End of training
Browse files- README.md +9 -22
- model.safetensors +1 -1
- tokenizer.json +2 -2
- training_args.bin +2 -2
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -41,36 +41,23 @@ The following hyperparameters were used during training:
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_ratio: 0.1
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
|
|
51 |
-
| 0.
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.3223 | 1.84 | 700 | 0.2214 |
|
57 |
-
| 0.2887 | 2.1 | 800 | 0.2132 |
|
58 |
-
| 0.2823 | 2.36 | 900 | 0.2036 |
|
59 |
-
| 0.2691 | 2.62 | 1000 | 0.2044 |
|
60 |
-
| 0.2615 | 2.89 | 1100 | 0.1978 |
|
61 |
-
| 0.2429 | 3.15 | 1200 | 0.1966 |
|
62 |
-
| 0.2253 | 3.41 | 1300 | 0.1975 |
|
63 |
-
| 0.2274 | 3.67 | 1400 | 0.1916 |
|
64 |
-
| 0.2354 | 3.94 | 1500 | 0.1925 |
|
65 |
-
| 0.2025 | 4.2 | 1600 | 0.1956 |
|
66 |
-
| 0.1988 | 4.46 | 1700 | 0.1956 |
|
67 |
-
| 0.2216 | 4.72 | 1800 | 0.1962 |
|
68 |
-
| 0.2082 | 4.99 | 1900 | 0.1955 |
|
69 |
|
70 |
|
71 |
### Framework versions
|
72 |
|
73 |
- Transformers 4.38.2
|
74 |
-
- Pytorch 2.
|
75 |
- Datasets 2.18.0
|
76 |
- Tokenizers 0.15.2
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.2208
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_ratio: 0.1
|
44 |
+
- num_epochs: 3
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 1.6993 | 0.45 | 200 | 0.3259 |
|
51 |
+
| 0.4165 | 0.9 | 400 | 0.2624 |
|
52 |
+
| 0.3401 | 1.35 | 600 | 0.2353 |
|
53 |
+
| 0.2937 | 1.8 | 800 | 0.2160 |
|
54 |
+
| 0.2655 | 2.25 | 1000 | 0.2244 |
|
55 |
+
| 0.2427 | 2.7 | 1200 | 0.2208 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|
59 |
|
60 |
- Transformers 4.38.2
|
61 |
+
- Pytorch 2.2.1+cu121
|
62 |
- Datasets 2.18.0
|
63 |
- Tokenizers 0.15.2
|
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:b019a40f9f32687fd74cba0bf640d3da7fad44cd4750ed03c2389a69a3501c60
|
3 |
size 990345064
|
tokenizer.json
CHANGED
@@ -2,13 +2,13 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
-
"Fixed":
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 89,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
+
"Fixed": 89
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
training_args.bin
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 sha256:0367e46bf3e8bea1456b28a3f9b13dcbf6d25654b455fd12a1d630b7db7d5438
|
3 |
+
size 5112
|