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 Community
esfrankel17 commited on
Commit
fd32b92
·
verified ·
1 Parent(s): 734f80d

Training in progress, epoch 2

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 +2 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c43761c22cb57a754ff2fc430a5db796cb51c5b13e8d9a401d592f82a613c8a8
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf038e680714e5427cafdc6c44a438b876f2d1d4aae59a23e526f73f5747a39
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d07e76e75b000c3963cbf0d54cf4d3f310fbed9314cf78a6df13e21001418c5
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36c03b44d82ff203f7dc98b0449ccb1c64d5132f8f7235c8b18305850b8497a
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:241b6fd9d1d921abfb41966efae389465397a8f9fcd9ab0f0ae2c23396514c99
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7872d626a9ea7b993561f9020c8a1de5a75d02cfd80e8d4bea4e72f137a12c
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:bbc1d1ecb47a5ab35ad780572601f40aaa280d5b2640bf5d2357713d6825ec37
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa5af5c9bbc6b8a4a3fb4f2b9ab57c7eb3af1760e1357a3cb396775dd9114f7
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,5 @@
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"}
 
 
 
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"}
6
+ {"current_steps": 36, "total_steps": 36, "eval_loss": 0.4672066271305084, "epoch": 2.8514851485148514, "percentage": 100.0, "elapsed_time": "0:22:25", "remaining_time": "0:00:00"}
7
+ {"current_steps": 36, "total_steps": 36, "epoch": 2.8514851485148514, "percentage": 100.0, "elapsed_time": "0:23:21", "remaining_time": "0:00:00"}