Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_platypus

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
esfrankel17 commited on
Commit
734f80d
·
verified ·
1 Parent(s): e64a51e

Training in progress, epoch 1

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ddd7657ff752050081fe0e1bb6b7eb516e99a90c0c7a545479957f41aef7318
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43761c22cb57a754ff2fc430a5db796cb51c5b13e8d9a401d592f82a613c8a8
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:f9c99750c9110baadeb8522bf7982cacbded55e341b372bb8a7501d6a8bd0b61
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d07e76e75b000c3963cbf0d54cf4d3f310fbed9314cf78a6df13e21001418c5
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b7ab1f28f91726f3f51e00e6dfc91c540c572a3b2150874a091436cec22cb28
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:241b6fd9d1d921abfb41966efae389465397a8f9fcd9ab0f0ae2c23396514c99
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:c25913acdafdc46cf2154a78f4f481c900f7a885de3aec904da04c692114a743
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc1d1ecb47a5ab35ad780572601f40aaa280d5b2640bf5d2357713d6825ec37
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,2 +1,5 @@
1
  {"current_steps": 10, "total_steps": 36, "loss": 0.6264, "learning_rate": 5e-06, "epoch": 0.7920792079207921, "percentage": 27.78, "elapsed_time": "0:05:22", "remaining_time": "0:13:59"}
2
  {"current_steps": 12, "total_steps": 36, "eval_loss": 0.5223038792610168, "epoch": 0.9504950495049505, "percentage": 33.33, "elapsed_time": "0:06:54", "remaining_time": "0:13:49"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 36, "loss": 0.6264, "learning_rate": 5e-06, "epoch": 0.7920792079207921, "percentage": 27.78, "elapsed_time": "0:05:22", "remaining_time": "0:13:59"}
2
  {"current_steps": 12, "total_steps": 36, "eval_loss": 0.5223038792610168, "epoch": 0.9504950495049505, "percentage": 33.33, "elapsed_time": "0:06:54", "remaining_time": "0:13:49"}
3
+ {"current_steps": 20, "total_steps": 36, "loss": 0.5367, "learning_rate": 5e-06, "epoch": 1.5841584158415842, "percentage": 55.56, "elapsed_time": "0:11:48", "remaining_time": "0:09:26"}
4
+ {"current_steps": 25, "total_steps": 36, "eval_loss": 0.4788552224636078, "epoch": 1.9801980198019802, "percentage": 69.44, "elapsed_time": "0:14:40", "remaining_time": "0:06:27"}
5
+ {"current_steps": 30, "total_steps": 36, "loss": 0.4893, "learning_rate": 5e-06, "epoch": 2.376237623762376, "percentage": 83.33, "elapsed_time": "0:18:05", "remaining_time": "0:03:37"}