penfever commited on
Commit
fbf676c
·
verified ·
1 Parent(s): eca2161

Training in progress, step 1600

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64a4ec56f142c9f76671fd542624ea226cec104f1b8e9cd557dc97a8184725f4
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:952de354da07df65ccea0d0f5d32dab424b5fe666ba337ab6c2f9c52dcfbc48c
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:621d12af10d5dcb2ded2fd2d808a2248829268da3f39cacac9e6dcf4fcc3dc36
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:683b033ffb1a83a9853ec6b0e7aaebd522e1716f43828649698a5b9a0519217b
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:d2c6c4ecd175c4bd9d3a369b9551b84c1f2c3ca1ed2ad06da3b0d3d753a78dfc
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b316a0e38b86aceb5bcca72d66eccbce6bbfecfb5910794e7c28b6095d2b00
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:dcc00edfdca62ad34f574f268b3e06457d85acfa34d64277db5b049ff1914cf7
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e65eb75d8a7859d9cdb9a4a0071d9c10e24a9406177be252d3f7ef7cdc50c135
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -278,3 +278,43 @@
278
  {"current_steps": 1390, "total_steps": 3850, "loss": 0.252, "lr": 3.227031632576122e-05, "epoch": 2.5277525022747955, "percentage": 36.1, "elapsed_time": "9:17:46", "remaining_time": "16:27:08"}
279
  {"current_steps": 1395, "total_steps": 3850, "loss": 0.2679, "lr": 3.219859278108972e-05, "epoch": 2.5368516833484986, "percentage": 36.23, "elapsed_time": "9:19:53", "remaining_time": "16:25:19"}
280
  {"current_steps": 1400, "total_steps": 3850, "loss": 0.2602, "lr": 3.212661854338438e-05, "epoch": 2.5459508644222018, "percentage": 36.36, "elapsed_time": "9:21:57", "remaining_time": "16:23:25"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
278
  {"current_steps": 1390, "total_steps": 3850, "loss": 0.252, "lr": 3.227031632576122e-05, "epoch": 2.5277525022747955, "percentage": 36.1, "elapsed_time": "9:17:46", "remaining_time": "16:27:08"}
279
  {"current_steps": 1395, "total_steps": 3850, "loss": 0.2679, "lr": 3.219859278108972e-05, "epoch": 2.5368516833484986, "percentage": 36.23, "elapsed_time": "9:19:53", "remaining_time": "16:25:19"}
280
  {"current_steps": 1400, "total_steps": 3850, "loss": 0.2602, "lr": 3.212661854338438e-05, "epoch": 2.5459508644222018, "percentage": 36.36, "elapsed_time": "9:21:57", "remaining_time": "16:23:25"}
281
+ {"current_steps": 1405, "total_steps": 3850, "loss": 0.2626, "lr": 3.20543950917863e-05, "epoch": 2.5550500454959053, "percentage": 36.49, "elapsed_time": "9:25:04", "remaining_time": "16:23:20"}
282
+ {"current_steps": 1410, "total_steps": 3850, "loss": 0.2769, "lr": 3.1981923910558164e-05, "epoch": 2.564149226569609, "percentage": 36.62, "elapsed_time": "9:27:01", "remaining_time": "16:21:14"}
283
+ {"current_steps": 1415, "total_steps": 3850, "loss": 0.2531, "lr": 3.190920648905376e-05, "epoch": 2.573248407643312, "percentage": 36.75, "elapsed_time": "9:29:01", "remaining_time": "16:19:11"}
284
+ {"current_steps": 1420, "total_steps": 3850, "loss": 0.253, "lr": 3.183624432168736e-05, "epoch": 2.5823475887170155, "percentage": 36.88, "elapsed_time": "9:30:47", "remaining_time": "16:16:47"}
285
+ {"current_steps": 1425, "total_steps": 3850, "loss": 0.2737, "lr": 3.1763038907902976e-05, "epoch": 2.5914467697907186, "percentage": 37.01, "elapsed_time": "9:32:47", "remaining_time": "16:14:44"}
286
+ {"current_steps": 1430, "total_steps": 3850, "loss": 0.2465, "lr": 3.16895917521436e-05, "epoch": 2.600545950864422, "percentage": 37.14, "elapsed_time": "9:34:55", "remaining_time": "16:12:56"}
