ryanmarten commited on
Commit
70f0ccc
·
verified ·
1 Parent(s): e656d8b

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c24a5f6c5267a4bab26707b8c55323a48fb08c24487dad967b3eafc5a2df63a7
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212e3c4b92abca77bbc1f748cb1759951fc305280e1a47ba2fd5330d154a4e7b
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb1fb839bfcc9df8dd90e8b26089eb70743e557b945847593f7981dd0b881c70
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7a33598dd0f35b34c840983368eab97318abc550f06c37bd930ce5db206faa
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b5dd1865ed4a5c2ae642f26755f894c8d674c5bb13da81eabaf22a5d1f29ac2
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668fa255d0e61491f5153196cfcb2c2ae0dbaa268a72b1c0a4a770f70f95c853
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aabe33e4ec88d60c8aa47bf070dc28e1f066151636456f662084f0a334b0bab7
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a0e065e440ace5b107ef3e6813bb3dfead91cb4f1359b7f5c977eb41e5c1392
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -17,3 +17,40 @@
17
  {"current_steps": 17, "total_steps": 117, "loss": 0.8024, "lr": 9.944154131125643e-06, "epoch": 1.759493670886076, "percentage": 14.53, "elapsed_time": "0:08:00", "remaining_time": "0:47:03"}
18
  {"current_steps": 18, "total_steps": 117, "loss": 0.8504, "lr": 9.91964794299315e-06, "epoch": 1.8607594936708862, "percentage": 15.38, "elapsed_time": "0:08:20", "remaining_time": "0:45:55"}
19
  {"current_steps": 19, "total_steps": 117, "loss": 0.7831, "lr": 9.890738003669029e-06, "epoch": 1.9620253164556962, "percentage": 16.24, "elapsed_time": "0:08:44", "remaining_time": "0:45:07"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  {"current_steps": 17, "total_steps": 117, "loss": 0.8024, "lr": 9.944154131125643e-06, "epoch": 1.759493670886076, "percentage": 14.53, "elapsed_time": "0:08:00", "remaining_time": "0:47:03"}
18
  {"current_steps": 18, "total_steps": 117, "loss": 0.8504, "lr": 9.91964794299315e-06, "epoch": 1.8607594936708862, "percentage": 15.38, "elapsed_time": "0:08:20", "remaining_time": "0:45:55"}
19
  {"current_steps": 19, "total_steps": 117, "loss": 0.7831, "lr": 9.890738003669029e-06, "epoch": 1.9620253164556962, "percentage": 16.24, "elapsed_time": "0:08:44", "remaining_time": "0:45:07"}
20
+ {"current_steps": 20, "total_steps": 117, "loss": 0.7317, "lr": 9.857450191464337e-06, "epoch": 2.1012658227848102, "percentage": 17.09, "elapsed_time": "0:09:46", "remaining_time": "0:47:26"}
21
+ {"current_steps": 21, "total_steps": 117, "loss": 0.7074, "lr": 9.819814303479268e-06, "epoch": 2.2025316455696204, "percentage": 17.95, "elapsed_time": "0:10:15", "remaining_time": "0:46:52"}
22
+ {"current_steps": 22, "total_steps": 117, "loss": 0.6884, "lr": 9.777864028930705e-06, "epoch": 2.3037974683544302, "percentage": 18.8, "elapsed_time": "0:10:44", "remaining_time": "0:46:24"}
23
+ {"current_steps": 23, "total_steps": 117, "loss": 0.6394, "lr": 9.731636918995821e-06, "epoch": 2.4050632911392404, "percentage": 19.66, "elapsed_time": "0:11:10", "remaining_time": "0:45:41"}
24
