sedrickkeh commited on
Commit
06d11cc
·
verified ·
1 Parent(s): 9d56449

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:e81c50b203c74f459d2c59824fcbf9c70b12fa1e53280d840671adf39003ba45
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cad8332c89e96afcd145b7621bdb23f377fc64bc20d8f2e81057f2122dbe91f
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a11bfe9c7f1c50b500251cffe4c4948970e6c9a914096551af1866b32a2028b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:436ff98f973629560ada114b2327ea88d1541140f70fd58e72546eb71c03c806
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:d27d89b3c88d5a41d6baa56b3a761793699cb8270daf06ea137519493c05e16d
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd3473698dfdf11fabb0274a9554bbf167094e27ec5e32006f2344907039378c
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a6449434b5538c4fab358923e296ab4927b2bda77d0283a14efadc059308683
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13b71493ba11dbebdaf2f54fb1c81023c3a6f554617bf51d45ec0df1f5a497f6
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -42,3 +42,44 @@
42
  {"current_steps": 42, "total_steps": 123, "loss": 1.4435, "lr": 8.380874501370098e-06, "epoch": 1.016, "percentage": 34.15, "elapsed_time": "0:39:45", "remaining_time": "1:16:39"}
43
  {"current_steps": 43, "total_steps": 123, "loss": 0.9858, "lr": 8.274303669726427e-06, "epoch": 1.04, "percentage": 34.96, "elapsed_time": "0:40:38", "remaining_time": "1:15:36"}
44
  {"current_steps": 44, "total_steps": 123, "loss": 0.7881, "lr": 8.165062269044353e-06, "epoch": 1.064, "percentage": 35.77, "elapsed_time": "0:41:37", "remaining_time": "1:14:44"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  {"current_steps": 42, "total_steps": 123, "loss": 1.4435, "lr": 8.380874501370098e-06, "epoch": 1.016, "percentage": 34.15, "elapsed_time": "0:39:45", "remaining_time": "1:16:39"}
43
  {"current_steps": 43, "total_steps": 123, "loss": 0.9858, "lr": 8.274303669726427e-06, "epoch": 1.04, "percentage": 34.96, "elapsed_time": "0:40:38", "remaining_time": "1:15:36"}
44
  {"current_steps": 44, "total_steps": 123, "loss": 0.7881, "lr": 8.165062269044353e-06, "epoch": 1.064, "percentage": 35.77, "elapsed_time": "0:41:37", "remaining_time": "1:14:44"}
45
+ {"current_steps": 45, "total_steps": 123, "loss": 0.8529, "lr": 8.053239398177191e-06, "epoch": 1.088, "percentage": 36.59, "elapsed_time": "0:42:32", "remaining_time": "1:13:43"}
46
+ {"current_steps": 46, "total_steps": 123, "loss": 0.8778, "lr": 7.938926261462366e-06, "epoch": 1.112, "percentage": 37.4, "elapsed_time": "0:43:33", "remaining_time": "1:12:53"}
47
+ {"current_steps": 47, "total_steps": 123, "loss": 0.9103, "lr": 7.822216094333847e-06, "epoch": 1.1360000000000001, "percentage": 38.21, "elapsed_time": "0:44:27", "remaining_time": "1:11:54"}
48
+ {"current_steps": 48, "total_steps": 123, "loss": 0.848, "lr": 7.703204087277989e-06, "epoch": 1.16, "percentage": 39.02, "elapsed_time": "0:45:26", "remaining_time": "1:11:00"}
49
+ {"current_steps": 49, "total_steps": 123, "loss": 0.896, "lr": 7.5819873081948105e-06, "epoch": 1.184, "percentage": 39.84, "elapsed_time": "0:46:25", "remaining_time": "1:10:05"}
50
+ {"current_steps": 50, "total_steps": 123, "loss": 0.8881, "lr": 7.45866462322802e-06, "epoch": 1.208, "percentage": 40.65, "elapsed_time": "0:47:18", "remaining_time": "1:09:04"}
