sedrickkeh commited on
Commit
0e5faad
·
verified ·
1 Parent(s): bf0268c

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 sha256:338402fbe0bc309cc6ff04501479787704a977a07f029ceda52bf51e636ecff3
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbed3a95a23542fde6274aed9329d62c687e9e51e2a7c12433db3d84eba8bd9c
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:afb09093bd56175cbbf1c0f4ff9923730c7aed24728b2997df33af86005d1f50
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461569734e10f3f1ee497f5b4a91bf468f525fb0032666b625eca2a71d6d5dd4
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c7bf2250f129014dcd4b3d1305790fa584b21de0a288aeeeb049a5bb3e0b0ba
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa467bbc0c0cc72928f6812861f481c7bd432d6a8cf84142c88609ec150fdd7e
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:baee0eabcd9db051bc15973841c3eed9fc961bd40108ea71b2e9c47ea48aafa8
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0047785afb9f5bb807f15cea25b24cdf96e4ce6ebfe0d8eb755b36c6131f7cd6
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -81,3 +81,38 @@
81
  {"current_steps": 81, "total_steps": 156, "loss": 0.6928, "lr": 5.559822380516539e-06, "epoch": 1.5477707006369426, "percentage": 51.92, "elapsed_time": "0:18:23", "remaining_time": "0:17:01"}
82
  {"current_steps": 82, "total_steps": 156, "loss": 0.7225, "lr": 5.448196544517168e-06, "epoch": 1.5668789808917198, "percentage": 52.56, "elapsed_time": "0:18:34", "remaining_time": "0:16:45"}
83
  {"current_steps": 83, "total_steps": 156, "loss": 0.7372, "lr": 5.336345028060199e-06, "epoch": 1.5859872611464967, "percentage": 53.21, "elapsed_time": "0:18:48", "remaining_time": "0:16:32"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81
  {"current_steps": 81, "total_steps": 156, "loss": 0.6928, "lr": 5.559822380516539e-06, "epoch": 1.5477707006369426, "percentage": 51.92, "elapsed_time": "0:18:23", "remaining_time": "0:17:01"}
82
  {"current_steps": 82, "total_steps": 156, "loss": 0.7225, "lr": 5.448196544517168e-06, "epoch": 1.5668789808917198, "percentage": 52.56, "elapsed_time": "0:18:34", "remaining_time": "0:16:45"}
83
  {"current_steps": 83, "total_steps": 156, "loss": 0.7372, "lr": 5.336345028060199e-06, "epoch": 1.5859872611464967, "percentage": 53.21, "elapsed_time": "0:18:48", "remaining_time": "0:16:32"}
84
+ {"current_steps": 84, "total_steps": 156, "loss": 0.6999, "lr": 5.224324151752575e-06, "epoch": 1.605095541401274, "percentage": 53.85, "elapsed_time": "0:19:04", "remaining_time": "0:16:20"}
85
+ {"current_steps": 85, "total_steps": 156, "loss": 0.7043, "lr": 5.112190321479026e-06, "epoch": 1.6242038216560508, "percentage": 54.49, "elapsed_time": "0:19:13", "remaining_time": "0:16:03"}
86
+ {"current_steps": 86, "total_steps": 156, "loss": 0.6697, "lr": 5e-06, "epoch": 1.643312101910828, "percentage": 55.13, "elapsed_time": "0:19:25", "remaining_time": "0:15:49"}
87
+ {"current_steps": 87, "total_steps": 156, "loss": 0.7563, "lr": 4.887809678520976e-06, "epoch": 1.662420382165605, "percentage": 55.77, "elapsed_time": "0:19:36", "remaining_time": "0:15:32"}
