Hugging Face's logo

mlfoundations-dev
/
seed_math_allenai_math

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
d29ffde
·
verified ·
1 Parent(s): b830210

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbfd47bba13145d37b484d764588bd3e16cb1529f2e3bca34fbf7c33d37ce688
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b5a2496b9793262a61ac233059674c306fabb7c41601f6bf02b8d861c6eeb5
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:e5b6141f4a633cf4f59f58c05ce0d96e99da21a4774d0aba237471d345868427
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe512bc0461b339eb9a67b93806006373d632b046e4f8ed1bb59a3fde4e2b2b4
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8baa853a64832c0638f69d63b4607d8e51352a99b103987fab30078e3dbefef5
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4426154a69a030d786150c598594d0b2fcd53b416fc03beffd3716a9d5ae9999
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8818194fede976b42cfcac33bcfbce42246b677f67dccea86c1e533056429d73
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c47ff0bea024d7b3a9a43fffd381a65fe8961843d4bbdf3506a1acd58a3c3d
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,6 @@
2
  {"current_steps": 13, "total_steps": 39, "eval_loss": 0.42128339409828186, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:14:38", "remaining_time": "0:29:16"}
3
  {"current_steps": 20, "total_steps": 39, "loss": 0.4266, "lr": 5e-06, "epoch": 1.5384615384615383, "percentage": 51.28, "elapsed_time": "0:23:24", "remaining_time": "0:22:14"}
4
  {"current_steps": 26, "total_steps": 39, "eval_loss": 0.3593507707118988, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:30:15", "remaining_time": "0:15:07"}
 
 
 
 
2
  {"current_steps": 13, "total_steps": 39, "eval_loss": 0.42128339409828186, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:14:38", "remaining_time": "0:29:16"}
3
  {"current_steps": 20, "total_steps": 39, "loss": 0.4266, "lr": 5e-06, "epoch": 1.5384615384615383, "percentage": 51.28, "elapsed_time": "0:23:24", "remaining_time": "0:22:14"}
4
  {"current_steps": 26, "total_steps": 39, "eval_loss": 0.3593507707118988, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:30:15", "remaining_time": "0:15:07"}
5
+ {"current_steps": 30, "total_steps": 39, "loss": 0.3759, "lr": 5e-06, "epoch": 2.3076923076923075, "percentage": 76.92, "elapsed_time": "0:35:47", "remaining_time": "0:10:44"}
6
+ {"current_steps": 39, "total_steps": 39, "eval_loss": 0.33126652240753174, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:47:10", "remaining_time": "0:00:00"}
7
+ {"current_steps": 39, "total_steps": 39, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:48:24", "remaining_time": "0:00:00"}