Hugging Face's logo

mlfoundations-dev
/
seed_math_hendrycks

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
983296b
·
verified ·
1 Parent(s): d5157da

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 sha256:1eae121eaf5feaddb7387e001484a92492817a201b3749d34aca0686066f53dc
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4dd31151ec5ee2850cd8eb1d425fcb21456cdf9886ee671dd2b55a3f6e6335
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:f33a7f5dc7fabec33d17da328dee3021032d7df35a70ca6b2d8e07b0b60d1150
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2066f92ec1e7f5420912cbbbc422985eaeabc309e5a2055b8cbba7800ee6c24c
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:cdabcdf01a30c2a8a8356b599553e0314a89c16e861dec2942391859e1d70864
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff1936cca74ea54f1362389f09fc0929aab47cca38a84e079439071ec1698c6
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:768d604dce0cda37762a3874c9ed815e62e5ac49617c6abccc0a76f76c334ed4
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac67668fca55f5b852fc5938b8e8bb646ab3c6c32155e0afd762ebb8bdaa0d04
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 96, "loss": 0.4298, "lr": 5e-06, "epoch": 0.622568093385214, "percentage": 20.83, "elapsed_time": "0:19:13", "remaining_time": "1:13:04"}
3
  {"current_steps": 30, "total_steps": 96, "loss": 0.3929, "lr": 5e-06, "epoch": 0.933852140077821, "percentage": 31.25, "elapsed_time": "0:28:48", "remaining_time": "1:03:22"}
4
  {"current_steps": 32, "total_steps": 96, "eval_loss": 0.3781737685203552, "epoch": 0.9961089494163424, "percentage": 33.33, "elapsed_time": "0:31:24", "remaining_time": "1:02:48"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 96, "loss": 0.4298, "lr": 5e-06, "epoch": 0.622568093385214, "percentage": 20.83, "elapsed_time": "0:19:13", "remaining_time": "1:13:04"}
3
  {"current_steps": 30, "total_steps": 96, "loss": 0.3929, "lr": 5e-06, "epoch": 0.933852140077821, "percentage": 31.25, "elapsed_time": "0:28:48", "remaining_time": "1:03:22"}
4
  {"current_steps": 32, "total_steps": 96, "eval_loss": 0.3781737685203552, "epoch": 0.9961089494163424, "percentage": 33.33, "elapsed_time": "0:31:24", "remaining_time": "1:02:48"}
5
+ {"current_steps": 40, "total_steps": 96, "loss": 0.3965, "lr": 5e-06, "epoch": 1.245136186770428, "percentage": 41.67, "elapsed_time": "0:40:05", "remaining_time": "0:56:07"}
6
+ {"current_steps": 50, "total_steps": 96, "loss": 0.3502, "lr": 5e-06, "epoch": 1.556420233463035, "percentage": 52.08, "elapsed_time": "0:49:40", "remaining_time": "0:45:41"}
7
+ {"current_steps": 60, "total_steps": 96, "loss": 0.3474, "lr": 5e-06, "epoch": 1.867704280155642, "percentage": 62.5, "elapsed_time": "0:59:15", "remaining_time": "0:35:33"}
8
+ {"current_steps": 64, "total_steps": 96, "eval_loss": 0.3496624529361725, "epoch": 1.9922178988326849, "percentage": 66.67, "elapsed_time": "1:03:53", "remaining_time": "0:31:56"}