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
Inference Endpoints
Model card Files Community
esfrankel17 commited on
Commit
e19c4a7
•
1 Parent(s): 5975bf7

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 +8 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:754d0357e91f4559cccc653125d6ccfb728d363cc5de8e2087bfe9d48a4bd279
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:793f39c6138ddd7db420b0d4d53f50104ecc7336ad84df41d1715abfe43ed706
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26b41cee62fcde9277c7c550393d5d8faa74da44152fb7dc4277edebc449d122
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f725d749018e75ddd0957b12e0e5cb5ea029c73d40a88f195ef4945871cb5cb8
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:e3e8defda30bfcd3e3ab2fab21e63734d5e22c63b9d135ee4ad8ca5f053d5fff
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a214837b7da508738e9c3390ab95e61faa4f74d7fe5afab612768f0c271f1ff
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:f1138a9c95687c7d03dde3081909672541a8ea94eb3b37f7cf88547ba64606a4
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9e3ce9951ba304ec86a7d3c05216be97d2e814afb5ad9463683d1b0e96e9e1
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -12,3 +12,11 @@
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"}
 
 
 
 
 
 
 
 
 
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"}
15
+ {"current_steps": 130, "total_steps": 183, "loss": 0.36, "learning_rate": 5e-06, "epoch": 2.101010101010101, "percentage": 71.04, "elapsed_time": "1:12:06", "remaining_time": "0:29:23"}
16
+ {"current_steps": 140, "total_steps": 183, "loss": 0.3487, "learning_rate": 5e-06, "epoch": 2.2626262626262625, "percentage": 76.5, "elapsed_time": "1:17:21", "remaining_time": "0:23:45"}
17
+ {"current_steps": 150, "total_steps": 183, "loss": 0.348, "learning_rate": 5e-06, "epoch": 2.4242424242424243, "percentage": 81.97, "elapsed_time": "1:22:37", "remaining_time": "0:18:10"}
18
+ {"current_steps": 160, "total_steps": 183, "loss": 0.3508, "learning_rate": 5e-06, "epoch": 2.5858585858585856, "percentage": 87.43, "elapsed_time": "1:27:51", "remaining_time": "0:12:37"}
19
+ {"current_steps": 170, "total_steps": 183, "loss": 0.3486, "learning_rate": 5e-06, "epoch": 2.7474747474747474, "percentage": 92.9, "elapsed_time": "1:33:08", "remaining_time": "0:07:07"}
20
+ {"current_steps": 180, "total_steps": 183, "loss": 0.3467, "learning_rate": 5e-06, "epoch": 2.909090909090909, "percentage": 98.36, "elapsed_time": "1:38:23", "remaining_time": "0:01:38"}
21
+ {"current_steps": 183, "total_steps": 183, "eval_loss": 0.3988819718360901, "epoch": 2.9575757575757575, "percentage": 100.0, "elapsed_time": "1:41:45", "remaining_time": "0:00:00"}
22
+ {"current_steps": 183, "total_steps": 183, "epoch": 2.9575757575757575, "percentage": 100.0, "elapsed_time": "1:42:44", "remaining_time": "0:00:00"}