287
+ {"current_steps": 1435, "total_steps": 3850, "loss": 0.2768, "lr": 3.161590436382023e-05, "epoch": 2.6096451319381258, "percentage": 37.27, "elapsed_time": "9:36:45", "remaining_time": "16:10:38"}
288
+ {"current_steps": 1440, "total_steps": 3850, "loss": 0.2575, "lr": 3.1541978257280915e-05, "epoch": 2.618744313011829, "percentage": 37.4, "elapsed_time": "9:38:45", "remaining_time": "16:08:36"}
289
+ {"current_steps": 1445, "total_steps": 3850, "loss": 0.2686, "lr": 3.1467814951779564e-05, "epoch": 2.6278434940855324, "percentage": 37.53, "elapsed_time": "9:40:50", "remaining_time": "16:06:43"}
290
+ {"current_steps": 1450, "total_steps": 3850, "loss": 0.2567, "lr": 3.139341597144478e-05, "epoch": 2.6369426751592355, "percentage": 37.66, "elapsed_time": "9:42:58", "remaining_time": "16:04:55"}
291
+ {"current_steps": 1455, "total_steps": 3850, "loss": 0.2758, "lr": 3.13187828452485e-05, "epoch": 2.646041856232939, "percentage": 37.79, "elapsed_time": "9:44:43", "remaining_time": "16:02:28"}
292
+ {"current_steps": 1460, "total_steps": 3850, "loss": 0.2685, "lr": 3.1243917106974583e-05, "epoch": 2.6551410373066426, "percentage": 37.92, "elapsed_time": "9:46:39", "remaining_time": "16:00:21"}
293
+ {"current_steps": 1465, "total_steps": 3850, "loss": 0.2673, "lr": 3.116882029518732e-05, "epoch": 2.6642402183803457, "percentage": 38.05, "elapsed_time": "9:48:42", "remaining_time": "15:58:24"}
294
+ {"current_steps": 1470, "total_steps": 3850, "loss": 0.2791, "lr": 3.109349395319976e-05, "epoch": 2.673339399454049, "percentage": 38.18, "elapsed_time": "9:50:29", "remaining_time": "15:56:02"}
295
+ {"current_steps": 1475, "total_steps": 3850, "loss": 0.2586, "lr": 3.101793962904205e-05, "epoch": 2.6824385805277524, "percentage": 38.31, "elapsed_time": "9:52:30", "remaining_time": "15:54:02"}
296
+ {"current_steps": 1480, "total_steps": 3850, "loss": 0.2669, "lr": 3.094215887542957e-05, "epoch": 2.691537761601456, "percentage": 38.44, "elapsed_time": "9:54:31", "remaining_time": "15:52:02"}
297
+ {"current_steps": 1485, "total_steps": 3850, "loss": 0.2708, "lr": 3.086615324973107e-05, "epoch": 2.700636942675159, "percentage": 38.57, "elapsed_time": "9:56:36", "remaining_time": "15:50:09"}
298
+ {"current_steps": 1490, "total_steps": 3850, "loss": 0.2633, "lr": 3.07899243139366e-05, "epoch": 2.7097361237488626, "percentage": 38.7, "elapsed_time": "9:58:30", "remaining_time": "15:47:57"}
299
+ {"current_steps": 1495, "total_steps": 3850, "loss": 0.2602, "lr": 3.0713473634625507e-05, "epoch": 2.7188353048225657, "percentage": 38.83, "elapsed_time": "10:00:23", "remaining_time": "15:45:45"}
300
+ {"current_steps": 1500, "total_steps": 3850, "loss": 0.2542, "lr": 3.0636802782934146e-05, "epoch": 2.7279344858962693, "percentage": 38.96, "elapsed_time": "10:02:32", "remaining_time": "15:43:58"}
301
+ {"current_steps": 1505, "total_steps": 3850, "loss": 0.2629, "lr": 3.055991333452364e-05, "epoch": 2.737033666969973, "percentage": 39.09, "elapsed_time": "10:04:37", "remaining_time": "15:42:04"}
302
+ {"current_steps": 1510, "total_steps": 3850, "loss": 0.2536, "lr": 3.0482806869547495e-05, "epoch": 2.746132848043676, "percentage": 39.22, "elapsed_time": "10:06:36", "remaining_time": "15:40:02"}
303
+ {"current_steps": 1515, "total_steps": 3850, "loss": 0.2677, "lr": 3.0405484972619116e-05, "epoch": 2.7552320291173795, "percentage": 39.35, "elapsed_time": "10:08:31", "remaining_time": "15:37:52"}
