Hugging Face's logo

mlfoundations-dev
/
stackoverflow_5000tasks_1p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
f5f9274
·
verified ·
1 Parent(s): 8e869c2

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:bcc877cea556a711fb7f936e111c0d9341384325f69a08d35757e333d0b71a6c
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973fbe57928254dacad753290724c874d67b28c8e37b3d5ce72f1d0861c5e552
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87e3d657043237744545710c8b4f5f86cbb5aa76da694cc3142838a1b1a128c6
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a508af6c992cc0c1f31093cc3c336f2386643fc270427d439a27646a5b80516
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1963dec9742c7d893804bb04af1560769e764e65ed6ffebb1462718727f22963
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52385c3ab716ac1b8981793332dfbede0045acd5aeb4496171f51fef87caa87b
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ba60837b2c8d51abe677ce56cdebc61dfcccd0bca4fa57d5f9ddea39099cddf
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1d5c61266288a993f66e244041b328c00ca85b44e692716b1e3e64f13d5ce2f
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,8 @@
2
  {"current_steps": 20, "total_steps": 105, "loss": 0.8974, "lr": 5e-06, "epoch": 0.5714285714285714, "percentage": 19.05, "elapsed_time": "0:10:46", "remaining_time": "0:45:45"}
3
  {"current_steps": 30, "total_steps": 105, "loss": 0.8534, "lr": 5e-06, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "0:16:06", "remaining_time": "0:40:15"}
4
  {"current_steps": 35, "total_steps": 105, "eval_loss": 0.8311977386474609, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:10", "remaining_time": "0:38:21"}
 
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 105, "loss": 0.8974, "lr": 5e-06, "epoch": 0.5714285714285714, "percentage": 19.05, "elapsed_time": "0:10:46", "remaining_time": "0:45:45"}
3
  {"current_steps": 30, "total_steps": 105, "loss": 0.8534, "lr": 5e-06, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "0:16:06", "remaining_time": "0:40:15"}
4
  {"current_steps": 35, "total_steps": 105, "eval_loss": 0.8311977386474609, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:10", "remaining_time": "0:38:21"}
5
+ {"current_steps": 40, "total_steps": 105, "loss": 0.8148, "lr": 5e-06, "epoch": 1.1428571428571428, "percentage": 38.1, "elapsed_time": "0:23:00", "remaining_time": "0:37:22"}
6
+ {"current_steps": 50, "total_steps": 105, "loss": 0.7837, "lr": 5e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "0:28:20", "remaining_time": "0:31:10"}
7
+ {"current_steps": 60, "total_steps": 105, "loss": 0.7796, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:41", "remaining_time": "0:25:15"}
8
+ {"current_steps": 70, "total_steps": 105, "loss": 0.7696, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:38:59", "remaining_time": "0:19:29"}
9
+ {"current_steps": 70, "total_steps": 105, "eval_loss": 0.803409218788147, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:24", "remaining_time": "0:19:42"}