End of training
Browse files- README.md +12 -5
- pytorch_model.bin +1 -1
- tokenizer_config.json +4 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -32,14 +32,21 @@ More information needed
|
|
32 |
|
33 |
The following hyperparameters were used during training:
|
34 |
- learning_rate: 2e-05
|
35 |
-
- train_batch_size:
|
36 |
-
- eval_batch_size:
|
37 |
- seed: 42
|
38 |
-
- gradient_accumulation_steps:
|
39 |
-
- total_train_batch_size:
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
-
- num_epochs:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
|
44 |
### Framework versions
|
45 |
|
|
|
32 |
|
33 |
The following hyperparameters were used during training:
|
34 |
- learning_rate: 2e-05
|
35 |
+
- train_batch_size: 8
|
36 |
+
- eval_batch_size: 8
|
37 |
- seed: 42
|
38 |
+
- gradient_accumulation_steps: 16
|
39 |
+
- total_train_batch_size: 128
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 1
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
47 |
+
|:-------------:|:-----:|:----:|:---------------:|:----:|:-------:|
|
48 |
+
| No log | 0.96 | 21 | 1.3691 | 0.0 | 19.0 |
|
49 |
+
|
50 |
|
51 |
### Framework versions
|
52 |
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990236853
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3e134b4a856674b2ca06ce11c3cd228a1458bdedaf9bcaad9262f3dacc7d8f1
|
3 |
size 990236853
|
tokenizer_config.json
CHANGED
@@ -104,8 +104,12 @@
|
|
104 |
"clean_up_tokenization_spaces": true,
|
105 |
"eos_token": "</s>",
|
106 |
"extra_ids": 100,
|
|
|
107 |
"model_max_length": 1000000000000000019884624838656,
|
108 |
"pad_token": "<pad>",
|
|
|
109 |
"tokenizer_class": "T5Tokenizer",
|
|
|
|
|
110 |
"unk_token": "<unk>"
|
111 |
}
|
|
|
104 |
"clean_up_tokenization_spaces": true,
|
105 |
"eos_token": "</s>",
|
106 |
"extra_ids": 100,
|
107 |
+
"max_length": 1024,
|
108 |
"model_max_length": 1000000000000000019884624838656,
|
109 |
"pad_token": "<pad>",
|
110 |
+
"stride": 0,
|
111 |
"tokenizer_class": "T5Tokenizer",
|
112 |
+
"truncation_side": "right",
|
113 |
+
"truncation_strategy": "longest_first",
|
114 |
"unk_token": "<unk>"
|
115 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4155
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2da484213889f405fb841ef3ea597caa56d45c6ea603341ac9cf26117859e10b
|
3 |
size 4155
|