penfever commited on
Commit
c08a7f8
·
verified ·
1 Parent(s): 235f81e

Training in progress, step 1778

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadff5100613856585a1913d2b91ad7852abffb3c19b0f6411d69a41f987e6bb
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15a230f61ef0cc37ef69a9c134f5df345cbed99397ff0e355cc08e1b5ab63e2d
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccd9cf8f11161a4becc57d3392bea467c0da0b3026ed9c63ae68b1a34e99d927
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98898fa35e4a8d23c9d51514dd11ec34b14d9315b8f76c6eeafdd27560c73519
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b42890f8ae45e948f8816ff34a8c117d9b12f71ae3ada495b2a29a002d024659
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343eb36eac76901b12cb1c9d317ccd698e1b0763c01bd4478307ef4e75c4faee
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15d4d625ae71e0411c1187071289ffefce6829aac0349eb0e3529d584cd6fe95
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb845df649ff0243844cd9b1f1ba6258a9a1e5a2c9562935af488f3f4dbf838e
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -304,3 +304,53 @@
304
  {"current_steps": 1520, "total_steps": 1778, "loss": 0.175, "lr": 2.5309253970418056e-06, "epoch": 5.984251968503937, "percentage": 85.49, "elapsed_time": "3:50:38", "remaining_time": "0:39:08"}
305
  {"current_steps": 1525, "total_steps": 1778, "loss": 0.1631, "lr": 2.436164788616815e-06, "epoch": 6.003937007874016, "percentage": 85.77, "elapsed_time": "3:51:24", "remaining_time": "0:38:23"}
306
  {"current_steps": 1530, "total_steps": 1778, "loss": 0.1686, "lr": 2.3430970191858873e-06, "epoch": 6.0236220472440944, "percentage": 86.05, "elapsed_time": "3:52:12", "remaining_time": "0:37:38"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
304
  {"current_steps": 1520, "total_steps": 1778, "loss": 0.175, "lr": 2.5309253970418056e-06, "epoch": 5.984251968503937, "percentage": 85.49, "elapsed_time": "3:50:38", "remaining_time": "0:39:08"}
305
  {"current_steps": 1525, "total_steps": 1778, "loss": 0.1631, "lr": 2.436164788616815e-06, "epoch": 6.003937007874016, "percentage": 85.77, "elapsed_time": "3:51:24", "remaining_time": "0:38:23"}
306
  {"current_steps": 1530, "total_steps": 1778, "loss": 0.1686, "lr": 2.3430970191858873e-06, "epoch": 6.0236220472440944, "percentage": 86.05, "elapsed_time": "3:52:12", "remaining_time": "0:37:38"}
307
+ {"current_steps": 1535, "total_steps": 1778, "loss": 0.1567, "lr": 2.2517310588143372e-06, "epoch": 6.043307086614173, "percentage": 86.33, "elapsed_time": "3:52:55", "remaining_time": "0:36:52"}
308
+ {"current_steps": 1540, "total_steps": 1778, "loss": 0.1598, "lr": 2.1620757135435875e-06, "epoch": 6.062992125984252, "percentage": 86.61, "elapsed_time": "3:53:44", "remaining_time": "0:36:07"}
309
+ {"current_steps": 1545, "total_steps": 1778, "loss": 0.1627, "lr": 2.0741396245424263e-06, "epoch": 6.082677165354331, "percentage": 86.9, "elapsed_time": "3:54:33", "remaining_time": "0:35:22"}
310
+ {"current_steps": 1550, "total_steps": 1778, "loss": 0.1662, "lr": 1.9879312672741326e-06, "epoch": 6.102362204724409, "percentage": 87.18, "elapsed_time": "3:55:22", "remaining_time": "0:34:37"}
