sedrickkeh commited on
Commit
4f813a2
·
verified ·
1 Parent(s): d984aa2

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:b11d911ab7b14854fd8bd020c012b82ce151dee76ad7aeb668b487959eb9453e
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c13beebf6127a0267bafd027370504f77248023011af850da5bc45ba4fc53c
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2da57d287645406380451ee3f3c19c837c79d025b2c99db3c6fc4b482a16961e
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:370ac76e50ffb73fc5b098b14e5b25cba72a374a852a58cb405c62a8c8c002ed
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:a1fb349968c9e57266439c1708515c69201cfd76e18624b7b2bdae749961e49d
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5420556514127ab4f53a0e23c48154eae6637a0d817e4b665c44c9f5930fc980
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:e7b09be53c07f347864e90c84c14ab9dae3cbf9594a16fc1d36e1afa1b5d50b2
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9306734476160a11e3fcb1c73fd533eec4c10df3c45ac3e80727afb6d60f56dd
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -30,3 +30,30 @@
30
  {"current_steps": 30, "total_steps": 78, "loss": 0.3502, "lr": 7.754484907260513e-06, "epoch": 1.139240506329114, "percentage": 38.46, "elapsed_time": "0:11:51", "remaining_time": "0:18:59"}
31
  {"current_steps": 31, "total_steps": 78, "loss": 0.3366, "lr": 7.564496387029532e-06, "epoch": 1.1772151898734178, "percentage": 39.74, "elapsed_time": "0:12:13", "remaining_time": "0:18:31"}
32
  {"current_steps": 32, "total_steps": 78, "loss": 0.3378, "lr": 7.369343312364994e-06, "epoch": 1.2151898734177216, "percentage": 41.03, "elapsed_time": "0:12:35", "remaining_time": "0:18:06"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  {"current_steps": 30, "total_steps": 78, "loss": 0.3502, "lr": 7.754484907260513e-06, "epoch": 1.139240506329114, "percentage": 38.46, "elapsed_time": "0:11:51", "remaining_time": "0:18:59"}
31
  {"current_steps": 31, "total_steps": 78, "loss": 0.3366, "lr": 7.564496387029532e-06, "epoch": 1.1772151898734178, "percentage": 39.74, "elapsed_time": "0:12:13", "remaining_time": "0:18:31"}
32
  {"current_steps": 32, "total_steps": 78, "loss": 0.3378, "lr": 7.369343312364994e-06, "epoch": 1.2151898734177216, "percentage": 41.03, "elapsed_time": "0:12:35", "remaining_time": "0:18:06"}
33
+ {"current_steps": 33, "total_steps": 78, "loss": 0.3459, "lr": 7.169418695587791e-06, "epoch": 1.2531645569620253, "percentage": 42.31, "elapsed_time": "0:12:56", "remaining_time": "0:17:39"}
34
+ {"current_steps": 34, "total_steps": 78, "loss": 0.2932, "lr": 6.965125158269619e-06, "epoch": 1.2911392405063291, "percentage": 43.59, "elapsed_time": "0:13:16", "remaining_time": "0:17:10"}
35
+ {"current_steps": 35, "total_steps": 78, "loss": 0.3038, "lr": 6.7568741204067145e-06, "epoch": 1.3291139240506329, "percentage": 44.87, "elapsed_time": "0:13:40", "remaining_time": "0:16:47"}
36
+ {"current_steps": 36, "total_steps": 78, "loss": 0.3305, "lr": 6.545084971874738e-06, "epoch": 1.3670886075949367, "percentage": 46.15, "elapsed_time": "0:14:02", "remaining_time": "0:16:22"}
37
+ {"current_steps": 37, "total_steps": 78, "loss": 0.3243, "lr": 6.330184227833376e-06, "epoch": 1.4050632911392404, "percentage": 47.44, "elapsed_time": "0:14:24", "remaining_time": "0:15:57"}
38
+ {"current_steps": 38, "total_steps": 78, "loss": 0.3097, "lr": 6.112604669781572e-06, "epoch": 1.4430379746835442, "percentage": 48.72, "elapsed_time": "0:14:45", "remaining_time": "0:15:32"}
39
+ {"current_steps": 39, "total_steps": 78, "loss": 0.2806, "lr": 5.892784473993184e-06, "epoch": 1.481012658227848, "percentage": 50.0, "elapsed_time": "0:15:08", "remaining_time": "0:15:08"}
40
+ {"current_steps": 40, "total_steps": 78, "loss": 0.3565, "lr": 5.671166329088278e-06, "epoch": 1.518987341772152, "percentage": 51.28, "elapsed_time": "0:15:30", "remaining_time": "0:14:44"}
