penfever commited on
Commit
69d449b
·
verified ·
1 Parent(s): bc88ab8

Training in progress, step 8400

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9ff29f01d66754a7c0b40fe6cf643ebb562aa3805aadb35ae2f275d7e7cc7aa
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8cca581268f84db32402d3a5d5a696d25449755c38410afe48dcdb207a58efc
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:388fd5ef868aacc98ffff465190c2fb1025c09dc9996fce95fad4d868a8096e5
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e5248e1e7e430d5f32387fcb7a62dc9148c4e79d1f726e7793412325bfa9517
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8aa679502b30435f63541a099f77dc655666608ddfe02c7f3e2ce6b6480c9086
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd646f173467a5f94a2a9924aff2ffe467e6f2436365912dcc884dd2d8827c1
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:f2133b06dd91ea338aaf0b0fe9cee68a31dc47ee71ea41510cd6e4c85f494062
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b7fc6114fb01c41e7aa8e80291ea0992e5034e07e73b6c3ddedd357ac8514a
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1672,3 +1672,43 @@
1672
  {"current_steps": 8195, "total_steps": 9128, "loss": 0.1227, "lr": 1.2622814916533765e-06, "epoch": 6.285385500575374, "percentage": 89.78, "elapsed_time": "4:20:50", "remaining_time": "0:29:41"}
1673
  {"current_steps": 8200, "total_steps": 9128, "loss": 0.1211, "lr": 1.248944952462312e-06, "epoch": 6.289221327196011, "percentage": 89.83, "elapsed_time": "4:22:06", "remaining_time": "0:29:39"}
1674
  {"current_steps": 8205, "total_steps": 9128, "loss": 0.1247, "lr": 1.2356769700171035e-06, "epoch": 6.2930571538166475, "percentage": 89.89, "elapsed_time": "4:24:42", "remaining_time": "0:29:46"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1672
  {"current_steps": 8195, "total_steps": 9128, "loss": 0.1227, "lr": 1.2622814916533765e-06, "epoch": 6.285385500575374, "percentage": 89.78, "elapsed_time": "4:20:50", "remaining_time": "0:29:41"}
1673
  {"current_steps": 8200, "total_steps": 9128, "loss": 0.1211, "lr": 1.248944952462312e-06, "epoch": 6.289221327196011, "percentage": 89.83, "elapsed_time": "4:22:06", "remaining_time": "0:29:39"}
1674
  {"current_steps": 8205, "total_steps": 9128, "loss": 0.1247, "lr": 1.2356769700171035e-06, "epoch": 6.2930571538166475, "percentage": 89.89, "elapsed_time": "4:24:42", "remaining_time": "0:29:46"}
1675
+ {"current_steps": 8210, "total_steps": 9128, "loss": 0.1318, "lr": 1.2224775928275378e-06, "epoch": 6.296892980437284, "percentage": 89.94, "elapsed_time": "4:26:04", "remaining_time": "0:29:45"}
1676
+ {"current_steps": 8215, "total_steps": 9128, "loss": 0.1188, "lr": 1.2093468691525634e-06, "epoch": 6.300728807057921, "percentage": 90.0, "elapsed_time": "4:27:21", "remaining_time": "0:29:42"}
1677
+ {"current_steps": 8220, "total_steps": 9128, "loss": 0.1153, "lr": 1.196284847000142e-06, "epoch": 6.304564633678558, "percentage": 90.05, "elapsed_time": "4:28:36", "remaining_time": "0:29:40"}
1678
+ {"current_steps": 8225, "total_steps": 9128, "loss": 0.1205, "lr": 1.1832915741270235e-06, "epoch": 6.308400460299194, "percentage": 90.11, "elapsed_time": "4:29:52", "remaining_time": "0:29:37"}
1679
+ {"current_steps": 8230, "total_steps": 9128, "loss": 0.1202, "lr": 1.1703670980386272e-06, "epoch": 6.312236286919831, "percentage": 90.16, "elapsed_time": "4:31:08", "remaining_time": "0:29:35"}
1680
