sedrickkeh commited on
Commit
49bae1e
·
verified ·
1 Parent(s): 48a0a93

Training in progress, epoch 4

Browse files
model-00001-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52d96f4e8bc59d7681cc21bd4d176a6e3a2dd5dd0a1050064a255d33632ae8d8
3
  size 4891730992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35d193c3b9db208711cda75647166c9cc6c8a0a5cf63ae1e5736449f399315d4
3
  size 4891730992
model-00002-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bb4b1dd4b8fdbf0d9523254bb48f3f781c3ee8f2a590709fd829ae33c56870f
3
  size 4876059352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:686e2ac636b14a8f74c627532fb1c6ab7aa7d693b1a03434438d8a1e7a04fba2
3
  size 4876059352
model-00003-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd66f77ac90668c85641ed7ad9ad4f7c99732ec97f953cddafaf1ee368793ce4
3
  size 4876059384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df6a4e206e5ee46a3f87aad6333e8edb0d1149c86c083d164327373b69c7b70c
3
  size 4876059384
model-00004-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ab98c3e978b717ebe9cc55236a668312f5f5f761fc6ab57910b504c321bcc91
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c498c419cf69f648b818c64265ef630d778158154dfbd0df4babf6276364bd7a
3
  size 4876059416
model-00005-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc0edce5d48cdecb82bfc144eb2e01a4dd66da21a31b621343cdef8e8d3bbe3b
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f62b64fd3d915847af98809fc286d11a6cf57e00d515930405ed941534e7df
3
  size 4876059416
model-00006-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85b4b2733a8b910211b2bc52a4a9b4274895c67cc9af0eb2d39a85f78d2633be
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c37811b272b4c7287948b9d557397e86a3d2acb2a3e567b15df61796e4d732c9
3
  size 4876059416
model-00007-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dcd07ed057cc64ce9f667af1d85f6af6e742610c616f93e1dd6c7dcca2001b4
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b4c4f9aa6ad2d3085ec7c73da509383eaf06d75bf67aeb007439564bd3b7c1
3
  size 4876059416
model-00008-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53971e2c0d8d0356bb90a59a7f3584faff3222261c829112007aaf74f1172544
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4824381e946e92fa4d323b3caf4215459dd741e234ca048d68da9f0a89663bf
3
  size 4876059416
model-00009-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73a0abc4f102d4d38c118bd0243f5bf9acffd95594f372e4d778f28e3d3af737
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2d852aa959a7a5d8598662c3bf13dbb59649ad7581d295c61492e1706f8997a
3
  size 4876059416
model-00010-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a36796f79385e23b43e3aa54c76df6752023bf3f6946f8fe5ca77393475eb7b
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d892c73f96f855bb8e0bf0d22dea06d7daa73b5423be39a4017b1c3acb91093f
3
  size 4876059416
model-00011-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48066b1280de31f25e71d38d174f0fddbaa3e499470073f8df58c3bbfd2a40dc
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a602a147616fe8a4c4a0665e0affd1d39639dd3d90f8100730b995177115ad
3
  size 4876059416
model-00012-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1033a0dee2e273fe31d2417929817668c6f4e15bcb23d809076d82b4816ca9b3
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f957fa10e3a011d9e64cb56e23a08e2a2349dc7b5c91a62d45a8e0507c2012
3
  size 4876059416
model-00013-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0da724a91b99045ef3d072ade65bb63b0c63a3a7317c635a4cd88d7318939414
