Fine tuning mt5-small: final iteration
Browse files
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: google/mt5-small
|
5 |
+
tags:
|
6 |
+
- summarization
|
7 |
+
- generated_from_trainer
|
8 |
+
metrics:
|
9 |
+
- rouge
|
10 |
+
model-index:
|
11 |
+
- name: mt5-small-mt5-finetuned-final
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# mt5-small-mt5-finetuned-final
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 1.1778
|
23 |
+
- Rouge1: 0.2833
|
24 |
+
- Rouge2: 0.1521
|
25 |
+
- Rougel: 0.2758
|
26 |
+
- Rougelsum: 0.2768
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 0.0056
|
46 |
+
- train_batch_size: 12
|
47 |
+
- eval_batch_size: 12
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 20
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
57 |
+
| 5.9607 | 1.0 | 100 | 4.8449 | 0.1763 | 0.0684 | 0.1763 | 0.1761 |
|
58 |
+
| 4.9088 | 2.0 | 200 | 3.9878 | 0.3076 | 0.1348 | 0.2803 | 0.2815 |
|
59 |
+
| 2.9924 | 3.0 | 300 | 2.2397 | 0.2790 | 0.1378 | 0.2575 | 0.2592 |
|
60 |
+
| 2.2734 | 4.0 | 400 | 1.9866 | 0.2987 | 0.1629 | 0.2868 | 0.2872 |
|
61 |
+
| 1.9431 | 5.0 | 500 | 1.7408 | 0.2251 | 0.1380 | 0.2231 | 0.2237 |
|
62 |
+
| 2.317 | 6.0 | 600 | 1.9235 | 0.2421 | 0.0922 | 0.2276 | 0.2282 |
|
63 |
+
| 1.8526 | 7.0 | 700 | 1.6342 | 0.3120 | 0.1636 | 0.2943 | 0.2944 |
|
64 |
+
| 1.7029 | 8.0 | 800 | 1.6244 | 0.2469 | 0.1361 | 0.2421 | 0.2427 |
|
65 |
+
| 1.6725 | 9.0 | 900 | 1.5803 | 0.2637 | 0.1362 | 0.2551 | 0.2560 |
|
66 |
+
| 1.5852 | 10.0 | 1000 | 1.5617 | 0.2963 | 0.1634 | 0.2907 | 0.2917 |
|
67 |
+
| 1.4625 | 11.0 | 1100 | 1.4049 | 0.2750 | 0.1383 | 0.2570 | 0.2576 |
|
68 |
+
| 1.3895 | 12.0 | 1200 | 1.4234 | 0.2969 | 0.1646 | 0.2917 | 0.2927 |
|
69 |
+
| 1.3584 | 13.0 | 1300 | 1.3807 | 0.3370 | 0.1601 | 0.3088 | 0.3099 |
|
70 |
+
| 1.2759 | 14.0 | 1400 | 1.3524 | 0.2890 | 0.1307 | 0.2654 | 0.2663 |
|
71 |
+
| 1.222 | 15.0 | 1500 | 1.3110 | 0.2718 | 0.1339 | 0.2566 | 0.2597 |
|
72 |
+
| 1.1515 | 16.0 | 1600 | 1.2297 | 0.3314 | 0.1626 | 0.3033 | 0.3038 |
|
73 |
+
| 1.0888 | 17.0 | 1700 | 1.1897 | 0.3028 | 0.1358 | 0.2769 | 0.2792 |
|
74 |
+
| 1.039 | 18.0 | 1800 | 1.1970 | 0.2833 | 0.1521 | 0.2758 | 0.2768 |
|
75 |
+
| 0.9907 | 19.0 | 1900 | 1.1790 | 0.2833 | 0.1521 | 0.2758 | 0.2768 |
|
76 |
+
| 0.9563 | 20.0 | 2000 | 1.1778 | 0.2833 | 0.1521 | 0.2758 | 0.2768 |
|
77 |
+
|
78 |
+
|
79 |
+
### Framework versions
|
80 |
+
|
81 |
+
- Transformers 4.48.3
|
82 |
+
- Pytorch 2.5.1+cu124
|
83 |
+
- Datasets 3.3.2
|
84 |
+
- Tokenizers 0.21.0
|
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": "4.48.3"
|
6 |
+
}
|
runs/Feb26_13-33-27_6e02d8b34194/events.out.tfevents.1740576829.6e02d8b34194.13349.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80a7f7d0561289ed4786cef9eb55c4e7f1ae538d0b41fbce7d78a3576eddfd58
|
3 |
+
size 19420
|
runs/Feb26_13-33-27_6e02d8b34194/events.out.tfevents.1740578413.6e02d8b34194.13349.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1082cdd973cfdc3f663a3628cbc867814f5f25ab6a313ddb3efda02aa03240a1
|
3 |
+
size 562
|