Hugging Face's logo

mlfoundations-dev
/
b2_math_random_0.3k

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
d508856
·
verified ·
1 Parent(s): b416331

Training in progress, epoch 3

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 +9 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9e5b0b8cceff827ecdd1c921b4b86f4769d060f926879ac27b0f8fc9e61651b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd857594d4af45d45bfc7f5a6b6c9bd851166ba2f36265d5b254904a061213ca
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00b450252a1865d93bb5031d2beeab91933c06ad4bde74dd9360fb18aa16f85a
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca48f74ca194dcfe8e4aef7ea62a7458ba40932a4e014c1f92f240df0d41be2
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10122419481832c896bfd95ceab10bcea849812a733804fff77a9d6fbdc9690c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfebbe76012986422bce526746cad1f1c72eb67f7516faa2e307de839724de88
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07f86ae8e417d3de15615cd98a4d81a9688aaaac65a5500a12f07705e2ff6e1b
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f16258df7f537f6df03df53b3bfa2d1d8b5927baddd1ba16de508460fc46258b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -35,3 +35,12 @@
35
  {"current_steps": 35, "total_steps": 117, "loss": 0.3374, "lr": 8.862084796122998e-06, "epoch": 3.6582278481012658, "percentage": 29.91, "elapsed_time": "0:15:23", "remaining_time": "0:36:03"}
36
  {"current_steps": 36, "total_steps": 117, "loss": 0.2619, "lr": 8.765357330018056e-06, "epoch": 3.759493670886076, "percentage": 30.77, "elapsed_time": "0:15:39", "remaining_time": "0:35:14"}
37
  {"current_steps": 37, "total_steps": 117, "loss": 0.2689, "lr": 8.665259359149132e-06, "epoch": 3.8607594936708862, "percentage": 31.62, "elapsed_time": "0:15:52", "remaining_time": "0:34:19"}
 
 
 
 
 
 
 
 
 
 
35
  {"current_steps": 35, "total_steps": 117, "loss": 0.3374, "lr": 8.862084796122998e-06, "epoch": 3.6582278481012658, "percentage": 29.91, "elapsed_time": "0:15:23", "remaining_time": "0:36:03"}
36
  {"current_steps": 36, "total_steps": 117, "loss": 0.2619, "lr": 8.765357330018056e-06, "epoch": 3.759493670886076, "percentage": 30.77, "elapsed_time": "0:15:39", "remaining_time": "0:35:14"}
37
  {"current_steps": 37, "total_steps": 117, "loss": 0.2689, "lr": 8.665259359149132e-06, "epoch": 3.8607594936708862, "percentage": 31.62, "elapsed_time": "0:15:52", "remaining_time": "0:34:19"}
38
+ {"current_steps": 38, "total_steps": 117, "loss": 0.3241, "lr": 8.561880484756726e-06, "epoch": 3.962025316455696, "percentage": 32.48, "elapsed_time": "0:16:14", "remaining_time": "0:33:46"}
39
+ {"current_steps": 39, "total_steps": 117, "loss": 0.2336, "lr": 8.455313244934324e-06, "epoch": 4.10126582278481, "percentage": 33.33, "elapsed_time": "0:17:27", "remaining_time": "0:34:54"}
40
+ {"current_steps": 40, "total_steps": 117, "loss": 0.2686, "lr": 8.345653031794292e-06, "epoch": 4.2025316455696204, "percentage": 34.19, "elapsed_time": "0:17:56", "remaining_time": "0:34:32"}
41
+ {"current_steps": 41, "total_steps": 117, "loss": 0.2302, "lr": 8.232998006078998e-06, "epoch": 4.30379746835443, "percentage": 35.04, "elapsed_time": "0:18:12", "remaining_time": "0:33:44"}
42
+ {"current_steps": 42, "total_steps": 117, "loss": 0.2307, "lr": 8.117449009293668e-06, "epoch": 4.405063291139241, "percentage": 35.9, "elapsed_time": "0:18:32", "remaining_time": "0:33:06"}
43
+ {"current_steps": 43, "total_steps": 117, "loss": 0.2473, "lr": 7.99910947343957e-06, "epoch": 4.506329113924051, "percentage": 36.75, "elapsed_time": "0:19:02", "remaining_time": "0:32:46"}
44
+ {"current_steps": 44, "total_steps": 117, "loss": 0.1837, "lr": 7.87808532842837e-06, "epoch": 4.6075949367088604, "percentage": 37.61, "elapsed_time": "0:19:17", "remaining_time": "0:32:00"}
45
+ {"current_steps": 45, "total_steps": 117, "loss": 0.2433, "lr": 7.754484907260513e-06, "epoch": 4.708860759493671, "percentage": 38.46, "elapsed_time": "0:19:41", "remaining_time": "0:31:30"}
46
+ {"current_steps": 46, "total_steps": 117, "loss": 0.226, "lr": 7.628418849052523e-06, "epoch": 4.810126582278481, "percentage": 39.32, "elapsed_time": "0:20:03", "remaining_time": "0:30:57"}