sedrickkeh commited on
Commit
8235fcc
·
verified ·
1 Parent(s): 19d7730

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:e21e77e3555c44a9d4a2541ad28fbfcc12a0635b86bb8db84dacbf81524fb6af
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95d31946bbbbeb162b4280bd54c6e8c41021baee8998f3a7097d7023599d0b5b
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d856f8fb0c4171bfe11d7cefad1df650b3a61b040d3a1b53e44ff7a7bb6d632
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daec58c955b7029f0cd83063538b3fdea31bec27d0a6f7eaca3fc119d6dfd24e
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dbe1cbadf40dccac2e25433e981518b5304365dea17062b6af173db9dd6730a
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7920250d39b0fc203c3b0faa27dce3652cf0e7381ee6354ec159800b1588b55
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cd882f8e3200a4333a2ed2d76ca28b3e5959b90dd3c3ace8c5a37322def5497
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5cd3432f3ef2000e2ae477fca4dc10a169d12c573e38df721ad74627b45c73
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -25,3 +25,29 @@
25
  {"current_steps": 25, "total_steps": 78, "loss": 0.9123, "lr": 8.613974319136959e-06, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:40:33", "remaining_time": "1:25:58"}
26
  {"current_steps": 26, "total_steps": 78, "loss": 0.9606, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:42:17", "remaining_time": "1:24:35"}
27
  {"current_steps": 27, "total_steps": 78, "loss": 1.805, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:44:54", "remaining_time": "1:24:50"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  {"current_steps": 25, "total_steps": 78, "loss": 0.9123, "lr": 8.613974319136959e-06, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:40:33", "remaining_time": "1:25:58"}
26
  {"current_steps": 26, "total_steps": 78, "loss": 0.9606, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:42:17", "remaining_time": "1:24:35"}
27
  {"current_steps": 27, "total_steps": 78, "loss": 1.805, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:44:54", "remaining_time": "1:24:50"}
28
+ {"current_steps": 28, "total_steps": 78, "loss": 0.9238, "lr": 8.117449009293668e-06, "epoch": 1.073482428115016, "percentage": 35.9, "elapsed_time": "0:46:43", "remaining_time": "1:23:26"}
29
+ {"current_steps": 29, "total_steps": 78, "loss": 0.8597, "lr": 7.938926261462366e-06, "epoch": 1.1118210862619808, "percentage": 37.18, "elapsed_time": "0:48:24", "remaining_time": "1:21:47"}
30
+ {"current_steps": 30, "total_steps": 78, "loss": 0.8425, "lr": 7.754484907260513e-06, "epoch": 1.1501597444089458, "percentage": 38.46, "elapsed_time": "0:49:59", "remaining_time": "1:19:59"}
31
+ {"current_steps": 31, "total_steps": 78, "loss": 0.9266, "lr": 7.564496387029532e-06, "epoch": 1.1884984025559104, "percentage": 39.74, "elapsed_time": "0:51:35", "remaining_time": "1:18:12"}
32
+ {"current_steps": 32, "total_steps": 78, "loss": 0.9045, "lr": 7.369343312364994e-06, "epoch": 1.2268370607028753, "percentage": 41.03, "elapsed_time": "0:53:06", "remaining_time": "1:16:20"}
33
+ {"current_steps": 33, "total_steps": 78, "loss": 0.9039, "lr": 7.169418695587791e-06, "epoch": 1.2651757188498403, "percentage": 42.31, "elapsed_time": "0:54:46", "remaining_time": "1:14:41"}
34
+ {"current_steps": 34, "total_steps": 78, "loss": 0.8709, "lr": 6.965125158269619e-06, "epoch": 1.3035143769968052, "percentage": 43.59, "elapsed_time": "0:56:20", "remaining_time": "1:12:54"}
35
+ {"current_steps": 35, "total_steps": 78, "loss": 0.8737, "lr": 6.7568741204067145e-06, "epoch": 1.34185303514377, "percentage": 44.87, "elapsed_time": "0:57:56", "remaining_time": "1:11:11"}
