Hugging Face's logo

mlfoundations-dev
/
oh_v1-2_only_metamath

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
esfrankel17 commited on
Commit
e4252d7
•
1 Parent(s): 0b2e1b3

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 sha256:25e6beebb48bab38c8c57bab993ca9143dca53877cd5a32bed0e2f3e7fce5fac
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6067076d9880bb75a3428014a8645c2a17b076d361e627304677bb125e2564f
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:000d9c2d7c744680fd7f6e2b7db26ec49d3a1b73a2a10ad2a9a28799655d745a
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a1ad244bc93038e259ad23ca9c2944218aace1be4a97ed9e66dd520debadf83
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4891bd4d3359360d4dc6d79ce9cde3b769d26d3794f96d96a75124877c187540
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b7268272de5e82b6be9d4a983f10df6a20d15227ba993f02dd4ee8187e0fab
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46468ec99d03e88fc1356d8884610dca7cf538161c787bf244ea1086775213ad
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:323469e33100288b46f62d318444ef7eb73250447e2ed2742fab7ed320ae627f
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,6 @@
3
  {"current_steps": 20, "total_steps": 45, "loss": 0.5522, "learning_rate": 5e-06, "epoch": 1.3089430894308944, "percentage": 44.44, "elapsed_time": "0:11:50", "remaining_time": "0:14:48"}
4
  {"current_steps": 30, "total_steps": 45, "loss": 0.4763, "learning_rate": 5e-06, "epoch": 1.959349593495935, "percentage": 66.67, "elapsed_time": "0:17:09", "remaining_time": "0:08:34"}
5
  {"current_steps": 30, "total_steps": 45, "eval_loss": 0.4720878303050995, "epoch": 1.959349593495935, "percentage": 66.67, "elapsed_time": "0:17:35", "remaining_time": "0:08:47"}
 
 
 
 
3
  {"current_steps": 20, "total_steps": 45, "loss": 0.5522, "learning_rate": 5e-06, "epoch": 1.3089430894308944, "percentage": 44.44, "elapsed_time": "0:11:50", "remaining_time": "0:14:48"}
4
  {"current_steps": 30, "total_steps": 45, "loss": 0.4763, "learning_rate": 5e-06, "epoch": 1.959349593495935, "percentage": 66.67, "elapsed_time": "0:17:09", "remaining_time": "0:08:34"}
5
  {"current_steps": 30, "total_steps": 45, "eval_loss": 0.4720878303050995, "epoch": 1.959349593495935, "percentage": 66.67, "elapsed_time": "0:17:35", "remaining_time": "0:08:47"}
6
+ {"current_steps": 40, "total_steps": 45, "loss": 0.4862, "learning_rate": 5e-06, "epoch": 2.617886178861789, "percentage": 88.89, "elapsed_time": "0:23:56", "remaining_time": "0:02:59"}
7
+ {"current_steps": 45, "total_steps": 45, "eval_loss": 0.4539353549480438, "epoch": 2.943089430894309, "percentage": 100.0, "elapsed_time": "0:27:49", "remaining_time": "0:00:00"}
8
+ {"current_steps": 45, "total_steps": 45, "epoch": 2.943089430894309, "percentage": 100.0, "elapsed_time": "0:28:40", "remaining_time": "0:00:00"}