penfever commited on
Commit
aa7fb24
·
verified ·
1 Parent(s): de3e885

Training in progress, step 7000

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:863fe3e3806ace2e3acf927592677fab360b3fd8b48ff71f8204001c88af0fdd
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5086132c9f502bd4723f8ba160a1a614efb64c5c5125aaf8d4a0a3b79ce72aaf
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07612fab458191fccc1a2960aa38044042d3106115511aeb3fe8e2d3efc018b7
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d7c209ba3bfb8ab21140181564f665c8dee0bbfd6da7a7e84191ff2f8f3956c
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:b59b9259fef69fbfc24a830e98675de31c42fde5f1460f7e1d82ebd4250d915e
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40632a91cf420ddacbd0f4583c295d85fb35cbd260f57c0b567be3105c53b946
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:e48615c8bb9426b01c30f6f680bf2089005289004c1ab9b64032769a4ee42082
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b202f33bab19e42272fb957bcdfc9404e14b28471eb5eb6a3f460c2b60c3ee8
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -2062,3 +2062,43 @@
2062
  {"current_steps": 6790, "total_steps": 8169, "loss": 0.1411, "lr": 3.3777332125605876e-06, "epoch": 5.818337617823479, "percentage": 83.12, "elapsed_time": "1 day, 17:47:28", "remaining_time": "8:29:15"}
2063
  {"current_steps": 6795, "total_steps": 8169, "loss": 0.1388, "lr": 3.354008257785004e-06, "epoch": 5.822622107969152, "percentage": 83.18, "elapsed_time": "1 day, 17:50:18", "remaining_time": "8:27:36"}
2064
  {"current_steps": 6800, "total_steps": 8169, "loss": 0.1341, "lr": 3.3303592898288996e-06, "epoch": 5.8269065981148245, "percentage": 83.24, "elapsed_time": "1 day, 17:53:11", "remaining_time": "8:25:57"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2062
  {"current_steps": 6790, "total_steps": 8169, "loss": 0.1411, "lr": 3.3777332125605876e-06, "epoch": 5.818337617823479, "percentage": 83.12, "elapsed_time": "1 day, 17:47:28", "remaining_time": "8:29:15"}
2063
  {"current_steps": 6795, "total_steps": 8169, "loss": 0.1388, "lr": 3.354008257785004e-06, "epoch": 5.822622107969152, "percentage": 83.18, "elapsed_time": "1 day, 17:50:18", "remaining_time": "8:27:36"}
2064
  {"current_steps": 6800, "total_steps": 8169, "loss": 0.1341, "lr": 3.3303592898288996e-06, "epoch": 5.8269065981148245, "percentage": 83.24, "elapsed_time": "1 day, 17:53:11", "remaining_time": "8:25:57"}
2065
+ {"current_steps": 6805, "total_steps": 8169, "loss": 0.1378, "lr": 3.3067864166467724e-06, "epoch": 5.831191088260497, "percentage": 83.3, "elapsed_time": "1 day, 17:57:20", "remaining_time": "8:24:34"}
2066
+ {"current_steps": 6810, "total_steps": 8169, "loss": 0.1342, "lr": 3.2832897458457746e-06, "epoch": 5.83547557840617, "percentage": 83.36, "elapsed_time": "1 day, 18:00:12", "remaining_time": "8:22:55"}
2067
+ {"current_steps": 6815, "total_steps": 8169, "loss": 0.1378, "lr": 3.2598693846852037e-06, "epoch": 5.8397600685518425, "percentage": 83.43, "elapsed_time": "1 day, 18:03:03", "remaining_time": "8:21:16"}
2068
+ {"current_steps": 6820, "total_steps": 8169, "loss": 0.1404, "lr": 3.2365254400760036e-06, "epoch": 5.844044558697515, "percentage": 83.49, "elapsed_time": "1 day, 18:05:44", "remaining_time": "8:19:35"}
2069
+ {"current_steps": 6825, "total_steps": 8169, "loss": 0.131, "lr": 3.2132580185802876e-06, "epoch": 5.848329048843188, "percentage": 83.55, "elapsed_time": "1 day, 18:08:39", "remaining_time": "8:17:56"}
2070
+ {"current_steps": 6830, "total_steps": 8169, "loss": 0.1443, "lr": 3.190067226410858e-06, "epoch": 5.8526135389888605, "percentage": 83.61, "elapsed_time": "1 day, 18:11:36", "remaining_time": "8:16:18"}
