Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_metamath_40k

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
edb2612
·
verified ·
1 Parent(s): 272fc5e

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 sha256:90d55bf7af01f1578948925e98359218c72b29643801e8c5c07b8119099e7328
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48d659e5f0032cd09709799dde307878c8f90e7ffc8ae948fe722a905ba9df8
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:362ef6362626c236134434502d1d8de8a606bd4af857c96460f23c416008c2d8
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816b656c804c407faae45a8e29c140be5700decfac9a61811443049a84c62d95
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:992820d125a299a41788ee7bea10f78ac2e2b4952a3997fe224bd56ed5796497
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f36ff833a600bf5b4553add78463b6e797d69c782694965ed2524e2e042f007
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bf0d01966c107a3c258d95901a64f0e5cc0caaf2f57744b2c92d9a3c4d0595e
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32f4410bda13942b56bcccd6f1b041b71320764331f12ea3492514568e6ef409
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,6 @@
3
  {"current_steps": 20, "total_steps": 45, "loss": 0.3359, "learning_rate": 5e-06, "epoch": 1.285140562248996, "percentage": 44.44, "elapsed_time": "1:32:44", "remaining_time": "1:55:55"}
4
  {"current_steps": 30, "total_steps": 45, "loss": 0.3019, "learning_rate": 5e-06, "epoch": 1.927710843373494, "percentage": 66.67, "elapsed_time": "2:17:49", "remaining_time": "1:08:54"}
5
  {"current_steps": 31, "total_steps": 45, "eval_loss": 0.2970140278339386, "epoch": 1.9919678714859437, "percentage": 68.89, "elapsed_time": "2:24:08", "remaining_time": "1:05:05"}
 
 
 
 
3
  {"current_steps": 20, "total_steps": 45, "loss": 0.3359, "learning_rate": 5e-06, "epoch": 1.285140562248996, "percentage": 44.44, "elapsed_time": "1:32:44", "remaining_time": "1:55:55"}
4
  {"current_steps": 30, "total_steps": 45, "loss": 0.3019, "learning_rate": 5e-06, "epoch": 1.927710843373494, "percentage": 66.67, "elapsed_time": "2:17:49", "remaining_time": "1:08:54"}
5
  {"current_steps": 31, "total_steps": 45, "eval_loss": 0.2970140278339386, "epoch": 1.9919678714859437, "percentage": 68.89, "elapsed_time": "2:24:08", "remaining_time": "1:05:05"}
6
+ {"current_steps": 40, "total_steps": 45, "loss": 0.2815, "learning_rate": 5e-06, "epoch": 2.570281124497992, "percentage": 88.89, "elapsed_time": "3:05:21", "remaining_time": "0:23:10"}
7
+ {"current_steps": 45, "total_steps": 45, "eval_loss": 0.2824314832687378, "epoch": 2.891566265060241, "percentage": 100.0, "elapsed_time": "3:30:20", "remaining_time": "0:00:00"}
8
+ {"current_steps": 45, "total_steps": 45, "epoch": 2.891566265060241, "percentage": 100.0, "elapsed_time": "3:31:06", "remaining_time": "0:00:00"}