36
+ {"current_steps": 36, "total_steps": 78, "loss": 0.8212, "lr": 6.545084971874738e-06, "epoch": 1.3801916932907348, "percentage": 46.15, "elapsed_time": "0:59:35", "remaining_time": "1:09:31"}
37
+ {"current_steps": 37, "total_steps": 78, "loss": 0.8911, "lr": 6.330184227833376e-06, "epoch": 1.4185303514376997, "percentage": 47.44, "elapsed_time": "1:01:09", "remaining_time": "1:07:45"}
38
+ {"current_steps": 38, "total_steps": 78, "loss": 0.8792, "lr": 6.112604669781572e-06, "epoch": 1.4568690095846646, "percentage": 48.72, "elapsed_time": "1:02:48", "remaining_time": "1:06:07"}
39
+ {"current_steps": 39, "total_steps": 78, "loss": 0.898, "lr": 5.892784473993184e-06, "epoch": 1.4952076677316293, "percentage": 50.0, "elapsed_time": "1:04:36", "remaining_time": "1:04:36"}
40
+ {"current_steps": 40, "total_steps": 78, "loss": 0.8933, "lr": 5.671166329088278e-06, "epoch": 1.5335463258785942, "percentage": 51.28, "elapsed_time": "1:06:15", "remaining_time": "1:02:56"}
41
+ {"current_steps": 41, "total_steps": 78, "loss": 0.8078, "lr": 5.448196544517168e-06, "epoch": 1.571884984025559, "percentage": 52.56, "elapsed_time": "1:07:36", "remaining_time": "1:01:01"}
42
+ {"current_steps": 42, "total_steps": 78, "loss": 0.9273, "lr": 5.224324151752575e-06, "epoch": 1.610223642172524, "percentage": 53.85, "elapsed_time": "1:09:02", "remaining_time": "0:59:11"}
43
+ {"current_steps": 43, "total_steps": 78, "loss": 0.8608, "lr": 5e-06, "epoch": 1.648562300319489, "percentage": 55.13, "elapsed_time": "1:10:34", "remaining_time": "0:57:26"}
44
+ {"current_steps": 44, "total_steps": 78, "loss": 0.8584, "lr": 4.775675848247427e-06, "epoch": 1.6869009584664538, "percentage": 56.41, "elapsed_time": "1:12:08", "remaining_time": "0:55:44"}
45
+ {"current_steps": 45, "total_steps": 78, "loss": 0.867, "lr": 4.551803455482833e-06, "epoch": 1.7252396166134185, "percentage": 57.69, "elapsed_time": "1:13:43", "remaining_time": "0:54:04"}
46
+ {"current_steps": 46, "total_steps": 78, "loss": 0.9153, "lr": 4.3288336709117246e-06, "epoch": 1.7635782747603834, "percentage": 58.97, "elapsed_time": "1:15:34", "remaining_time": "0:52:34"}
47
+ {"current_steps": 47, "total_steps": 78, "loss": 0.8913, "lr": 4.107215526006818e-06, "epoch": 1.8019169329073481, "percentage": 60.26, "elapsed_time": "1:17:20", "remaining_time": "0:51:00"}
48
+ {"current_steps": 48, "total_steps": 78, "loss": 0.9051, "lr": 3.887395330218429e-06, "epoch": 1.840255591054313, "percentage": 61.54, "elapsed_time": "1:18:54", "remaining_time": "0:49:19"}
49
+ {"current_steps": 49, "total_steps": 78, "loss": 0.7876, "lr": 3.669815772166625e-06, "epoch": 1.878594249201278, "percentage": 62.82, "elapsed_time": "1:20:22", "remaining_time": "0:47:33"}
50
+ {"current_steps": 50, "total_steps": 78, "loss": 0.9688, "lr": 3.4549150281252635e-06, "epoch": 1.9169329073482428, "percentage": 64.1, "elapsed_time": "1:21:55", "remaining_time": "0:45:52"}
51
+ {"current_steps": 51, "total_steps": 78, "loss": 0.8987, "lr": 3.2431258795932863e-06, "epoch": 1.9552715654952078, "percentage": 65.38, "elapsed_time": "1:23:43", "remaining_time": "0:44:19"}
52
+ {"current_steps": 52, "total_steps": 78, "loss": 0.8741, "lr": 3.0348748417303826e-06, "epoch": 1.9936102236421727, "percentage": 66.67, "elapsed_time": "1:25:33", "remaining_time": "0:42:46"}
53
+ {"current_steps": 53, "total_steps": 78, "loss": 1.6146, "lr": 2.83058130441221e-06, "epoch": 2.0319488817891376, "percentage": 67.95, "elapsed_time": "1:28:16", "remaining_time": "0:41:38"}