2071
+ {"current_steps": 6835, "total_steps": 8169, "loss": 0.1319, "lr": 3.1669531694307e-06, "epoch": 5.856898029134533, "percentage": 83.67, "elapsed_time": "1 day, 18:14:20", "remaining_time": "8:14:37"}
2072
+ {"current_steps": 6840, "total_steps": 8169, "loss": 0.1379, "lr": 3.1439159531525344e-06, "epoch": 5.861182519280206, "percentage": 83.73, "elapsed_time": "1 day, 18:17:10", "remaining_time": "8:12:58"}
2073
+ {"current_steps": 6845, "total_steps": 8169, "loss": 0.1414, "lr": 3.1209556827382915e-06, "epoch": 5.8654670094258785, "percentage": 83.79, "elapsed_time": "1 day, 18:20:04", "remaining_time": "8:11:18"}
2074
+ {"current_steps": 6850, "total_steps": 8169, "loss": 0.1338, "lr": 3.098072462998671e-06, "epoch": 5.869751499571551, "percentage": 83.85, "elapsed_time": "1 day, 18:22:58", "remaining_time": "8:09:39"}
2075
+ {"current_steps": 6855, "total_steps": 8169, "loss": 0.1355, "lr": 3.07526639839264e-06, "epoch": 5.874035989717224, "percentage": 83.91, "elapsed_time": "1 day, 18:25:43", "remaining_time": "8:07:58"}
2076
+ {"current_steps": 6860, "total_steps": 8169, "loss": 0.1388, "lr": 3.0525375930269584e-06, "epoch": 5.8783204798628965, "percentage": 83.98, "elapsed_time": "1 day, 18:28:31", "remaining_time": "8:06:18"}
2077
+ {"current_steps": 6865, "total_steps": 8169, "loss": 0.138, "lr": 3.0298861506557076e-06, "epoch": 5.882604970008569, "percentage": 84.04, "elapsed_time": "1 day, 18:31:19", "remaining_time": "8:04:37"}
2078
+ {"current_steps": 6870, "total_steps": 8169, "loss": 0.148, "lr": 3.0073121746798196e-06, "epoch": 5.886889460154242, "percentage": 84.1, "elapsed_time": "1 day, 18:34:05", "remaining_time": "8:02:56"}
2079
+ {"current_steps": 6875, "total_steps": 8169, "loss": 0.123, "lr": 2.9848157681466093e-06, "epoch": 5.8911739502999145, "percentage": 84.16, "elapsed_time": "1 day, 18:36:58", "remaining_time": "8:01:16"}
2080
+ {"current_steps": 6880, "total_steps": 8169, "loss": 0.1421, "lr": 2.96239703374928e-06, "epoch": 5.895458440445587, "percentage": 84.22, "elapsed_time": "1 day, 18:39:46", "remaining_time": "7:59:35"}
2081
+ {"current_steps": 6885, "total_steps": 8169, "loss": 0.1323, "lr": 2.940056073826494e-06, "epoch": 5.89974293059126, "percentage": 84.28, "elapsed_time": "1 day, 18:42:38", "remaining_time": "7:57:54"}
2082
+ {"current_steps": 6890, "total_steps": 8169, "loss": 0.1284, "lr": 2.917792990361863e-06, "epoch": 5.9040274207369325, "percentage": 84.34, "elapsed_time": "1 day, 18:45:35", "remaining_time": "7:56:15"}
2083
+ {"current_steps": 6895, "total_steps": 8169, "loss": 0.126, "lr": 2.8956078849835133e-06, "epoch": 5.908311910882605, "percentage": 84.4, "elapsed_time": "1 day, 18:48:28", "remaining_time": "7:54:34"}
2084
+ {"current_steps": 6900, "total_steps": 8169, "loss": 0.1297, "lr": 2.873500858963607e-06, "epoch": 5.912596401028278, "percentage": 84.47, "elapsed_time": "1 day, 18:51:14", "remaining_time": "7:52:53"}
2085
+ {"current_steps": 6905, "total_steps": 8169, "loss": 0.1409, "lr": 2.85147201321788e-06, "epoch": 5.9168808911739506, "percentage": 84.53, "elapsed_time": "1 day, 18:53:57", "remaining_time": "7:51:10"}
2086
+ {"current_steps": 6910, "total_steps": 8169, "loss": 0.1465, "lr": 2.829521448305199e-06, "epoch": 5.921165381319623, "percentage": 84.59, "elapsed_time": "1 day, 18:56:45", "remaining_time": "7:49:29"}
2087
+ {"current_steps": 6915, "total_steps": 8169, "loss": 0.1578, "lr": 2.807649264427079e-06, "epoch": 5.925449871465296, "percentage": 84.65, "elapsed_time": "1 day, 18:59:33", "remaining_time": "7:47:47"}
