penfever commited on
Commit
34c4c7f
·
verified ·
1 Parent(s): e1739ae

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:ad4ea33eeeba571528837842f89bf91a16a1597f414f34be8156d15606b7814a
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57d25aae8a58725f17c9c616a6387dbcebbe45e4a54cc2f97d6d07098cb6356
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6928da316d1adf208d8587d8a37d90ce79de3e06b20d338908d6ede080f33ffd
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd9e371fee33a1bc1be0823986cd049ed81083767fbabaa6bdb5f97018f5af5
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:e9e429810c471b2da039a72090ab2ffd8f8f4b269c3c1be2054304d53986048f
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e54625be17b73b5ae9abd74af2b033e629f18bced0421411ba66b62b3552930f
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82128247196921d19e0abba920b721c16a661f33c9863814c3eb022e358b8896
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145ed0475c0364754f0670a061b1b1daf88c3cb5966292562b61156781ca91a0
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -279,3 +279,46 @@
279
  {"current_steps": 1395, "total_steps": 9128, "loss": 0.2485, "lr": 3.9662596282398824e-05, "epoch": 1.0698120444955888, "percentage": 15.28, "elapsed_time": "8:59:50", "remaining_time": "2 days, 1:52:30"}
280
  {"current_steps": 1400, "total_steps": 9128, "loss": 0.2602, "lr": 3.965556550150541e-05, "epoch": 1.0736478711162256, "percentage": 15.34, "elapsed_time": "9:02:39", "remaining_time": "2 days, 1:55:25"}
281
  {"current_steps": 1405, "total_steps": 9128, "loss": 0.2187, "lr": 3.964846285683658e-05, "epoch": 1.0774836977368623, "percentage": 15.39, "elapsed_time": "9:06:29", "remaining_time": "2 days, 2:03:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  {"current_steps": 1395, "total_steps": 9128, "loss": 0.2485, "lr": 3.9662596282398824e-05, "epoch": 1.0698120444955888, "percentage": 15.28, "elapsed_time": "8:59:50", "remaining_time": "2 days, 1:52:30"}
280
  {"current_steps": 1400, "total_steps": 9128, "loss": 0.2602, "lr": 3.965556550150541e-05, "epoch": 1.0736478711162256, "percentage": 15.34, "elapsed_time": "9:02:39", "remaining_time": "2 days, 1:55:25"}
281
  {"current_steps": 1405, "total_steps": 9128, "loss": 0.2187, "lr": 3.964846285683658e-05, "epoch": 1.0774836977368623, "percentage": 15.39, "elapsed_time": "9:06:29", "remaining_time": "2 days, 2:03:55"}
282
+ {"current_steps": 1410, "total_steps": 9128, "loss": 0.2228, "lr": 3.964128837436071e-05, "epoch": 1.0813195243574991, "percentage": 15.45, "elapsed_time": "9:09:21", "remaining_time": "2 days, 2:07:01"}
283
+ {"current_steps": 1415, "total_steps": 9128, "loss": 0.2294, "lr": 3.963404208030879e-05, "epoch": 1.0851553509781358, "percentage": 15.5, "elapsed_time": "9:12:13", "remaining_time": "2 days, 2:10:04"}
284
+ {"current_steps": 1420, "total_steps": 9128, "loss": 0.2407, "lr": 3.962672400117441e-05, "epoch": 1.0889911775987726, "percentage": 15.56, "elapsed_time": "9:14:57", "remaining_time": "2 days, 2:12:23"}
285
+ {"current_steps": 1425, "total_steps": 9128, "loss": 0.2316, "lr": 3.961933416371358e-05, "epoch": 1.0928270042194093, "percentage": 15.61, "elapsed_time": "9:17:55", "remaining_time": "2 days, 2:15:57"}
286
+ {"current_steps": 1430, "total_steps": 9128, "loss": 0.2308, "lr": 3.961187259494469e-05, "epoch": 1.0966628308400461, "percentage": 15.67, "elapsed_time": "9:20:56", "remaining_time": "2 days, 2:19:42"}
287
+ {"current_steps": 1435, "total_steps": 9128, "loss": 0.2019, "lr": 3.960433932214839e-05, "epoch": 1.1004986574606828, "percentage": 15.72, "elapsed_time": "9:23:55", "remaining_time": "2 days, 2:23:13"}
288
+ {"current_steps": 1440, "total_steps": 9128, "loss": 0.2047, "lr": 3.9596734372867474e-05, "epoch": 1.1043344840813196, "percentage": 15.78, "elapsed_time": "9:26:53", "remaining_time": "2 days, 2:26:33"}