+ {"current_steps": 24, "total_steps": 117, "loss": 0.6071, "lr": 9.681174353198687e-06, "epoch": 2.5063291139240507, "percentage": 20.51, "elapsed_time": "0:11:31", "remaining_time": "0:44:40"}
25
+ {"current_steps": 25, "total_steps": 117, "loss": 0.6714, "lr": 9.626521502369984e-06, "epoch": 2.607594936708861, "percentage": 21.37, "elapsed_time": "0:11:49", "remaining_time": "0:43:31"}
26
+ {"current_steps": 26, "total_steps": 117, "loss": 0.5986, "lr": 9.567727288213005e-06, "epoch": 2.708860759493671, "percentage": 22.22, "elapsed_time": "0:12:08", "remaining_time": "0:42:30"}
27
+ {"current_steps": 27, "total_steps": 117, "loss": 0.6327, "lr": 9.504844339512096e-06, "epoch": 2.810126582278481, "percentage": 23.08, "elapsed_time": "0:12:28", "remaining_time": "0:41:33"}
28
+ {"current_steps": 28, "total_steps": 117, "loss": 0.6285, "lr": 9.437928945022772e-06, "epoch": 2.911392405063291, "percentage": 23.93, "elapsed_time": "0:12:47", "remaining_time": "0:40:38"}
29
+ {"current_steps": 29, "total_steps": 117, "loss": 0.6241, "lr": 9.36704100308565e-06, "epoch": 3.050632911392405, "percentage": 24.79, "elapsed_time": "0:14:08", "remaining_time": "0:42:53"}
30
+ {"current_steps": 30, "total_steps": 117, "loss": 0.5083, "lr": 9.292243968009332e-06, "epoch": 3.151898734177215, "percentage": 25.64, "elapsed_time": "0:14:30", "remaining_time": "0:42:04"}
31
+ {"current_steps": 31, "total_steps": 117, "loss": 0.4989, "lr": 9.213604793270196e-06, "epoch": 3.2531645569620253, "percentage": 26.5, "elapsed_time": "0:14:51", "remaining_time": "0:41:14"}
32
+ {"current_steps": 32, "total_steps": 117, "loss": 0.5224, "lr": 9.131193871579975e-06, "epoch": 3.3544303797468356, "percentage": 27.35, "elapsed_time": "0:15:18", "remaining_time": "0:40:38"}
33
+ {"current_steps": 33, "total_steps": 117, "loss": 0.5043, "lr": 9.045084971874738e-06, "epoch": 3.4556962025316453, "percentage": 28.21, "elapsed_time": "0:15:40", "remaining_time": "0:39:54"}
34
+ {"current_steps": 34, "total_steps": 117, "loss": 0.5066, "lr": 8.955355173281709e-06, "epoch": 3.5569620253164556, "percentage": 29.06, "elapsed_time": "0:16:10", "remaining_time": "0:39:30"}
35
+ {"current_steps": 35, "total_steps": 117, "loss": 0.4884, "lr": 8.862084796122998e-06, "epoch": 3.6582278481012658, "percentage": 29.91, "elapsed_time": "0:16:38", "remaining_time": "0:38:58"}
36
+ {"current_steps": 36, "total_steps": 117, "loss": 0.5393, "lr": 8.765357330018056e-06, "epoch": 3.759493670886076, "percentage": 30.77, "elapsed_time": "0:17:04", "remaining_time": "0:38:24"}
37
+ {"current_steps": 37, "total_steps": 117, "loss": 0.5067, "lr": 8.665259359149132e-06, "epoch": 3.8607594936708862, "percentage": 31.62, "elapsed_time": "0:17:25", "remaining_time": "0:37:40"}
38
+ {"current_steps": 38, "total_steps": 117, "loss": 0.4978, "lr": 8.561880484756726e-06, "epoch": 3.962025316455696, "percentage": 32.48, "elapsed_time": "0:17:48", "remaining_time": "0:37:02"}
39
+ {"current_steps": 39, "total_steps": 117, "loss": 0.4271, "lr": 8.455313244934324e-06, "epoch": 4.10126582278481, "percentage": 33.33, "elapsed_time": "0:18:58", "remaining_time": "0:37:56"}
40
+ {"current_steps": 40, "total_steps": 117, "loss": 0.4186, "lr": 8.345653031794292e-06, "epoch": 4.2025316455696204, "percentage": 34.19, "elapsed_time": "0:19:18", "remaining_time": "0:37:10"}
