sedrickkeh commited on
Commit
832f890
·
verified ·
1 Parent(s): aa6946f

Training in progress, epoch 1

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97764a9866951e8589f28110586f8f72d50935a43e82355b2a1470553826f987
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa019a00fb5b953a084bf8cf49acc6d3ae34ff0365e888f4c6a522611e757d34
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cade4f3e899c6f8095395caca3f7783098cf011068d796947c908e60b2572a5
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e5c374cc0fefbe1de1eaa2079a6c08a2769ff90faa436cfe9e2624fa02d525
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:f3ac867d249866036d3ee01065f6f0563f66761e3da56006dd2172c636ea767e
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc383ecd13245bda4b7a39604aaf0e0332962eaa2b7104b3a96a14ef512b7e8
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:ee0b05387e8c4a685dffe3b867dc85412c1d2dcc08061fe9007008f9bfd3fa5f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5bd13d9aa33a92d0792d6ac3e10a728a270de3da05d5eadb77f17355819079
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -28,3 +28,30 @@
28
  {"current_steps": 28, "total_steps": 78, "loss": 0.846, "lr": 8.117449009293668e-06, "epoch": 1.0632911392405062, "percentage": 35.9, "elapsed_time": "0:17:22", "remaining_time": "0:31:00"}
29
  {"current_steps": 29, "total_steps": 78, "loss": 0.774, "lr": 7.938926261462366e-06, "epoch": 1.1012658227848102, "percentage": 37.18, "elapsed_time": "0:17:57", "remaining_time": "0:30:19"}
30
  {"current_steps": 30, "total_steps": 78, "loss": 0.7537, "lr": 7.754484907260513e-06, "epoch": 1.139240506329114, "percentage": 38.46, "elapsed_time": "0:18:31", "remaining_time": "0:29:39"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  {"current_steps": 28, "total_steps": 78, "loss": 0.846, "lr": 8.117449009293668e-06, "epoch": 1.0632911392405062, "percentage": 35.9, "elapsed_time": "0:17:22", "remaining_time": "0:31:00"}
29
  {"current_steps": 29, "total_steps": 78, "loss": 0.774, "lr": 7.938926261462366e-06, "epoch": 1.1012658227848102, "percentage": 37.18, "elapsed_time": "0:17:57", "remaining_time": "0:30:19"}
30
  {"current_steps": 30, "total_steps": 78, "loss": 0.7537, "lr": 7.754484907260513e-06, "epoch": 1.139240506329114, "percentage": 38.46, "elapsed_time": "0:18:31", "remaining_time": "0:29:39"}
31
+ {"current_steps": 31, "total_steps": 78, "loss": 0.7517, "lr": 7.564496387029532e-06, "epoch": 1.1772151898734178, "percentage": 39.74, "elapsed_time": "0:19:07", "remaining_time": "0:28:59"}
32
+ {"current_steps": 32, "total_steps": 78, "loss": 0.8413, "lr": 7.369343312364994e-06, "epoch": 1.2151898734177216, "percentage": 41.03, "elapsed_time": "0:19:38", "remaining_time": "0:28:13"}
33
+ {"current_steps": 33, "total_steps": 78, "loss": 0.7552, "lr": 7.169418695587791e-06, "epoch": 1.2531645569620253, "percentage": 42.31, "elapsed_time": "0:20:14", "remaining_time": "0:27:36"}
34
+ {"current_steps": 34, "total_steps": 78, "loss": 0.7406, "lr": 6.965125158269619e-06, "epoch": 1.2911392405063291, "percentage": 43.59, "elapsed_time": "0:20:45", "remaining_time": "0:26:52"}
35
+ {"current_steps": 35, "total_steps": 78, "loss": 0.8121, "lr": 6.7568741204067145e-06, "epoch": 1.3291139240506329, "percentage": 44.87, "elapsed_time": "0:21:17", "remaining_time": "0:26:09"}
36
+ {"current_steps": 36, "total_steps": 78, "loss": 0.7502, "lr": 6.545084971874738e-06, "epoch": 1.3670886075949367, "percentage": 46.15, "elapsed_time": "0:21:49", "remaining_time": "0:25:28"}
37
+ {"current_steps": 37, "total_steps": 78, "loss": 0.7571, "lr": 6.330184227833376e-06, "epoch": 1.4050632911392404, "percentage": 47.44, "elapsed_time": "0:22:19", "remaining_time": "0:24:43"}
38
+ {"current_steps": 38, "total_steps": 78, "loss": 0.8121, "lr": 6.112604669781572e-06, "epoch": 1.4430379746835442, "percentage": 48.72, "elapsed_time": "0:22:58", "remaining_time": "0:24:10"}