289
+ {"current_steps": 1445, "total_steps": 9128, "loss": 0.214, "lr": 3.958905777490682e-05, "epoch": 1.1081703107019563, "percentage": 15.83, "elapsed_time": "9:29:50", "remaining_time": "2 days, 2:29:50"}
290
+ {"current_steps": 1450, "total_steps": 9128, "loss": 0.2369, "lr": 3.9581309556333243e-05, "epoch": 1.112006137322593, "percentage": 15.89, "elapsed_time": "9:32:03", "remaining_time": "2 days, 2:29:10"}
291
+ {"current_steps": 1455, "total_steps": 9128, "loss": 0.2408, "lr": 3.957348974547543e-05, "epoch": 1.1158419639432298, "percentage": 15.94, "elapsed_time": "9:34:50", "remaining_time": "2 days, 2:31:27"}
292
+ {"current_steps": 1460, "total_steps": 9128, "loss": 0.2451, "lr": 3.956559837092381e-05, "epoch": 1.1196777905638666, "percentage": 15.99, "elapsed_time": "9:37:42", "remaining_time": "2 days, 2:34:06"}
293
+ {"current_steps": 1465, "total_steps": 9128, "loss": 0.2433, "lr": 3.955763546153047e-05, "epoch": 1.1235136171845033, "percentage": 16.05, "elapsed_time": "9:40:34", "remaining_time": "2 days, 2:36:47"}
294
+ {"current_steps": 1470, "total_steps": 9128, "loss": 0.2365, "lr": 3.9549601046409024e-05, "epoch": 1.12734944380514, "percentage": 16.1, "elapsed_time": "9:43:25", "remaining_time": "2 days, 2:39:23"}
295
+ {"current_steps": 1475, "total_steps": 9128, "loss": 0.2257, "lr": 3.9541495154934544e-05, "epoch": 1.1311852704257768, "percentage": 16.16, "elapsed_time": "9:46:26", "remaining_time": "2 days, 2:42:44"}
296
+ {"current_steps": 1480, "total_steps": 9128, "loss": 0.2349, "lr": 3.953331781674341e-05, "epoch": 1.1350210970464134, "percentage": 16.21, "elapsed_time": "9:49:25", "remaining_time": "2 days, 2:45:52"}
297
+ {"current_steps": 1485, "total_steps": 9128, "loss": 0.2282, "lr": 3.952506906173323e-05, "epoch": 1.1388569236670503, "percentage": 16.27, "elapsed_time": "9:52:22", "remaining_time": "2 days, 2:48:49"}
298
+ {"current_steps": 1490, "total_steps": 9128, "loss": 0.2392, "lr": 3.951674892006272e-05, "epoch": 1.142692750287687, "percentage": 16.32, "elapsed_time": "9:55:23", "remaining_time": "2 days, 2:52:06"}
299
+ {"current_steps": 1495, "total_steps": 9128, "loss": 0.2291, "lr": 3.9508357422151604e-05, "epoch": 1.1465285769083238, "percentage": 16.38, "elapsed_time": "9:58:23", "remaining_time": "2 days, 2:55:12"}
300
+ {"current_steps": 1500, "total_steps": 9128, "loss": 0.2331, "lr": 3.949989459868049e-05, "epoch": 1.1503644035289604, "percentage": 16.43, "elapsed_time": "10:01:19", "remaining_time": "2 days, 2:57:56"}
301
+ {"current_steps": 1505, "total_steps": 9128, "loss": 0.2342, "lr": 3.949136048059077e-05, "epoch": 1.1542002301495973, "percentage": 16.49, "elapsed_time": "10:04:03", "remaining_time": "2 days, 2:59:37"}
302
+ {"current_steps": 1510, "total_steps": 9128, "loss": 0.2258, "lr": 3.9482755099084496e-05, "epoch": 1.158036056770234, "percentage": 16.54, "elapsed_time": "10:06:45", "remaining_time": "2 days, 3:01:06"}
303
+ {"current_steps": 1515, "total_steps": 9128, "loss": 0.227, "lr": 3.947407848562425e-05, "epoch": 1.1618718833908708, "percentage": 16.6, "elapsed_time": "10:08:55", "remaining_time": "2 days, 2:59:54"}
304
+ {"current_steps": 1520, "total_steps": 9128, "loss": 0.2268, "lr": 3.946533067193309e-05, "epoch": 1.1657077100115074, "percentage": 16.65, "elapsed_time": "10:11:48", "remaining_time": "2 days, 3:02:17"}
305
+ {"current_steps": 1525, "total_steps": 9128, "loss": 0.2258, "lr": 3.945651168999435e-05, "epoch": 1.1695435366321443, "percentage": 16.71, "elapsed_time": "10:14:36", "remaining_time": "2 days, 3:04:08"}
306
+ {"current_steps": 1530, "total_steps": 9128, "loss": 0.2261, "lr": 3.94476215720516e-05, "epoch": 1.173379363252781, "percentage": 16.76, "elapsed_time": "10:17:34", "remaining_time": "2 days, 3:06:51"}