41
+ {"current_steps": 41, "total_steps": 78, "loss": 0.2935, "lr": 5.448196544517168e-06, "epoch": 1.5569620253164556, "percentage": 52.56, "elapsed_time": "0:15:52", "remaining_time": "0:14:19"}
42
+ {"current_steps": 42, "total_steps": 78, "loss": 0.3026, "lr": 5.224324151752575e-06, "epoch": 1.5949367088607596, "percentage": 53.85, "elapsed_time": "0:16:15", "remaining_time": "0:13:56"}
43
+ {"current_steps": 43, "total_steps": 78, "loss": 0.3221, "lr": 5e-06, "epoch": 1.6329113924050633, "percentage": 55.13, "elapsed_time": "0:16:37", "remaining_time": "0:13:31"}
44
+ {"current_steps": 44, "total_steps": 78, "loss": 0.3033, "lr": 4.775675848247427e-06, "epoch": 1.6708860759493671, "percentage": 56.41, "elapsed_time": "0:16:57", "remaining_time": "0:13:06"}
45
+ {"current_steps": 45, "total_steps": 78, "loss": 0.3059, "lr": 4.551803455482833e-06, "epoch": 1.7088607594936709, "percentage": 57.69, "elapsed_time": "0:17:20", "remaining_time": "0:12:43"}
46
+ {"current_steps": 46, "total_steps": 78, "loss": 0.3011, "lr": 4.3288336709117246e-06, "epoch": 1.7468354430379747, "percentage": 58.97, "elapsed_time": "0:17:40", "remaining_time": "0:12:17"}
47
+ {"current_steps": 47, "total_steps": 78, "loss": 0.3253, "lr": 4.107215526006818e-06, "epoch": 1.7848101265822784, "percentage": 60.26, "elapsed_time": "0:18:01", "remaining_time": "0:11:53"}
48
+ {"current_steps": 48, "total_steps": 78, "loss": 0.3514, "lr": 3.887395330218429e-06, "epoch": 1.8227848101265822, "percentage": 61.54, "elapsed_time": "0:18:24", "remaining_time": "0:11:30"}
49
+ {"current_steps": 49, "total_steps": 78, "loss": 0.308, "lr": 3.669815772166625e-06, "epoch": 1.8607594936708862, "percentage": 62.82, "elapsed_time": "0:18:47", "remaining_time": "0:11:07"}
50
+ {"current_steps": 50, "total_steps": 78, "loss": 0.3251, "lr": 3.4549150281252635e-06, "epoch": 1.8987341772151898, "percentage": 64.1, "elapsed_time": "0:19:10", "remaining_time": "0:10:44"}
51
+ {"current_steps": 51, "total_steps": 78, "loss": 0.3039, "lr": 3.2431258795932863e-06, "epoch": 1.9367088607594938, "percentage": 65.38, "elapsed_time": "0:19:33", "remaining_time": "0:10:21"}
52
+ {"current_steps": 52, "total_steps": 78, "loss": 0.298, "lr": 3.0348748417303826e-06, "epoch": 1.9746835443037973, "percentage": 66.67, "elapsed_time": "0:19:54", "remaining_time": "0:09:57"}
53
+ {"current_steps": 53, "total_steps": 78, "loss": 0.5808, "lr": 2.83058130441221e-06, "epoch": 2.0126582278481013, "percentage": 67.95, "elapsed_time": "0:21:05", "remaining_time": "0:09:57"}
54
+ {"current_steps": 54, "total_steps": 78, "loss": 0.3013, "lr": 2.6306566876350072e-06, "epoch": 2.050632911392405, "percentage": 69.23, "elapsed_time": "0:21:29", "remaining_time": "0:09:33"}
55
+ {"current_steps": 55, "total_steps": 78, "loss": 0.319, "lr": 2.43550361297047e-06, "epoch": 2.088607594936709, "percentage": 70.51, "elapsed_time": "0:21:50", "remaining_time": "0:09:08"}
56
+ {"current_steps": 56, "total_steps": 78, "loss": 0.2785, "lr": 2.245515092739488e-06, "epoch": 2.1265822784810124, "percentage": 71.79, "elapsed_time": "0:22:14", "remaining_time": "0:08:44"}
57
+ {"current_steps": 57, "total_steps": 78, "loss": 0.2878, "lr": 2.061073738537635e-06, "epoch": 2.1645569620253164, "percentage": 73.08, "elapsed_time": "0:22:36", "remaining_time": "0:08:19"}
58
+ {"current_steps": 58, "total_steps": 78, "loss": 0.3001, "lr": 1.8825509907063328e-06, "epoch": 2.2025316455696204, "percentage": 74.36, "elapsed_time": "0:22:58", "remaining_time": "0:07:55"}
59
+ {"current_steps": 59, "total_steps": 78, "loss": 0.3073, "lr": 1.7103063703014372e-06, "epoch": 2.240506329113924, "percentage": 75.64, "elapsed_time": "0:23:21", "remaining_time": "0:07:31"}