88
+ {"current_steps": 88, "total_steps": 156, "loss": 0.714, "lr": 4.775675848247427e-06, "epoch": 1.6815286624203822, "percentage": 56.41, "elapsed_time": "0:19:49", "remaining_time": "0:15:19"}
89
+ {"current_steps": 89, "total_steps": 156, "loss": 0.6812, "lr": 4.663654971939802e-06, "epoch": 1.700636942675159, "percentage": 57.05, "elapsed_time": "0:19:58", "remaining_time": "0:15:02"}
90
+ {"current_steps": 90, "total_steps": 156, "loss": 0.7148, "lr": 4.551803455482833e-06, "epoch": 1.7197452229299364, "percentage": 57.69, "elapsed_time": "0:20:11", "remaining_time": "0:14:48"}
91
+ {"current_steps": 91, "total_steps": 156, "loss": 0.7023, "lr": 4.4401776194834615e-06, "epoch": 1.7388535031847132, "percentage": 58.33, "elapsed_time": "0:20:22", "remaining_time": "0:14:33"}
92
+ {"current_steps": 92, "total_steps": 156, "loss": 0.7438, "lr": 4.3288336709117246e-06, "epoch": 1.7579617834394905, "percentage": 58.97, "elapsed_time": "0:20:34", "remaining_time": "0:14:19"}
93
+ {"current_steps": 93, "total_steps": 156, "loss": 0.6842, "lr": 4.217827674798845e-06, "epoch": 1.7770700636942676, "percentage": 59.62, "elapsed_time": "0:20:46", "remaining_time": "0:14:04"}
94
+ {"current_steps": 94, "total_steps": 156, "loss": 0.6574, "lr": 4.107215526006818e-06, "epoch": 1.7961783439490446, "percentage": 60.26, "elapsed_time": "0:20:57", "remaining_time": "0:13:49"}
95
+ {"current_steps": 95, "total_steps": 156, "loss": 0.7421, "lr": 3.997052921083637e-06, "epoch": 1.8152866242038217, "percentage": 60.9, "elapsed_time": "0:21:09", "remaining_time": "0:13:35"}
96
+ {"current_steps": 96, "total_steps": 156, "loss": 0.7061, "lr": 3.887395330218429e-06, "epoch": 1.8343949044585988, "percentage": 61.54, "elapsed_time": "0:21:22", "remaining_time": "0:13:21"}
97
+ {"current_steps": 97, "total_steps": 156, "loss": 0.6998, "lr": 3.778297969310529e-06, "epoch": 1.8535031847133758, "percentage": 62.18, "elapsed_time": "0:21:34", "remaining_time": "0:13:07"}
98
+ {"current_steps": 98, "total_steps": 156, "loss": 0.7187, "lr": 3.669815772166625e-06, "epoch": 1.872611464968153, "percentage": 62.82, "elapsed_time": "0:21:44", "remaining_time": "0:12:52"}
99
+ {"current_steps": 99, "total_steps": 156, "loss": 0.6835, "lr": 3.562003362839914e-06, "epoch": 1.89171974522293, "percentage": 63.46, "elapsed_time": "0:21:57", "remaining_time": "0:12:38"}
100
+ {"current_steps": 100, "total_steps": 156, "loss": 0.6395, "lr": 3.4549150281252635e-06, "epoch": 1.910828025477707, "percentage": 64.1, "elapsed_time": "0:22:05", "remaining_time": "0:12:22"}
101
+ {"current_steps": 101, "total_steps": 156, "loss": 0.7582, "lr": 3.3486046902241663e-06, "epoch": 1.929936305732484, "percentage": 64.74, "elapsed_time": "0:22:18", "remaining_time": "0:12:09"}
102
+ {"current_steps": 102, "total_steps": 156, "loss": 0.6748, "lr": 3.2431258795932863e-06, "epoch": 1.9490445859872612, "percentage": 65.38, "elapsed_time": "0:22:27", "remaining_time": "0:11:53"}
103