51
+ {"current_steps": 51, "total_steps": 123, "loss": 0.9257, "lr": 7.333336616128369e-06, "epoch": 1.232, "percentage": 41.46, "elapsed_time": "0:48:15", "remaining_time": "1:08:07"}
52
+ {"current_steps": 52, "total_steps": 123, "loss": 0.8823, "lr": 7.206105506216107e-06, "epoch": 1.256, "percentage": 42.28, "elapsed_time": "0:49:06", "remaining_time": "1:07:02"}
53
+ {"current_steps": 53, "total_steps": 123, "loss": 0.822, "lr": 7.0770750650094335e-06, "epoch": 1.28, "percentage": 43.09, "elapsed_time": "0:49:55", "remaining_time": "1:05:56"}
54
+ {"current_steps": 54, "total_steps": 123, "loss": 0.7433, "lr": 6.946350531586959e-06, "epoch": 1.304, "percentage": 43.9, "elapsed_time": "0:50:44", "remaining_time": "1:04:49"}
55
+ {"current_steps": 55, "total_steps": 123, "loss": 0.9697, "lr": 6.814038526753205e-06, "epoch": 1.328, "percentage": 44.72, "elapsed_time": "0:51:39", "remaining_time": "1:03:51"}
56
+ {"current_steps": 56, "total_steps": 123, "loss": 0.8388, "lr": 6.680246966077151e-06, "epoch": 1.3519999999999999, "percentage": 45.53, "elapsed_time": "0:52:29", "remaining_time": "1:02:47"}
57
+ {"current_steps": 57, "total_steps": 123, "loss": 0.898, "lr": 6.545084971874738e-06, "epoch": 1.376, "percentage": 46.34, "elapsed_time": "0:53:13", "remaining_time": "1:01:37"}
58
+ {"current_steps": 58, "total_steps": 123, "loss": 0.9156, "lr": 6.408662784207149e-06, "epoch": 1.4, "percentage": 47.15, "elapsed_time": "0:54:09", "remaining_time": "1:00:42"}
59
+ {"current_steps": 59, "total_steps": 123, "loss": 0.8781, "lr": 6.271091670967437e-06, "epoch": 1.424, "percentage": 47.97, "elapsed_time": "0:55:04", "remaining_time": "0:59:44"}
60
+ {"current_steps": 60, "total_steps": 123, "loss": 0.8464, "lr": 6.132483837128823e-06, "epoch": 1.448, "percentage": 48.78, "elapsed_time": "0:56:07", "remaining_time": "0:58:55"}
61
+ {"current_steps": 61, "total_steps": 123, "loss": 0.8604, "lr": 5.9929523332287275e-06, "epoch": 1.472, "percentage": 49.59, "elapsed_time": "0:57:07", "remaining_time": "0:58:03"}
62
+ {"current_steps": 62, "total_steps": 123, "loss": 0.9152, "lr": 5.85261096316312e-06, "epoch": 1.496, "percentage": 50.41, "elapsed_time": "0:58:05", "remaining_time": "0:57:09"}
63
+ {"current_steps": 63, "total_steps": 123, "loss": 0.8257, "lr": 5.711574191366427e-06, "epoch": 1.52, "percentage": 51.22, "elapsed_time": "0:58:56", "remaining_time": "0:56:08"}
64
+ {"current_steps": 64, "total_steps": 123, "loss": 0.893, "lr": 5.569957049452703e-06, "epoch": 1.544, "percentage": 52.03, "elapsed_time": "0:59:44", "remaining_time": "0:55:04"}
65
+ {"current_steps": 65, "total_steps": 123, "loss": 0.8719, "lr": 5.4278750423942e-06, "epoch": 1.568, "percentage": 52.85, "elapsed_time": "1:00:34", "remaining_time": "0:54:03"}
66
+ {"current_steps": 66, "total_steps": 123, "loss": 0.8374, "lr": 5.285444054313841e-06, "epoch": 1.592, "percentage": 53.66, "elapsed_time": "1:01:34", "remaining_time": "0:53:10"}
67
+ {"current_steps": 67, "total_steps": 123, "loss": 0.9636, "lr": 5.142780253968481e-06, "epoch": 1.616, "percentage": 54.47, "elapsed_time": "1:02:32", "remaining_time": "0:52:16"}
68
