Hugging Face's logo

mlfoundations-dev
/
stackexchange_math

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
86894d9
·
verified ·
1 Parent(s): 1e487af

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfd9bd85d8d96d2eba1487df718e2d3fa617e860fb28c97409c5cd4ebdecb146
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02aac37dd9aa15bc3560fe5e69ca0b77756de7dfe8ccae39fbd580477e2926c3
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:fc083b8c3731b1af9da1119262420bdabe6d6bcef4017d557947ac22b27d17a0
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45829dcaea6e0a9d53d00d47b18d451f15d358c01462e5ab8470535a3c9c1ac
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31a8fb13193fc0086c5377b328002946bb81c6d6c4e36f6b5f375546b2bef4b7
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b819cb0bea9df019df50bf9befa835c693ca05c9fe0802f9560c85823a433d
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b1b665e281144de5a11cb815bb8ebe150c102fdce7a22f719a13219e362362b
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1bc1381cb053c689d51dd2acfbcf8bd2a20fcc1110d44399ee2d1a054539dd
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,8 @@
3
  {"current_steps": 30, "total_steps": 126, "loss": 0.6462, "lr": 5e-06, "epoch": 0.7100591715976331, "percentage": 23.81, "elapsed_time": "0:16:01", "remaining_time": "0:51:16"}
4
  {"current_steps": 40, "total_steps": 126, "loss": 0.629, "lr": 5e-06, "epoch": 0.9467455621301775, "percentage": 31.75, "elapsed_time": "0:21:20", "remaining_time": "0:45:53"}
5
  {"current_steps": 42, "total_steps": 126, "eval_loss": 0.6316158175468445, "epoch": 0.9940828402366864, "percentage": 33.33, "elapsed_time": "0:23:01", "remaining_time": "0:46:02"}
 
 
 
 
 
 
3
  {"current_steps": 30, "total_steps": 126, "loss": 0.6462, "lr": 5e-06, "epoch": 0.7100591715976331, "percentage": 23.81, "elapsed_time": "0:16:01", "remaining_time": "0:51:16"}
4
  {"current_steps": 40, "total_steps": 126, "loss": 0.629, "lr": 5e-06, "epoch": 0.9467455621301775, "percentage": 31.75, "elapsed_time": "0:21:20", "remaining_time": "0:45:53"}
5
  {"current_steps": 42, "total_steps": 126, "eval_loss": 0.6316158175468445, "epoch": 0.9940828402366864, "percentage": 33.33, "elapsed_time": "0:23:01", "remaining_time": "0:46:02"}
6
+ {"current_steps": 50, "total_steps": 126, "loss": 0.6475, "lr": 5e-06, "epoch": 1.183431952662722, "percentage": 39.68, "elapsed_time": "0:28:20", "remaining_time": "0:43:05"}
7
+ {"current_steps": 60, "total_steps": 126, "loss": 0.5883, "lr": 5e-06, "epoch": 1.4201183431952662, "percentage": 47.62, "elapsed_time": "0:33:40", "remaining_time": "0:37:02"}
8
+ {"current_steps": 70, "total_steps": 126, "loss": 0.5813, "lr": 5e-06, "epoch": 1.6568047337278107, "percentage": 55.56, "elapsed_time": "0:39:00", "remaining_time": "0:31:12"}
9
+ {"current_steps": 80, "total_steps": 126, "loss": 0.5807, "lr": 5e-06, "epoch": 1.893491124260355, "percentage": 63.49, "elapsed_time": "0:44:19", "remaining_time": "0:25:29"}
10
+ {"current_steps": 84, "total_steps": 126, "eval_loss": 0.6118831038475037, "epoch": 1.9881656804733727, "percentage": 66.67, "elapsed_time": "0:47:10", "remaining_time": "0:23:35"}