Hugging Face's logo

CharlesLi
/
mistral_llama_2_code_math_0_full

Text Generation
Transformers
TensorBoard
Safetensors
mistral
alignment-handbook
trl
sft
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Metrics Community
CharlesLi commited on
Commit
e18dc28
·
verified ·
1 Parent(s): 4f0f349

Model save

Browse files
Files changed (10) hide show
  1. README.md +1 -0
  2. all_results.json +8 -3
  3. eval_results.json +8 -0
  4. model-00001-of-00003.safetensors +1 -1
  5. model-00002-of-00003.safetensors +1 -1
  6. model-00003-of-00003.safetensors +1 -1
  7. runs/Jan20_00-00-50_dgx-a100-14/events.out.tfevents.1737328598.dgx-a100-14.585960.1 +3 -0
  8. runs/Jan20_00-08-05_dgx-a100-13/events.out.tfevents.1737328636.dgx-a100-13.964584.0 +3 -0
  9. train_results.json +3 -3
  10. training_args.bin +1 -1
README.md CHANGED
@@ -5,6 +5,7 @@ base_model: mistralai/Mistral-7B-Instruct-v0.1
5
  tags:
6
  - trl
7
  - sft
 
8
  - generated_from_trainer
9
  datasets:
10
  - generator
 
5
  tags:
6
  - trl
7
  - sft
8
+ - alignment-handbook
9
  - generated_from_trainer
10
  datasets:
11
  - generator
all_results.json CHANGED
@@ -1,9 +1,14 @@
1
  {
2
  "epoch": 1.0,
 
 
 
 
 
3
  "total_flos": 261724569600.0,
4
- "train_loss": 1.163278341293335,
5
- "train_runtime": 18.7864,
6
  "train_samples": 480,
7
- "train_samples_per_second": 4.737,
8
  "train_steps_per_second": 0.16
9
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 0.8714168667793274,
4
+ "eval_runtime": 0.7342,
5
+ "eval_samples": 20,
6
+ "eval_samples_per_second": 4.086,
7
+ "eval_steps_per_second": 1.362,
8
  "total_flos": 261724569600.0,
9
+ "train_loss": 1.163399616877238,
10
+ "train_runtime": 18.7784,
11
  "train_samples": 480,
12
+ "train_samples_per_second": 4.739,
13
  "train_steps_per_second": 0.16
14
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.8714168667793274,
4
+ "eval_runtime": 0.7342,
5
+ "eval_samples": 20,
6
+ "eval_samples_per_second": 4.086,
7
+ "eval_steps_per_second": 1.362
8
+ }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53ff7288e44a8ffaba793ecf04f6c5ad03d174de8cffd773fe501da070ded140
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a07ea007d78bd0d48bd523688c14319944afea100bef7b3200d7bcb62a1c910f
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd5dc2c301730b9960042a6d50e325c9eeb56a793d7cb4ebd48232b95018e873
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f15f81ace1df79e40f5925242e8fadcf464ba365d4bea49426331e231085a7f
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcb6a6d754a1a71fae2dbf276aa7d9e819b61b0afd90f2319164198873c3ae47
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f2cc112490fbbd711ae1844f5a9496379520ccd1d7d56a89d5d1fa279204fa9
3
  size 4540516344
runs/Jan20_00-00-50_dgx-a100-14/events.out.tfevents.1737328598.dgx-a100-14.585960.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3ae15291a917298a5b181434fb4ba0802ddcc5dfcac5249471ddc9065f0da9
3
+ size 354
runs/Jan20_00-08-05_dgx-a100-13/events.out.tfevents.1737328636.dgx-a100-13.964584.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdfd77c23e4d955c93071c83b5625265d9a1de986fc5b94a3ac192e4360e19f0
3
+ size 6206
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 261724569600.0,
4
- "train_loss": 1.163278341293335,
5
- "train_runtime": 18.7864,
6
  "train_samples": 480,
7
- "train_samples_per_second": 4.737,
8
  "train_steps_per_second": 0.16
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 261724569600.0,
4
+ "train_loss": 1.163399616877238,
5
+ "train_runtime": 18.7784,
6
  "train_samples": 480,
7
+ "train_samples_per_second": 4.739,
8
  "train_steps_per_second": 0.16
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dd100349c91880750b55a16682715a5d5b1857529c8c500819d7b1a7ed12bc2
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b59feb474c59127d5f77cf70fa81c08363492b0eb2d92f761d9c18239efc01e
3
  size 7032