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f09b78ccb4b4830ec3dfc68bdade8d0e1699ffac4f8de3f135ab28619ff69b
3
  size 4876059416
model-00014-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6aa83ff370467d1b542666dec2c7e0d0fafbabf75f2492a7c8d0c11506f109b2
3
  size 2123397800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3168b44df4a5652648169b22b2ed25d6a5781c1d825c0620933ae2ea79e29528
3
  size 2123397800
trainer_log.jsonl CHANGED
@@ -229,3 +229,64 @@
229
  {"current_steps": 229, "total_steps": 315, "loss": 0.0137, "lr": 1.9060776169557083e-06, "epoch": 3.634920634920635, "percentage": 72.7, "elapsed_time": "0:59:27", "remaining_time": "0:22:19"}
230
  {"current_steps": 230, "total_steps": 315, "loss": 0.0298, "lr": 1.864979722519068e-06, "epoch": 3.6507936507936507, "percentage": 73.02, "elapsed_time": "0:59:39", "remaining_time": "0:22:03"}
231
  {"current_steps": 231, "total_steps": 315, "loss": 0.0137, "lr": 1.8242279218092968e-06, "epoch": 3.6666666666666665, "percentage": 73.33, "elapsed_time": "0:59:52", "remaining_time": "0:21:46"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
229
  {"current_steps": 229, "total_steps": 315, "loss": 0.0137, "lr": 1.9060776169557083e-06, "epoch": 3.634920634920635, "percentage": 72.7, "elapsed_time": "0:59:27", "remaining_time": "0:22:19"}
230
  {"current_steps": 230, "total_steps": 315, "loss": 0.0298, "lr": 1.864979722519068e-06, "epoch": 3.6507936507936507, "percentage": 73.02, "elapsed_time": "0:59:39", "remaining_time": "0:22:03"}
231
  {"current_steps": 231, "total_steps": 315, "loss": 0.0137, "lr": 1.8242279218092968e-06, "epoch": 3.6666666666666665, "percentage": 73.33, "elapsed_time": "0:59:52", "remaining_time": "0:21:46"}
232
+ {"current_steps": 232, "total_steps": 315, "loss": 0.0114, "lr": 1.7838267136625536e-06, "epoch": 3.682539682539683, "percentage": 73.65, "elapsed_time": "1:00:04", "remaining_time": "0:21:29"}
233
+ {"current_steps": 233, "total_steps": 315, "loss": 0.013, "lr": 1.743780558210979e-06, "epoch": 3.6984126984126986, "percentage": 73.97, "elapsed_time": "1:00:16", "remaining_time": "0:21:12"}
234
+ {"current_steps": 234, "total_steps": 315, "loss": 0.0217, "lr": 1.704093876390312e-06, "epoch": 3.7142857142857144, "percentage": 74.29, "elapsed_time": "1:00:29", "remaining_time": "0:20:56"}
235
+ {"current_steps": 235, "total_steps": 315, "loss": 0.0089, "lr": 1.664771049451837e-06, "epoch": 3.7301587301587302, "percentage": 74.6, "elapsed_time": "1:00:41", "remaining_time": "0:20:39"}
236
+ {"current_steps": 236, "total_steps": 315, "loss": 0.0085, "lr": 1.6258164184787123e-06, "epoch": 3.746031746031746, "percentage": 74.92, "elapsed_time": "1:00:53", "remaining_time": "0:20:23"}
237
+ {"current_steps": 237, "total_steps": 315, "loss": 0.0075, "lr": 1.5872342839067305e-06, "epoch": 3.761904761904762, "percentage": 75.24, "elapsed_time": "1:01:06", "remaining_time": "0:20:06"}
238
+ {"current_steps": 238, "total_steps": 315, "loss": 0.0108, "lr": 1.5490289050495678e-06, "epoch": 3.7777777777777777, "percentage": 75.56, "elapsed_time": "1:01:18", "remaining_time": "0:19:49"}
239
+ {"current_steps": 239, "total_steps": 315, "loss": 0.0086, "lr": 1.511204499628574e-06, "epoch": 3.7936507936507935, "percentage": 75.87, "elapsed_time": "1:01:30", "remaining_time": "0:19:33"}
240
+ {"current_steps": 240, "total_steps": 315, "loss": 0.0135, "lr": 1.4737652433071515e-06, "epoch": 3.8095238095238093, "percentage": 76.19, "elapsed_time": "1:01:42", "remaining_time": "0:19:16"}
