time": "0:05:04"}
334
+ {"current_steps": 334, "total_steps": 335, "loss": 0.3051, "lr": 2.178676792996548e-09, "epoch": 4.975791433891993, "percentage": 99.7, "elapsed_time": "14:08:09", "remaining_time": "0:02:32"}
335
+ {"current_steps": 335, "total_steps": 335, "loss": 0.2973, "lr": 0.0, "epoch": 4.990689013035381, "percentage": 100.0, "elapsed_time": "14:10:37", "remaining_time": "0:00:00"}
336
+ {"current_steps": 335, "total_steps": 335, "epoch": 4.990689013035381, "percentage": 100.0, "elapsed_time": "14:12:08", "remaining_time": "0:00:00"}