Hugging Face's logo

mlfoundations-dev
/
stackexchange_physics

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
a39d635
·
verified ·
1 Parent(s): 83ef13c

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f59201d4c216922af808b1938607345ecead5b92e31c0901eccb70a6ac2b571f
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:610086ac9ffff9b16e9530d125dee5da92a6575cc44dc095ac83fc1a63528792
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94bce3cfc1f1a58459a28e6dbe21f3f469662702fe4c932ae24d702ac3c13864
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9210fa4377520f201cd9be644e9ab75aae4e78441d062abcdbe59a9286bdefc
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:035e282ec66917b870fa23434ee9db0a7a136c04c4c369c86727cb9f5ab33704
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b817b07c4f01179c96abdceab5be15674df82c28b5bfeec97e1c718d4558dc77
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:518299feab5f3912bd2e7a31661a8358579c1c20944cdd8289477ca394ad6c0e
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46dff82b63fb222885c41b41b8770a2022dd0aa06d0a94828aae7608365bc073
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,7 @@
3
  {"current_steps": 30, "total_steps": 108, "loss": 0.9015, "lr": 5e-06, "epoch": 0.8275862068965517, "percentage": 27.78, "elapsed_time": "0:15:58", "remaining_time": "0:41:32"}
4
  {"current_steps": 36, "total_steps": 108, "eval_loss": 0.8885926604270935, "epoch": 0.993103448275862, "percentage": 33.33, "elapsed_time": "0:19:41", "remaining_time": "0:39:23"}
5
  {"current_steps": 40, "total_steps": 108, "loss": 0.936, "lr": 5e-06, "epoch": 1.103448275862069, "percentage": 37.04, "elapsed_time": "0:22:51", "remaining_time": "0:38:50"}
 
 
 
 
 
3
  {"current_steps": 30, "total_steps": 108, "loss": 0.9015, "lr": 5e-06, "epoch": 0.8275862068965517, "percentage": 27.78, "elapsed_time": "0:15:58", "remaining_time": "0:41:32"}
4
  {"current_steps": 36, "total_steps": 108, "eval_loss": 0.8885926604270935, "epoch": 0.993103448275862, "percentage": 33.33, "elapsed_time": "0:19:41", "remaining_time": "0:39:23"}
5
  {"current_steps": 40, "total_steps": 108, "loss": 0.936, "lr": 5e-06, "epoch": 1.103448275862069, "percentage": 37.04, "elapsed_time": "0:22:51", "remaining_time": "0:38:50"}
6
+ {"current_steps": 50, "total_steps": 108, "loss": 0.8346, "lr": 5e-06, "epoch": 1.3793103448275863, "percentage": 46.3, "elapsed_time": "0:28:07", "remaining_time": "0:32:37"}
7
+ {"current_steps": 60, "total_steps": 108, "loss": 0.8219, "lr": 5e-06, "epoch": 1.6551724137931034, "percentage": 55.56, "elapsed_time": "0:33:22", "remaining_time": "0:26:42"}
8
+ {"current_steps": 70, "total_steps": 108, "loss": 0.8158, "lr": 5e-06, "epoch": 1.9310344827586206, "percentage": 64.81, "elapsed_time": "0:38:40", "remaining_time": "0:20:59"}
9
+ {"current_steps": 72, "total_steps": 108, "eval_loss": 0.8567079305648804, "epoch": 1.986206896551724, "percentage": 66.67, "elapsed_time": "0:40:22", "remaining_time": "0:20:11"}