sedrickkeh commited on
Commit
293c342
·
verified ·
1 Parent(s): 68bca9d

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8921bdeef09b11686f9ecf587d0edbd874781fedfbe1f609865b91b1e01260a7
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e8d025c81448fe223f254f9dfb58f949d32f792169647fc2e025efe74165981
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a8d6a30bbf4168f07b757057303e53dba7574db649fcad22beb444e659a1b1f
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5effc4788b886c4851376e5f6a22b7ca3deebce94f857f84a2522882b72befd
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:f2954517d2b8d88a67593737053e620fac843e22102eaad33e526d223da06318
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1323742a931c87a99c1d17accfeffff95e2a430060bfa9192ce317a7e51928a
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:796456a701a51ca3f86b8d091d2e784b735382e3b763acf204c1e1426651210d
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03455892ee940458ab133fa67acd9d69ebfb56a21e403b2214a9118604fe00e2
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -66,3 +66,29 @@
66
  {"current_steps": 66, "total_steps": 93, "loss": 0.3663, "lr": 4.783084907995156e-06, "epoch": 2.112, "percentage": 70.97, "elapsed_time": "0:37:16", "remaining_time": "0:15:14"}
67
  {"current_steps": 67, "total_steps": 93, "loss": 0.3979, "lr": 4.463982917305155e-06, "epoch": 2.144, "percentage": 72.04, "elapsed_time": "0:37:53", "remaining_time": "0:14:42"}
68
  {"current_steps": 68, "total_steps": 93, "loss": 0.2757, "lr": 4.152811217759529e-06, "epoch": 2.176, "percentage": 73.12, "elapsed_time": "0:38:25", "remaining_time": "0:14:07"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
  {"current_steps": 66, "total_steps": 93, "loss": 0.3663, "lr": 4.783084907995156e-06, "epoch": 2.112, "percentage": 70.97, "elapsed_time": "0:37:16", "remaining_time": "0:15:14"}
67
  {"current_steps": 67, "total_steps": 93, "loss": 0.3979, "lr": 4.463982917305155e-06, "epoch": 2.144, "percentage": 72.04, "elapsed_time": "0:37:53", "remaining_time": "0:14:42"}
68
  {"current_steps": 68, "total_steps": 93, "loss": 0.2757, "lr": 4.152811217759529e-06, "epoch": 2.176, "percentage": 73.12, "elapsed_time": "0:38:25", "remaining_time": "0:14:07"}
69
+ {"current_steps": 69, "total_steps": 93, "loss": 0.3429, "lr": 3.850015559820465e-06, "epoch": 2.208, "percentage": 74.19, "elapsed_time": "0:38:57", "remaining_time": "0:13:32"}
70
+ {"current_steps": 70, "total_steps": 93, "loss": 0.3981, "lr": 3.5560296953512296e-06, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "0:39:27", "remaining_time": "0:12:58"}
71
+ {"current_steps": 71, "total_steps": 93, "loss": 0.37, "lr": 3.2712747562708115e-06, "epoch": 2.2720000000000002, "percentage": 76.34, "elapsed_time": "0:39:55", "remaining_time": "0:12:22"}
72
+ {"current_steps": 72, "total_steps": 93, "loss": 0.4165, "lr": 2.9961586512864947e-06, "epoch": 2.304, "percentage": 77.42, "elapsed_time": "0:40:26", "remaining_time": "0:11:47"}
73
+ {"current_steps": 73, "total_steps": 93, "loss": 0.3389, "lr": 2.7310754815685627e-06, "epoch": 2.336, "percentage": 78.49, "elapsed_time": "0:40:56", "remaining_time": "0:11:13"}
74
+ {"current_steps": 74, "total_steps": 93, "loss": 0.3643, "lr": 2.4764049762041874e-06, "epoch": 2.368, "percentage": 79.57, "elapsed_time": "0:41:31", "remaining_time": "0:10:39"}
75
+ {"current_steps": 75, "total_steps": 93, "loss": 0.2996, "lr": 2.2325119482391466e-06, "epoch": 2.4, "percentage": 80.65, "elapsed_time": "0:41:59", "remaining_time": "0:10:04"}