39
+ {"current_steps": 39, "total_steps": 78, "loss": 0.7245, "lr": 5.892784473993184e-06, "epoch": 1.481012658227848, "percentage": 50.0, "elapsed_time": "0:23:29", "remaining_time": "0:23:29"}
40
+ {"current_steps": 40, "total_steps": 78, "loss": 0.8151, "lr": 5.671166329088278e-06, "epoch": 1.518987341772152, "percentage": 51.28, "elapsed_time": "0:24:02", "remaining_time": "0:22:50"}
41
+ {"current_steps": 41, "total_steps": 78, "loss": 0.7679, "lr": 5.448196544517168e-06, "epoch": 1.5569620253164556, "percentage": 52.56, "elapsed_time": "0:24:40", "remaining_time": "0:22:16"}
42
+ {"current_steps": 42, "total_steps": 78, "loss": 0.7851, "lr": 5.224324151752575e-06, "epoch": 1.5949367088607596, "percentage": 53.85, "elapsed_time": "0:25:16", "remaining_time": "0:21:39"}
43
+ {"current_steps": 43, "total_steps": 78, "loss": 0.7489, "lr": 5e-06, "epoch": 1.6329113924050633, "percentage": 55.13, "elapsed_time": "0:25:54", "remaining_time": "0:21:05"}
44
+ {"current_steps": 44, "total_steps": 78, "loss": 0.7555, "lr": 4.775675848247427e-06, "epoch": 1.6708860759493671, "percentage": 56.41, "elapsed_time": "0:26:29", "remaining_time": "0:20:27"}
45
+ {"current_steps": 45, "total_steps": 78, "loss": 0.7379, "lr": 4.551803455482833e-06, "epoch": 1.7088607594936709, "percentage": 57.69, "elapsed_time": "0:27:03", "remaining_time": "0:19:50"}
46
+ {"current_steps": 46, "total_steps": 78, "loss": 0.825, "lr": 4.3288336709117246e-06, "epoch": 1.7468354430379747, "percentage": 58.97, "elapsed_time": "0:27:39", "remaining_time": "0:19:14"}
47
+ {"current_steps": 47, "total_steps": 78, "loss": 0.7141, "lr": 4.107215526006818e-06, "epoch": 1.7848101265822784, "percentage": 60.26, "elapsed_time": "0:28:11", "remaining_time": "0:18:35"}
48
+ {"current_steps": 48, "total_steps": 78, "loss": 0.7823, "lr": 3.887395330218429e-06, "epoch": 1.8227848101265822, "percentage": 61.54, "elapsed_time": "0:28:42", "remaining_time": "0:17:56"}
49
+ {"current_steps": 49, "total_steps": 78, "loss": 0.7229, "lr": 3.669815772166625e-06, "epoch": 1.8607594936708862, "percentage": 62.82, "elapsed_time": "0:29:18", "remaining_time": "0:17:20"}
50
+ {"current_steps": 50, "total_steps": 78, "loss": 0.7157, "lr": 3.4549150281252635e-06, "epoch": 1.8987341772151898, "percentage": 64.1, "elapsed_time": "0:29:55", "remaining_time": "0:16:45"}
51
+ {"current_steps": 51, "total_steps": 78, "loss": 0.8632, "lr": 3.2431258795932863e-06, "epoch": 1.9367088607594938, "percentage": 65.38, "elapsed_time": "0:30:31", "remaining_time": "0:16:09"}
52
+ {"current_steps": 52, "total_steps": 78, "loss": 0.7676, "lr": 3.0348748417303826e-06, "epoch": 1.9746835443037973, "percentage": 66.67, "elapsed_time": "0:31:09", "remaining_time": "0:15:34"}
53
+ {"current_steps": 53, "total_steps": 78, "loss": 1.222, "lr": 2.83058130441221e-06, "epoch": 2.0126582278481013, "percentage": 67.95, "elapsed_time": "0:32:29", "remaining_time": "0:15:19"}
54
+ {"current_steps": 54, "total_steps": 78, "loss": 0.7512, "lr": 2.6306566876350072e-06, "epoch": 2.050632911392405, "percentage": 69.23, "elapsed_time": "0:33:02", "remaining_time": "0:14:40"}
55
+ {"current_steps": 55, "total_steps": 78, "loss": 0.722, "lr": 2.43550361297047e-06, "epoch": 2.088607594936709, "percentage": 70.51, "elapsed_time": "0:33:41", "remaining_time": "0:14:05"}
56
+ {"current_steps": 56, "total_steps": 78, "loss": 0.6983, "lr": 2.245515092739488e-06, "epoch": 2.1265822784810124, "percentage": 71.79, "elapsed_time": "0:34:13", "remaining_time": "0:13:26"}
57
+ {"current_steps": 57, "total_steps": 78, "loss": 0.7094, "lr": 2.061073738537635e-06, "epoch": 2.1645569620253164, "percentage": 73.08, "elapsed_time": "0:34:45", "remaining_time": "0:12:48"}