Elalimy commited on
Commit
2525579
·
verified ·
1 Parent(s): 76ecdc9

End of training

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
+ base_model: Helsinki-NLP/opus-mt-ar-en
9
+ model-index:
10
+ - name: my_awesome_peft_finetuned_helsinki_model
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # my_awesome_peft_finetuned_helsinki_model
18
+
19
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ar-en](https://huggingface.co/Helsinki-NLP/opus-mt-ar-en) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.2304
22
+ - Bleu: 45.042
23
+ - Gen Len: 15.21
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
+ - train_batch_size: 24
44
+ - eval_batch_size: 24
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 3
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
54
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
55
+ | 1.377 | 1.0 | 2500 | 1.2377 | 45.1725 | 15.2305 |
56
+ | 1.3663 | 2.0 | 5000 | 1.2313 | 45.0712 | 15.219 |
57
+ | 1.3591 | 3.0 | 7500 | 1.2304 | 45.042 | 15.21 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - PEFT 0.8.2
63
+ - Transformers 4.37.2
64
+ - Pytorch 2.1.0+cu121
65
+ - Datasets 2.17.1
66
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8807e9d7ae910885845482a987e4dda5b76755b2d0f67252c0d23271d400865
3
  size 2369344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0aca313e96e56ff9a89b0be0e871f3b78d9ba8a1d9c226bcdea473b1d7633bc
3
  size 2369344
runs/Feb27_23-24-59_3eaac49a1964/events.out.tfevents.1709076300.3eaac49a1964.483.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f1645440cd314b4d8d1a8d00489d87351779d20249969eca0eee60658dc7627
3
- size 8240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f1e240bf1421786f7a898bc3f45eff17ce6849050c91b55c71161868568f8a6
3
+ size 9121