Hugging Face's logo

thrunlab
/
sparse_mistral_7b_refined_web_50p_2024-04-14

Text Generation
Transformers
Safetensors
sparse_llama
Generated from Trainer
custom_code
Model card Files Community
vxbrandon commited on
Commit
b7ac4c9
·
verified ·
1 Parent(s): 41d5d57

End of training

Browse files
Files changed (4) hide show
  1. README.md +18 -8
  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
@@ -4,18 +4,18 @@ base_model: mistralai/Mistral-7B-v0.1
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
- - name: sparse_mistral_7b_refined_web_50p_2024-04-13
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
- # sparse_mistral_7b_refined_web_50p_2024-04-13
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: 2.1985
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: 2350
49
 
50
  ### Training results
51
 
@@ -141,10 +141,20 @@ The following hyperparameters were used during training:
141
  | 2.2436 | 0.7 | 2200 | 2.2460 |
142
  | 2.2156 | 0.71 | 2225 | 2.2477 |
143
  | 2.1348 | 0.72 | 2250 | 2.2455 |
144
- | 2.1338 | 0.73 | 2275 | 2.2450 |
145
- | 2.2147 | 0.74 | 2300 | 2.2455 |
146
- | 2.2766 | 0.74 | 2325 | 2.2444 |
147
- | 2.204 | 0.75 | 2350 | 2.2458 |
 
 
 
 
 
 
 
 
 
 
148
 
149
 
150
  ### Framework versions
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
+ - name: sparse_mistral_7b_refined_web_50p_2024-04-14
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
+ # sparse_mistral_7b_refined_web_50p_2024-04-14
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: 2.1982
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: 2600
49
 
50
  ### Training results
51
 
 
141
  | 2.2436 | 0.7 | 2200 | 2.2460 |
142
  | 2.2156 | 0.71 | 2225 | 2.2477 |
143
  | 2.1348 | 0.72 | 2250 | 2.2455 |
144
+ | 2.1351 | 0.73 | 2275 | 2.2451 |
145
+ | 2.215 | 0.74 | 2300 | 2.2459 |
146
+ | 2.2761 | 0.74 | 2325 | 2.2466 |
147
+ | 2.2039 | 0.75 | 2350 | 2.2466 |
148
+ | 2.172 | 0.76 | 2375 | 2.2453 |
149
+ | 2.1675 | 0.77 | 2400 | 2.2455 |
150
+ | 2.2627 | 0.78 | 2425 | 2.2462 |
151
+ | 2.1231 | 0.78 | 2450 | 2.2453 |
152
+ | 2.2615 | 0.79 | 2475 | 2.2460 |
153
+ | 2.1383 | 0.8 | 2500 | 2.2448 |
154
+ | 2.2105 | 0.81 | 2525 | 2.2449 |
155
+ | 2.2157 | 0.82 | 2550 | 2.2446 |
156
+ | 2.1304 | 0.82 | 2575 | 2.2439 |
157
+ | 2.2038 | 0.83 | 2600 | 2.2450 |
158
 
159
 
160
  ### Framework versions
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbf0447bcf87b2a6c7579a17f8aa5abe6ab841b309928000f4843d007ee0b7fc
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95f8b6b5bd4056741da16e9e4b9c0544041ad9216c46241909ddc8d5a92d9acb
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b40eb43d1ecf752070536446d4dc3d9ff6cf490c016317856633564dd003279
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bdd6a42d939c247d05ede7ffec57756f1507890108ca0436057a97c0fb3823f
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2862d4a8c36e6e37f905d9dad166f80a06c03158590de0c43299b178555ecde3
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:851365d702999b4d8ef266f96d02c583fcf74e3e899b34bbf0f26ec208af10c2
3
  size 4540516344