Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_evol_instruct_70k

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
esfrankel17 commited on
Commit
4873513
·
verified ·
1 Parent(s): ae9f948

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8b999897876f4ed711336b2164c4182f3080bb65aee611bc6f9e3ed2de61305
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a491a47eadc403171a69820429560d4c190070caa8b177f9bcecf2ff739acbb0
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:c204fd2ec27b64bc55e1cbeb840af5f839a65864369113dc1204dacdab309917
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a965b2005275b30d513a4473c5b6579493c564ea100851115b393eb5230b74d5
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9da8183b265b2d0a4b7465eeacc34b9ebf33b6af291cb987f1b9d91ef1528f5f
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f3a2b6663bcda66e2d59c3c8f17b9e238ba2d344994f37525028e71c4a7b806
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9306a9924ce9d035f61df8c13d65470464a6f5ab9ba06449d16540309a56c41e
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:287592f0fa0593103726f92985613c112b063340021b8614ca39fb1fcfb0eda1
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 93, "loss": 0.8626, "learning_rate": 5e-06, "epoch": 0.6274509803921569, "percentage": 21.51, "elapsed_time": "0:10:40", "remaining_time": "0:38:58"}
3
  {"current_steps": 30, "total_steps": 93, "loss": 0.8287, "learning_rate": 5e-06, "epoch": 0.9411764705882353, "percentage": 32.26, "elapsed_time": "0:15:57", "remaining_time": "0:33:31"}
4
  {"current_steps": 31, "total_steps": 93, "eval_loss": 0.8302477598190308, "epoch": 0.9725490196078431, "percentage": 33.33, "elapsed_time": "0:17:16", "remaining_time": "0:34:33"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 93, "loss": 0.8626, "learning_rate": 5e-06, "epoch": 0.6274509803921569, "percentage": 21.51, "elapsed_time": "0:10:40", "remaining_time": "0:38:58"}
3
  {"current_steps": 30, "total_steps": 93, "loss": 0.8287, "learning_rate": 5e-06, "epoch": 0.9411764705882353, "percentage": 32.26, "elapsed_time": "0:15:57", "remaining_time": "0:33:31"}
4
  {"current_steps": 31, "total_steps": 93, "eval_loss": 0.8302477598190308, "epoch": 0.9725490196078431, "percentage": 33.33, "elapsed_time": "0:17:16", "remaining_time": "0:34:33"}
5
+ {"current_steps": 40, "total_steps": 93, "loss": 0.8027, "learning_rate": 5e-06, "epoch": 1.2588235294117647, "percentage": 43.01, "elapsed_time": "0:22:36", "remaining_time": "0:29:57"}
6
+ {"current_steps": 50, "total_steps": 93, "loss": 0.7677, "learning_rate": 5e-06, "epoch": 1.572549019607843, "percentage": 53.76, "elapsed_time": "0:27:48", "remaining_time": "0:23:55"}
7
+ {"current_steps": 60, "total_steps": 93, "loss": 0.7548, "learning_rate": 5e-06, "epoch": 1.8862745098039215, "percentage": 64.52, "elapsed_time": "0:33:02", "remaining_time": "0:18:10"}
8
+ {"current_steps": 63, "total_steps": 93, "eval_loss": 0.7995137572288513, "epoch": 1.9803921568627452, "percentage": 67.74, "elapsed_time": "0:35:12", "remaining_time": "0:16:45"}