241
+ {"current_steps": 241, "total_steps": 315, "loss": 0.0187, "lr": 1.4367152692297799e-06, "epoch": 3.825396825396825, "percentage": 76.51, "elapsed_time": "1:01:54", "remaining_time": "0:19:00"}
242
+ {"current_steps": 242, "total_steps": 315, "loss": 0.0111, "lr": 1.4000586675657312e-06, "epoch": 3.8412698412698414, "percentage": 76.83, "elapsed_time": "1:02:06", "remaining_time": "0:18:44"}
243
+ {"current_steps": 243, "total_steps": 315, "loss": 0.0147, "lr": 1.3637994850575342e-06, "epoch": 3.857142857142857, "percentage": 77.14, "elapsed_time": "1:02:18", "remaining_time": "0:18:27"}
244
+ {"current_steps": 244, "total_steps": 315, "loss": 0.0236, "lr": 1.3279417245742288e-06, "epoch": 3.873015873015873, "percentage": 77.46, "elapsed_time": "1:02:30", "remaining_time": "0:18:11"}
245
+ {"current_steps": 245, "total_steps": 315, "loss": 0.006, "lr": 1.2924893446694648e-06, "epoch": 3.888888888888889, "percentage": 77.78, "elapsed_time": "1:02:42", "remaining_time": "0:17:55"}
246
+ {"current_steps": 246, "total_steps": 315, "loss": 0.0286, "lr": 1.257446259144494e-06, "epoch": 3.9047619047619047, "percentage": 78.1, "elapsed_time": "1:02:54", "remaining_time": "0:17:38"}
247
+ {"current_steps": 247, "total_steps": 315, "loss": 0.0143, "lr": 1.222816336616104e-06, "epoch": 3.9206349206349205, "percentage": 78.41, "elapsed_time": "1:03:06", "remaining_time": "0:17:22"}
248
+ {"current_steps": 248, "total_steps": 315, "loss": 0.0177, "lr": 1.1886034000895341e-06, "epoch": 3.9365079365079367, "percentage": 78.73, "elapsed_time": "1:03:18", "remaining_time": "0:17:06"}
249
+ {"current_steps": 249, "total_steps": 315, "loss": 0.0132, "lr": 1.1548112265364336e-06, "epoch": 3.9523809523809526, "percentage": 79.05, "elapsed_time": "1:03:30", "remaining_time": "0:16:50"}
250
+ {"current_steps": 250, "total_steps": 315, "loss": 0.0206, "lr": 1.1214435464779006e-06, "epoch": 3.9682539682539684, "percentage": 79.37, "elapsed_time": "1:03:44", "remaining_time": "0:16:34"}
251
+ {"current_steps": 251, "total_steps": 315, "loss": 0.0131, "lr": 1.088504043572643e-06, "epoch": 3.984126984126984, "percentage": 79.68, "elapsed_time": "1:03:56", "remaining_time": "0:16:18"}
252
+ {"current_steps": 252, "total_steps": 315, "loss": 0.0079, "lr": 1.055996354210323e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "1:04:08", "remaining_time": "0:16:02"}
253
+ {"current_steps": 253, "total_steps": 315, "loss": 0.0027, "lr": 1.0239240671101065e-06, "epoch": 4.015873015873016, "percentage": 80.32, "elapsed_time": "1:08:23", "remaining_time": "0:16:45"}
254
+ {"current_steps": 254, "total_steps": 315, "loss": 0.0063, "lr": 9.922907229244905e-07, "epoch": 4.031746031746032, "percentage": 80.63, "elapsed_time": "1:08:35", "remaining_time": "0:16:28"}
255
+ {"current_steps": 255, "total_steps": 315, "loss": 0.0032, "lr": 9.610998138484262e-07, "epoch": 4.0476190476190474, "percentage": 80.95, "elapsed_time": "1:08:47", "remaining_time": "0:16:11"}
256
+ {"current_steps": 256, "total_steps": 315, "loss": 0.0036, "lr": 9.303547832337934e-07, "epoch": 4.063492063492063, "percentage": 81.27, "elapsed_time": "1:08:59", "remaining_time": "0:15:54"}
257
+ {"current_steps": 257, "total_steps": 315, "loss": 0.0034, "lr": 9.000590252092701e-07, "epoch": 4.079365079365079, "percentage": 81.59, "elapsed_time": "1:09:11", "remaining_time": "0:15:36"}
258
