Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_slim_orca_550k

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
ae9846b
•
1 Parent(s): 3119434

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 +12 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c429eb4e4d229ed71830e461c02e82792a51b7620e3b63574ac52b80e6e3f80
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76f9d1b113ac6306fe1f7cff1e7eaf0cd199642d3456726c7de30b843997c500
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:548f646ed4825e6a7b265d8ac5eeea58feed1906b9fd01f2e8cb2eaa9e825d79
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea75547d43f74d420897b2e70f75133c5f1f1fee187bb5277213be1dd229c0dc
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06787f9e7f0ed5604b3156a5c33af436805f11e7ba9c06925a1458dae19d487a
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95fc91e1dd89cc48d865d81c6a14cc8b9837fe63e9b50c160d64c10f3b427bde
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11828c49060608387dc3edf48f367c006a7acd0a78ba9751e317e8ac8b466a15
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecf865bbbd3d1e6d4abb3b5b23ac05fdf477c81c145ccc082258c0e7499527eb
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -10,3 +10,15 @@
10
  {"current_steps": 100, "total_steps": 321, "loss": 0.6853, "learning_rate": 5e-06, "epoch": 0.9313154831199069, "percentage": 31.15, "elapsed_time": "0:51:26", "remaining_time": "1:53:41"}
11
  {"current_steps": 107, "total_steps": 321, "eval_loss": 0.6684155464172363, "epoch": 0.9965075669383003, "percentage": 33.33, "elapsed_time": "0:56:25", "remaining_time": "1:52:50"}
12
  {"current_steps": 110, "total_steps": 321, "loss": 0.7062, "learning_rate": 5e-06, "epoch": 1.0244470314318976, "percentage": 34.27, "elapsed_time": "0:58:46", "remaining_time": "1:52:43"}
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  {"current_steps": 100, "total_steps": 321, "loss": 0.6853, "learning_rate": 5e-06, "epoch": 0.9313154831199069, "percentage": 31.15, "elapsed_time": "0:51:26", "remaining_time": "1:53:41"}
11
  {"current_steps": 107, "total_steps": 321, "eval_loss": 0.6684155464172363, "epoch": 0.9965075669383003, "percentage": 33.33, "elapsed_time": "0:56:25", "remaining_time": "1:52:50"}
12
  {"current_steps": 110, "total_steps": 321, "loss": 0.7062, "learning_rate": 5e-06, "epoch": 1.0244470314318976, "percentage": 34.27, "elapsed_time": "0:58:46", "remaining_time": "1:52:43"}
13
+ {"current_steps": 120, "total_steps": 321, "loss": 0.6098, "learning_rate": 5e-06, "epoch": 1.1175785797438882, "percentage": 37.38, "elapsed_time": "1:03:54", "remaining_time": "1:47:03"}
14
+ {"current_steps": 130, "total_steps": 321, "loss": 0.6019, "learning_rate": 5e-06, "epoch": 1.210710128055879, "percentage": 40.5, "elapsed_time": "1:09:01", "remaining_time": "1:41:24"}
15
+ {"current_steps": 140, "total_steps": 321, "loss": 0.6043, "learning_rate": 5e-06, "epoch": 1.3038416763678695, "percentage": 43.61, "elapsed_time": "1:14:10", "remaining_time": "1:35:53"}
16
+ {"current_steps": 150, "total_steps": 321, "loss": 0.6023, "learning_rate": 5e-06, "epoch": 1.3969732246798603, "percentage": 46.73, "elapsed_time": "1:19:18", "remaining_time": "1:30:24"}
17
+ {"current_steps": 160, "total_steps": 321, "loss": 0.6021, "learning_rate": 5e-06, "epoch": 1.490104772991851, "percentage": 49.84, "elapsed_time": "1:24:27", "remaining_time": "1:24:59"}
18
+ {"current_steps": 170, "total_steps": 321, "loss": 0.6002, "learning_rate": 5e-06, "epoch": 1.5832363213038416, "percentage": 52.96, "elapsed_time": "1:29:34", "remaining_time": "1:19:33"}
19
+ {"current_steps": 180, "total_steps": 321, "loss": 0.5935, "learning_rate": 5e-06, "epoch": 1.6763678696158324, "percentage": 56.07, "elapsed_time": "1:34:41", "remaining_time": "1:14:10"}
20
+ {"current_steps": 190, "total_steps": 321, "loss": 0.589, "learning_rate": 5e-06, "epoch": 1.7694994179278232, "percentage": 59.19, "elapsed_time": "1:39:50", "remaining_time": "1:08:50"}
21
+ {"current_steps": 200, "total_steps": 321, "loss": 0.5954, "learning_rate": 5e-06, "epoch": 1.8626309662398137, "percentage": 62.31, "elapsed_time": "1:44:57", "remaining_time": "1:03:30"}
22
+ {"current_steps": 210, "total_steps": 321, "loss": 0.591, "learning_rate": 5e-06, "epoch": 1.9557625145518043, "percentage": 65.42, "elapsed_time": "1:50:05", "remaining_time": "0:58:11"}
23
+ {"current_steps": 214, "total_steps": 321, "eval_loss": 0.6565061807632446, "epoch": 1.9930151338766007, "percentage": 66.67, "elapsed_time": "1:53:44", "remaining_time": "0:56:52"}
24
+ {"current_steps": 220, "total_steps": 321, "loss": 0.5986, "learning_rate": 5e-06, "epoch": 2.0488940628637953, "percentage": 68.54, "elapsed_time": "1:57:39", "remaining_time": "0:54:00"}