Hugging Face's logo

thrunlab
/
sparse_llama_7b_hf_refined_web_70p_2024-03-25

Text Generation
Transformers
Safetensors
sparse_llama
Generated from Trainer
custom_code
Model card Files Community
lukeleeai commited on
Commit
b88a146
•
1 Parent(s): f155ab7

End of training

Browse files
Files changed (4) hide show
  1. README.md +10 -2
  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
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.2098
18
 
19
  ## Model description
20
 
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
44
  - total_eval_batch_size: 4
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - training_steps: 400
48
 
49
  ### Training results
50
 
@@ -66,6 +66,14 @@ The following hyperparameters were used during training:
66
  | 2.2974 | 0.11 | 350 | 2.4353 |
67
  | 2.2216 | 0.12 | 375 | 2.4379 |
68
  | 2.3179 | 0.13 | 400 | 2.4340 |
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 2.1991
18
 
19
  ## Model description
20
 
 
44
  - total_eval_batch_size: 4
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - training_steps: 600
48
 
49
  ### Training results
50
 
 
66
  | 2.2974 | 0.11 | 350 | 2.4353 |
67
  | 2.2216 | 0.12 | 375 | 2.4379 |
68
  | 2.3179 | 0.13 | 400 | 2.4340 |
69
+ | 2.3006 | 0.14 | 425 | 2.4333 |
70
+ | 2.2603 | 0.14 | 450 | 2.4333 |
71
+ | 2.3371 | 0.15 | 475 | 2.4384 |
72
+ | 2.3453 | 0.16 | 500 | 2.4328 |
73
+ | 2.254 | 0.17 | 525 | 2.4306 |
74
+ | 2.2423 | 0.18 | 550 | 2.4298 |
75
+ | 2.3666 | 0.18 | 575 | 2.4293 |
76
+ | 2.259 | 0.19 | 600 | 2.4298 |
77
 
78
 
79
  ### Framework versions
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce920b71ed7544e16c341f33c7515146baaa0ca48cf9e16af48b34dfed49ec7c
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2eeda07e5777cb71b397fabe1cc89e4a4c8a67693af5a6640949caaa37e2eeb
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ee4cb77d3c66150af8a7ab43a6f87a819efdc95b58495cbf2f8ec6701990c55
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f259e0d97d25924b7438e4b0d76e0a8bd88d4abab3deb1c52693208a224b15
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50a90335469617f6151eaa6de98b9da76ca032f5ad2fde2ec6ba78129e89c12e
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff293b3c82ed13b59edfb7cfdcce8fab53b9b26e7dab0bcfc322dcd4b97801c
3
  size 3590488816