311
+ {"current_steps": 1555, "total_steps": 1778, "loss": 0.1567, "lr": 1.903458950679613e-06, "epoch": 6.122047244094488, "percentage": 87.46, "elapsed_time": "3:56:10", "remaining_time": "0:33:52"}
312
+ {"current_steps": 1560, "total_steps": 1778, "loss": 0.1614, "lr": 1.820730816376548e-06, "epoch": 6.141732283464567, "percentage": 87.74, "elapsed_time": "3:56:50", "remaining_time": "0:33:05"}
313
+ {"current_steps": 1565, "total_steps": 1778, "loss": 0.1621, "lr": 1.7397548378747142e-06, "epoch": 6.161417322834645, "percentage": 88.02, "elapsed_time": "3:57:37", "remaining_time": "0:32:20"}
314
+ {"current_steps": 1570, "total_steps": 1778, "loss": 0.1624, "lr": 1.660538819807458e-06, "epoch": 6.181102362204724, "percentage": 88.3, "elapsed_time": "3:58:27", "remaining_time": "0:31:35"}
315
+ {"current_steps": 1575, "total_steps": 1778, "loss": 0.1588, "lr": 1.5830903971794765e-06, "epoch": 6.200787401574803, "percentage": 88.58, "elapsed_time": "3:59:14", "remaining_time": "0:30:50"}
316
+ {"current_steps": 1580, "total_steps": 1778, "loss": 0.1672, "lr": 1.5074170346309357e-06, "epoch": 6.2204724409448815, "percentage": 88.86, "elapsed_time": "4:00:02", "remaining_time": "0:30:04"}
317
+ {"current_steps": 1585, "total_steps": 1778, "loss": 0.1613, "lr": 1.4335260257180262e-06, "epoch": 6.24015748031496, "percentage": 89.15, "elapsed_time": "4:00:44", "remaining_time": "0:29:18"}
318
+ {"current_steps": 1590, "total_steps": 1778, "loss": 0.1592, "lr": 1.3614244922099796e-06, "epoch": 6.259842519685039, "percentage": 89.43, "elapsed_time": "4:01:25", "remaining_time": "0:28:32"}
319
+ {"current_steps": 1595, "total_steps": 1778, "loss": 0.1642, "lr": 1.2911193834026548e-06, "epoch": 6.2795275590551185, "percentage": 89.71, "elapsed_time": "4:02:18", "remaining_time": "0:27:48"}
320
+ {"current_steps": 1600, "total_steps": 1778, "loss": 0.1638, "lr": 1.222617475448773e-06, "epoch": 6.299212598425197, "percentage": 89.99, "elapsed_time": "4:02:58", "remaining_time": "0:27:01"}
321
+ {"current_steps": 1605, "total_steps": 1778, "loss": 0.1605, "lr": 1.1559253707048046e-06, "epoch": 6.318897637795276, "percentage": 90.27, "elapsed_time": "4:03:47", "remaining_time": "0:26:16"}
322
+ {"current_steps": 1610, "total_steps": 1778, "loss": 0.161, "lr": 1.0910494970946073e-06, "epoch": 6.338582677165355, "percentage": 90.55, "elapsed_time": "4:04:36", "remaining_time": "0:25:31"}
323
+ {"current_steps": 1615, "total_steps": 1778, "loss": 0.1668, "lr": 1.027996107489908e-06, "epoch": 6.358267716535433, "percentage": 90.83, "elapsed_time": "4:05:21", "remaining_time": "0:24:45"}
324
+ {"current_steps": 1620, "total_steps": 1778, "loss": 0.1536, "lr": 9.667712791076345e-07, "epoch": 6.377952755905512, "percentage": 91.11, "elapsed_time": "4:06:13", "remaining_time": "0:24:00"}
325
+ {"current_steps": 1625, "total_steps": 1778, "loss": 0.1652, "lr": 9.073809129241784e-07, "epoch": 6.397637795275591, "percentage": 91.39, "elapsed_time": "4:06:56", "remaining_time": "0:23:15"}