307
+ {"current_steps": 1535, "total_steps": 9128, "loss": 0.2249, "lr": 3.9438660350608475e-05, "epoch": 1.1772151898734178, "percentage": 16.82, "elapsed_time": "10:20:29", "remaining_time": "2 days, 3:09:19"}
308
+ {"current_steps": 1540, "total_steps": 9128, "loss": 0.229, "lr": 3.9429628058428586e-05, "epoch": 1.1810510164940544, "percentage": 16.87, "elapsed_time": "10:23:31", "remaining_time": "2 days, 3:12:16"}
309
+ {"current_steps": 1545, "total_steps": 9128, "loss": 0.2301, "lr": 3.942052472853538e-05, "epoch": 1.1848868431146913, "percentage": 16.93, "elapsed_time": "10:26:22", "remaining_time": "2 days, 3:14:16"}
310
+ {"current_steps": 1550, "total_steps": 9128, "loss": 0.204, "lr": 3.941135039421204e-05, "epoch": 1.188722669735328, "percentage": 16.98, "elapsed_time": "10:28:35", "remaining_time": "2 days, 3:13:14"}
311
+ {"current_steps": 1555, "total_steps": 9128, "loss": 0.225, "lr": 3.940210508900134e-05, "epoch": 1.1925584963559648, "percentage": 17.04, "elapsed_time": "10:31:10", "remaining_time": "2 days, 3:13:50"}
312
+ {"current_steps": 1560, "total_steps": 9128, "loss": 0.222, "lr": 3.939278884670553e-05, "epoch": 1.1963943229766014, "percentage": 17.09, "elapsed_time": "10:34:01", "remaining_time": "2 days, 3:15:51"}
313
+ {"current_steps": 1565, "total_steps": 9128, "loss": 0.228, "lr": 3.938340170138625e-05, "epoch": 1.2002301495972383, "percentage": 17.15, "elapsed_time": "10:36:54", "remaining_time": "2 days, 3:17:53"}
314
+ {"current_steps": 1570, "total_steps": 9128, "loss": 0.2196, "lr": 3.937394368736433e-05, "epoch": 1.204065976217875, "percentage": 17.2, "elapsed_time": "10:39:36", "remaining_time": "2 days, 3:19:05"}
315
+ {"current_steps": 1575, "total_steps": 9128, "loss": 0.2142, "lr": 3.936441483921974e-05, "epoch": 1.2079018028385118, "percentage": 17.25, "elapsed_time": "10:42:23", "remaining_time": "2 days, 3:20:37"}
316
+ {"current_steps": 1580, "total_steps": 9128, "loss": 0.2247, "lr": 3.935481519179141e-05, "epoch": 1.2117376294591484, "percentage": 17.31, "elapsed_time": "10:45:25", "remaining_time": "2 days, 3:23:20"}
317
+ {"current_steps": 1585, "total_steps": 9128, "loss": 0.2482, "lr": 3.934514478017713e-05, "epoch": 1.2155734560797853, "percentage": 17.36, "elapsed_time": "10:47:18", "remaining_time": "2 days, 3:20:34"}
318
+ {"current_steps": 1590, "total_steps": 9128, "loss": 0.2448, "lr": 3.933540363973341e-05, "epoch": 1.219409282700422, "percentage": 17.42, "elapsed_time": "10:48:32", "remaining_time": "2 days, 3:14:39"}
319
+ {"current_steps": 1595, "total_steps": 9128, "loss": 0.231, "lr": 3.9325591806075364e-05, "epoch": 1.2232451093210588, "percentage": 17.47, "elapsed_time": "10:49:47", "remaining_time": "2 days, 3:08:53"}
320
+ {"current_steps": 1600, "total_steps": 9128, "loss": 0.2322, "lr": 3.9315709315076576e-05, "epoch": 1.2270809359416954, "percentage": 17.53, "elapsed_time": "10:51:01", "remaining_time": "2 days, 3:03:04"}
321
+ {"current_steps": 1605, "total_steps": 9128, "loss": 0.2292, "lr": 3.930575620286894e-05, "epoch": 1.230916762562332, "percentage": 17.58, "elapsed_time": "10:53:44", "remaining_time": "2 days, 3:04:15"}
322
+ {"current_steps": 1610, "total_steps": 9128, "loss": 0.2275, "lr": 3.929573250584258e-05, "epoch": 1.234752589182969, "percentage": 17.64, "elapsed_time": "10:54:58", "remaining_time": "2 days, 2:58:28"}
323
+ {"current_steps": 1615, "total_steps": 9128, "loss": 0.2357, "lr": 3.928563826064568e-05, "epoch": 1.2385884158036058, "percentage": 17.69, "elapsed_time": "10:56:13", "remaining_time": "2 days, 2:52:45"}
324
+ {"current_steps": 1620, "total_steps": 9128, "loss": 0.218, "lr": 3.927547350418433e-05, "epoch": 1.2424242424242424, "percentage": 17.75, "elapsed_time": "10:57:29", "remaining_time": "2 days, 2:47:09"}