Hugging Face's logo

mlfoundations-dev
/
no_pipeline_math_1k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
neginr commited on
Commit
7ebeaf6
·
verified ·
1 Parent(s): 88535b3

Training in progress, epoch 4

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 +10 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7df9762409878c8044e7072461b50d37d303649b323d91e01be7e13280ba10ae
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28260644ec85faa3d2168e5c7a451d94d2611a585c51540bca96e92edeed0118
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19f944ea0557155b81a1ef12abb6aa0fc658a81d7fe3dfb4c77e491c06ff4940
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd2d716379f2e469ab27d94bb5becb77402feb285eb56a1a902451f33bed161b
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e1d2954103ae223378fa80d2312e7c4afb5bfd562de210f020ec4254b45684d
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40b292a8ffb2ea9c2c7e96f152fb10c8759fbd1b160719d2ce824b36acbe0c6
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:195f8f6d2a7f7aa36409ddcfac16dca65da26a55a6449e4540bb0b043483c6a2
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c1415fa1bbe04bb3e776f9afd9ee7d3da8926e72e8bcd68e8e87a76cc3fb31
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -38,3 +38,13 @@
38
  {"current_steps": 38, "total_steps": 70, "loss": 0.2817, "lr": 1.0249306917380731e-05, "epoch": 3.619047619047619, "percentage": 54.29, "elapsed_time": "0:18:23", "remaining_time": "0:15:29"}
39
  {"current_steps": 39, "total_steps": 70, "loss": 0.2455, "lr": 9.750693082619274e-06, "epoch": 3.7142857142857144, "percentage": 55.71, "elapsed_time": "0:18:47", "remaining_time": "0:14:55"}
40
  {"current_steps": 40, "total_steps": 70, "loss": 0.2564, "lr": 9.252699064135759e-06, "epoch": 3.8095238095238093, "percentage": 57.14, "elapsed_time": "0:19:08", "remaining_time": "0:14:21"}
 
 
 
 
 
 
 
 
 
 
 
38
  {"current_steps": 38, "total_steps": 70, "loss": 0.2817, "lr": 1.0249306917380731e-05, "epoch": 3.619047619047619, "percentage": 54.29, "elapsed_time": "0:18:23", "remaining_time": "0:15:29"}
39
  {"current_steps": 39, "total_steps": 70, "loss": 0.2455, "lr": 9.750693082619274e-06, "epoch": 3.7142857142857144, "percentage": 55.71, "elapsed_time": "0:18:47", "remaining_time": "0:14:55"}
40
  {"current_steps": 40, "total_steps": 70, "loss": 0.2564, "lr": 9.252699064135759e-06, "epoch": 3.8095238095238093, "percentage": 57.14, "elapsed_time": "0:19:08", "remaining_time": "0:14:21"}
41
+ {"current_steps": 41, "total_steps": 70, "loss": 0.2483, "lr": 8.756562953525151e-06, "epoch": 3.9047619047619047, "percentage": 58.57, "elapsed_time": "0:19:29", "remaining_time": "0:13:46"}
42
+ {"current_steps": 42, "total_steps": 70, "loss": 0.2364, "lr": 8.263518223330698e-06, "epoch": 4.0, "percentage": 60.0, "elapsed_time": "0:19:39", "remaining_time": "0:13:06"}
43
+ {"current_steps": 43, "total_steps": 70, "loss": 0.2149, "lr": 7.774790660436857e-06, "epoch": 4.095238095238095, "percentage": 61.43, "elapsed_time": "0:21:57", "remaining_time": "0:13:46"}
44
+ {"current_steps": 44, "total_steps": 70, "loss": 0.2378, "lr": 7.291595318569951e-06, "epoch": 4.190476190476191, "percentage": 62.86, "elapsed_time": "0:22:22", "remaining_time": "0:13:13"}
45
+ {"current_steps": 45, "total_steps": 70, "loss": 0.1971, "lr": 6.815133497483157e-06, "epoch": 4.285714285714286, "percentage": 64.29, "elapsed_time": "0:22:42", "remaining_time": "0:12:37"}
46
+ {"current_steps": 46, "total_steps": 70, "loss": 0.2102, "lr": 6.34658975633605e-06, "epoch": 4.380952380952381, "percentage": 65.71, "elapsed_time": "0:22:59", "remaining_time": "0:11:59"}
47
+ {"current_steps": 47, "total_steps": 70, "loss": 0.1968, "lr": 5.887128968693887e-06, "epoch": 4.476190476190476, "percentage": 67.14, "elapsed_time": "0:23:17", "remaining_time": "0:11:23"}
48
+ {"current_steps": 48, "total_steps": 70, "loss": 0.1904, "lr": 5.43789342646837e-06, "epoch": 4.571428571428571, "percentage": 68.57, "elapsed_time": "0:23:39", "remaining_time": "0:10:50"}
49
+ {"current_steps": 49, "total_steps": 70, "loss": 0.1865, "lr": 5.000000000000003e-06, "epoch": 4.666666666666667, "percentage": 70.0, "elapsed_time": "0:24:01", "remaining_time": "0:10:17"}
50
+ {"current_steps": 50, "total_steps": 70, "loss": 0.1748, "lr": 4.5745373613424075e-06, "epoch": 4.761904761904762, "percentage": 71.43, "elapsed_time": "0:24:17", "remaining_time": "0:09:42"}