Hugging Face's logo

mlfoundations-dev
/
seed_math_tiger_lab_math

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
35776ca
·
verified ·
1 Parent(s): 4ef9006

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:f92b30d78af28804de10af929b0d8acf2644d0676fabf714741dc8b777b2c7a7
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83cd5c11472ba667e05df04a9156d140c64651834a131f5eec951960f66972c4
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71a37d7f53fb0a34e8624c9f9520f22380a184b17874d24c2f1cacc7ca1590ae
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11ea2d8a5a391396b71e7c11fb659f1a15ac98a9ab62d99396f0ae66a4298150
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:774698f9e35ed0f4b7b1d1591eb4e5e45bc533e0c547abc821c3ce42461141ef
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce074b9d8ea905c3006910a2c16a3f51a1b7086ebec96daa27980777b2f4d0b
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7796d457f83068b1d260904207dec7fac1688f384fa30ea0ce11af2d84520cf0
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba7b97d7a8f35e469a36249c715fc66fd6289da7f15c3838ab29a05b32fc3b2
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,7 @@
1
  {"current_steps": 10, "total_steps": 78, "loss": 0.6611, "lr": 5e-06, "epoch": 0.3827751196172249, "percentage": 12.82, "elapsed_time": "0:09:38", "remaining_time": "1:05:35"}
2
  {"current_steps": 20, "total_steps": 78, "loss": 0.5553, "lr": 5e-06, "epoch": 0.7655502392344498, "percentage": 25.64, "elapsed_time": "0:19:11", "remaining_time": "0:55:40"}
3
  {"current_steps": 26, "total_steps": 78, "eval_loss": 0.49977537989616394, "epoch": 0.9952153110047847, "percentage": 33.33, "elapsed_time": "0:25:29", "remaining_time": "0:50:59"}
 
 
 
 
 
1
  {"current_steps": 10, "total_steps": 78, "loss": 0.6611, "lr": 5e-06, "epoch": 0.3827751196172249, "percentage": 12.82, "elapsed_time": "0:09:38", "remaining_time": "1:05:35"}
2
  {"current_steps": 20, "total_steps": 78, "loss": 0.5553, "lr": 5e-06, "epoch": 0.7655502392344498, "percentage": 25.64, "elapsed_time": "0:19:11", "remaining_time": "0:55:40"}
3
  {"current_steps": 26, "total_steps": 78, "eval_loss": 0.49977537989616394, "epoch": 0.9952153110047847, "percentage": 33.33, "elapsed_time": "0:25:29", "remaining_time": "0:50:59"}
4
+ {"current_steps": 30, "total_steps": 78, "loss": 0.558, "lr": 5e-06, "epoch": 1.1483253588516746, "percentage": 38.46, "elapsed_time": "0:30:20", "remaining_time": "0:48:32"}
5
+ {"current_steps": 40, "total_steps": 78, "loss": 0.4847, "lr": 5e-06, "epoch": 1.5311004784688995, "percentage": 51.28, "elapsed_time": "0:39:54", "remaining_time": "0:37:54"}
6
+ {"current_steps": 50, "total_steps": 78, "loss": 0.4678, "lr": 5e-06, "epoch": 1.9138755980861244, "percentage": 64.1, "elapsed_time": "0:49:27", "remaining_time": "0:27:42"}
7
+ {"current_steps": 52, "total_steps": 78, "eval_loss": 0.46811407804489136, "epoch": 1.9904306220095693, "percentage": 66.67, "elapsed_time": "0:52:02", "remaining_time": "0:26:01"}