Hugging Face's logo

mlfoundations-dev
/
stackexchange_health

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
37407ea
·
verified ·
1 Parent(s): ad1acde

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:aefb2d01ab83e0d11464d765ee27d539781435e7c5ea3bcc269679a160f61fd8
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05f2975f98936eb28e0ec246099ae5fef451e68269028824d6e52d8e7475ce61
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45a1fb5fcc097dfcc4a8a30a772a3b7d86baab0417da53877afc1fec4f726273
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81cfd71374e3f44990cd3a8c20be766c7005ca6bf68874b58eb543b2cadd3526
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:d474a9c6c6e700e99eddd4dee25048ab7253578c3a1163c787a3d4eae7e20508
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec1d036f03083a400de3ae0bd231e56db675340c9d6f51714054d9ffe67b0cb9
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dcdbf06d9d47095e0d563058164609b2de5fabb1a2d38fefacbf87645919dcb
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d94f78048f6b003d29b95b744e00d13329fed85c6aa771f6e87ba06e4baf34fe
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 8, "total_steps": 24, "eval_loss": 1.0346832275390625, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:04:28", "remaining_time": "0:08:56"}
2
  {"current_steps": 10, "total_steps": 24, "loss": 1.088, "lr": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:06:42", "remaining_time": "0:09:23"}
3
  {"current_steps": 16, "total_steps": 24, "eval_loss": 0.9845033884048462, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:09:59", "remaining_time": "0:04:59"}
 
 
 
 
1
  {"current_steps": 8, "total_steps": 24, "eval_loss": 1.0346832275390625, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:04:28", "remaining_time": "0:08:56"}
2
  {"current_steps": 10, "total_steps": 24, "loss": 1.088, "lr": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:06:42", "remaining_time": "0:09:23"}
3
  {"current_steps": 16, "total_steps": 24, "eval_loss": 0.9845033884048462, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:09:59", "remaining_time": "0:04:59"}
4
+ {"current_steps": 20, "total_steps": 24, "loss": 0.9526, "lr": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:13:23", "remaining_time": "0:02:40"}
5
+ {"current_steps": 24, "total_steps": 24, "eval_loss": 0.9666845798492432, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:16:55", "remaining_time": "0:00:00"}
6
+ {"current_steps": 24, "total_steps": 24, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:18:08", "remaining_time": "0:00:00"}