pszemraj commited on
Commit
5a95ac7
1 Parent(s): 4b6c14e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -22
README.md CHANGED
@@ -25,14 +25,13 @@ model-index:
25
  - name: Rouge1
26
  type: rouge
27
  value: 42.3629
 
 
28
  ---
29
 
30
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
- should probably proofread and complete it, then remove this comment. -->
32
-
33
  # tFINE-base-300m-samsum
34
 
35
- This model is a fine-tuned version of [pszemraj/tFINE-base-300m](https://huggingface.co/pszemraj/tFINE-base-300m) on the samsum dataset.
36
  It achieves the following results on the evaluation set:
37
  - Loss: 1.9820
38
  - Rouge1: 42.3629
@@ -41,17 +40,8 @@ It achieves the following results on the evaluation set:
41
  - Rougelsum: 38.7792
42
  - Gen Len: 27.8033
43
 
44
- ## Model description
45
-
46
- More information needed
47
-
48
- ## Intended uses & limitations
49
-
50
- More information needed
51
-
52
- ## Training and evaluation data
53
-
54
- More information needed
55
 
56
  ## Training procedure
57
 
@@ -71,6 +61,9 @@ The following hyperparameters were used during training:
71
 
72
  ### Training results
73
 
 
 
 
74
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
75
  |:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
76
  | 1.9528 | 0.9989 | 115 | 1.9189 | 40.093 | 18.2018 | 33.9749 | 36.9071 | 29.3333 |
@@ -78,10 +71,3 @@ The following hyperparameters were used during training:
78
  | 1.1696 | 2.9967 | 345 | 1.9820 | 42.3629 | 18.4285 | 34.6339 | 38.7792 | 27.8033 |
79
  | 0.9359 | 3.9957 | 460 | 2.1588 | 41.2237 | 17.8161 | 33.7101 | 37.9569 | 30.18 |
80
 
81
-
82
- ### Framework versions
83
-
84
- - Transformers 4.44.0
85
- - Pytorch 2.2.0+cu121
86
- - Datasets 2.20.0
87
- - Tokenizers 0.19.1
 
25
  - name: Rouge1
26
  type: rouge
27
  value: 42.3629
28
+ library_name: transformers
29
+ pipeline_tag: summarization
30
  ---
31
 
 
 
 
32
  # tFINE-base-300m-samsum
33
 
34
+ An example fine-tune of [pszemraj/tFINE-base-300m](https://hf.co/pszemraj/tFINE-base-300m) for summarization using the samsum dataset.
35
  It achieves the following results on the evaluation set:
36
  - Loss: 1.9820
37
  - Rouge1: 42.3629
 
40
  - Rougelsum: 38.7792
41
  - Gen Len: 27.8033
42
 
43
+ > [!NOTE]
44
+ > The base model was pre-trained with CTX 1024 and fine-tuned on samsum with 1024 CTX inputs.
 
 
 
 
 
 
 
 
 
45
 
46
  ## Training procedure
47
 
 
61
 
62
  ### Training results
63
 
64
+ > keep epoch 3 checkpt as final
65
+
66
+
67
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
68
  |:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
69
  | 1.9528 | 0.9989 | 115 | 1.9189 | 40.093 | 18.2018 | 33.9749 | 36.9071 | 29.3333 |
 
71
  | 1.1696 | 2.9967 | 345 | 1.9820 | 42.3629 | 18.4285 | 34.6339 | 38.7792 | 27.8033 |
72
  | 0.9359 | 3.9957 | 460 | 2.1588 | 41.2237 | 17.8161 | 33.7101 | 37.9569 | 30.18 |
73