326
+ {"current_steps": 1630, "total_steps": 1778, "loss": 0.1671, "lr": 8.498307331066446e-07, "epoch": 6.417322834645669, "percentage": 91.68, "elapsed_time": "4:07:42", "remaining_time": "0:22:29"}
327
+ {"current_steps": 1635, "total_steps": 1778, "loss": 0.1607, "lr": 7.941262864611387e-07, "epoch": 6.437007874015748, "percentage": 91.96, "elapsed_time": "4:08:23", "remaining_time": "0:21:43"}
328
+ {"current_steps": 1640, "total_steps": 1778, "loss": 0.1662, "lr": 7.402729418981769e-07, "epoch": 6.456692913385827, "percentage": 92.24, "elapsed_time": "4:09:08", "remaining_time": "0:20:57"}
329
+ {"current_steps": 1645, "total_steps": 1778, "loss": 0.1578, "lr": 6.882758899151886e-07, "epoch": 6.4763779527559056, "percentage": 92.52, "elapsed_time": "4:09:50", "remaining_time": "0:20:12"}
330
+ {"current_steps": 1650, "total_steps": 1778, "loss": 0.16, "lr": 6.381401420962729e-07, "epoch": 6.496062992125984, "percentage": 92.8, "elapsed_time": "4:10:29", "remaining_time": "0:19:25"}
331
+ {"current_steps": 1655, "total_steps": 1778, "loss": 0.1641, "lr": 5.898705306291508e-07, "epoch": 6.515748031496063, "percentage": 93.08, "elapsed_time": "4:11:17", "remaining_time": "0:18:40"}
332
+ {"current_steps": 1660, "total_steps": 1778, "loss": 0.1635, "lr": 5.434717078394447e-07, "epoch": 6.535433070866142, "percentage": 93.36, "elapsed_time": "4:12:01", "remaining_time": "0:17:54"}
333
+ {"current_steps": 1665, "total_steps": 1778, "loss": 0.1655, "lr": 4.98948145742264e-07, "epoch": 6.55511811023622, "percentage": 93.64, "elapsed_time": "4:12:41", "remaining_time": "0:17:09"}
334
+ {"current_steps": 1670, "total_steps": 1778, "loss": 0.1598, "lr": 4.563041356111919e-07, "epoch": 6.574803149606299, "percentage": 93.93, "elapsed_time": "4:13:27", "remaining_time": "0:16:23"}
335
+ {"current_steps": 1675, "total_steps": 1778, "loss": 0.1624, "lr": 4.155437875646828e-07, "epoch": 6.594488188976378, "percentage": 94.21, "elapsed_time": "4:14:11", "remaining_time": "0:15:37"}
336
+ {"current_steps": 1680, "total_steps": 1778, "loss": 0.1545, "lr": 3.7667103016992167e-07, "epoch": 6.6141732283464565, "percentage": 94.49, "elapsed_time": "4:14:53", "remaining_time": "0:14:52"}
337
+ {"current_steps": 1685, "total_steps": 1778, "loss": 0.1667, "lr": 3.396896100641689e-07, "epoch": 6.633858267716535, "percentage": 94.77, "elapsed_time": "4:15:33", "remaining_time": "0:14:06"}
338
+ {"current_steps": 1690, "total_steps": 1778, "loss": 0.1612, "lr": 3.0460309159366486e-07, "epoch": 6.653543307086614, "percentage": 95.05, "elapsed_time": "4:16:15", "remaining_time": "0:13:20"}
339
+ {"current_steps": 1695, "total_steps": 1778, "loss": 0.1625, "lr": 2.714148564700914e-07, "epoch": 6.673228346456693, "percentage": 95.33, "elapsed_time": "4:16:51", "remaining_time": "0:12:34"}
340
+ {"current_steps": 1700, "total_steps": 1778, "loss": 0.1627, "lr": 2.401281034446212e-07, "epoch": 6.692913385826771, "percentage": 95.61, "elapsed_time": "4:17:38", "remaining_time": "0:11:49"}
341