+ {"current_steps": 68, "total_steps": 123, "loss": 0.7453, "lr": 5e-06, "epoch": 1.6400000000000001, "percentage": 55.28, "elapsed_time": "1:03:25", "remaining_time": "0:51:18"}
69
+ {"current_steps": 69, "total_steps": 123, "loss": 0.8727, "lr": 4.85721974603152e-06, "epoch": 1.6640000000000001, "percentage": 56.1, "elapsed_time": "1:04:18", "remaining_time": "0:50:19"}
70
+ {"current_steps": 70, "total_steps": 123, "loss": 0.8197, "lr": 4.71455594568616e-06, "epoch": 1.688, "percentage": 56.91, "elapsed_time": "1:05:05", "remaining_time": "0:49:17"}
71
+ {"current_steps": 71, "total_steps": 123, "loss": 0.8977, "lr": 4.572124957605803e-06, "epoch": 1.712, "percentage": 57.72, "elapsed_time": "1:06:03", "remaining_time": "0:48:23"}
72
+ {"current_steps": 72, "total_steps": 123, "loss": 0.8524, "lr": 4.430042950547298e-06, "epoch": 1.736, "percentage": 58.54, "elapsed_time": "1:07:01", "remaining_time": "0:47:28"}
73
+ {"current_steps": 73, "total_steps": 123, "loss": 0.8718, "lr": 4.2884258086335755e-06, "epoch": 1.76, "percentage": 59.35, "elapsed_time": "1:07:59", "remaining_time": "0:46:34"}
74
+ {"current_steps": 74, "total_steps": 123, "loss": 0.8436, "lr": 4.147389036836881e-06, "epoch": 1.784, "percentage": 60.16, "elapsed_time": "1:09:00", "remaining_time": "0:45:41"}
75
+ {"current_steps": 75, "total_steps": 123, "loss": 0.9016, "lr": 4.007047666771274e-06, "epoch": 1.808, "percentage": 60.98, "elapsed_time": "1:10:02", "remaining_time": "0:44:49"}
76
+ {"current_steps": 76, "total_steps": 123, "loss": 0.8374, "lr": 3.867516162871177e-06, "epoch": 1.8319999999999999, "percentage": 61.79, "elapsed_time": "1:10:50", "remaining_time": "0:43:48"}
77
+ {"current_steps": 77, "total_steps": 123, "loss": 0.833, "lr": 3.7289083290325668e-06, "epoch": 1.8559999999999999, "percentage": 62.6, "elapsed_time": "1:11:51", "remaining_time": "0:42:55"}
78
+ {"current_steps": 78, "total_steps": 123, "loss": 0.9076, "lr": 3.5913372157928515e-06, "epoch": 1.88, "percentage": 63.41, "elapsed_time": "1:12:47", "remaining_time": "0:41:59"}
79
+ {"current_steps": 79, "total_steps": 123, "loss": 0.8753, "lr": 3.4549150281252635e-06, "epoch": 1.904, "percentage": 64.23, "elapsed_time": "1:13:47", "remaining_time": "0:41:05"}
80
+ {"current_steps": 80, "total_steps": 123, "loss": 0.8169, "lr": 3.319753033922849e-06, "epoch": 1.928, "percentage": 65.04, "elapsed_time": "1:14:30", "remaining_time": "0:40:02"}
81
+ {"current_steps": 81, "total_steps": 123, "loss": 0.8877, "lr": 3.1859614732467957e-06, "epoch": 1.952, "percentage": 65.85, "elapsed_time": "1:15:30", "remaining_time": "0:39:08"}
82
+ {"current_steps": 82, "total_steps": 123, "loss": 0.7909, "lr": 3.053649468413043e-06, "epoch": 1.976, "percentage": 66.67, "elapsed_time": "1:16:20", "remaining_time": "0:38:10"}
83
+ {"current_steps": 83, "total_steps": 123, "loss": 1.3689, "lr": 2.9229249349905686e-06, "epoch": 2.008, "percentage": 67.48, "elapsed_time": "1:18:26", "remaining_time": "0:37:48"}
84
+ {"current_steps": 84, "total_steps": 123, "loss": 0.8718, "lr": 2.7938944937838924e-06, "epoch": 2.032, "percentage": 68.29, "elapsed_time": "1:19:27", "remaining_time": "0:36:53"}
85
+ {"current_steps": 85, "total_steps": 123, "loss": 0.8144, "lr": 2.6666633838716317e-06, "epoch": 2.056, "percentage": 69.11, "elapsed_time": "1:20:25", "remaining_time": "0:35:57"}