Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_airoboros

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
0f839eb
•
1 Parent(s): 0b82567

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:064843fdd202f923a17d6b23dfdd83bf1704b4dc40476dd0d973421c42ea4af6
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d4486ead5e47a9a114029b12ff4543c7eeb81b2890e52b677d4b6d9e30c196
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05e9af8806620d65be64b2c9555838a129c7b0310fcf44bedf667dd258c43fb2
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa5168e17cfd0a249022e2854175aaec2a8ded94346662ba672f86bc8a43ef22
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35bbf4a8a2627505f83d512bbeb6a96732e3e80aea4764c0e9a24df35cbc620e
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af0e268c68b4b2102ff5582d74e1bdcffbb0f40b05972e278fe4b12ce53d505
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5593fa10ba8c2eaf4349e7420e4995d40981fc3177768c1e886ba8a4a2369e72
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:541b951dd05c81d8e45884d423786498305ea9b26047a6418558bf60a0ac0fd5
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,6 @@
3
  {"current_steps": 20, "total_steps": 48, "loss": 0.7853, "learning_rate": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:11:47", "remaining_time": "0:16:30"}
4
  {"current_steps": 30, "total_steps": 48, "loss": 0.7293, "learning_rate": 5e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "0:17:07", "remaining_time": "0:10:16"}
5
  {"current_steps": 32, "total_steps": 48, "eval_loss": 0.7811707258224487, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:18:22", "remaining_time": "0:09:11"}
 
 
 
 
3
  {"current_steps": 20, "total_steps": 48, "loss": 0.7853, "learning_rate": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:11:47", "remaining_time": "0:16:30"}
4
  {"current_steps": 30, "total_steps": 48, "loss": 0.7293, "learning_rate": 5e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "0:17:07", "remaining_time": "0:10:16"}
5
  {"current_steps": 32, "total_steps": 48, "eval_loss": 0.7811707258224487, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:18:22", "remaining_time": "0:09:11"}
6
+ {"current_steps": 40, "total_steps": 48, "loss": 0.677, "learning_rate": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:23:31", "remaining_time": "0:04:42"}
7
+ {"current_steps": 48, "total_steps": 48, "eval_loss": 0.765191376209259, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:28:53", "remaining_time": "0:00:00"}
8
+ {"current_steps": 48, "total_steps": 48, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:29:50", "remaining_time": "0:00:00"}