Hugging Face's logo

mlfoundations-dev
/
stackexchange_mathematica

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
fad8d5c
·
verified ·
1 Parent(s): fa59a22

Training in progress, epoch 3

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 +6 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79dcfcc2bc1375365d1f8a0b58f7d98fea5d444f0ef3f049c001211d2a56021d
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f490f8f3ddddbab50b791a0e1660e0a581da7baa37a1ad9acf56d422b439b03f
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89d5dcbe68216b3fb9710d0fe9a8e0aa092681a5b426aa3e96d70e69e4270117
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b960eb29d1c2bf041a6461835b94de02e4382a4383131eb995bd129223103a92
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5def9276deb21fa066de9f2b72d57be4b8f3f62bed2f135b43ad54a1054bb44e
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:836d2aa820972139c2b727f69a815a3af384aac1912900cccdb3d43fac8878d8
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a603cb707ad0bade23479df385057c837eea0d35ca180887b9072f31109884a
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09a0670e44b07cd57070b172fe35bd95eec47446c56ce765ffd1e8f48ec6a7d2
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -8,3 +8,9 @@
8
  {"current_steps": 70, "total_steps": 120, "loss": 0.6992, "lr": 5e-06, "epoch": 1.75, "percentage": 58.33, "elapsed_time": "0:38:43", "remaining_time": "0:27:39"}
9
  {"current_steps": 80, "total_steps": 120, "loss": 0.6946, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:44:01", "remaining_time": "0:22:00"}
10
  {"current_steps": 80, "total_steps": 120, "eval_loss": 0.7181093096733093, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:44:28", "remaining_time": "0:22:14"}
 
 
 
 
 
 
 
8
  {"current_steps": 70, "total_steps": 120, "loss": 0.6992, "lr": 5e-06, "epoch": 1.75, "percentage": 58.33, "elapsed_time": "0:38:43", "remaining_time": "0:27:39"}
9
  {"current_steps": 80, "total_steps": 120, "loss": 0.6946, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:44:01", "remaining_time": "0:22:00"}
10
  {"current_steps": 80, "total_steps": 120, "eval_loss": 0.7181093096733093, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:44:28", "remaining_time": "0:22:14"}
11
+ {"current_steps": 90, "total_steps": 120, "loss": 0.651, "lr": 5e-06, "epoch": 2.25, "percentage": 75.0, "elapsed_time": "0:51:04", "remaining_time": "0:17:01"}
12
+ {"current_steps": 100, "total_steps": 120, "loss": 0.6462, "lr": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:56:23", "remaining_time": "0:11:16"}
13
+ {"current_steps": 110, "total_steps": 120, "loss": 0.6444, "lr": 5e-06, "epoch": 2.75, "percentage": 91.67, "elapsed_time": "1:01:42", "remaining_time": "0:05:36"}
14
+ {"current_steps": 120, "total_steps": 120, "loss": 0.6445, "lr": 5e-06, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:06:58", "remaining_time": "0:00:00"}
15
+ {"current_steps": 120, "total_steps": 120, "eval_loss": 0.7114487886428833, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:08:43", "remaining_time": "0:00:00"}
16
+ {"current_steps": 120, "total_steps": 120, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:09:58", "remaining_time": "0:00:00"}