2088
+ {"current_steps": 6920, "total_steps": 8169, "loss": 0.1398, "lr": 2.785855561427231e-06, "epoch": 5.929734361610969, "percentage": 84.71, "elapsed_time": "1 day, 19:02:22", "remaining_time": "7:46:05"}
2089
+ {"current_steps": 6925, "total_steps": 8169, "loss": 0.1401, "lr": 2.7641404387911253e-06, "epoch": 5.934018851756641, "percentage": 84.77, "elapsed_time": "1 day, 19:05:16", "remaining_time": "7:44:24"}
2090
+ {"current_steps": 6930, "total_steps": 8169, "loss": 0.1451, "lr": 2.7425039956455113e-06, "epoch": 5.938303341902314, "percentage": 84.83, "elapsed_time": "1 day, 19:08:01", "remaining_time": "7:42:42"}
2091
+ {"current_steps": 6935, "total_steps": 8169, "loss": 0.137, "lr": 2.720946330757972e-06, "epoch": 5.942587832047987, "percentage": 84.89, "elapsed_time": "1 day, 19:10:49", "remaining_time": "7:41:00"}
2092
+ {"current_steps": 6940, "total_steps": 8169, "loss": 0.1357, "lr": 2.699467542536498e-06, "epoch": 5.946872322193659, "percentage": 84.96, "elapsed_time": "1 day, 19:13:26", "remaining_time": "7:39:16"}
2093
+ {"current_steps": 6945, "total_steps": 8169, "loss": 0.1437, "lr": 2.678067729028999e-06, "epoch": 5.951156812339332, "percentage": 85.02, "elapsed_time": "1 day, 19:16:09", "remaining_time": "7:37:33"}
2094
+ {"current_steps": 6950, "total_steps": 8169, "loss": 0.15, "lr": 2.6567469879228824e-06, "epoch": 5.955441302485005, "percentage": 85.08, "elapsed_time": "1 day, 19:18:47", "remaining_time": "7:35:48"}
2095
+ {"current_steps": 6955, "total_steps": 8169, "loss": 0.1364, "lr": 2.635505416544595e-06, "epoch": 5.959725792630677, "percentage": 85.14, "elapsed_time": "1 day, 19:21:27", "remaining_time": "7:34:05"}
2096
+ {"current_steps": 6960, "total_steps": 8169, "loss": 0.1504, "lr": 2.6143431118591967e-06, "epoch": 5.96401028277635, "percentage": 85.2, "elapsed_time": "1 day, 19:24:06", "remaining_time": "7:32:21"}
2097
+ {"current_steps": 6965, "total_steps": 8169, "loss": 0.1461, "lr": 2.593260170469891e-06, "epoch": 5.968294772922023, "percentage": 85.26, "elapsed_time": "1 day, 19:26:46", "remaining_time": "7:30:37"}
2098
+ {"current_steps": 6970, "total_steps": 8169, "loss": 0.1394, "lr": 2.5722566886176047e-06, "epoch": 5.972579263067695, "percentage": 85.32, "elapsed_time": "1 day, 19:29:42", "remaining_time": "7:28:55"}
2099
+ {"current_steps": 6975, "total_steps": 8169, "loss": 0.1468, "lr": 2.5513327621805473e-06, "epoch": 5.976863753213368, "percentage": 85.38, "elapsed_time": "1 day, 19:32:17", "remaining_time": "7:27:10"}
2100
+ {"current_steps": 6980, "total_steps": 8169, "loss": 0.1368, "lr": 2.530488486673757e-06, "epoch": 5.981148243359041, "percentage": 85.44, "elapsed_time": "1 day, 19:34:53", "remaining_time": "7:25:25"}
2101
+ {"current_steps": 6985, "total_steps": 8169, "loss": 0.1423, "lr": 2.50972395724868e-06, "epoch": 5.985432733504713, "percentage": 85.51, "elapsed_time": "1 day, 19:37:42", "remaining_time": "7:23:42"}
2102
+ {"current_steps": 6990, "total_steps": 8169, "loss": 0.1447, "lr": 2.48903926869273e-06, "epoch": 5.989717223650386, "percentage": 85.57, "elapsed_time": "1 day, 19:40:32", "remaining_time": "7:22:00"}
2103
+ {"current_steps": 6995, "total_steps": 8169, "loss": 0.1581, "lr": 2.468434515428868e-06, "epoch": 5.994001713796059, "percentage": 85.63, "elapsed_time": "1 day, 19:43:01", "remaining_time": "7:20:14"}
2104
+ {"current_steps": 7000, "total_steps": 8169, "loss": 0.154, "lr": 2.4479097915151438e-06, "epoch": 5.998286203941731, "percentage": 85.69, "elapsed_time": "1 day, 19:45:52", "remaining_time": "7:18:31"}