304
+ {"current_steps": 1520, "total_steps": 3850, "loss": 0.2677, "lr": 3.0327949232779242e-05, "epoch": 2.7643312101910826, "percentage": 39.48, "elapsed_time": "10:10:35", "remaining_time": "15:35:58"}
305
+ {"current_steps": 1525, "total_steps": 3850, "loss": 0.2581, "lr": 3.0250201243463297e-05, "epoch": 2.773430391264786, "percentage": 39.61, "elapsed_time": "10:12:30", "remaining_time": "15:33:49"}
306
+ {"current_steps": 1530, "total_steps": 3850, "loss": 0.2579, "lr": 3.0172242602468637e-05, "epoch": 2.7825295723384897, "percentage": 39.74, "elapsed_time": "10:14:44", "remaining_time": "15:32:10"}
307
+ {"current_steps": 1535, "total_steps": 3850, "loss": 0.2651, "lr": 3.009407491192172e-05, "epoch": 2.791628753412193, "percentage": 39.87, "elapsed_time": "10:16:53", "remaining_time": "15:30:21"}
308
+ {"current_steps": 1540, "total_steps": 3850, "loss": 0.2521, "lr": 3.0015699778245177e-05, "epoch": 2.8007279344858964, "percentage": 40.0, "elapsed_time": "10:18:42", "remaining_time": "15:28:03"}
309
+ {"current_steps": 1545, "total_steps": 3850, "loss": 0.2713, "lr": 2.9937118812124796e-05, "epoch": 2.8098271155595995, "percentage": 40.13, "elapsed_time": "10:20:33", "remaining_time": "15:25:48"}
310
+ {"current_steps": 1550, "total_steps": 3850, "loss": 0.2442, "lr": 2.9858333628476423e-05, "epoch": 2.818926296633303, "percentage": 40.26, "elapsed_time": "10:22:35", "remaining_time": "15:23:51"}
311
+ {"current_steps": 1555, "total_steps": 3850, "loss": 0.27, "lr": 2.977934584641278e-05, "epoch": 2.8280254777070066, "percentage": 40.39, "elapsed_time": "10:24:25", "remaining_time": "15:21:34"}
312
+ {"current_steps": 1560, "total_steps": 3850, "loss": 0.2648, "lr": 2.9700157089210174e-05, "epoch": 2.8371246587807097, "percentage": 40.52, "elapsed_time": "10:26:23", "remaining_time": "15:19:30"}
313
+ {"current_steps": 1565, "total_steps": 3850, "loss": 0.2607, "lr": 2.9620768984275163e-05, "epoch": 2.846223839854413, "percentage": 40.65, "elapsed_time": "10:28:21", "remaining_time": "15:17:26"}
314
+ {"current_steps": 1570, "total_steps": 3850, "loss": 0.2631, "lr": 2.9541183163111076e-05, "epoch": 2.8553230209281164, "percentage": 40.78, "elapsed_time": "10:30:19", "remaining_time": "15:15:22"}
315
+ {"current_steps": 1575, "total_steps": 3850, "loss": 0.2534, "lr": 2.9461401261284536e-05, "epoch": 2.86442220200182, "percentage": 40.91, "elapsed_time": "10:32:32", "remaining_time": "15:13:39"}
316
+ {"current_steps": 1580, "total_steps": 3850, "loss": 0.2388, "lr": 2.9381424918391775e-05, "epoch": 2.873521383075523, "percentage": 41.04, "elapsed_time": "10:34:43", "remaining_time": "15:11:55"}
317
+ {"current_steps": 1585, "total_steps": 3850, "loss": 0.2704, "lr": 2.9301255778025014e-05, "epoch": 2.8826205641492266, "percentage": 41.17, "elapsed_time": "10:36:49", "remaining_time": "15:10:02"}
318
+ {"current_steps": 1590, "total_steps": 3850, "loss": 0.2617, "lr": 2.9220895487738627e-05, "epoch": 2.8917197452229297, "percentage": 41.3, "elapsed_time": "10:38:38", "remaining_time": "15:07:45"}
319
+ {"current_steps": 1595, "total_steps": 3850, "loss": 0.2699, "lr": 2.9140345699015328e-05, "epoch": 2.9008189262966333, "percentage": 41.43, "elapsed_time": "10:40:37", "remaining_time": "15:05:42"}
320
+ {"current_steps": 1600, "total_steps": 3850, "loss": 0.286, "lr": 2.905960806723219e-05, "epoch": 2.909918107370337, "percentage": 41.56, "elapsed_time": "10:42:28", "remaining_time": "15:03:29"}