Hugging Face's logo

FemkeBakker
/
AmsterdamDocClassificationLlama200T3Epochs

Text Generation
Transformers
TensorBoard
Safetensors
Dutch
llama
trl
sft
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
FemkeBakker commited on
Commit
b83a966
•
1 Parent(s): 7eb07e0

End of training

Browse files
Files changed (4) hide show
  1. README.md +9 -4
  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
@@ -6,18 +6,18 @@ tags:
6
  - sft
7
  - generated_from_trainer
8
  model-index:
9
- - name: AmsterdamDocClassificationLlama200T2Epochs
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- # AmsterdamDocClassificationLlama200T2Epochs
17
 
18
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.8173
21
 
22
  ## Model description
23
 
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
47
  - lr_scheduler_warmup_ratio: 0.1
48
- - num_epochs: 2
49
 
50
  ### Training results
51
 
@@ -61,6 +61,11 @@ The following hyperparameters were used during training:
61
  | 0.7785 | 1.5915 | 984 | 0.8186 |
62
  | 0.7233 | 1.7903 | 1107 | 0.8178 |
63
  | 0.8389 | 1.9891 | 1230 | 0.8173 |
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
6
  - sft
7
  - generated_from_trainer
8
  model-index:
9
+ - name: AmsterdamDocClassificationLlama200T3Epochs
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # AmsterdamDocClassificationLlama200T3Epochs
17
 
18
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.8116
21
 
22
  ## Model description
23
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
47
  - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 3
49
 
50
  ### Training results
51
 
 
61
  | 0.7785 | 1.5915 | 984 | 0.8186 |
62
  | 0.7233 | 1.7903 | 1107 | 0.8178 |
63
  | 0.8389 | 1.9891 | 1230 | 0.8173 |
64
+ | 0.976 | 2.1891 | 1353 | 0.8148 |
65
+ | 0.6826 | 2.3879 | 1476 | 0.8127 |
66
+ | 0.7712 | 2.5867 | 1599 | 0.8117 |
67
+ | 0.9744 | 2.7855 | 1722 | 0.8116 |
68
+ | 1.0399 | 2.9842 | 1845 | 0.8116 |
69
 
70
 
71
  ### Framework versions
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cf4cf6e2c71348172d27f2376502975dfcc82bee1d80bfcbd66f8abfce61387
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b692a6d4c6e8ec163a1de77b6727ec788aeabb707d8b1b99f3c1438781431c9e
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a3505503f6fc2d2b3e643508f9cbaaa011f697476c6495e010af250d8fae9a3
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a325847cf927478607ee6cad40199e6d0e27f240ce29675f15869d2fd19876ee
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9838c85a591378dd3901ff01832276a21e47513c7baef128eadfa84241af0914
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ae1c7ff465abb64ce2e04c165757182afae025b6eb9f31a24e98dd9e227741d
3
  size 3590488816