Hugging Face's logo

mlfoundations-dev
/
stackexchange_parenting

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
64d089b
·
verified ·
1 Parent(s): 3d8a26c

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bab302b9b7491a830b87efcf7982b68f3ad0bc1d9ea2e145e47687a046bd95f6
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7eed145ab81aee983cf736774b464b0e064114f1552a8e2b69c4f7fc46114f
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b414e9fd95ef2eb05c1cbfd003e9ff28e26e1c0a4d6f911a583e8d1600e2c41
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09db305b1406b3eb8361900bdac92f2cca92831cf6ed6f7fb088ffe294f37c17
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fb3db0eada4fa094048724d833d2016df74bb2d2ea147db31cefff169e69722
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2555567f03757165752020cfb88c034609ab12124095ab0e912d73ccaaea7b07
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:a1f6295a6756bff4a747e15ab8ef9ee7c01fe6baebcfc3ac22472688aed4d1c6
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7529c2b70f47e0793e27b44ef69c308b9c4efa18d512289f98c10174652184
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 54, "loss": 1.1508, "lr": 5e-06, "epoch": 0.5298013245033113, "percentage": 18.52, "elapsed_time": "0:05:26", "remaining_time": "0:23:54"}
2
  {"current_steps": 18, "total_steps": 54, "eval_loss": 1.0110349655151367, "epoch": 0.9536423841059603, "percentage": 33.33, "elapsed_time": "0:10:13", "remaining_time": "0:20:26"}
3
  {"current_steps": 20, "total_steps": 54, "loss": 1.0692, "lr": 5e-06, "epoch": 1.0728476821192052, "percentage": 37.04, "elapsed_time": "0:12:11", "remaining_time": "0:20:43"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 54, "loss": 1.1508, "lr": 5e-06, "epoch": 0.5298013245033113, "percentage": 18.52, "elapsed_time": "0:05:26", "remaining_time": "0:23:54"}
2
  {"current_steps": 18, "total_steps": 54, "eval_loss": 1.0110349655151367, "epoch": 0.9536423841059603, "percentage": 33.33, "elapsed_time": "0:10:13", "remaining_time": "0:20:26"}
3
  {"current_steps": 20, "total_steps": 54, "loss": 1.0692, "lr": 5e-06, "epoch": 1.0728476821192052, "percentage": 37.04, "elapsed_time": "0:12:11", "remaining_time": "0:20:43"}
4
+ {"current_steps": 30, "total_steps": 54, "loss": 0.9634, "lr": 5e-06, "epoch": 1.6026490066225165, "percentage": 55.56, "elapsed_time": "0:17:29", "remaining_time": "0:13:59"}
5
+ {"current_steps": 37, "total_steps": 54, "eval_loss": 0.9528446197509766, "epoch": 1.9735099337748343, "percentage": 68.52, "elapsed_time": "0:21:26", "remaining_time": "0:09:51"}
6
+ {"current_steps": 40, "total_steps": 54, "loss": 0.9627, "lr": 5e-06, "epoch": 2.1456953642384105, "percentage": 74.07, "elapsed_time": "0:24:10", "remaining_time": "0:08:27"}