Hugging Face's logo

mlfoundations-dev
/
oh_v1-2_only_camel_math

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
esfrankel17 commited on
Commit
5975bf7
·
verified ·
1 Parent(s): d92d89d

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 +7 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d04d407d06154d8fc2e8fe2a3860fc847bb5b04c2ebee8fc7ee3f54e50d32be2
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:754d0357e91f4559cccc653125d6ccfb728d363cc5de8e2087bfe9d48a4bd279
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:aa412308ae6adb022095670312cb7600cdf71b39d18b9d8be7def03ab7c01b86
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26b41cee62fcde9277c7c550393d5d8faa74da44152fb7dc4277edebc449d122
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:a41fb7486019a475c4bbc268b0349f5b0dd33443e2e0509324eace8a716b126d
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3e8defda30bfcd3e3ab2fab21e63734d5e22c63b9d135ee4ad8ca5f053d5fff
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56ec4805c3c1af45c0c1bd566993c8e504228cacdde6eec6e813e3e7fb633688
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1138a9c95687c7d03dde3081909672541a8ea94eb3b37f7cf88547ba64606a4
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -5,3 +5,10 @@
5
  {"current_steps": 50, "total_steps": 183, "loss": 0.4144, "learning_rate": 5e-06, "epoch": 0.8080808080808081, "percentage": 27.32, "elapsed_time": "0:26:26", "remaining_time": "1:10:20"}
6
  {"current_steps": 60, "total_steps": 183, "loss": 0.4052, "learning_rate": 5e-06, "epoch": 0.9696969696969697, "percentage": 32.79, "elapsed_time": "0:31:43", "remaining_time": "1:05:02"}
7
  {"current_steps": 61, "total_steps": 183, "eval_loss": 0.41120877861976624, "epoch": 0.9858585858585859, "percentage": 33.33, "elapsed_time": "0:33:25", "remaining_time": "1:06:51"}
 
 
 
 
 
 
 
 
5
  {"current_steps": 50, "total_steps": 183, "loss": 0.4144, "learning_rate": 5e-06, "epoch": 0.8080808080808081, "percentage": 27.32, "elapsed_time": "0:26:26", "remaining_time": "1:10:20"}
6
  {"current_steps": 60, "total_steps": 183, "loss": 0.4052, "learning_rate": 5e-06, "epoch": 0.9696969696969697, "percentage": 32.79, "elapsed_time": "0:31:43", "remaining_time": "1:05:02"}
7
  {"current_steps": 61, "total_steps": 183, "eval_loss": 0.41120877861976624, "epoch": 0.9858585858585859, "percentage": 33.33, "elapsed_time": "0:33:25", "remaining_time": "1:06:51"}
8
+ {"current_steps": 70, "total_steps": 183, "loss": 0.3938, "learning_rate": 5e-06, "epoch": 1.1313131313131313, "percentage": 38.25, "elapsed_time": "0:38:51", "remaining_time": "1:02:43"}
9
+ {"current_steps": 80, "total_steps": 183, "loss": 0.3746, "learning_rate": 5e-06, "epoch": 1.2929292929292928, "percentage": 43.72, "elapsed_time": "0:44:07", "remaining_time": "0:56:48"}
10
+ {"current_steps": 90, "total_steps": 183, "loss": 0.3748, "learning_rate": 5e-06, "epoch": 1.4545454545454546, "percentage": 49.18, "elapsed_time": "0:49:21", "remaining_time": "0:51:00"}
11
+ {"current_steps": 100, "total_steps": 183, "loss": 0.3751, "learning_rate": 5e-06, "epoch": 1.6161616161616161, "percentage": 54.64, "elapsed_time": "0:54:38", "remaining_time": "0:45:20"}
12
+ {"current_steps": 110, "total_steps": 183, "loss": 0.3737, "learning_rate": 5e-06, "epoch": 1.7777777777777777, "percentage": 60.11, "elapsed_time": "0:59:53", "remaining_time": "0:39:44"}
13
+ {"current_steps": 120, "total_steps": 183, "loss": 0.3753, "learning_rate": 5e-06, "epoch": 1.9393939393939394, "percentage": 65.57, "elapsed_time": "1:05:08", "remaining_time": "0:34:11"}
14
+ {"current_steps": 123, "total_steps": 183, "eval_loss": 0.3987608253955841, "epoch": 1.9878787878787878, "percentage": 67.21, "elapsed_time": "1:07:45", "remaining_time": "0:33:03"}