eddieman78
commited on
Commit
•
56e744a
1
Parent(s):
49bd110
End
Browse files- README.md +9 -6
- model.safetensors +1 -1
- tokenizer.json +2 -16
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
base_model: google/flan-t5-base
|
6 |
model-index:
|
7 |
- name: ner-mem-base
|
8 |
results: []
|
@@ -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:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -40,13 +40,16 @@ The following hyperparameters were used during training:
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
-
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
-
| Training Loss | Epoch | Step
|
48 |
-
|
49 |
-
|
|
|
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: google/flan-t5-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
model-index:
|
7 |
- name: ner-mem-base
|
8 |
results: []
|
|
|
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: 0.0018
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 4
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
49 |
+
| 0.0036 | 1.0 | 14981 | 0.0022 |
|
50 |
+
| 0.0025 | 2.0 | 29962 | 0.0019 |
|
51 |
+
| 0.0023 | 3.0 | 44943 | 0.0018 |
|
52 |
+
| 0.0023 | 4.0 | 59924 | 0.0018 |
|
53 |
|
54 |
|
55 |
### Framework versions
|
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 sha256:4828ddfbdc012773b98304414aeef066bb16ed0611e51ec6b11bccdd7a968643
|
3 |
size 990345064
|
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 512,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 512
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 0,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "<pad>"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1504192d253ece5b63b7ec6017da782c436f8e412c003c8a1ef2e774a7f9d7ae
|
3 |
size 5048
|