Hugging Face's logo

mlfoundations-dev
/
stackexchange_ell

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
5376900
·
verified ·
1 Parent(s): d6a7716

Training in progress, epoch 2

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 sha256:7875754ed6ad7abce28c184971f31584bbd4d515f1cbe0bc7a5dd6a189446dcd
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f8b15b2b6ffa18688438a4014cbd753fed5e3d74eb0da6a3bd56c223ab9163
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:bea4f072e1bfa407e5aa5cb4a77231390f7bf8fcc1aa3d2dbcebcf20f75a38bf
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17aa27fdc228739695fdf3fa1aa93be7d6510346f678e27b4956b8d097e8094d
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:e86902fe08d71aa52717997c49395a7fc0fbaa8c9e7bea22779ea51d362bb7ab
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca68e1d0836955bdebbb6cb96dde39e40cb5a010526a05984f090c0a8ab4a3d5
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a789d2bb83b386aa74fc60fdea48f3fb2d12b0c55263e68295711309ebfc8b7
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a1ce397d7f763640433408bfd7212512b77e22b8af5ed757a70cdb1f8336a7
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,6 @@
3
  {"current_steps": 20, "total_steps": 42, "loss": 0.9836, "lr": 5e-06, "epoch": 1.376068376068376, "percentage": 47.62, "elapsed_time": "0:12:10", "remaining_time": "0:13:23"}
4
  {"current_steps": 29, "total_steps": 42, "eval_loss": 0.8846853971481323, "epoch": 1.9914529914529915, "percentage": 69.05, "elapsed_time": "0:17:04", "remaining_time": "0:07:39"}
5
  {"current_steps": 30, "total_steps": 42, "loss": 0.9321, "lr": 5e-06, "epoch": 2.0683760683760686, "percentage": 71.43, "elapsed_time": "0:18:52", "remaining_time": "0:07:32"}
 
 
 
 
3
  {"current_steps": 20, "total_steps": 42, "loss": 0.9836, "lr": 5e-06, "epoch": 1.376068376068376, "percentage": 47.62, "elapsed_time": "0:12:10", "remaining_time": "0:13:23"}
4
  {"current_steps": 29, "total_steps": 42, "eval_loss": 0.8846853971481323, "epoch": 1.9914529914529915, "percentage": 69.05, "elapsed_time": "0:17:04", "remaining_time": "0:07:39"}
5
  {"current_steps": 30, "total_steps": 42, "loss": 0.9321, "lr": 5e-06, "epoch": 2.0683760683760686, "percentage": 71.43, "elapsed_time": "0:18:52", "remaining_time": "0:07:32"}
6
+ {"current_steps": 40, "total_steps": 42, "loss": 0.824, "lr": 5e-06, "epoch": 2.752136752136752, "percentage": 95.24, "elapsed_time": "0:24:08", "remaining_time": "0:01:12"}
7
+ {"current_steps": 42, "total_steps": 42, "eval_loss": 0.8475070595741272, "epoch": 2.888888888888889, "percentage": 100.0, "elapsed_time": "0:26:40", "remaining_time": "0:00:00"}
8
+ {"current_steps": 42, "total_steps": 42, "epoch": 2.888888888888889, "percentage": 100.0, "elapsed_time": "0:27:55", "remaining_time": "0:00:00"}