hlillemark commited on
Commit
506bac8
·
verified ·
1 Parent(s): b30015c

Training in progress, step 670

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80a75922bbe71cf04eeae60f8faa44e32811e7a0dbef5da46903c9c052a49fa9
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90bc2cb43ef69f683577064c90eab93a6187d058d056d6216eb49e0d28fbcdde
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ce1d7974b1ac53127e4393a19a887614a23d7ff63ae64b8cef4b45d0d5b9a48
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d782789c466ff853e5d061730ee0850433aaa60d4568054ea0cdbdfa5ff88e5
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6b440d3810a01f165fa6acc0ba880bd85ac7d6c5dc570a254613a37cccb498e
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8fb2b1f224c7bf76645e9e27afcecfd02845fed45c3f3138e07be0ae4a11c6
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f277fabaf661bf9352705206db6161334a7daae21382c22e995adcf8e766bcdc
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:710e856f7645c4cbc62939c8216d3d9867cf902080a41977bca2e66268c02484
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -65,3 +65,17 @@
65
  {"current_steps": 550, "total_steps": 670, "loss": 0.0091, "lr": 9.457478323545749e-07, "epoch": 8.208955223880597, "percentage": 82.09, "elapsed_time": "0:32:22", "remaining_time": "0:07:03"}
66
  {"current_steps": 550, "total_steps": 670, "eval_loss": 2.2086477279663086, "epoch": 8.208955223880597, "percentage": 82.09, "elapsed_time": "0:32:23", "remaining_time": "0:07:03"}
67
  {"current_steps": 560, "total_steps": 670, "loss": 0.0065, "lr": 7.988611635181099e-07, "epoch": 8.35820895522388, "percentage": 83.58, "elapsed_time": "0:32:50", "remaining_time": "0:06:27"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
  {"current_steps": 550, "total_steps": 670, "loss": 0.0091, "lr": 9.457478323545749e-07, "epoch": 8.208955223880597, "percentage": 82.09, "elapsed_time": "0:32:22", "remaining_time": "0:07:03"}
66
  {"current_steps": 550, "total_steps": 670, "eval_loss": 2.2086477279663086, "epoch": 8.208955223880597, "percentage": 82.09, "elapsed_time": "0:32:23", "remaining_time": "0:07:03"}
67
  {"current_steps": 560, "total_steps": 670, "loss": 0.0065, "lr": 7.988611635181099e-07, "epoch": 8.35820895522388, "percentage": 83.58, "elapsed_time": "0:32:50", "remaining_time": "0:06:27"}
68
+ {"current_steps": 570, "total_steps": 670, "loss": 0.0104, "lr": 6.633752576786251e-07, "epoch": 8.507462686567164, "percentage": 85.07, "elapsed_time": "0:33:18", "remaining_time": "0:05:50"}
69
+ {"current_steps": 580, "total_steps": 670, "loss": 0.006, "lr": 5.396577872130676e-07, "epoch": 8.656716417910447, "percentage": 86.57, "elapsed_time": "0:33:45", "remaining_time": "0:05:14"}
70
+ {"current_steps": 590, "total_steps": 670, "loss": 0.006, "lr": 4.2804448812404754e-07, "epoch": 8.805970149253731, "percentage": 88.06, "elapsed_time": "0:34:13", "remaining_time": "0:04:38"}
71
+ {"current_steps": 600, "total_steps": 670, "loss": 0.0054, "lr": 3.288382489424502e-07, "epoch": 8.955223880597014, "percentage": 89.55, "elapsed_time": "0:34:41", "remaining_time": "0:04:02"}
72
+ {"current_steps": 600, "total_steps": 670, "eval_loss": 2.2865116596221924, "epoch": 8.955223880597014, "percentage": 89.55, "elapsed_time": "0:34:42", "remaining_time": "0:04:02"}
73
+ {"current_steps": 610, "total_steps": 670, "loss": 0.006, "lr": 2.4230828876927293e-07, "epoch": 9.104477611940299, "percentage": 91.04, "elapsed_time": "0:35:09", "remaining_time": "0:03:27"}
74
+ {"current_steps": 620, "total_steps": 670, "loss": 0.0033, "lr": 1.6868942668726408e-07, "epoch": 9.253731343283581, "percentage": 92.54, "elapsed_time": "0:35:37", "remaining_time": "0:02:52"}
75
+ {"current_steps": 630, "total_steps": 670, "loss": 0.0064, "lr": 1.0818144452496293e-07, "epoch": 9.402985074626866, "percentage": 94.03, "elapsed_time": "0:36:04", "remaining_time": "0:02:17"}
76
+ {"current_steps": 640, "total_steps": 670, "loss": 0.0023, "lr": 6.094854470245326e-08, "epoch": 9.552238805970148, "percentage": 95.52, "elapsed_time": "0:36:31", "remaining_time": "0:01:42"}
77
+ {"current_steps": 650, "total_steps": 670, "loss": 0.0038, "lr": 2.711890463007405e-08, "epoch": 9.701492537313433, "percentage": 97.01, "elapsed_time": "0:36:58", "remaining_time": "0:01:08"}
78
+ {"current_steps": 650, "total_steps": 670, "eval_loss": 2.301581621170044, "epoch": 9.701492537313433, "percentage": 97.01, "elapsed_time": "0:36:59", "remaining_time": "0:01:08"}
79
+ {"current_steps": 660, "total_steps": 670, "loss": 0.0037, "lr": 6.784328869339218e-09, "epoch": 9.850746268656717, "percentage": 98.51, "elapsed_time": "0:37:27", "remaining_time": "0:00:34"}
80
+ {"current_steps": 670, "total_steps": 670, "loss": 0.0034, "lr": 0.0, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:37:55", "remaining_time": "0:00:00"}
81
+ {"current_steps": 670, "total_steps": 670, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:44:38", "remaining_time": "0:00:00"}