Hugging Face's logo

mlfoundations-dev
/
oh_v1.3_slim_orca_x.25

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
gsmyrnis commited on
Commit
7051c41
·
verified ·
1 Parent(s): d38fb9d

Training in progress, epoch 3

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +14 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc4529d730ab3288bce62be1734151d0133046bbb6af7d26e3b04add8cc79312
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672b3ca03cdeb3f0174460c321abd9f39683d0cb478ecdea5705f29e44f91e26
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:ce74d2b49064c8d7199464d5cb08efabfd1cb03d27e2317d34650e0f5dd73b7c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69d40c0538513c6b3ff9726a5d1adbbb064e1adb4fa3693e963db847edfea2d8
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:932532e525868a1bede4a12047d70c312150e5fba0aa8f451691799129d01607
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f7a9ed3688c8646bf0eea79307b42771aa52b1ac260ba65e54155a5126dbeca
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:dcdff0ea063266a5c7d4eee21a565ae6dbac89887d151b91a044f1082b65082e
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3689612a88e74b6d7caa128b57cf3d2db4e2df5a6864126c991240736ba585df
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -31,3 +31,17 @@
31
  {"current_steps": 290, "total_steps": 432, "loss": 0.6721, "learning_rate": 5e-06, "epoch": 2.013888888888889, "percentage": 67.13, "elapsed_time": "0:33:23", "remaining_time": "0:16:20"}
32
  {"current_steps": 300, "total_steps": 432, "loss": 0.6364, "learning_rate": 5e-06, "epoch": 2.0833333333333335, "percentage": 69.44, "elapsed_time": "0:34:24", "remaining_time": "0:15:08"}
33
  {"current_steps": 310, "total_steps": 432, "loss": 0.6336, "learning_rate": 5e-06, "epoch": 2.1527777777777777, "percentage": 71.76, "elapsed_time": "0:35:26", "remaining_time": "0:13:56"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  {"current_steps": 290, "total_steps": 432, "loss": 0.6721, "learning_rate": 5e-06, "epoch": 2.013888888888889, "percentage": 67.13, "elapsed_time": "0:33:23", "remaining_time": "0:16:20"}
32
  {"current_steps": 300, "total_steps": 432, "loss": 0.6364, "learning_rate": 5e-06, "epoch": 2.0833333333333335, "percentage": 69.44, "elapsed_time": "0:34:24", "remaining_time": "0:15:08"}
33
  {"current_steps": 310, "total_steps": 432, "loss": 0.6336, "learning_rate": 5e-06, "epoch": 2.1527777777777777, "percentage": 71.76, "elapsed_time": "0:35:26", "remaining_time": "0:13:56"}
34
+ {"current_steps": 320, "total_steps": 432, "loss": 0.6332, "learning_rate": 5e-06, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "0:36:29", "remaining_time": "0:12:46"}
35
+ {"current_steps": 330, "total_steps": 432, "loss": 0.6352, "learning_rate": 5e-06, "epoch": 2.2916666666666665, "percentage": 76.39, "elapsed_time": "0:37:31", "remaining_time": "0:11:35"}
36
+ {"current_steps": 340, "total_steps": 432, "loss": 0.6368, "learning_rate": 5e-06, "epoch": 2.361111111111111, "percentage": 78.7, "elapsed_time": "0:38:33", "remaining_time": "0:10:26"}
37
+ {"current_steps": 350, "total_steps": 432, "loss": 0.6375, "learning_rate": 5e-06, "epoch": 2.4305555555555554, "percentage": 81.02, "elapsed_time": "0:39:37", "remaining_time": "0:09:17"}
38
+ {"current_steps": 360, "total_steps": 432, "loss": 0.6339, "learning_rate": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:40:41", "remaining_time": "0:08:08"}
39
+ {"current_steps": 370, "total_steps": 432, "loss": 0.6395, "learning_rate": 5e-06, "epoch": 2.5694444444444446, "percentage": 85.65, "elapsed_time": "0:41:44", "remaining_time": "0:06:59"}
40
+ {"current_steps": 380, "total_steps": 432, "loss": 0.6394, "learning_rate": 5e-06, "epoch": 2.638888888888889, "percentage": 87.96, "elapsed_time": "0:42:47", "remaining_time": "0:05:51"}
41
+ {"current_steps": 390, "total_steps": 432, "loss": 0.6393, "learning_rate": 5e-06, "epoch": 2.7083333333333335, "percentage": 90.28, "elapsed_time": "0:43:50", "remaining_time": "0:04:43"}
42
+ {"current_steps": 400, "total_steps": 432, "loss": 0.6369, "learning_rate": 5e-06, "epoch": 2.7777777777777777, "percentage": 92.59, "elapsed_time": "0:44:52", "remaining_time": "0:03:35"}
43
+ {"current_steps": 410, "total_steps": 432, "loss": 0.6401, "learning_rate": 5e-06, "epoch": 2.8472222222222223, "percentage": 94.91, "elapsed_time": "0:45:54", "remaining_time": "0:02:27"}
44
+ {"current_steps": 420, "total_steps": 432, "loss": 0.6356, "learning_rate": 5e-06, "epoch": 2.9166666666666665, "percentage": 97.22, "elapsed_time": "0:46:56", "remaining_time": "0:01:20"}
45
+ {"current_steps": 430, "total_steps": 432, "loss": 0.6375, "learning_rate": 5e-06, "epoch": 2.986111111111111, "percentage": 99.54, "elapsed_time": "0:47:57", "remaining_time": "0:00:13"}
46
+ {"current_steps": 432, "total_steps": 432, "eval_loss": 0.7165349721908569, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:49:50", "remaining_time": "0:00:00"}
47
+ {"current_steps": 432, "total_steps": 432, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:51:16", "remaining_time": "0:00:00"}