+ {"current_steps": 1705, "total_steps": 1778, "loss": 0.1585, "lr": 2.107458479996316e-07, "epoch": 6.71259842519685, "percentage": 95.89, "elapsed_time": "4:18:25", "remaining_time": "0:11:03"}
342
+ {"current_steps": 1710, "total_steps": 1778, "loss": 0.1671, "lr": 1.8327092205805641e-07, "epoch": 6.73228346456693, "percentage": 96.18, "elapsed_time": "4:19:04", "remaining_time": "0:10:18"}
343
+ {"current_steps": 1715, "total_steps": 1778, "loss": 0.1633, "lr": 1.577059737104447e-07, "epoch": 6.751968503937007, "percentage": 96.46, "elapsed_time": "4:19:54", "remaining_time": "0:09:32"}
344
+ {"current_steps": 1720, "total_steps": 1778, "loss": 0.1612, "lr": 1.3405346695972265e-07, "epoch": 6.771653543307087, "percentage": 96.74, "elapsed_time": "4:20:47", "remaining_time": "0:08:47"}
345
+ {"current_steps": 1725, "total_steps": 1778, "loss": 0.1636, "lr": 1.1231568148372562e-07, "epoch": 6.791338582677166, "percentage": 97.02, "elapsed_time": "4:21:37", "remaining_time": "0:08:02"}
346
+ {"current_steps": 1730, "total_steps": 1778, "loss": 0.1645, "lr": 9.249471241545849e-08, "epoch": 6.811023622047244, "percentage": 97.3, "elapsed_time": "4:22:21", "remaining_time": "0:07:16"}
347
+ {"current_steps": 1735, "total_steps": 1778, "loss": 0.1604, "lr": 7.459247014117488e-08, "epoch": 6.830708661417323, "percentage": 97.58, "elapsed_time": "4:22:58", "remaining_time": "0:06:31"}
348
+ {"current_steps": 1740, "total_steps": 1778, "loss": 0.161, "lr": 5.861068011624449e-08, "epoch": 6.850393700787402, "percentage": 97.86, "elapsed_time": "4:23:44", "remaining_time": "0:05:45"}
349
+ {"current_steps": 1745, "total_steps": 1778, "loss": 0.1682, "lr": 4.4550882698857214e-08, "epoch": 6.8700787401574805, "percentage": 98.14, "elapsed_time": "4:24:29", "remaining_time": "0:05:00"}
350
+ {"current_steps": 1750, "total_steps": 1778, "loss": 0.1602, "lr": 3.241443300154856e-08, "epoch": 6.889763779527559, "percentage": 98.43, "elapsed_time": "4:25:13", "remaining_time": "0:04:14"}
351
+ {"current_steps": 1755, "total_steps": 1778, "loss": 0.1612, "lr": 2.220250076060193e-08, "epoch": 6.909448818897638, "percentage": 98.71, "elapsed_time": "4:26:00", "remaining_time": "0:03:29"}
352
+ {"current_steps": 1760, "total_steps": 1778, "loss": 0.1601, "lr": 1.3916070223298772e-08, "epoch": 6.929133858267717, "percentage": 98.99, "elapsed_time": "4:26:51", "remaining_time": "0:02:43"}
353
+ {"current_steps": 1765, "total_steps": 1778, "loss": 0.1699, "lr": 7.55594005306337e-09, "epoch": 6.948818897637795, "percentage": 99.27, "elapsed_time": "4:27:30", "remaining_time": "0:01:58"}
354
+ {"current_steps": 1770, "total_steps": 1778, "loss": 0.1586, "lr": 3.122723252477755e-09, "epoch": 6.968503937007874, "percentage": 99.55, "elapsed_time": "4:28:16", "remaining_time": "0:01:12"}
355
+ {"current_steps": 1775, "total_steps": 1778, "loss": 0.1578, "lr": 6.168471042067303e-10, "epoch": 6.988188976377953, "percentage": 99.83, "elapsed_time": "4:28:57", "remaining_time": "0:00:27"}
356
+ {"current_steps": 1778, "total_steps": 1778, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "4:30:06", "remaining_time": "0:00:00"}