Hugging Face's logo

mlfoundations-dev
/
seed_math_tiger_math

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
7114235
·
verified ·
1 Parent(s): 21cd351

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed564385c4d3ea0815ace9e83e38d3e6ff7e1819a7edfd676e0eb7beca53c660
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b3b61f7c8e755e9e201e8619febda27122d46ed142a82de43ee2009e120ab8
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:b84527c77f5f3531ae1b601417bda031cd26314d0ad1a0935a6e8c91eb904637
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b22710375019297526ee7b7c8e84004a501fd148b0bae343a357c816bb4bba6
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:c6c4a4dc60105f10a29a268529cce469550a791bb1ce3b24367168eb650bdb6d
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5567be831cf9af369329db78f33b11de388c1d787ab8669bc3be5bf64bc38301
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66652ed0c5af86c216875e46dff8512bbdbfc513c20751273983cc66fcb23070
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb5375ebb103d46cd27e466acc25c1c6cb0606e36020513215908e860a9cc2f5
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -7,3 +7,7 @@
7
  {"current_steps": 60, "total_steps": 99, "loss": 0.4395, "lr": 5e-06, "epoch": 1.7785977859778597, "percentage": 60.61, "elapsed_time": "0:59:34", "remaining_time": "0:38:43"}
8
  {"current_steps": 67, "total_steps": 99, "eval_loss": 0.43678900599479675, "epoch": 1.985239852398524, "percentage": 67.68, "elapsed_time": "1:07:06", "remaining_time": "0:32:03"}
9
  {"current_steps": 70, "total_steps": 99, "loss": 0.4374, "lr": 5e-06, "epoch": 2.081180811808118, "percentage": 70.71, "elapsed_time": "1:10:59", "remaining_time": "0:29:24"}
 
 
 
 
 
7
  {"current_steps": 60, "total_steps": 99, "loss": 0.4395, "lr": 5e-06, "epoch": 1.7785977859778597, "percentage": 60.61, "elapsed_time": "0:59:34", "remaining_time": "0:38:43"}
8
  {"current_steps": 67, "total_steps": 99, "eval_loss": 0.43678900599479675, "epoch": 1.985239852398524, "percentage": 67.68, "elapsed_time": "1:07:06", "remaining_time": "0:32:03"}
9
  {"current_steps": 70, "total_steps": 99, "loss": 0.4374, "lr": 5e-06, "epoch": 2.081180811808118, "percentage": 70.71, "elapsed_time": "1:10:59", "remaining_time": "0:29:24"}
10
+ {"current_steps": 80, "total_steps": 99, "loss": 0.4127, "lr": 5e-06, "epoch": 2.376383763837638, "percentage": 80.81, "elapsed_time": "1:20:38", "remaining_time": "0:19:09"}
11
+ {"current_steps": 90, "total_steps": 99, "loss": 0.4063, "lr": 5e-06, "epoch": 2.671586715867159, "percentage": 90.91, "elapsed_time": "1:30:16", "remaining_time": "0:09:01"}
12
+ {"current_steps": 99, "total_steps": 99, "eval_loss": 0.4291580617427826, "epoch": 2.937269372693727, "percentage": 100.0, "elapsed_time": "1:40:47", "remaining_time": "0:00:00"}
13
+ {"current_steps": 99, "total_steps": 99, "epoch": 2.937269372693727, "percentage": 100.0, "elapsed_time": "1:42:02", "remaining_time": "0:00:00"}