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
ef391c5
•
1 Parent(s): ae9846b

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 +12 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76f9d1b113ac6306fe1f7cff1e7eaf0cd199642d3456726c7de30b843997c500
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57aba10ef0b3eaa28c26c3ec31ae9b3d1826d37b6f3bbcc5015e0a8e17b7b0b1
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:ea75547d43f74d420897b2e70f75133c5f1f1fee187bb5277213be1dd229c0dc
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30cc67455e9fee874f37ca48d4018f048dde2f96a569b945fedd6d68472d2a1c
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95fc91e1dd89cc48d865d81c6a14cc8b9837fe63e9b50c160d64c10f3b427bde
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a0bff790786b2ac0aae7110bf807c0ac78615b8027c5c11e5e243927615a243
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:ecf865bbbd3d1e6d4abb3b5b23ac05fdf477c81c145ccc082258c0e7499527eb
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f21091a0b3e0e38a6d2fab77470ab5c8b4bed638b7474a48a3bb8c625c88b5a
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -22,3 +22,15 @@
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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
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"}
25
+ {"current_steps": 230, "total_steps": 321, "loss": 0.5179, "learning_rate": 5e-06, "epoch": 2.142025611175786, "percentage": 71.65, "elapsed_time": "2:02:46", "remaining_time": "0:48:34"}
26
+ {"current_steps": 240, "total_steps": 321, "loss": 0.5178, "learning_rate": 5e-06, "epoch": 2.2351571594877764, "percentage": 74.77, "elapsed_time": "2:07:53", "remaining_time": "0:43:09"}
27
+ {"current_steps": 250, "total_steps": 321, "loss": 0.513, "learning_rate": 5e-06, "epoch": 2.328288707799767, "percentage": 77.88, "elapsed_time": "2:13:01", "remaining_time": "0:37:46"}
28
+ {"current_steps": 260, "total_steps": 321, "loss": 0.5137, "learning_rate": 5e-06, "epoch": 2.421420256111758, "percentage": 81.0, "elapsed_time": "2:18:07", "remaining_time": "0:32:24"}
29
+ {"current_steps": 270, "total_steps": 321, "loss": 0.5263, "learning_rate": 5e-06, "epoch": 2.5145518044237485, "percentage": 84.11, "elapsed_time": "2:23:14", "remaining_time": "0:27:03"}
30
+ {"current_steps": 280, "total_steps": 321, "loss": 0.5201, "learning_rate": 5e-06, "epoch": 2.607683352735739, "percentage": 87.23, "elapsed_time": "2:28:23", "remaining_time": "0:21:43"}
31
+ {"current_steps": 290, "total_steps": 321, "loss": 0.5181, "learning_rate": 5e-06, "epoch": 2.70081490104773, "percentage": 90.34, "elapsed_time": "2:33:32", "remaining_time": "0:16:24"}
32
+ {"current_steps": 300, "total_steps": 321, "loss": 0.5197, "learning_rate": 5e-06, "epoch": 2.7939464493597206, "percentage": 93.46, "elapsed_time": "2:38:39", "remaining_time": "0:11:06"}
33
+ {"current_steps": 310, "total_steps": 321, "loss": 0.5274, "learning_rate": 5e-06, "epoch": 2.887077997671711, "percentage": 96.57, "elapsed_time": "2:43:49", "remaining_time": "0:05:48"}
34
+ {"current_steps": 320, "total_steps": 321, "loss": 0.5134, "learning_rate": 5e-06, "epoch": 2.980209545983702, "percentage": 99.69, "elapsed_time": "2:48:58", "remaining_time": "0:00:31"}
35
+ {"current_steps": 321, "total_steps": 321, "eval_loss": 0.6689090132713318, "epoch": 2.9895227008149012, "percentage": 100.0, "elapsed_time": "2:51:46", "remaining_time": "0:00:00"}
36
+ {"current_steps": 321, "total_steps": 321, "epoch": 2.9895227008149012, "percentage": 100.0, "elapsed_time": "2:52:41", "remaining_time": "0:00:00"}