41
+ {"current_steps": 41, "total_steps": 117, "loss": 0.4145, "lr": 8.232998006078998e-06, "epoch": 4.30379746835443, "percentage": 35.04, "elapsed_time": "0:19:42", "remaining_time": "0:36:32"}
42
+ {"current_steps": 42, "total_steps": 117, "loss": 0.3187, "lr": 8.117449009293668e-06, "epoch": 4.405063291139241, "percentage": 35.9, "elapsed_time": "0:20:00", "remaining_time": "0:35:44"}
43
+ {"current_steps": 43, "total_steps": 117, "loss": 0.4154, "lr": 7.99910947343957e-06, "epoch": 4.506329113924051, "percentage": 36.75, "elapsed_time": "0:20:28", "remaining_time": "0:35:13"}
44
+ {"current_steps": 44, "total_steps": 117, "loss": 0.405, "lr": 7.87808532842837e-06, "epoch": 4.6075949367088604, "percentage": 37.61, "elapsed_time": "0:21:00", "remaining_time": "0:34:50"}
45
+ {"current_steps": 45, "total_steps": 117, "loss": 0.3854, "lr": 7.754484907260513e-06, "epoch": 4.708860759493671, "percentage": 38.46, "elapsed_time": "0:21:23", "remaining_time": "0:34:13"}
46
+ {"current_steps": 46, "total_steps": 117, "loss": 0.3138, "lr": 7.628418849052523e-06, "epoch": 4.810126582278481, "percentage": 39.32, "elapsed_time": "0:21:41", "remaining_time": "0:33:28"}
47
+ {"current_steps": 47, "total_steps": 117, "loss": 0.3596, "lr": 7.500000000000001e-06, "epoch": 4.911392405063291, "percentage": 40.17, "elapsed_time": "0:22:13", "remaining_time": "0:33:05"}
48
+ {"current_steps": 48, "total_steps": 117, "loss": 0.3498, "lr": 7.369343312364994e-06, "epoch": 5.050632911392405, "percentage": 41.03, "elapsed_time": "0:23:21", "remaining_time": "0:33:35"}
49
+ {"current_steps": 49, "total_steps": 117, "loss": 0.3278, "lr": 7.236565741578163e-06, "epoch": 5.151898734177215, "percentage": 41.88, "elapsed_time": "0:23:58", "remaining_time": "0:33:16"}
50
+ {"current_steps": 50, "total_steps": 117, "loss": 0.3213, "lr": 7.101786141547829e-06, "epoch": 5.253164556962025, "percentage": 42.74, "elapsed_time": "0:24:19", "remaining_time": "0:32:36"}
51
+ {"current_steps": 51, "total_steps": 117, "loss": 0.3747, "lr": 6.965125158269619e-06, "epoch": 5.3544303797468356, "percentage": 43.59, "elapsed_time": "0:24:50", "remaining_time": "0:32:09"}
52
+ {"current_steps": 52, "total_steps": 117, "loss": 0.3109, "lr": 6.8267051218319766e-06, "epoch": 5.455696202531645, "percentage": 44.44, "elapsed_time": "0:25:13", "remaining_time": "0:31:31"}
53
+ {"current_steps": 53, "total_steps": 117, "loss": 0.2898, "lr": 6.686649936914151e-06, "epoch": 5.556962025316456, "percentage": 45.3, "elapsed_time": "0:25:38", "remaining_time": "0:30:57"}
54
+ {"current_steps": 54, "total_steps": 117, "loss": 0.2991, "lr": 6.545084971874738e-06, "epoch": 5.658227848101266, "percentage": 46.15, "elapsed_time": "0:26:02", "remaining_time": "0:30:22"}
55
+ {"current_steps": 55, "total_steps": 117, "loss": 0.2762, "lr": 6.402136946530014e-06, "epoch": 5.759493670886076, "percentage": 47.01, "elapsed_time": "0:26:24", "remaining_time": "0:29:46"}
56
+ {"current_steps": 56, "total_steps": 117, "loss": 0.2439, "lr": 6.257933818722544e-06, "epoch": 5.860759493670886, "percentage": 47.86, "elapsed_time": "0:26:43", "remaining_time": "0:29:07"}