+ {"current_steps": 8235, "total_steps": 9128, "loss": 0.1271, "lr": 1.1575114659888298e-06, "epoch": 6.316072113540468, "percentage": 90.22, "elapsed_time": "4:32:25", "remaining_time": "0:29:32"}
1681
+ {"current_steps": 8240, "total_steps": 9128, "loss": 0.1236, "lr": 1.1447247249797888e-06, "epoch": 6.319907940161105, "percentage": 90.27, "elapsed_time": "4:33:44", "remaining_time": "0:29:30"}
1682
+ {"current_steps": 8245, "total_steps": 9128, "loss": 0.1194, "lr": 1.1320069217618125e-06, "epoch": 6.3237437667817415, "percentage": 90.33, "elapsed_time": "4:35:01", "remaining_time": "0:29:27"}
1683
+ {"current_steps": 8250, "total_steps": 9128, "loss": 0.1242, "lr": 1.1193581028331457e-06, "epoch": 6.327579593402378, "percentage": 90.38, "elapsed_time": "4:36:17", "remaining_time": "0:29:24"}
1684
+ {"current_steps": 8255, "total_steps": 9128, "loss": 0.1235, "lr": 1.1067783144398115e-06, "epoch": 6.331415420023015, "percentage": 90.44, "elapsed_time": "4:37:33", "remaining_time": "0:29:21"}
1685
+ {"current_steps": 8260, "total_steps": 9128, "loss": 0.113, "lr": 1.0942676025754628e-06, "epoch": 6.335251246643652, "percentage": 90.49, "elapsed_time": "4:38:47", "remaining_time": "0:29:17"}
1686
+ {"current_steps": 8265, "total_steps": 9128, "loss": 0.1174, "lr": 1.0818260129811863e-06, "epoch": 6.339087073264288, "percentage": 90.55, "elapsed_time": "4:40:01", "remaining_time": "0:29:14"}
1687
+ {"current_steps": 8270, "total_steps": 9128, "loss": 0.1148, "lr": 1.0694535911453508e-06, "epoch": 6.342922899884925, "percentage": 90.6, "elapsed_time": "4:41:16", "remaining_time": "0:29:10"}
1688
+ {"current_steps": 8275, "total_steps": 9128, "loss": 0.1159, "lr": 1.0571503823034356e-06, "epoch": 6.346758726505562, "percentage": 90.66, "elapsed_time": "4:42:30", "remaining_time": "0:29:07"}
1689
+ {"current_steps": 8280, "total_steps": 9128, "loss": 0.1161, "lr": 1.0449164314378702e-06, "epoch": 6.350594553126198, "percentage": 90.71, "elapsed_time": "4:43:47", "remaining_time": "0:29:03"}
1690
+ {"current_steps": 8285, "total_steps": 9128, "loss": 0.1172, "lr": 1.0327517832778588e-06, "epoch": 6.3544303797468356, "percentage": 90.76, "elapsed_time": "4:45:02", "remaining_time": "0:29:00"}
1691
+ {"current_steps": 8290, "total_steps": 9128, "loss": 0.1216, "lr": 1.0206564822992315e-06, "epoch": 6.358266206367472, "percentage": 90.82, "elapsed_time": "4:46:17", "remaining_time": "0:28:56"}
1692
+ {"current_steps": 8295, "total_steps": 9128, "loss": 0.1158, "lr": 1.008630572724274e-06, "epoch": 6.362102032988109, "percentage": 90.87, "elapsed_time": "4:47:33", "remaining_time": "0:28:52"}
1693
+ {"current_steps": 8300, "total_steps": 9128, "loss": 0.1238, "lr": 9.966740985215618e-07, "epoch": 6.365937859608746, "percentage": 90.93, "elapsed_time": "4:48:49", "remaining_time": "0:28:48"}
1694
+ {"current_steps": 8305, "total_steps": 9128, "loss": 0.1166, "lr": 9.847871034058065e-07, "epoch": 6.369773686229382, "percentage": 90.98, "elapsed_time": "4:50:08", "remaining_time": "0:28:45"}
1695
+ {"current_steps": 8310, "total_steps": 9128, "loss": 0.1241, "lr": 9.729696308376946e-07, "epoch": 6.373609512850019, "percentage": 91.04, "elapsed_time": "4:51:26", "remaining_time": "0:28:41"}
1696
+ {"current_steps": 8315, "total_steps": 9128, "loss": 0.1222, "lr": 9.612217240237244e-07, "epoch": 6.377445339470656, "percentage": 91.09, "elapsed_time": "4:52:46", "remaining_time": "0:28:37"}
1697
+ {"current_steps": 8320, "total_steps": 9128, "loss": 0.1221, "lr": 9.495434259160552e-07, "epoch": 6.381281166091293, "percentage": 91.15, "elapsed_time": "4:54:01", "remaining_time": "0:28:33"}
