Hugging Face's logo

mlfoundations-dev
/
b2_math_random_1k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
ryanmarten commited on
Commit
d6a3e40
·
verified ·
1 Parent(s): 90cdc44

Training in progress, epoch 6

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 sha256:188189b2039c1fdadd95494fd6b160d1b99ff049e1c8aaedb80cdc22bb0d14e1
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ebe5253cc5669709c2736dcbd1fae430d1664ea99a647bb6a31c3059f3883a
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71e4c837c479906e5319e9da1cba8528c9b95b6e7fb58491832f66649e78432c
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc9d75d8bf32e9aad689bdf2ed1257507d43dee609cb0d8ddd482b29eccb877a
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf26346e257d235fb761150db580c9bc434bfded46cb7b67063bc9adb4119b14
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713dc17fa47f7098494de402aa0c6e0a9d0c34873364094b2e8a029d1ea049b3
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d00576041ba1ff80d2b45e09261e1a06c0c1f6be48567d91e638b7b291bc65c8
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c943e920323a73c723668711077f0f01eac89ee82acb1c133a930b49cfa86b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -74,3 +74,6 @@
74
  {"current_steps": 66, "total_steps": 70, "loss": 0.1752, "lr": 1.9827512151456175e-07, "epoch": 6.336, "percentage": 94.29, "elapsed_time": "1:08:11", "remaining_time": "0:04:07"}
75
  {"current_steps": 67, "total_steps": 70, "loss": 0.1824, "lr": 1.1169173774871478e-07, "epoch": 6.432, "percentage": 95.71, "elapsed_time": "1:09:05", "remaining_time": "0:03:05"}
76
  {"current_steps": 68, "total_steps": 70, "loss": 0.1875, "lr": 4.9692246345985905e-08, "epoch": 6.5280000000000005, "percentage": 97.14, "elapsed_time": "1:10:12", "remaining_time": "0:02:03"}
 
 
 
 
74
  {"current_steps": 66, "total_steps": 70, "loss": 0.1752, "lr": 1.9827512151456175e-07, "epoch": 6.336, "percentage": 94.29, "elapsed_time": "1:08:11", "remaining_time": "0:04:07"}
75
  {"current_steps": 67, "total_steps": 70, "loss": 0.1824, "lr": 1.1169173774871478e-07, "epoch": 6.432, "percentage": 95.71, "elapsed_time": "1:09:05", "remaining_time": "0:03:05"}
76
  {"current_steps": 68, "total_steps": 70, "loss": 0.1875, "lr": 4.9692246345985905e-08, "epoch": 6.5280000000000005, "percentage": 97.14, "elapsed_time": "1:10:12", "remaining_time": "0:02:03"}
77
+ {"current_steps": 69, "total_steps": 70, "loss": 0.1734, "lr": 1.2430787810776556e-08, "epoch": 6.624, "percentage": 98.57, "elapsed_time": "1:11:07", "remaining_time": "0:01:01"}
78
+ {"current_steps": 70, "total_steps": 70, "loss": 0.1708, "lr": 0.0, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "1:12:11", "remaining_time": "0:00:00"}
79
+ {"current_steps": 70, "total_steps": 70, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "1:14:12", "remaining_time": "0:00:00"}