Hugging Face's logo

sedrickkeh
/
mistral_openhermes_v3

Text Generation
Transformers
Safetensors
mistral
llama-factory
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
212d745
·
verified ·
1 Parent(s): 8024d35

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +26 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:126342c23cb1bf41af2a94a23f369c45d0ce4c94b429fec2316eda716c5a2b45
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e081c4c477e73ac66effa621c12bae0f676518353bd73524075ee46f3a272dff
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3ac1433a765116c57fd3ad588db0651abbf2db4ba89dee841db6ccb4ad007e2
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33fa53459b2d69772df9e8f4d70ebde85990f3e43930743f0874b1ed07b74354
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2addfd87720baa6e974b20fccb982bfc8405174b060e7775c300857210673e61
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e8c9709c7349377da0b05a36754b6d0e3cb76918d3d23ce9e5cc2da05522cb
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -23,3 +23,29 @@
23
  {"current_steps": 230, "total_steps": 738, "loss": 0.5584, "learning_rate": 5e-06, "epoch": 0.9321175278622087, "percentage": 31.17, "elapsed_time": "6:23:14", "remaining_time": "14:06:27"}
24
  {"current_steps": 240, "total_steps": 738, "loss": 0.5563, "learning_rate": 5e-06, "epoch": 0.9726443768996961, "percentage": 32.52, "elapsed_time": "6:39:54", "remaining_time": "13:49:49"}
25
  {"current_steps": 246, "total_steps": 738, "eval_loss": 0.5481154918670654, "epoch": 0.9969604863221885, "percentage": 33.33, "elapsed_time": "6:59:11", "remaining_time": "13:58:23"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  {"current_steps": 230, "total_steps": 738, "loss": 0.5584, "learning_rate": 5e-06, "epoch": 0.9321175278622087, "percentage": 31.17, "elapsed_time": "6:23:14", "remaining_time": "14:06:27"}
24
  {"current_steps": 240, "total_steps": 738, "loss": 0.5563, "learning_rate": 5e-06, "epoch": 0.9726443768996961, "percentage": 32.52, "elapsed_time": "6:39:54", "remaining_time": "13:49:49"}
25
  {"current_steps": 246, "total_steps": 738, "eval_loss": 0.5481154918670654, "epoch": 0.9969604863221885, "percentage": 33.33, "elapsed_time": "6:59:11", "remaining_time": "13:58:23"}
26
+ {"current_steps": 250, "total_steps": 738, "loss": 0.5364, "learning_rate": 5e-06, "epoch": 1.0131712259371835, "percentage": 33.88, "elapsed_time": "7:05:48", "remaining_time": "13:51:11"}
27
+ {"current_steps": 260, "total_steps": 738, "loss": 0.4897, "learning_rate": 5e-06, "epoch": 1.0536980749746707, "percentage": 35.23, "elapsed_time": "7:22:38", "remaining_time": "13:33:46"}
28
+ {"current_steps": 270, "total_steps": 738, "loss": 0.487, "learning_rate": 5e-06, "epoch": 1.094224924012158, "percentage": 36.59, "elapsed_time": "7:39:28", "remaining_time": "13:16:26"}
29
+ {"current_steps": 280, "total_steps": 738, "loss": 0.4854, "learning_rate": 5e-06, "epoch": 1.1347517730496455, "percentage": 37.94, "elapsed_time": "7:56:21", "remaining_time": "12:59:10"}
30
+ {"current_steps": 290, "total_steps": 738, "loss": 0.4873, "learning_rate": 5e-06, "epoch": 1.1752786220871327, "percentage": 39.3, "elapsed_time": "8:13:12", "remaining_time": "12:41:54"}
31
+ {"current_steps": 300, "total_steps": 738, "loss": 0.4891, "learning_rate": 5e-06, "epoch": 1.21580547112462, "percentage": 40.65, "elapsed_time": "8:30:04", "remaining_time": "12:24:43"}
32
+ {"current_steps": 310, "total_steps": 738, "loss": 0.4851, "learning_rate": 5e-06, "epoch": 1.2563323201621075, "percentage": 42.01, "elapsed_time": "8:46:55", "remaining_time": "12:07:29"}
33