+ {"current_steps": 258, "total_steps": 315, "loss": 0.0029, "lr": 8.702158843056319e-07, "epoch": 4.095238095238095, "percentage": 81.9, "elapsed_time": "1:09:23", "remaining_time": "0:15:19"}
259
+ {"current_steps": 259, "total_steps": 315, "loss": 0.0041, "lr": 8.408286550865319e-07, "epoch": 4.111111111111111, "percentage": 82.22, "elapsed_time": "1:09:35", "remaining_time": "0:15:02"}
260
+ {"current_steps": 260, "total_steps": 315, "loss": 0.0039, "lr": 8.119005817847924e-07, "epoch": 4.1269841269841265, "percentage": 82.54, "elapsed_time": "1:09:48", "remaining_time": "0:14:45"}
261
+ {"current_steps": 261, "total_steps": 315, "loss": 0.0034, "lr": 7.834348579442552e-07, "epoch": 4.142857142857143, "percentage": 82.86, "elapsed_time": "1:10:00", "remaining_time": "0:14:29"}
262
+ {"current_steps": 262, "total_steps": 315, "loss": 0.0054, "lr": 7.554346260672263e-07, "epoch": 4.158730158730159, "percentage": 83.17, "elapsed_time": "1:10:12", "remaining_time": "0:14:12"}
263
+ {"current_steps": 263, "total_steps": 315, "loss": 0.0025, "lr": 7.279029772675572e-07, "epoch": 4.174603174603175, "percentage": 83.49, "elapsed_time": "1:10:25", "remaining_time": "0:13:55"}
264
+ {"current_steps": 264, "total_steps": 315, "loss": 0.002, "lr": 7.008429509293979e-07, "epoch": 4.190476190476191, "percentage": 83.81, "elapsed_time": "1:10:37", "remaining_time": "0:13:38"}
265
+ {"current_steps": 265, "total_steps": 315, "loss": 0.0053, "lr": 6.742575343716584e-07, "epoch": 4.2063492063492065, "percentage": 84.13, "elapsed_time": "1:10:50", "remaining_time": "0:13:21"}
266
+ {"current_steps": 266, "total_steps": 315, "loss": 0.0035, "lr": 6.481496625182271e-07, "epoch": 4.222222222222222, "percentage": 84.44, "elapsed_time": "1:11:02", "remaining_time": "0:13:05"}
267
+ {"current_steps": 267, "total_steps": 315, "loss": 0.0094, "lr": 6.225222175739598e-07, "epoch": 4.238095238095238, "percentage": 84.76, "elapsed_time": "1:11:14", "remaining_time": "0:12:48"}
268
+ {"current_steps": 268, "total_steps": 315, "loss": 0.002, "lr": 5.973780287065007e-07, "epoch": 4.253968253968254, "percentage": 85.08, "elapsed_time": "1:11:27", "remaining_time": "0:12:31"}
269
+ {"current_steps": 269, "total_steps": 315, "loss": 0.0185, "lr": 5.727198717339511e-07, "epoch": 4.26984126984127, "percentage": 85.4, "elapsed_time": "1:11:39", "remaining_time": "0:12:15"}
270
+ {"current_steps": 270, "total_steps": 315, "loss": 0.0016, "lr": 5.485504688184307e-07, "epoch": 4.285714285714286, "percentage": 85.71, "elapsed_time": "1:11:51", "remaining_time": "0:11:58"}
271
+ {"current_steps": 271, "total_steps": 315, "loss": 0.0029, "lr": 5.24872488165562e-07, "epoch": 4.301587301587301, "percentage": 86.03, "elapsed_time": "1:12:04", "remaining_time": "0:11:42"}
272
+ {"current_steps": 272, "total_steps": 315, "loss": 0.003, "lr": 5.016885437299113e-07, "epoch": 4.317460317460317, "percentage": 86.35, "elapsed_time": "1:12:16", "remaining_time": "0:11:25"}
273
+ {"current_steps": 273, "total_steps": 315, "loss": 0.0064, "lr": 4.790011949264173e-07, "epoch": 4.333333333333333, "percentage": 86.67, "elapsed_time": "1:12:29", "remaining_time": "0:11:09"}
274
+ {"current_steps": 274, "total_steps": 315, "loss": 0.0014, "lr": 4.5681294634784437e-07, "epoch": 4.349206349206349, "percentage": 86.98, "elapsed_time": "1:12:42", "remaining_time": "0:10:52"}
275
+ {"current_steps": 275, "total_steps": 315, "loss": 0.0012, "lr": 4.3512624748828225e-07, "epoch": 4.365079365079365, "percentage": 87.3, "elapsed_time": "1:12:54", "remaining_time": "0:10:36"}