1698
+ {"current_steps": 8325, "total_steps": 9128, "loss": 0.1129, "lr": 9.379347792123439e-07, "epoch": 6.38511699271193, "percentage": 91.2, "elapsed_time": "4:55:18", "remaining_time": "0:28:29"}
1699
+ {"current_steps": 8330, "total_steps": 9128, "loss": 0.1244, "lr": 9.263958263555884e-07, "epoch": 6.388952819332566, "percentage": 91.26, "elapsed_time": "4:56:35", "remaining_time": "0:28:24"}
1700
+ {"current_steps": 8335, "total_steps": 9128, "loss": 0.1171, "lr": 9.149266095339815e-07, "epoch": 6.392788645953203, "percentage": 91.31, "elapsed_time": "4:57:50", "remaining_time": "0:28:20"}
1701
+ {"current_steps": 8340, "total_steps": 9128, "loss": 0.1105, "lr": 9.035271706807447e-07, "epoch": 6.39662447257384, "percentage": 91.37, "elapsed_time": "4:59:03", "remaining_time": "0:28:15"}
1702
+ {"current_steps": 8345, "total_steps": 9128, "loss": 0.1117, "lr": 8.921975514739834e-07, "epoch": 6.400460299194476, "percentage": 91.42, "elapsed_time": "5:00:17", "remaining_time": "0:28:10"}
1703
+ {"current_steps": 8350, "total_steps": 9128, "loss": 0.117, "lr": 8.809377933365292e-07, "epoch": 6.404296125815113, "percentage": 91.48, "elapsed_time": "5:01:36", "remaining_time": "0:28:06"}
1704
+ {"current_steps": 8355, "total_steps": 9128, "loss": 0.1222, "lr": 8.69747937435792e-07, "epoch": 6.40813195243575, "percentage": 91.53, "elapsed_time": "5:02:51", "remaining_time": "0:28:01"}
1705
+ {"current_steps": 8360, "total_steps": 9128, "loss": 0.1163, "lr": 8.586280246836098e-07, "epoch": 6.411967779056386, "percentage": 91.59, "elapsed_time": "5:04:07", "remaining_time": "0:27:56"}
1706
+ {"current_steps": 8365, "total_steps": 9128, "loss": 0.1155, "lr": 8.475780957361013e-07, "epoch": 6.415803605677024, "percentage": 91.64, "elapsed_time": "5:05:24", "remaining_time": "0:27:51"}
1707
+ {"current_steps": 8370, "total_steps": 9128, "loss": 0.1217, "lr": 8.365981909935028e-07, "epoch": 6.41963943229766, "percentage": 91.7, "elapsed_time": "5:06:43", "remaining_time": "0:27:46"}
1708
+ {"current_steps": 8375, "total_steps": 9128, "loss": 0.113, "lr": 8.256883506000357e-07, "epoch": 6.423475258918297, "percentage": 91.75, "elapsed_time": "5:07:59", "remaining_time": "0:27:41"}
1709
+ {"current_steps": 8380, "total_steps": 9128, "loss": 0.1159, "lr": 8.148486144437661e-07, "epoch": 6.427311085538934, "percentage": 91.81, "elapsed_time": "5:09:14", "remaining_time": "0:27:36"}
1710
+ {"current_steps": 8385, "total_steps": 9128, "loss": 0.1159, "lr": 8.04079022156432e-07, "epoch": 6.43114691215957, "percentage": 91.86, "elapsed_time": "5:10:29", "remaining_time": "0:27:30"}
1711
+ {"current_steps": 8390, "total_steps": 9128, "loss": 0.1086, "lr": 7.933796131133253e-07, "epoch": 6.434982738780207, "percentage": 91.91, "elapsed_time": "5:11:44", "remaining_time": "0:27:25"}
1712
+ {"current_steps": 8395, "total_steps": 9128, "loss": 0.1195, "lr": 7.827504264331298e-07, "epoch": 6.438818565400844, "percentage": 91.97, "elapsed_time": "5:13:01", "remaining_time": "0:27:19"}
1713
+ {"current_steps": 8400, "total_steps": 9128, "loss": 0.1209, "lr": 7.721915009777902e-07, "epoch": 6.44265439202148, "percentage": 92.02, "elapsed_time": "5:14:18", "remaining_time": "0:27:14"}
1714
+ {"current_steps": 8405, "total_steps": 9128, "loss": 0.1102, "lr": 7.617028753523725e-07, "epoch": 6.446490218642118, "percentage": 92.08, "elapsed_time": "5:17:03", "remaining_time": "0:27:16"}