Hugging Face's logo

thrunlab
/
sparse_mistral_7b_refined_web_50p_2024-04-13

Text Generation
Transformers
Safetensors
sparse_llama
Generated from Trainer
custom_code
Model card Files Community
vxbrandon commited on
Commit
25ab377
•
1 Parent(s): c7f8f60

End of training

Browse files
Files changed (4) hide show
  1. README.md +16 -6
  2. model-00001-of-00003.safetensors +1 -1
  3. model-00002-of-00003.safetensors +1 -1
  4. model-00003-of-00003.safetensors +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.2040
19
 
20
  ## Model description
21
 
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
45
  - total_eval_batch_size: 16
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - training_steps: 1100
49
 
50
  ### Training results
51
 
@@ -91,10 +91,20 @@ The following hyperparameters were used during training:
91
  | 2.2528 | 0.3 | 950 | 2.2518 |
92
  | 2.2505 | 0.31 | 975 | 2.2500 |
93
  | 2.1683 | 0.32 | 1000 | 2.2502 |
94
- | 2.2186 | 0.33 | 1025 | 2.2493 |
95
- | 2.2386 | 0.34 | 1050 | 2.2502 |
96
- | 2.193 | 0.34 | 1075 | 2.2503 |
97
- | 2.2035 | 0.35 | 1100 | 2.2502 |
 
 
 
 
 
 
 
 
 
 
98
 
99
 
100
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.2023
19
 
20
  ## Model description
21
 
 
45
  - total_eval_batch_size: 16
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - training_steps: 1350
49
 
50
  ### Training results
51
 
 
91
  | 2.2528 | 0.3 | 950 | 2.2518 |
92
  | 2.2505 | 0.31 | 975 | 2.2500 |
93
  | 2.1683 | 0.32 | 1000 | 2.2502 |
94
+ | 2.2177 | 0.33 | 1025 | 2.2501 |
95
+ | 2.238 | 0.34 | 1050 | 2.2516 |
96
+ | 2.193 | 0.34 | 1075 | 2.2507 |
97
+ | 2.2025 | 0.35 | 1100 | 2.2502 |
98
+ | 2.0944 | 0.36 | 1125 | 2.2512 |
99
+ | 2.2272 | 0.37 | 1150 | 2.2508 |
100
+ | 2.2264 | 0.38 | 1175 | 2.2500 |
101
+ | 2.1837 | 0.38 | 1200 | 2.2507 |
102
+ | 2.1444 | 0.39 | 1225 | 2.2489 |
103
+ | 2.2464 | 0.4 | 1250 | 2.2499 |
104
+ | 2.1398 | 0.41 | 1275 | 2.2512 |
105
+ | 2.1929 | 0.42 | 1300 | 2.2502 |
106
+ | 2.2384 | 0.42 | 1325 | 2.2498 |
107
+ | 2.223 | 0.43 | 1350 | 2.2481 |
108
 
109
 
110
  ### Framework versions
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed0eee35d9d95d9415c95a2c5f231f135a3d5b76c279fc8d62a67d08eb4beb33
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c71016ed256a7c04ef05e4c1d6e0e3c8416ec82fcdd0da588c9b6bcaf3649291
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43bd237efecaee066533b24ca8094f58fccdff890ab2e86fd9f625f5f9bea202
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d53458b79bdc9dff99c9e778353ba978f85313189a8640276d4dcbc9adee4514
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a8f700a076ad2e614578f55fe56011e3b85294148c81c8374424bea4887ceb0
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f76caabedafe1308a40259576d419d87cb628e0625c30a281f44e963accf4d
3
  size 4540516344