+ {"current_steps": 320, "total_steps": 738, "loss": 0.4865, "learning_rate": 5e-06, "epoch": 1.2968591691995948, "percentage": 43.36, "elapsed_time": "9:03:45", "remaining_time": "11:50:17"}
34
+ {"current_steps": 330, "total_steps": 738, "loss": 0.4866, "learning_rate": 5e-06, "epoch": 1.337386018237082, "percentage": 44.72, "elapsed_time": "9:20:36", "remaining_time": "11:33:07"}
35
+ {"current_steps": 340, "total_steps": 738, "loss": 0.4938, "learning_rate": 5e-06, "epoch": 1.3779128672745693, "percentage": 46.07, "elapsed_time": "9:37:28", "remaining_time": "11:15:59"}
36
+ {"current_steps": 350, "total_steps": 738, "loss": 0.4925, "learning_rate": 5e-06, "epoch": 1.4184397163120568, "percentage": 47.43, "elapsed_time": "9:54:20", "remaining_time": "10:58:52"}
37
+ {"current_steps": 360, "total_steps": 738, "loss": 0.4948, "learning_rate": 5e-06, "epoch": 1.458966565349544, "percentage": 48.78, "elapsed_time": "10:11:13", "remaining_time": "10:41:47"}
38
+ {"current_steps": 370, "total_steps": 738, "loss": 0.4933, "learning_rate": 5e-06, "epoch": 1.4994934143870315, "percentage": 50.14, "elapsed_time": "10:28:05", "remaining_time": "10:24:41"}
39
+ {"current_steps": 380, "total_steps": 738, "loss": 0.4892, "learning_rate": 5e-06, "epoch": 1.5400202634245188, "percentage": 51.49, "elapsed_time": "10:44:56", "remaining_time": "10:07:36"}
40
+ {"current_steps": 390, "total_steps": 738, "loss": 0.4913, "learning_rate": 5e-06, "epoch": 1.580547112462006, "percentage": 52.85, "elapsed_time": "11:01:47", "remaining_time": "9:50:31"}
41
+ {"current_steps": 400, "total_steps": 738, "loss": 0.4921, "learning_rate": 5e-06, "epoch": 1.6210739614994933, "percentage": 54.2, "elapsed_time": "11:18:37", "remaining_time": "9:33:26"}
42
+ {"current_steps": 410, "total_steps": 738, "loss": 0.4865, "learning_rate": 5e-06, "epoch": 1.6616008105369806, "percentage": 55.56, "elapsed_time": "11:35:27", "remaining_time": "9:16:21"}
43
+ {"current_steps": 420, "total_steps": 738, "loss": 0.4886, "learning_rate": 5e-06, "epoch": 1.702127659574468, "percentage": 56.91, "elapsed_time": "11:52:15", "remaining_time": "8:59:17"}
44
+ {"current_steps": 430, "total_steps": 738, "loss": 0.4873, "learning_rate": 5e-06, "epoch": 1.7426545086119554, "percentage": 58.27, "elapsed_time": "12:09:06", "remaining_time": "8:42:14"}
45
+ {"current_steps": 440, "total_steps": 738, "loss": 0.488, "learning_rate": 5e-06, "epoch": 1.7831813576494429, "percentage": 59.62, "elapsed_time": "12:25:53", "remaining_time": "8:25:10"}
46
+ {"current_steps": 450, "total_steps": 738, "loss": 0.4885, "learning_rate": 5e-06, "epoch": 1.8237082066869301, "percentage": 60.98, "elapsed_time": "12:42:41", "remaining_time": "8:08:07"}
47
+ {"current_steps": 460, "total_steps": 738, "loss": 0.4916, "learning_rate": 5e-06, "epoch": 1.8642350557244174, "percentage": 62.33, "elapsed_time": "12:59:30", "remaining_time": "7:51:05"}
48
+ {"current_steps": 470, "total_steps": 738, "loss": 0.4883, "learning_rate": 5e-06, "epoch": 1.9047619047619047, "percentage": 63.69, "elapsed_time": "13:16:20", "remaining_time": "7:34:05"}
49
+ {"current_steps": 480, "total_steps": 738, "loss": 0.4871, "learning_rate": 5e-06, "epoch": 1.9452887537993921, "percentage": 65.04, "elapsed_time": "13:33:11", "remaining_time": "7:17:05"}
50
+ {"current_steps": 490, "total_steps": 738, "loss": 0.4893, "learning_rate": 5e-06, "epoch": 1.9858156028368794, "percentage": 66.4, "elapsed_time": "13:50:02", "remaining_time": "7:00:06"}
51
+ {"current_steps": 493, "total_steps": 738, "eval_loss": 0.5415348410606384, "epoch": 1.9979736575481257, "percentage": 66.8, "elapsed_time": "14:03:57", "remaining_time": "6:59:24"}