End of training
Browse files- README.md +3 -7
- generation_config.json +1 -1
- pytorch_model.bin +1 -1
- tokenizer.json +2 -16
README.md
CHANGED
|
@@ -33,21 +33,17 @@ More information needed
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
-
- learning_rate:
|
| 37 |
- train_batch_size: 1
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
-
- num_epochs:
|
| 43 |
-
|
| 44 |
-
### Training results
|
| 45 |
-
|
| 46 |
-
|
| 47 |
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
-
- Transformers 4.
|
| 51 |
- Pytorch 2.0.1+cu118
|
| 52 |
- Datasets 2.13.1
|
| 53 |
- Tokenizers 0.13.3
|
|
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 2e-05
|
| 37 |
- train_batch_size: 1
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 3
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
+
- Transformers 4.30.2
|
| 47 |
- Pytorch 2.0.1+cu118
|
| 48 |
- Datasets 2.13.1
|
| 49 |
- Tokenizers 0.13.3
|
generation_config.json
CHANGED
|
@@ -4,5 +4,5 @@
|
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"forced_eos_token_id": 2,
|
| 6 |
"pad_token_id": 1,
|
| 7 |
-
"transformers_version": "4.
|
| 8 |
}
|
|
|
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"forced_eos_token_id": 2,
|
| 6 |
"pad_token_id": 1,
|
| 7 |
+
"transformers_version": "4.30.2"
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 809178905
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a66a8ec257e49378d9a97b92f2b9d0403778f44f7a60c35243a6df8e8734f34
|
| 3 |
size 809178905
|
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": 1,
|
| 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,
|