End of training
Browse files- README.md +6 -24
- generation_config.json +1 -0
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -5,24 +5,9 @@ tags:
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- opus_books
|
| 8 |
-
metrics:
|
| 9 |
-
- bleu
|
| 10 |
model-index:
|
| 11 |
- name: booktranslation_opusdataset
|
| 12 |
-
results:
|
| 13 |
-
- task:
|
| 14 |
-
name: Sequence-to-sequence Language Modeling
|
| 15 |
-
type: text2text-generation
|
| 16 |
-
dataset:
|
| 17 |
-
name: opus_books
|
| 18 |
-
type: opus_books
|
| 19 |
-
config: de-en
|
| 20 |
-
split: train
|
| 21 |
-
args: de-en
|
| 22 |
-
metrics:
|
| 23 |
-
- name: Bleu
|
| 24 |
-
type: bleu
|
| 25 |
-
value: 3.9902
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,9 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus_books dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 2.
|
| 36 |
-
- Bleu: 3.9902
|
| 37 |
-
- Gen Len: 16.4661
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
@@ -59,14 +42,13 @@ The following hyperparameters were used during training:
|
|
| 59 |
- seed: 42
|
| 60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
- lr_scheduler_type: linear
|
| 62 |
-
- num_epochs:
|
| 63 |
|
| 64 |
### Training results
|
| 65 |
|
| 66 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 67 |
-
|
| 68 |
-
| 3.
|
| 69 |
-
| 3.0785 | 2.0 | 5148 | 2.8162 | 3.9902 | 16.4661 |
|
| 70 |
|
| 71 |
|
| 72 |
### Framework versions
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- opus_books
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: booktranslation_opusdataset
|
| 10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus_books dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.9578
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 42 |
- seed: 42
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 1
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 3.2775 | 1.0 | 2574 | 2.9578 |
|
|
|
|
| 52 |
|
| 53 |
|
| 54 |
### Framework versions
|
generation_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"decoder_start_token_id": 0,
|
| 3 |
"eos_token_id": 1,
|
| 4 |
"pad_token_id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 1,
|
| 5 |
"pad_token_id": 0,
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 242071641
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a09da0e3b4e0c0f68818a4529a4e2d96c926c4f25c623fd4bb82709c77244043
|
| 3 |
size 242071641
|