arifagustyawan
commited on
Commit
•
34e5089
1
Parent(s):
c844b92
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/flan-t5-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: flan-t5-base-sentiment-product-review
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# flan-t5-base-sentiment-product-review
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.8071
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0003
|
38 |
+
- train_batch_size: 16
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 50
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 33 | 1.0479 |
|
50 |
+
| No log | 2.0 | 66 | 0.9240 |
|
51 |
+
| No log | 3.0 | 99 | 0.8648 |
|
52 |
+
| No log | 4.0 | 132 | 0.8438 |
|
53 |
+
| No log | 5.0 | 165 | 0.8455 |
|
54 |
+
| No log | 6.0 | 198 | 0.8540 |
|
55 |
+
| No log | 7.0 | 231 | 0.8791 |
|
56 |
+
| No log | 8.0 | 264 | 0.8509 |
|
57 |
+
| No log | 9.0 | 297 | 0.9104 |
|
58 |
+
| No log | 10.0 | 330 | 0.9554 |
|
59 |
+
| No log | 11.0 | 363 | 0.9345 |
|
60 |
+
| No log | 12.0 | 396 | 0.9797 |
|
61 |
+
| No log | 13.0 | 429 | 0.9809 |
|
62 |
+
| No log | 14.0 | 462 | 1.0556 |
|
63 |
+
| No log | 15.0 | 495 | 1.1264 |
|
64 |
+
| 0.5004 | 16.0 | 528 | 1.1426 |
|
65 |
+
| 0.5004 | 17.0 | 561 | 1.2255 |
|
66 |
+
| 0.5004 | 18.0 | 594 | 1.2086 |
|
67 |
+
| 0.5004 | 19.0 | 627 | 1.2068 |
|
68 |
+
| 0.5004 | 20.0 | 660 | 1.2919 |
|
69 |
+
| 0.5004 | 21.0 | 693 | 1.3547 |
|
70 |
+
| 0.5004 | 22.0 | 726 | 1.3276 |
|
71 |
+
| 0.5004 | 23.0 | 759 | 1.3597 |
|
72 |
+
| 0.5004 | 24.0 | 792 | 1.4057 |
|
73 |
+
| 0.5004 | 25.0 | 825 | 1.4212 |
|
74 |
+
| 0.5004 | 26.0 | 858 | 1.5188 |
|
75 |
+
| 0.5004 | 27.0 | 891 | 1.5569 |
|
76 |
+
| 0.5004 | 28.0 | 924 | 1.5158 |
|
77 |
+
| 0.5004 | 29.0 | 957 | 1.5191 |
|
78 |
+
| 0.5004 | 30.0 | 990 | 1.5202 |
|
79 |
+
| 0.0793 | 31.0 | 1023 | 1.6140 |
|
80 |
+
| 0.0793 | 32.0 | 1056 | 1.6112 |
|
81 |
+
| 0.0793 | 33.0 | 1089 | 1.5900 |
|
82 |
+
| 0.0793 | 34.0 | 1122 | 1.6162 |
|
83 |
+
| 0.0793 | 35.0 | 1155 | 1.6261 |
|
84 |
+
| 0.0793 | 36.0 | 1188 | 1.6229 |
|
85 |
+
| 0.0793 | 37.0 | 1221 | 1.7149 |
|
86 |
+
| 0.0793 | 38.0 | 1254 | 1.7149 |
|
87 |
+
| 0.0793 | 39.0 | 1287 | 1.7502 |
|
88 |
+
| 0.0793 | 40.0 | 1320 | 1.7334 |
|
89 |
+
| 0.0793 | 41.0 | 1353 | 1.7409 |
|
90 |
+
| 0.0793 | 42.0 | 1386 | 1.7161 |
|
91 |
+
| 0.0793 | 43.0 | 1419 | 1.7235 |
|
92 |
+
| 0.0793 | 44.0 | 1452 | 1.7554 |
|
93 |
+
| 0.0793 | 45.0 | 1485 | 1.7640 |
|
94 |
+
| 0.0263 | 46.0 | 1518 | 1.7779 |
|
95 |
+
| 0.0263 | 47.0 | 1551 | 1.7784 |
|
96 |
+
| 0.0263 | 48.0 | 1584 | 1.7979 |
|
97 |
+
| 0.0263 | 49.0 | 1617 | 1.8056 |
|
98 |
+
| 0.0263 | 50.0 | 1650 | 1.8071 |
|
99 |
+
|
100 |
+
|
101 |
+
### Framework versions
|
102 |
+
|
103 |
+
- Transformers 4.35.2
|
104 |
+
- Pytorch 2.1.0+cu118
|
105 |
+
- Datasets 2.15.0
|
106 |
+
- Tokenizers 0.15.0
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.35.2"
|
7 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990345064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba622616d5cc0f0e234ab1795e8e4d1f317418757e64d2eb9705ca6bad0be050
|
3 |
size 990345064
|
runs/Nov23_12-15-54_47f48348d918/events.out.tfevents.1700741759.47f48348d918.362.0
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:e8a87a8efc0343c3d3f267d646105154dde8ce266baa2d131a45226ca1c9805b
|
3 |
+
size 19672
|