Tongyan Bai
commited on
Commit
•
731f54d
1
Parent(s):
8abfc26
https://huggingface.co/tongyanb/lab2_efficient
Browse files- README.md +26 -11
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -5,9 +5,24 @@ tags:
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- kde4
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: marian-finetuned-kde4-en-to-fr
|
| 10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -17,13 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
-
|
| 21 |
-
-
|
| 22 |
-
- eval_runtime: 162.904
|
| 23 |
-
- eval_samples_per_second: 12.903
|
| 24 |
-
- eval_steps_per_second: 0.203
|
| 25 |
-
- epoch: 0.0
|
| 26 |
-
- step: 4
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -43,15 +53,20 @@ More information needed
|
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
| 45 |
- learning_rate: 2e-05
|
| 46 |
-
- train_batch_size:
|
| 47 |
- eval_batch_size: 64
|
| 48 |
- seed: 42
|
| 49 |
-
- gradient_accumulation_steps:
|
| 50 |
- total_train_batch_size: 128
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: cosine
|
| 53 |
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
-
- num_epochs:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
### Framework versions
|
| 57 |
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- kde4
|
| 8 |
+
metrics:
|
| 9 |
+
- bleu
|
| 10 |
model-index:
|
| 11 |
- name: marian-finetuned-kde4-en-to-fr
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Sequence-to-sequence Language Modeling
|
| 15 |
+
type: text2text-generation
|
| 16 |
+
dataset:
|
| 17 |
+
name: kde4
|
| 18 |
+
type: kde4
|
| 19 |
+
config: en-fr
|
| 20 |
+
split: train
|
| 21 |
+
args: en-fr
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Bleu
|
| 24 |
+
type: bleu
|
| 25 |
+
value: 51.33567203419723
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.8956
|
| 36 |
+
- Bleu: 51.3357
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
- learning_rate: 2e-05
|
| 56 |
+
- train_batch_size: 32
|
| 57 |
- eval_batch_size: 64
|
| 58 |
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
- total_train_batch_size: 128
|
| 61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
- lr_scheduler_type: cosine
|
| 63 |
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
+
- num_epochs: 2
|
| 65 |
+
- mixed_precision_training: Native AMP
|
| 66 |
+
|
| 67 |
+
### Training results
|
| 68 |
+
|
| 69 |
+
|
| 70 |
|
| 71 |
### Framework versions
|
| 72 |
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 298705768
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fb7de141d8b840e8a7b8b270d55ec36a366fbccb421e2bc13b954ef2cb9f0e0
|
| 3 |
size 298705768
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5000340ec9b0be647c8cab6d70f6e3276ca03b78ba2f7487c69f51ccbd9ccac6
|
| 3 |
size 5112
|