276
+ {"current_steps": 276, "total_steps": 315, "loss": 0.0059, "lr": 4.139434924727359e-07, "epoch": 4.380952380952381, "percentage": 87.62, "elapsed_time": "1:13:08", "remaining_time": "0:10:20"}
277
+ {"current_steps": 277, "total_steps": 315, "loss": 0.0059, "lr": 3.9326701979281623e-07, "epoch": 4.396825396825397, "percentage": 87.94, "elapsed_time": "1:13:21", "remaining_time": "0:10:03"}
278
+ {"current_steps": 278, "total_steps": 315, "loss": 0.0031, "lr": 3.7309911204858997e-07, "epoch": 4.412698412698413, "percentage": 88.25, "elapsed_time": "1:13:34", "remaining_time": "0:09:47"}
279
+ {"current_steps": 279, "total_steps": 315, "loss": 0.0024, "lr": 3.534419956965823e-07, "epoch": 4.428571428571429, "percentage": 88.57, "elapsed_time": "1:13:47", "remaining_time": "0:09:31"}
280
+ {"current_steps": 280, "total_steps": 315, "loss": 0.005, "lr": 3.3429784080398765e-07, "epoch": 4.444444444444445, "percentage": 88.89, "elapsed_time": "1:13:59", "remaining_time": "0:09:14"}
281
+ {"current_steps": 281, "total_steps": 315, "loss": 0.0042, "lr": 3.1566876080910193e-07, "epoch": 4.4603174603174605, "percentage": 89.21, "elapsed_time": "1:14:12", "remaining_time": "0:08:58"}
282
+ {"current_steps": 282, "total_steps": 315, "loss": 0.0023, "lr": 2.9755681228800904e-07, "epoch": 4.476190476190476, "percentage": 89.52, "elapsed_time": "1:14:24", "remaining_time": "0:08:42"}
283
+ {"current_steps": 283, "total_steps": 315, "loss": 0.0037, "lr": 2.799639947275412e-07, "epoch": 4.492063492063492, "percentage": 89.84, "elapsed_time": "1:14:36", "remaining_time": "0:08:26"}
284
+ {"current_steps": 284, "total_steps": 315, "loss": 0.0025, "lr": 2.6289225030454556e-07, "epoch": 4.507936507936508, "percentage": 90.16, "elapsed_time": "1:14:48", "remaining_time": "0:08:09"}
285
+ {"current_steps": 285, "total_steps": 315, "loss": 0.0038, "lr": 2.4634346367147233e-07, "epoch": 4.523809523809524, "percentage": 90.48, "elapsed_time": "1:15:00", "remaining_time": "0:07:53"}
286
+ {"current_steps": 286, "total_steps": 315, "loss": 0.0052, "lr": 2.303194617483212e-07, "epoch": 4.5396825396825395, "percentage": 90.79, "elapsed_time": "1:15:12", "remaining_time": "0:07:37"}
287
+ {"current_steps": 287, "total_steps": 315, "loss": 0.0037, "lr": 2.1482201352095277e-07, "epoch": 4.555555555555555, "percentage": 91.11, "elapsed_time": "1:15:25", "remaining_time": "0:07:21"}
288
+ {"current_steps": 288, "total_steps": 315, "loss": 0.0026, "lr": 1.998528298458019e-07, "epoch": 4.571428571428571, "percentage": 91.43, "elapsed_time": "1:15:37", "remaining_time": "0:07:05"}
289
+ {"current_steps": 289, "total_steps": 315, "loss": 0.0006, "lr": 1.8541356326100436e-07, "epoch": 4.587301587301587, "percentage": 91.75, "elapsed_time": "1:15:49", "remaining_time": "0:06:49"}
290
+ {"current_steps": 290, "total_steps": 315, "loss": 0.0041, "lr": 1.7150580780396385e-07, "epoch": 4.603174603174603, "percentage": 92.06, "elapsed_time": "1:16:01", "remaining_time": "0:06:33"}
291
+ {"current_steps": 291, "total_steps": 315, "loss": 0.0022, "lr": 1.5813109883537792e-07, "epoch": 4.619047619047619, "percentage": 92.38, "elapsed_time": "1:16:13", "remaining_time": "0:06:17"}
292
+ {"current_steps": 292, "total_steps": 315, "loss": 0.0029, "lr": 1.4529091286973994e-07, "epoch": 4.634920634920634, "percentage": 92.7, "elapsed_time": "1:16:25", "remaining_time": "0:06:01"}