+ {"current_steps": 103, "total_steps": 156, "loss": 0.6935, "lr": 3.1385317079902743e-06, "epoch": 1.9681528662420382, "percentage": 66.03, "elapsed_time": "0:22:43", "remaining_time": "0:11:41"}
104
+ {"current_steps": 104, "total_steps": 156, "loss": 0.6842, "lr": 3.0348748417303826e-06, "epoch": 1.9872611464968153, "percentage": 66.67, "elapsed_time": "0:22:57", "remaining_time": "0:11:28"}
105
+ {"current_steps": 105, "total_steps": 156, "loss": 1.1038, "lr": 2.932207475167398e-06, "epoch": 2.0063694267515926, "percentage": 67.31, "elapsed_time": "0:23:57", "remaining_time": "0:11:38"}
106
+ {"current_steps": 106, "total_steps": 156, "loss": 0.6547, "lr": 2.83058130441221e-06, "epoch": 2.0254777070063694, "percentage": 67.95, "elapsed_time": "0:24:12", "remaining_time": "0:11:24"}
107
+ {"current_steps": 107, "total_steps": 156, "loss": 0.565, "lr": 2.7300475013022666e-06, "epoch": 2.0445859872611467, "percentage": 68.59, "elapsed_time": "0:24:21", "remaining_time": "0:11:09"}
108
+ {"current_steps": 108, "total_steps": 156, "loss": 0.5997, "lr": 2.6306566876350072e-06, "epoch": 2.0636942675159236, "percentage": 69.23, "elapsed_time": "0:24:35", "remaining_time": "0:10:55"}
109
+ {"current_steps": 109, "total_steps": 156, "loss": 0.5757, "lr": 2.532458909678266e-06, "epoch": 2.082802547770701, "percentage": 69.87, "elapsed_time": "0:24:47", "remaining_time": "0:10:41"}
110
+ {"current_steps": 110, "total_steps": 156, "loss": 0.6274, "lr": 2.43550361297047e-06, "epoch": 2.1019108280254777, "percentage": 70.51, "elapsed_time": "0:24:56", "remaining_time": "0:10:25"}
111
+ {"current_steps": 111, "total_steps": 156, "loss": 0.6346, "lr": 2.339839617423318e-06, "epoch": 2.121019108280255, "percentage": 71.15, "elapsed_time": "0:25:11", "remaining_time": "0:10:12"}
112
+ {"current_steps": 112, "total_steps": 156, "loss": 0.6, "lr": 2.245515092739488e-06, "epoch": 2.140127388535032, "percentage": 71.79, "elapsed_time": "0:25:24", "remaining_time": "0:09:59"}
113
+ {"current_steps": 113, "total_steps": 156, "loss": 0.6427, "lr": 2.1525775341577404e-06, "epoch": 2.159235668789809, "percentage": 72.44, "elapsed_time": "0:25:38", "remaining_time": "0:09:45"}
114
+ {"current_steps": 114, "total_steps": 156, "loss": 0.5617, "lr": 2.061073738537635e-06, "epoch": 2.178343949044586, "percentage": 73.08, "elapsed_time": "0:25:51", "remaining_time": "0:09:31"}
115
+ {"current_steps": 115, "total_steps": 156, "loss": 0.5894, "lr": 1.971049780795901e-06, "epoch": 2.1974522292993632, "percentage": 73.72, "elapsed_time": "0:26:02", "remaining_time": "0:09:16"}
116
+ {"current_steps": 116, "total_steps": 156, "loss": 0.5989, "lr": 1.8825509907063328e-06, "epoch": 2.21656050955414, "percentage": 74.36, "elapsed_time": "0:26:11", "remaining_time": "0:09:01"}
117
+ {"current_steps": 117, "total_steps": 156, "loss": 0.6264, "lr": 1.7956219300748796e-06, "epoch": 2.2356687898089174, "percentage": 75.0, "elapsed_time": "0:26:25", "remaining_time": "0:08:48"}
118
+ {"current_steps": 118, "total_steps": 156, "loss": 0.5717, "lr": 1.7103063703014372e-06, "epoch": 2.254777070063694, "percentage": 75.64, "elapsed_time": "0:26:37", "remaining_time": "0:08:34"}