DesilDev commited on
Commit
a354662
·
verified ·
1 Parent(s): 52b23ec

End of training

Browse files
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: DesilDev/Blocksmith
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - samsum
8
+ metrics:
9
+ - rouge
10
+ model-index:
11
+ - name: BlocksmithV2
12
+ results:
13
+ - task:
14
+ name: Sequence-to-sequence Language Modeling
15
+ type: text2text-generation
16
+ dataset:
17
+ name: samsum
18
+ type: samsum
19
+ config: samsum
20
+ split: validation
21
+ args: samsum
22
+ metrics:
23
+ - name: Rouge1
24
+ type: rouge
25
+ value: 39.0411
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # BlocksmithV2
32
+
33
+ This model is a fine-tuned version of [DesilDev/Blocksmith](https://huggingface.co/DesilDev/Blocksmith) on the samsum dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.8786
36
+ - Rouge1: 39.0411
37
+ - Rouge2: 16.2095
38
+ - Rougel: 32.6745
39
+ - Rougelsum: 35.9911
40
+ - Gen Len: 16.28
41
+
42
+ ## Model description
43
+
44
+ More information needed
45
+
46
+ ## Intended uses & limitations
47
+
48
+ More information needed
49
+
50
+ ## Training and evaluation data
51
+
52
+ More information needed
53
+
54
+ ## Training procedure
55
+
56
+ ### Training hyperparameters
57
+
58
+ The following hyperparameters were used during training:
59
+ - learning_rate: 2e-05
60
+ - train_batch_size: 16
61
+ - eval_batch_size: 16
62
+ - seed: 42
63
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
+ - lr_scheduler_type: linear
65
+ - num_epochs: 1
66
+ - mixed_precision_training: Native AMP
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
71
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
72
+ | 2.115 | 1.0 | 921 | 1.8786 | 39.0411 | 16.2095 | 32.6745 | 35.9911 | 16.28 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.42.4
78
+ - Pytorch 2.3.1+cu121
79
+ - Datasets 2.20.0
80
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.42.4"
6
+ }
runs/Aug11_10-54-31_af363f7b90b5/events.out.tfevents.1723373691.af363f7b90b5.251.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:789d9a8a5a6f8a556bc0593b4f59f63b04b3dcf7faf3d0ec2bc88c4d5eaa8f34
3
- size 12020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e9939568160f5263cd9fd714bb3f9a8146b009e474140851e4a591160dcb438
3
+ size 12899