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
fa59a22
·
verified ·
1 Parent(s): 196d456

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:812366bed4ead9a10d34277e1b08a4999b9f68e8fbdc2afa34bfa356f6915d18
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79dcfcc2bc1375365d1f8a0b58f7d98fea5d444f0ef3f049c001211d2a56021d
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d2a4e23e3be22820f6d6bf5bc241b410805d18f7ef3aa9cdd97d9a58b23d662
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89d5dcbe68216b3fb9710d0fe9a8e0aa092681a5b426aa3e96d70e69e4270117
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16fd5faa6708abd6491206046b9ae3f3a308052913d865a247c278e04ca1de05
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5def9276deb21fa066de9f2b72d57be4b8f3f62bed2f135b43ad54a1054bb44e
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:dd6b6d8ef53f58aebb103cb7f53ac8b3a053b938f7f08581aa4d1b020608c42d
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a603cb707ad0bade23479df385057c837eea0d35ca180887b9072f31109884a
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,8 @@
3
  {"current_steps": 30, "total_steps": 120, "loss": 0.7811, "lr": 5e-06, "epoch": 0.75, "percentage": 25.0, "elapsed_time": "0:15:59", "remaining_time": "0:47:59"}
4
  {"current_steps": 40, "total_steps": 120, "loss": 0.7595, "lr": 5e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:21:16", "remaining_time": "0:42:33"}
5
  {"current_steps": 40, "total_steps": 120, "eval_loss": 0.7516233921051025, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:21:44", "remaining_time": "0:43:28"}
 
 
 
 
 
 
3
  {"current_steps": 30, "total_steps": 120, "loss": 0.7811, "lr": 5e-06, "epoch": 0.75, "percentage": 25.0, "elapsed_time": "0:15:59", "remaining_time": "0:47:59"}
4
  {"current_steps": 40, "total_steps": 120, "loss": 0.7595, "lr": 5e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:21:16", "remaining_time": "0:42:33"}
5
  {"current_steps": 40, "total_steps": 120, "eval_loss": 0.7516233921051025, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:21:44", "remaining_time": "0:43:28"}
6
+ {"current_steps": 50, "total_steps": 120, "loss": 0.7169, "lr": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:28:10", "remaining_time": "0:39:27"}
7
+ {"current_steps": 60, "total_steps": 120, "loss": 0.7105, "lr": 5e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:33:27", "remaining_time": "0:33:27"}
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"}