76
+ {"current_steps": 76, "total_steps": 93, "loss": 0.4327, "lr": 1.9997457720866554e-06, "epoch": 2.432, "percentage": 81.72, "elapsed_time": "0:42:32", "remaining_time": "0:09:30"}
77
+ {"current_steps": 77, "total_steps": 93, "loss": 0.315, "lr": 1.7784398830519002e-06, "epoch": 2.464, "percentage": 82.8, "elapsed_time": "0:42:59", "remaining_time": "0:08:56"}
78
+ {"current_steps": 78, "total_steps": 93, "loss": 0.343, "lr": 1.5689112996891576e-06, "epoch": 2.496, "percentage": 83.87, "elapsed_time": "0:43:43", "remaining_time": "0:08:24"}
79
+ {"current_steps": 79, "total_steps": 93, "loss": 0.3484, "lr": 1.3714601696757713e-06, "epoch": 2.528, "percentage": 84.95, "elapsed_time": "0:44:17", "remaining_time": "0:07:51"}
80
+ {"current_steps": 80, "total_steps": 93, "loss": 0.4159, "lr": 1.1863693398535115e-06, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "0:44:41", "remaining_time": "0:07:15"}
81
+ {"current_steps": 81, "total_steps": 93, "loss": 0.384, "lr": 1.01390395105318e-06, "epoch": 2.592, "percentage": 87.1, "elapsed_time": "0:45:10", "remaining_time": "0:06:41"}
82
+ {"current_steps": 82, "total_steps": 93, "loss": 0.3486, "lr": 8.543110582829272e-07, "epoch": 2.624, "percentage": 88.17, "elapsed_time": "0:45:40", "remaining_time": "0:06:07"}
83
+ {"current_steps": 83, "total_steps": 93, "loss": 0.3445, "lr": 7.078192768243486e-07, "epoch": 2.656, "percentage": 89.25, "elapsed_time": "0:46:15", "remaining_time": "0:05:34"}
84
+ {"current_steps": 84, "total_steps": 93, "loss": 0.3915, "lr": 5.746384547432738e-07, "epoch": 2.6879999999999997, "percentage": 90.32, "elapsed_time": "0:46:59", "remaining_time": "0:05:02"}
85
+ {"current_steps": 85, "total_steps": 93, "loss": 0.4302, "lr": 4.549593722844492e-07, "epoch": 2.7199999999999998, "percentage": 91.4, "elapsed_time": "0:47:33", "remaining_time": "0:04:28"}
86
+ {"current_steps": 86, "total_steps": 93, "loss": 0.2589, "lr": 3.4895346858066723e-07, "epoch": 2.752, "percentage": 92.47, "elapsed_time": "0:48:07", "remaining_time": "0:03:55"}
87
+ {"current_steps": 87, "total_steps": 93, "loss": 0.3742, "lr": 2.5677259606786686e-07, "epoch": 2.784, "percentage": 93.55, "elapsed_time": "0:48:42", "remaining_time": "0:03:21"}
88
+ {"current_steps": 88, "total_steps": 93, "loss": 0.3535, "lr": 1.7854880295797406e-07, "epoch": 2.816, "percentage": 94.62, "elapsed_time": "0:49:08", "remaining_time": "0:02:47"}
89
+ {"current_steps": 89, "total_steps": 93, "loss": 0.3458, "lr": 1.1439414408111471e-07, "epoch": 2.848, "percentage": 95.7, "elapsed_time": "0:49:34", "remaining_time": "0:02:13"}
90
+ {"current_steps": 90, "total_steps": 93, "loss": 0.4665, "lr": 6.440052036815081e-08, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "0:50:10", "remaining_time": "0:01:40"}
91
+ {"current_steps": 91, "total_steps": 93, "loss": 0.3022, "lr": 2.86395472034795e-08, "epoch": 2.912, "percentage": 97.85, "elapsed_time": "0:50:43", "remaining_time": "0:01:06"}
92
+ {"current_steps": 92, "total_steps": 93, "loss": 0.3701, "lr": 7.162451836685291e-09, "epoch": 2.944, "percentage": 98.92, "elapsed_time": "0:51:12", "remaining_time": "0:00:33"}
93
+ {"current_steps": 93, "total_steps": 93, "loss": 0.295, "lr": 0.0, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:51:38", "remaining_time": "0:00:00"}
94
+ {"current_steps": 93, "total_steps": 93, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:53:56", "remaining_time": "0:00:00"}